Quantifying heterogeneity of lesion uptake in dynamic contrast enhanced MRI for breast cancer diagnosis

NASA Astrophysics Data System (ADS)

Karahaliou, A.; Vassiou, K.; Skiadopoulos, S.; Kanavou, T.; Yiakoumelos, A.; Costaridou, L.

2009-07-01

The current study investigates whether texture features extracted from lesion kinetics feature maps can be used for breast cancer diagnosis. Fifty five women with 57 breast lesions (27 benign, 30 malignant) were subjected to dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) on 1.5T system. A linear-slope model was fitted pixel-wise to a representative lesion slice time series and fitted parameters were used to create three kinetic maps (wash out, time to peak enhancement and peak enhancement). 28 grey level co-occurrence matrices features were extracted from each lesion kinetic map. The ability of texture features per map in discriminating malignant from benign lesions was investigated using a Probabilistic Neural Network classifier. Additional classification was performed by combining classification outputs of most discriminating feature subsets from the three maps, via majority voting. The combined scheme outperformed classification based on individual maps achieving area under Receiver Operating Characteristics curve 0.960±0.029. Results suggest that heterogeneity of breast lesion kinetics, as quantified by texture analysis, may contribute to computer assisted tissue characterization in DCE-MRI.

Tissue Tracking: Applications for Brain MRI Classification

DTIC Science & Technology

2007-01-01

General Hospital, Center for Morphometric Analysis.10,11 The IBSR data-sets are T1-weighted, 3D coronal brain scans after having been positionally...learned priors,” Image Processing, IEEE Transactions on 9(2), pp. 299–301, 2000. 5. P. Olver, G. Sapiro, and A. Tannenbaum, “Invariant Geometric Evolutions...MRI,” NeuroImage 22(3), pp. 1060–1075, 2004. 16. A. Zijdenbos, B. Dawant, R. Margolin, and A. Palmer, “ Morphometric analysis of white matter lesions in

Classification of clinical significance of MRI prostate findings using 3D convolutional neural networks

NASA Astrophysics Data System (ADS)

Mehrtash, Alireza; Sedghi, Alireza; Ghafoorian, Mohsen; Taghipour, Mehdi; Tempany, Clare M.; Wells, William M.; Kapur, Tina; Mousavi, Parvin; Abolmaesumi, Purang; Fedorov, Andriy

2017-03-01

Prostate cancer (PCa) remains a leading cause of cancer mortality among American men. Multi-parametric magnetic resonance imaging (mpMRI) is widely used to assist with detection of PCa and characterization of its aggressiveness. Computer-aided diagnosis (CADx) of PCa in MRI can be used as clinical decision support system to aid radiologists in interpretation and reporting of mpMRI. We report on the development of a convolution neural network (CNN) model to support CADx in PCa based on the appearance of prostate tissue in mpMRI, conducted as part of the SPIE-AAPM-NCI PROSTATEx challenge. The performance of different combinations of mpMRI inputs to CNN was assessed and the best result was achieved using DWI and DCE-MRI modalities together with the zonal information of the finding. On the test set, the model achieved an area under the receiver operating characteristic curve of 0.80.

Efficacy of texture, shape, and intensity features for robust posterior-fossa tumor segmentation in MRI

NASA Astrophysics Data System (ADS)

Ahmed, S.; Iftekharuddin, K. M.; Ogg, R. J.; Laningham, F. H.

2009-02-01

Our previous works suggest that fractal-based texture features are very useful for detection, segmentation and classification of posterior-fossa (PF) pediatric brain tumor in multimodality MRI. In this work, we investigate and compare efficacy of our texture features such as fractal and multifractional Brownian motion (mBm), and intensity along with another useful level-set based shape feature in PF tumor segmentation. We study feature selection and ranking using Kullback -Leibler Divergence (KLD) and subsequent tumor segmentation; all in an integrated Expectation Maximization (EM) framework. We study the efficacy of all four features in both multimodality as well as disparate MRI modalities such as T1, T2 and FLAIR. Both KLD feature plots and information theoretic entropy measure suggest that mBm feature offers the maximum separation between tumor and non-tumor tissues in T1 and FLAIR MRI modalities. The same metrics show that intensity feature offers the maximum separation between tumor and non-tumor tissue in T2 MRI modality. The efficacies of these features are further validated in segmenting PF tumor using both single modality and multimodality MRI for six pediatric patients with over 520 real MR images.

Quantification of neonatal lung parenchymal density via ultrashort echo time MRI with comparison to CT.

PubMed

Higano, Nara S; Fleck, Robert J; Spielberg, David R; Walkup, Laura L; Hahn, Andrew D; Thomen, Robert P; Merhar, Stephanie L; Kingma, Paul S; Tkach, Jean A; Fain, Sean B; Woods, Jason C

2017-10-01

To demonstrate that ultrashort echo time (UTE) magnetic resonance imaging (MRI) can achieve computed tomography (CT)-like quantification of lung parenchyma in free-breathing, non-sedated neonates. Because infant CTs are used sparingly, parenchymal disease evaluation via UTE MRI has potential for translational impact. Two neonatal control cohorts without suspected pulmonary morbidities underwent either a research UTE MRI (n = 5; 1.5T) or a clinically-ordered CT (n = 9). Whole-lung means and anterior-posterior gradients of UTE-measured image intensity (arbitrary units, au, normalized to muscle) and CT-measured density (g/cm 3 ) were compared (Mann-Whitney U-test). Separately, a diseased neonatal cohort (n = 5) with various pulmonary morbidities underwent both UTE MRI and CT. UTE intensity and CT density were compared with Spearman correlations within ∼33 anatomically matched regions of interest (ROIs) in each diseased subject, spanning low- to high-density tissues. Radiological classifications were evaluated in all ROIs, with mean UTE intensities and CT densities compared in each classification. In control subjects, whole-lung UTE intensities (0.51 ± 0.04 au) were similar to CT densities (0.44 ± 0.09 g/cm 3 ) (P = 0.062), as were UTE (0.021 ± 0.020 au/cm) and CT (0.034 ± 0.024 [g/cm 3 ]/cm) anterior-posterior gradients (P = 0.351). In diseased subjects' ROIs, significant correlations were observed between UTE and CT (P ≤0.007 in each case). Relative differences between UTE and CT were small in all classifications (4-25%). These results demonstrate a strong association between UTE image intensity and CT density, both between whole-lung tissue in control patients and regional radiological pathologies in diseased patients. This indicates the potential for UTE MRI to longitudinally evaluate neonatal pulmonary disease and to provide visualization of pathologies similar to CT, without sedation/anesthesia or ionizing radiation. 3 Technical Efficacy: Stage 2 J. Magn. Reson. Imaging 2017;46:992-1000. © 2017 International Society for Magnetic Resonance in Medicine.

Biased visualization of hypoperfused tissue by computed tomography due to short imaging duration: improved classification by image down-sampling and vascular models.

PubMed

Mikkelsen, Irene Klærke; Jones, P Simon; Ribe, Lars Riisgaard; Alawneh, Josef; Puig, Josep; Bekke, Susanne Lise; Tietze, Anna; Gillard, Jonathan H; Warburton, Elisabeth A; Pedraza, Salva; Baron, Jean-Claude; Østergaard, Leif; Mouridsen, Kim

2015-07-01

Lesion detection in acute stroke by computed-tomography perfusion (CTP) can be affected by incomplete bolus coverage in veins and hypoperfused tissue, so-called bolus truncation (BT), and low contrast-to-noise ratio (CNR). We examined the BT-frequency and hypothesized that image down-sampling and a vascular model (VM) for perfusion calculation would improve normo- and hypoperfused tissue classification. CTP datasets from 40 acute stroke patients were retrospectively analysed for BT. In 16 patients with hypoperfused tissue but no BT, repeated 2-by-2 image down-sampling and uniform filtering was performed, comparing CNR to perfusion-MRI levels and tissue classification to that of unprocessed data. By simulating reduced scan duration, the minimum scan-duration at which estimated lesion volumes came within 10% of their true volume was compared for VM and state-of-the-art algorithms. BT in veins and hypoperfused tissue was observed in 9/40 (22.5%) and 17/40 patients (42.5%), respectively. Down-sampling to 128 × 128 resolution yielded CNR comparable to MR data and improved tissue classification (p = 0.0069). VM reduced minimum scan duration, providing reliable maps of cerebral blood flow and mean transit time: 5 s (p = 0.03) and 7 s (p < 0.0001), respectively). BT is not uncommon in stroke CTP with 40-s scan duration. Applying image down-sampling and VM improve tissue classification. • Too-short imaging duration is common in clinical acute stroke CTP imaging. • The consequence is impaired identification of hypoperfused tissue in acute stroke patients. • The vascular model is less sensitive than current algorithms to imaging duration. • Noise reduction by image down-sampling improves identification of hypoperfused tissue by CTP.

Magnetic resonance imaging classification of haemodialysis-related amyloidosis of the shoulder: risk factors and arthroscopic treatment.

PubMed

Ando, Akira; Hagiwara, Yoshihiro; Sekiguchi, Takuya; Koide, Masashi; Kanazawa, Kenji; Watanabe, Takashi; Itoi, Eiji

2017-07-01

This study proposed new magnetic resonance imaging (MRI) of haemodialysis shoulders (HDS) focusing on the changes of the rotator cuff, and rotator interval and risk factors for the development of HDS were examined. Eighty-five shoulders in 72 patients with a chief complaint of shoulder pain during haemodialysis and at least 10 years of haemodialysis were included. They were classified into 5 groups based on the thickness of the rotator cuff and conditions of rotator interval. Clinical and radiological findings in each grade were examined, and risk factors for the development of HDS were evaluated. Arthroscopic surgeries were performed on 22 shoulders in 20 patients, and arthroscopic findings were also evaluated. Positive correlations for the development of HDS were observed in duration of haemodialysis, positive hepatitis C virus (HCV) infection, and previous haemodialysis-related orthopaedic surgery (P < 0.001, respectively). Strong correlations were observed between positive HCV and the progression of HDS (odds ratio 24.8, 95 % confidence interval 5.7-107.6). Arthroscopically, progression of the surrounding soft tissue degeneration was observed, and operative times were lengthened depending on the progression of MRI grading. A new MRI classification of HDS which may be helpful when considering arthroscopic surgeries has been proposed. Positive HCV infection was strongly associated with the progression of HDS on MRI. Conditions of the rotator interval and the rotator cuff based on the MRI classification should be examined when treating HDS patients. III.

Classification of breast MRI lesions using small-size training sets: comparison of deep learning approaches

NASA Astrophysics Data System (ADS)

Amit, Guy; Ben-Ari, Rami; Hadad, Omer; Monovich, Einat; Granot, Noa; Hashoul, Sharbell

2017-03-01

Diagnostic interpretation of breast MRI studies requires meticulous work and a high level of expertise. Computerized algorithms can assist radiologists by automatically characterizing the detected lesions. Deep learning approaches have shown promising results in natural image classification, but their applicability to medical imaging is limited by the shortage of large annotated training sets. In this work, we address automatic classification of breast MRI lesions using two different deep learning approaches. We propose a novel image representation for dynamic contrast enhanced (DCE) breast MRI lesions, which combines the morphological and kinetics information in a single multi-channel image. We compare two classification approaches for discriminating between benign and malignant lesions: training a designated convolutional neural network and using a pre-trained deep network to extract features for a shallow classifier. The domain-specific trained network provided higher classification accuracy, compared to the pre-trained model, with an area under the ROC curve of 0.91 versus 0.81, and an accuracy of 0.83 versus 0.71. Similar accuracy was achieved in classifying benign lesions, malignant lesions, and normal tissue images. The trained network was able to improve accuracy by using the multi-channel image representation, and was more robust to reductions in the size of the training set. A small-size convolutional neural network can learn to accurately classify findings in medical images using only a few hundred images from a few dozen patients. With sufficient data augmentation, such a network can be trained to outperform a pre-trained out-of-domain classifier. Developing domain-specific deep-learning models for medical imaging can facilitate technological advancements in computer-aided diagnosis.

Detection of white matter lesion regions in MRI using SLIC0 and convolutional neural network.

PubMed

Diniz, Pedro Henrique Bandeira; Valente, Thales Levi Azevedo; Diniz, João Otávio Bandeira; Silva, Aristófanes Corrêa; Gattass, Marcelo; Ventura, Nina; Muniz, Bernardo Carvalho; Gasparetto, Emerson Leandro

2018-04-19

White matter lesions are non-static brain lesions that have a prevalence rate up to 98% in the elderly population. Because they may be associated with several brain diseases, it is important that they are detected as soon as possible. Magnetic Resonance Imaging (MRI) provides three-dimensional data with the possibility to detect and emphasize contrast differences in soft tissues, providing rich information about the human soft tissue anatomy. However, the amount of data provided for these images is far too much for manual analysis/interpretation, representing a difficult and time-consuming task for specialists. This work presents a computational methodology capable of detecting regions of white matter lesions of the brain in MRI of FLAIR modality. The techniques highlighted in this methodology are SLIC0 clustering for candidate segmentation and convolutional neural networks for candidate classification. The methodology proposed here consists of four steps: (1) images acquisition, (2) images preprocessing, (3) candidates segmentation and (4) candidates classification. The methodology was applied on 91 magnetic resonance images provided by DASA, and achieved an accuracy of 98.73%, specificity of 98.77% and sensitivity of 78.79% with 0.005 of false positives, without any false positives reduction technique, in detection of white matter lesion regions. It is demonstrated the feasibility of the analysis of brain MRI using SLIC0 and convolutional neural network techniques to achieve success in detection of white matter lesions regions. Copyright © 2018. Published by Elsevier B.V.

Towards in vivo focal cortical dysplasia phenotyping using quantitative MRI.

PubMed

Adler, Sophie; Lorio, Sara; Jacques, Thomas S; Benova, Barbora; Gunny, Roxana; Cross, J Helen; Baldeweg, Torsten; Carmichael, David W

2017-01-01

Focal cortical dysplasias (FCDs) are a range of malformations of cortical development each with specific histopathological features. Conventional radiological assessment of standard structural MRI is useful for the localization of lesions but is unable to accurately predict the histopathological features. Quantitative MRI offers the possibility to probe tissue biophysical properties in vivo and may bridge the gap between radiological assessment and ex-vivo histology. This review will cover histological, genetic and radiological features of FCD following the ILAE classification and will explain how quantitative voxel- and surface-based techniques can characterise these features. We will provide an overview of the quantitative MRI measures available, their link with biophysical properties and finally the potential application of quantitative MRI to the problem of FCD subtyping. Future research linking quantitative MRI to FCD histological properties should improve clinical protocols, allow better characterisation of lesions in vivo and tailored surgical planning to the individual.

Unifying framework for multimodal brain MRI segmentation based on Hidden Markov Chains.

PubMed

Bricq, S; Collet, Ch; Armspach, J P

2008-12-01

In the frame of 3D medical imaging, accurate segmentation of multimodal brain MR images is of interest for many brain disorders. However, due to several factors such as noise, imaging artifacts, intrinsic tissue variation and partial volume effects, tissue classification remains a challenging task. In this paper, we present a unifying framework for unsupervised segmentation of multimodal brain MR images including partial volume effect, bias field correction, and information given by a probabilistic atlas. Here-proposed method takes into account neighborhood information using a Hidden Markov Chain (HMC) model. Due to the limited resolution of imaging devices, voxels may be composed of a mixture of different tissue types, this partial volume effect is included to achieve an accurate segmentation of brain tissues. Instead of assigning each voxel to a single tissue class (i.e., hard classification), we compute the relative amount of each pure tissue class in each voxel (mixture estimation). Further, a bias field estimation step is added to the proposed algorithm to correct intensity inhomogeneities. Furthermore, atlas priors were incorporated using probabilistic brain atlas containing prior expectations about the spatial localization of different tissue classes. This atlas is considered as a complementary sensor and the proposed method is extended to multimodal brain MRI without any user-tunable parameter (unsupervised algorithm). To validate this new unifying framework, we present experimental results on both synthetic and real brain images, for which the ground truth is available. Comparison with other often used techniques demonstrates the accuracy and the robustness of this new Markovian segmentation scheme.

Rotationally invariant clustering of diffusion MRI data using spherical harmonics

NASA Astrophysics Data System (ADS)

Liptrot, Matthew; Lauze, François

2016-03-01

We present a simple approach to the voxelwise classification of brain tissue acquired with diffusion weighted MRI (DWI). The approach leverages the power of spherical harmonics to summarise the diffusion information, sampled at many points over a sphere, using only a handful of coefficients. We use simple features that are invariant to the rotation of the highly orientational diffusion data. This provides a way to directly classify voxels whose diffusion characteristics are similar yet whose primary diffusion orientations differ. Subsequent application of machine-learning to the spherical harmonic coefficients therefore may permit classification of DWI voxels according to their inferred underlying fibre properties, whilst ignoring the specifics of orientation. After smoothing apparent diffusion coefficients volumes, we apply a spherical harmonic transform, which models the multi-directional diffusion data as a collection of spherical basis functions. We use the derived coefficients as voxelwise feature vectors for classification. Using a simple Gaussian mixture model, we examined the classification performance for a range of sub-classes (3-20). The results were compared against existing alternatives for tissue classification e.g. fractional anisotropy (FA) or the standard model used by Camino.1 The approach was implemented on both two publicly-available datasets: an ex-vivo pig brain and in-vivo human brain from the Human Connectome Project (HCP). We have demonstrated how a robust classification of DWI data can be performed without the need for a model reconstruction step. This avoids the potential confounds and uncertainty that such models may impose, and has the benefit of being computable directly from the DWI volumes. As such, the method could prove useful in subsequent pre-processing stages, such as model fitting, where it could inform about individual voxel complexities and improve model parameter choice.

Structural brain changes versus self-report: machine-learning classification of chronic fatigue syndrome patients.

PubMed

Sevel, Landrew S; Boissoneault, Jeff; Letzen, Janelle E; Robinson, Michael E; Staud, Roland

2018-05-30

Chronic fatigue syndrome (CFS) is a disorder associated with fatigue, pain, and structural/functional abnormalities seen during magnetic resonance brain imaging (MRI). Therefore, we evaluated the performance of structural MRI (sMRI) abnormalities in the classification of CFS patients versus healthy controls and compared it to machine learning (ML) classification based upon self-report (SR). Participants included 18 CFS patients and 15 healthy controls (HC). All subjects underwent T1-weighted sMRI and provided visual analogue-scale ratings of fatigue, pain intensity, anxiety, depression, anger, and sleep quality. sMRI data were segmented using FreeSurfer and 61 regions based on functional and structural abnormalities previously reported in patients with CFS. Classification was performed in RapidMiner using a linear support vector machine and bootstrap optimism correction. We compared ML classifiers based on (1) 61 a priori sMRI regional estimates and (2) SR ratings. The sMRI model achieved 79.58% classification accuracy. The SR (accuracy = 95.95%) outperformed both sMRI models. Estimates from multiple brain areas related to cognition, emotion, and memory contributed strongly to group classification. This is the first ML-based group classification of CFS. Our findings suggest that sMRI abnormalities are useful for discriminating CFS patients from HC, but SR ratings remain most effective in classification tasks.

Detection of Focal Cortical Dysplasia Lesions in MRI Using Textural Features

NASA Astrophysics Data System (ADS)

Loyek, Christian; Woermann, Friedrich G.; Nattkemper, Tim W.

Focal cortical dysplasia (FCD) is a frequent cause of medically refractory partial epilepsy. The visual identification of FCD lesions on magnetic resonance images (MRI) is a challenging task in standard radiological analysis. Quantitative image analysis which tries to assist in the diagnosis of FCD lesions is an active field of research. In this work we investigate the potential of different texture features, in order to explore to what extent they are suitable for detecting lesional tissue. As a result we can show first promising results based on segmentation and texture classification.

Single Subject Classification of Alzheimer's Disease and Behavioral Variant Frontotemporal Dementia Using Anatomical, Diffusion Tensor, and Resting-State Functional Magnetic Resonance Imaging.

PubMed

Bouts, Mark J R J; Möller, Christiane; Hafkemeijer, Anne; van Swieten, John C; Dopper, Elise; van der Flier, Wiesje M; Vrenken, Hugo; Wink, Alle Meije; Pijnenburg, Yolande A L; Scheltens, Philip; Barkhof, Frederik; Schouten, Tijn M; de Vos, Frank; Feis, Rogier A; van der Grond, Jeroen; de Rooij, Mark; Rombouts, Serge A R B

2018-01-01

Overlapping clinical symptoms often complicate differential diagnosis between patients with Alzheimer's disease (AD) and behavioral variant frontotemporal dementia (bvFTD). Magnetic resonance imaging (MRI) reveals disease specific structural and functional differences that aid in differentiating AD from bvFTD patients. However, the benefit of combining structural and functional connectivity measures to-on a subject-basis-differentiate these dementia-types is not yet known. Anatomical, diffusion tensor (DTI), and resting-state functional MRI (rs-fMRI) of 30 patients with early stage AD, 23 with bvFTD, and 35 control subjects were collected and used to calculate measures of structural and functional tissue status. All measures were used separately or selectively combined as predictors for training an elastic net regression classifier. Each classifier's ability to accurately distinguish dementia-types was quantified by calculating the area under the receiver operating characteristic curves (AUC). Highest AUC values for AD and bvFTD discrimination were obtained when mean diffusivity, full correlations between rs-fMRI-derived independent components, and fractional anisotropy (FA) were combined (0.811). Similarly, combining gray matter density (GMD), FA, and rs-fMRI correlations resulted in highest AUC of 0.922 for control and bvFTD classifications. This, however, was not observed for control and AD differentiations. Classifications with GMD (0.940) and a GMD and DTI combination (0.941) resulted in similar AUC values (p = 0.41). Combining functional and structural connectivity measures improve dementia-type differentiations and may contribute to more accurate and substantiated differential diagnosis of AD and bvFTD patients. Imaging protocols for differential diagnosis may benefit from also including DTI and rs-fMRI.

Multiresolution texture models for brain tumor segmentation in MRI.

PubMed

Iftekharuddin, Khan M; Ahmed, Shaheen; Hossen, Jakir

2011-01-01

In this study we discuss different types of texture features such as Fractal Dimension (FD) and Multifractional Brownian Motion (mBm) for estimating random structures and varying appearance of brain tissues and tumors in magnetic resonance images (MRI). We use different selection techniques including KullBack - Leibler Divergence (KLD) for ranking different texture and intensity features. We then exploit graph cut, self organizing maps (SOM) and expectation maximization (EM) techniques to fuse selected features for brain tumors segmentation in multimodality T1, T2, and FLAIR MRI. We use different similarity metrics to evaluate quality and robustness of these selected features for tumor segmentation in MRI for real pediatric patients. We also demonstrate a non-patient-specific automated tumor prediction scheme by using improved AdaBoost classification based on these image features.

Progress toward automatic classification of human brown adipose tissue using biomedical imaging

NASA Astrophysics Data System (ADS)

Gifford, Aliya; Towse, Theodore F.; Walker, Ronald C.; Avison, Malcom J.; Welch, E. B.

2015-03-01

Brown adipose tissue (BAT) is a small but significant tissue, which may play an important role in obesity and the pathogenesis of metabolic syndrome. Interest in studying BAT in adult humans is increasing, but in order to quantify BAT volume in a single measurement or to detect changes in BAT over the time course of a longitudinal experiment, BAT needs to first be reliably differentiated from surrounding tissue. Although the uptake of the radiotracer 18F-Fluorodeoxyglucose (18F-FDG) in adipose tissue on positron emission tomography (PET) scans following cold exposure is accepted as an indication of BAT, it is not a definitive indicator, and to date there exists no standardized method for segmenting BAT. Consequently, there is a strong need for robust automatic classification of BAT based on properties measured with biomedical imaging. In this study we begin the process of developing an automated segmentation method based on properties obtained from fat-water MRI and PET-CT scans acquired on ten healthy adult subjects.

Multiclass feature selection for improved pediatric brain tumor segmentation

NASA Astrophysics Data System (ADS)

Ahmed, Shaheen; Iftekharuddin, Khan M.

2012-03-01

In our previous work, we showed that fractal-based texture features are effective in detection, segmentation and classification of posterior-fossa (PF) pediatric brain tumor in multimodality MRI. We exploited an information theoretic approach such as Kullback-Leibler Divergence (KLD) for feature selection and ranking different texture features. We further incorporated the feature selection technique with segmentation method such as Expectation Maximization (EM) for segmentation of tumor T and non tumor (NT) tissues. In this work, we extend the two class KLD technique to multiclass for effectively selecting the best features for brain tumor (T), cyst (C) and non tumor (NT). We further obtain segmentation robustness for each tissue types by computing Bay's posterior probabilities and corresponding number of pixels for each tissue segments in MRI patient images. We evaluate improved tumor segmentation robustness using different similarity metric for 5 patients in T1, T2 and FLAIR modalities.

Prospective multi-centre Voxel Based Morphometry study employing scanner specific segmentations: Procedure development using CaliBrain structural MRI data

PubMed Central

2009-01-01

Background Structural Magnetic Resonance Imaging (sMRI) of the brain is employed in the assessment of a wide range of neuropsychiatric disorders. In order to improve statistical power in such studies it is desirable to pool scanning resources from multiple centres. The CaliBrain project was designed to provide for an assessment of scanner differences at three centres in Scotland, and to assess the practicality of pooling scans from multiple-centres. Methods We scanned healthy subjects twice on each of the 3 scanners in the CaliBrain project with T1-weighted sequences. The tissue classifier supplied within the Statistical Parametric Mapping (SPM5) application was used to map the grey and white tissue for each scan. We were thus able to assess within scanner variability and between scanner differences. We have sought to correct for between scanner differences by adjusting the probability mappings of tissue occupancy (tissue priors) used in SPM5 for tissue classification. The adjustment procedure resulted in separate sets of tissue priors being developed for each scanner and we refer to these as scanner specific priors. Results Voxel Based Morphometry (VBM) analyses and metric tests indicated that the use of scanner specific priors reduced tissue classification differences between scanners. However, the metric results also demonstrated that the between scanner differences were not reduced to the level of within scanner variability, the ideal for scanner harmonisation. Conclusion Our results indicate the development of scanner specific priors for SPM can assist in pooling of scan resources from different research centres. This can facilitate improvements in the statistical power of quantitative brain imaging studies. PMID:19445668

Brain tumour classification and abnormality detection using neuro-fuzzy technique and Otsu thresholding.

PubMed

Renjith, Arokia; Manjula, P; Mohan Kumar, P

2015-01-01

Brain tumour is one of the main causes for an increase in transience among children and adults. This paper proposes an improved method based on Magnetic Resonance Imaging (MRI) brain image classification and image segmentation approach. Automated classification is encouraged by the need of high accuracy when dealing with a human life. The detection of the brain tumour is a challenging problem, due to high diversity in tumour appearance and ambiguous tumour boundaries. MRI images are chosen for detection of brain tumours, as they are used in soft tissue determinations. First of all, image pre-processing is used to enhance the image quality. Second, dual-tree complex wavelet transform multi-scale decomposition is used to analyse texture of an image. Feature extraction extracts features from an image using gray-level co-occurrence matrix (GLCM). Then, the Neuro-Fuzzy technique is used to classify the stages of brain tumour as benign, malignant or normal based on texture features. Finally, tumour location is detected using Otsu thresholding. The classifier performance is evaluated based on classification accuracies. The simulated results show that the proposed classifier provides better accuracy than previous method.

Biomarkers for Musculoskeletal Pain Conditions: Use of Brain Imaging and Machine Learning.

PubMed

Boissoneault, Jeff; Sevel, Landrew; Letzen, Janelle; Robinson, Michael; Staud, Roland

2017-01-01

Chronic musculoskeletal pain condition often shows poor correlations between tissue abnormalities and clinical pain. Therefore, classification of pain conditions like chronic low back pain, osteoarthritis, and fibromyalgia depends mostly on self report and less on objective findings like X-ray or magnetic resonance imaging (MRI) changes. However, recent advances in structural and functional brain imaging have identified brain abnormalities in chronic pain conditions that can be used for illness classification. Because the analysis of complex and multivariate brain imaging data is challenging, machine learning techniques have been increasingly utilized for this purpose. The goal of machine learning is to train specific classifiers to best identify variables of interest on brain MRIs (i.e., biomarkers). This report describes classification techniques capable of separating MRI-based brain biomarkers of chronic pain patients from healthy controls with high accuracy (70-92%) using machine learning, as well as critical scientific, practical, and ethical considerations related to their potential clinical application. Although self-report remains the gold standard for pain assessment, machine learning may aid in the classification of chronic pain disorders like chronic back pain and fibromyalgia as well as provide mechanistic information regarding their neural correlates.

Interactive lesion segmentation on dynamic contrast enhanced breast MRI using a Markov model

NASA Astrophysics Data System (ADS)

Wu, Qiu; Salganicoff, Marcos; Krishnan, Arun; Fussell, Donald S.; Markey, Mia K.

2006-03-01

The purpose of this study is to develop a method for segmenting lesions on Dynamic Contrast-Enhanced (DCE) breast MRI. DCE breast MRI, in which the breast is imaged before, during, and after the administration of a contrast agent, enables a truly 3D examination of breast tissues. This functional angiogenic imaging technique provides noninvasive assessment of microcirculatory characteristics of tissues in addition to traditional anatomical structure information. Since morphological features and kinetic curves from segmented lesions are to be used for diagnosis and treatment decisions, lesion segmentation is a key pre-processing step for classification. In our study, the ROI is defined by a bounding box containing the enhancement region in the subtraction image, which is generated by subtracting the pre-contrast image from 1st post-contrast image. A maximum a posteriori (MAP) estimate of the class membership (lesion vs. non-lesion) for each voxel is obtained using the Iterative Conditional Mode (ICM) method. The prior distribution of the class membership is modeled as a multi-level logistic model, a Markov Random Field model in which the class membership of each voxel is assumed to depend upon its nearest neighbors only. The likelihood distribution is assumed to be Gaussian. The parameters of each Gaussian distribution are estimated from a dozen voxels manually selected as representative of the class. The experimental segmentation results demonstrate anatomically plausible breast tissue segmentation and the predicted class membership of voxels from the interactive segmentation algorithm agrees with the manual classifications made by inspection of the kinetic enhancement curves. The proposed method is advantageous in that it is efficient, flexible, and robust.

Joint deep shape and appearance learning: application to optic pathway glioma segmentation

NASA Astrophysics Data System (ADS)

Mansoor, Awais; Li, Ien; Packer, Roger J.; Avery, Robert A.; Linguraru, Marius George

2017-03-01

Automated tissue characterization is one of the major applications of computer-aided diagnosis systems. Deep learning techniques have recently demonstrated impressive performance for the image patch-based tissue characterization. However, existing patch-based tissue classification techniques struggle to exploit the useful shape information. Local and global shape knowledge such as the regional boundary changes, diameter, and volumetrics can be useful in classifying the tissues especially in scenarios where the appearance signature does not provide significant classification information. In this work, we present a deep neural network-based method for the automated segmentation of the tumors referred to as optic pathway gliomas (OPG) located within the anterior visual pathway (AVP; optic nerve, chiasm or tracts) using joint shape and appearance learning. Voxel intensity values of commonly used MRI sequences are generally not indicative of OPG. To be considered an OPG, current clinical practice dictates that some portion of AVP must demonstrate shape enlargement. The method proposed in this work integrates multiple sequence magnetic resonance image (T1, T2, and FLAIR) along with local boundary changes to train a deep neural network. For training and evaluation purposes, we used a dataset of multiple sequence MRI obtained from 20 subjects (10 controls, 10 NF1+OPG). To our best knowledge, this is the first deep representation learning-based approach designed to merge shape and multi-channel appearance data for the glioma detection. In our experiments, mean misclassification errors of 2:39% and 0:48% were observed respectively for glioma and control patches extracted from the AVP. Moreover, an overall dice similarity coefficient of 0:87+/-0:13 (0:93+/-0:06 for healthy tissue, 0:78+/-0:18 for glioma tissue) demonstrates the potential of the proposed method in the accurate localization and early detection of OPG.

A discrete polar Stockwell transform for enhanced characterization of tissue structure using MRI.

PubMed

Pridham, Glen; Steenwijk, Martijn D; Geurts, Jeroen J G; Zhang, Yunyan

2018-05-02

The purpose of this study was to present an effective algorithm for computing the discrete polar Stockwell transform (PST), investigate its unique multiscale and multi-orientation features, and explore potentially new applications including denoising and tissue segmentation. We investigated PST responses using both synthetic and MR images. Moreover, we compared the features of PST with both Gabor and Morlet wavelet transforms, and compared the PST with two wavelet approaches for denoising using MRI. Using a synthetic image, we also tested the edge effect of PST through signal-padding. Then, we constructed a partially supervised classifier using radial, marginal PST spectra of T2-weighted MRI, acquired from postmortem brains with multiple sclerosis. The classification involved three histology-verified tissue types: normal appearing white matter (NAWM), lesion, or other, along with 5-fold cross-validation. The PST generated a series of images with varying orientations or rotation-invariant scales. Radial frequencies highlighted image structures of different size, and angular frequencies enhanced structures by orientation. Signal-padding helped suppress boundary artifacts but required attention to incidental artifacts. In comparison, the Gabor transform produced more redundant images and the wavelet spectra appeared less spatially smooth than the PST. In addition, the PST demonstrated lower root-mean-square errors than other transforms in denoising and achieved a 93% accuracy for NAWM pixels (296/317), and 88% accuracy for lesion pixels (165/188) in MRI segmentation. The PST is a unique local spectral density-assessing tool which is sensitive to both structure orientations and scales. This may facilitate multiple new applications including advanced characterization of tissue structure in standard MRI. © 2018 International Society for Magnetic Resonance in Medicine.

Visual brain activity patterns classification with simultaneous EEG-fMRI: A multimodal approach.

PubMed

Ahmad, Rana Fayyaz; Malik, Aamir Saeed; Kamel, Nidal; Reza, Faruque; Amin, Hafeez Ullah; Hussain, Muhammad

2017-01-01

Classification of the visual information from the brain activity data is a challenging task. Many studies reported in the literature are based on the brain activity patterns using either fMRI or EEG/MEG only. EEG and fMRI considered as two complementary neuroimaging modalities in terms of their temporal and spatial resolution to map the brain activity. For getting a high spatial and temporal resolution of the brain at the same time, simultaneous EEG-fMRI seems to be fruitful. In this article, we propose a new method based on simultaneous EEG-fMRI data and machine learning approach to classify the visual brain activity patterns. We acquired EEG-fMRI data simultaneously on the ten healthy human participants by showing them visual stimuli. Data fusion approach is used to merge EEG and fMRI data. Machine learning classifier is used for the classification purposes. Results showed that superior classification performance has been achieved with simultaneous EEG-fMRI data as compared to the EEG and fMRI data standalone. This shows that multimodal approach improved the classification accuracy results as compared with other approaches reported in the literature. The proposed simultaneous EEG-fMRI approach for classifying the brain activity patterns can be helpful to predict or fully decode the brain activity patterns.

Brain MRI analysis for Alzheimer's disease diagnosis using an ensemble system of deep convolutional neural networks.

PubMed

Islam, Jyoti; Zhang, Yanqing

2018-05-31

Alzheimer's disease is an incurable, progressive neurological brain disorder. Earlier detection of Alzheimer's disease can help with proper treatment and prevent brain tissue damage. Several statistical and machine learning models have been exploited by researchers for Alzheimer's disease diagnosis. Analyzing magnetic resonance imaging (MRI) is a common practice for Alzheimer's disease diagnosis in clinical research. Detection of Alzheimer's disease is exacting due to the similarity in Alzheimer's disease MRI data and standard healthy MRI data of older people. Recently, advanced deep learning techniques have successfully demonstrated human-level performance in numerous fields including medical image analysis. We propose a deep convolutional neural network for Alzheimer's disease diagnosis using brain MRI data analysis. While most of the existing approaches perform binary classification, our model can identify different stages of Alzheimer's disease and obtains superior performance for early-stage diagnosis. We conducted ample experiments to demonstrate that our proposed model outperformed comparative baselines on the Open Access Series of Imaging Studies dataset.

Age-specific MRI brain and head templates for healthy adults from 20 through 89 years of age

PubMed Central

Fillmore, Paul T.; Phillips-Meek, Michelle C.; Richards, John E.

2015-01-01

This study created and tested a database of adult, age-specific MRI brain and head templates. The participants included healthy adults from 20 through 89 years of age. The templates were done in five-year, 10-year, and multi-year intervals from 20 through 89 years, and consist of average T1W for the head and brain, and segmenting priors for gray matter (GM), white matter (WM), and cerebrospinal fluid (CSF). It was found that age-appropriate templates provided less biased tissue classification estimates than age-inappropriate reference data and reference data based on young adult templates. This database is available for use by other investigators and clinicians for their MRI studies, as well as other types of neuroimaging and electrophysiological research.1 PMID:25904864

Age-specific MRI templates for pediatric neuroimaging

PubMed Central

Sanchez, Carmen E.; Richards, John E.; Almli, C. Robert

2012-01-01

This study created a database of pediatric age-specific MRI brain templates for normalization and segmentation. Participants included children from 4.5 through 19.5 years, totaling 823 scans from 494 subjects. Open-source processing programs (FSL, SPM, ANTS) constructed head, brain and segmentation templates in 6 month intervals. The tissue classification (WM, GM, CSF) showed changes over age similar to previous reports. A volumetric analysis of age-related changes in WM and GM based on these templates showed expected increase/decrease pattern in GM and an increase in WM over the sampled ages. This database is available for use for neuroimaging studies (blindedforreview). PMID:22799759

Combining anatomical, diffusion, and resting state functional magnetic resonance imaging for individual classification of mild and moderate Alzheimer's disease.

PubMed

Schouten, Tijn M; Koini, Marisa; de Vos, Frank; Seiler, Stephan; van der Grond, Jeroen; Lechner, Anita; Hafkemeijer, Anne; Möller, Christiane; Schmidt, Reinhold; de Rooij, Mark; Rombouts, Serge A R B

2016-01-01

Magnetic resonance imaging (MRI) is sensitive to structural and functional changes in the brain caused by Alzheimer's disease (AD), and can therefore be used to help in diagnosing the disease. Improving classification of AD patients based on MRI scans might help to identify AD earlier in the disease's progress, which may be key in developing treatments for AD. In this study we used an elastic net classifier based on several measures derived from the MRI scans of mild to moderate AD patients (N = 77) from the prospective registry on dementia study and controls (N = 173) from the Austrian Stroke Prevention Family Study. We based our classification on measures from anatomical MRI, diffusion weighted MRI and resting state functional MRI. Our unimodal classification performance ranged from an area under the curve (AUC) of 0.760 (full correlations between functional networks) to 0.909 (grey matter density). When combining measures from multiple modalities in a stepwise manner, the classification performance improved to an AUC of 0.952. This optimal combination consisted of grey matter density, white matter density, fractional anisotropy, mean diffusivity, and sparse partial correlations between functional networks. Classification performance for mild AD as well as moderate AD also improved when using this multimodal combination. We conclude that different MRI modalities provide complementary information for classifying AD. Moreover, combining multiple modalities can substantially improve classification performance over unimodal classification.

Defining active sacroiliitis on MRI for classification of axial spondyloarthritis: update by the ASAS MRI working group.

PubMed

Lambert, Robert G W; Bakker, Pauline A C; van der Heijde, Désirée; Weber, Ulrich; Rudwaleit, Martin; Hermann, K G; Sieper, Joachim; Baraliakos, Xenofon; Bennett, Alex; Braun, Jürgen; Burgos-Vargas, Rubén; Dougados, Maxime; Pedersen, Susanne Juhl; Jurik, Anne Grethe; Maksymowych, Walter P; Marzo-Ortega, Helena; Østergaard, Mikkel; Poddubnyy, Denis; Reijnierse, Monique; van den Bosch, Filip; van der Horst-Bruinsma, Irene; Landewé, Robert

2016-11-01

To review and update the existing definition of a positive MRI for classification of axial spondyloarthritis (SpA). The Assessment in SpondyloArthritis International Society (ASAS) MRI working group conducted a consensus exercise to review the definition of a positive MRI for inclusion in the ASAS classification criteria of axial SpA. Existing definitions and new data relevant to the MRI diagnosis and classification of sacroiliitis and spondylitis in axial SpA, published since the ASAS definition first appeared in print in 2009, were reviewed and discussed. The precise wording of the existing definition was examined in detail and the data and a draft proposal were presented to and voted on by the ASAS membership. The clear presence of bone marrow oedema on MRI in subchondral bone is still considered to be the defining observation that determines the presence of active sacroiliitis. Structural damage lesions seen on MRI may contribute to a decision by the observer that inflammatory lesions are genuinely due to SpA but are not required to meet the definition. The existing definition was clarified adding guidelines and images to assist in the application of the definition. The definition of a positive MRI for classification of axial SpA should continue to primarily depend on the imaging features of 'active sacroiliitis' until more data are available regarding MRI features of structural damage in the sacroiliac joint and MRI features in the spine and their utility when used for classification purposes. Published by the BMJ Publishing Group Limited. For permission to use (where not already granted under a licence) please go to http://www.bmj.com/company/products-services/rights-and-licensing/.

A discriminative model-constrained EM approach to 3D MRI brain tissue classification and intensity non-uniformity correction

NASA Astrophysics Data System (ADS)

Wels, Michael; Zheng, Yefeng; Huber, Martin; Hornegger, Joachim; Comaniciu, Dorin

2011-06-01

We describe a fully automated method for tissue classification, which is the segmentation into cerebral gray matter (GM), cerebral white matter (WM), and cerebral spinal fluid (CSF), and intensity non-uniformity (INU) correction in brain magnetic resonance imaging (MRI) volumes. It combines supervised MRI modality-specific discriminative modeling and unsupervised statistical expectation maximization (EM) segmentation into an integrated Bayesian framework. While both the parametric observation models and the non-parametrically modeled INUs are estimated via EM during segmentation itself, a Markov random field (MRF) prior model regularizes segmentation and parameter estimation. Firstly, the regularization takes into account knowledge about spatial and appearance-related homogeneity of segments in terms of pairwise clique potentials of adjacent voxels. Secondly and more importantly, patient-specific knowledge about the global spatial distribution of brain tissue is incorporated into the segmentation process via unary clique potentials. They are based on a strong discriminative model provided by a probabilistic boosting tree (PBT) for classifying image voxels. It relies on the surrounding context and alignment-based features derived from a probabilistic anatomical atlas. The context considered is encoded by 3D Haar-like features of reduced INU sensitivity. Alignment is carried out fully automatically by means of an affine registration algorithm minimizing cross-correlation. Both types of features do not immediately use the observed intensities provided by the MRI modality but instead rely on specifically transformed features, which are less sensitive to MRI artifacts. Detailed quantitative evaluations on standard phantom scans and standard real-world data show the accuracy and robustness of the proposed method. They also demonstrate relative superiority in comparison to other state-of-the-art approaches to this kind of computational task: our method achieves average Dice coefficients of 0.93 ± 0.03 (WM) and 0.90 ± 0.05 (GM) on simulated mono-spectral and 0.94 ± 0.02 (WM) and 0.92 ± 0.04 (GM) on simulated multi-spectral data from the BrainWeb repository. The scores are 0.81 ± 0.09 (WM) and 0.82 ± 0.06 (GM) and 0.87 ± 0.05 (WM) and 0.83 ± 0.12 (GM) for the two collections of real-world data sets—consisting of 20 and 18 volumes, respectively—provided by the Internet Brain Segmentation Repository.

The role of pre-treatment MRI in established cases of slipped capital femoral epiphysis.

PubMed

Tins, Bernhard; Cassar-Pullicino, Victor; McCall, Iain

2009-06-01

Slipped capital femoral epiphysis (SCFE) often results in functional impairment and premature osteoarthritis despite surgical treatment. Treatment decisions are commonly based on the clinical history and radiographic appearance. This study assesses the pre-treatment features of SCFE and correlates them to the clinical history to: (1) define the underlying pathological mechanisms; (2) correlate the morphological hip abnormalities with the clinical classifications; (3) identify specific magnetic resonance imaging (MRI) features that could carry prognostic implications for treatment approach and outcome. Clinical history and pre- and posttreatment radiographs and pre-treatment MRIs of 14 patients with 15 affected hips were reviewed. Alignment, impingement, fulcrum formation, remodelling, osteopenia, synovitis, joint effusion, bone marrow and soft tissue oedema and status of the physis and the periosteal sleeve were assessed and related to the clinical history, in particular history of trauma, duration of clinical symptoms and ability to bear weight. Bone marrow oedema around the growth plate and joint effusion occurred in all patients. Synovitis occurred in 13/15 patients. 6 patients had a fall before presenting with SCFE. 5/6 had periarticular soft tissue oedema, complete disruption of the physis and partial periosteal sleeve disruption. 9 patients had no fall prior to presentation, physis and periost were intact in 7/9; periarticular oedema was not seen. 14/15 showed evidence of chronic remodelling. Despite an acute clinical history remodelling was present. A fulcrum-like alignment, impingement of the epiphysis on the metaphysis with a small area of physical contact, was seen in 8 patients, 6/8 had a prior fall. There was no case of avascular necrosis. Spontaneous reduction of SCFE occurred in 1 case, the only case without chronic remodelling. With MRI as gold standard radiographs underestimate the severity of SCFE. Synovitis, periphyseal oedema and joint effusion are regular features of SCFE. The clinical history and findings are unreliable for the classification of SCFE. Radiographs underestimate the severity of SCFE. SCFE is often a Salter Harris I injury due to a fall with considerable periarticular soft tissue trauma and a potentially unstable alignment of epi- and metaphysis. This can lead to spontaneous reduction prior to surgery, MRI can potentially identify unstable, reducible slips. If the mode of surgical treatment depends on the particular nature of the SCFE then MRI contributes to surgical decision-making. Level 4, case series.

A discriminative model-constrained EM approach to 3D MRI brain tissue classification and intensity non-uniformity correction.

PubMed

Wels, Michael; Zheng, Yefeng; Huber, Martin; Hornegger, Joachim; Comaniciu, Dorin

2011-06-07

We describe a fully automated method for tissue classification, which is the segmentation into cerebral gray matter (GM), cerebral white matter (WM), and cerebral spinal fluid (CSF), and intensity non-uniformity (INU) correction in brain magnetic resonance imaging (MRI) volumes. It combines supervised MRI modality-specific discriminative modeling and unsupervised statistical expectation maximization (EM) segmentation into an integrated Bayesian framework. While both the parametric observation models and the non-parametrically modeled INUs are estimated via EM during segmentation itself, a Markov random field (MRF) prior model regularizes segmentation and parameter estimation. Firstly, the regularization takes into account knowledge about spatial and appearance-related homogeneity of segments in terms of pairwise clique potentials of adjacent voxels. Secondly and more importantly, patient-specific knowledge about the global spatial distribution of brain tissue is incorporated into the segmentation process via unary clique potentials. They are based on a strong discriminative model provided by a probabilistic boosting tree (PBT) for classifying image voxels. It relies on the surrounding context and alignment-based features derived from a probabilistic anatomical atlas. The context considered is encoded by 3D Haar-like features of reduced INU sensitivity. Alignment is carried out fully automatically by means of an affine registration algorithm minimizing cross-correlation. Both types of features do not immediately use the observed intensities provided by the MRI modality but instead rely on specifically transformed features, which are less sensitive to MRI artifacts. Detailed quantitative evaluations on standard phantom scans and standard real-world data show the accuracy and robustness of the proposed method. They also demonstrate relative superiority in comparison to other state-of-the-art approaches to this kind of computational task: our method achieves average Dice coefficients of 0.93 ± 0.03 (WM) and 0.90 ± 0.05 (GM) on simulated mono-spectral and 0.94 ± 0.02 (WM) and 0.92 ± 0.04 (GM) on simulated multi-spectral data from the BrainWeb repository. The scores are 0.81 ± 0.09 (WM) and 0.82 ± 0.06 (GM) and 0.87 ± 0.05 (WM) and 0.83 ± 0.12 (GM) for the two collections of real-world data sets-consisting of 20 and 18 volumes, respectively-provided by the Internet Brain Segmentation Repository.

Probabilistic multiple sclerosis lesion classification based on modeling regional intensity variability and local neighborhood information.

PubMed

Harmouche, Rola; Subbanna, Nagesh K; Collins, D Louis; Arnold, Douglas L; Arbel, Tal

2015-05-01

In this paper, a fully automatic probabilistic method for multiple sclerosis (MS) lesion classification is presented, whereby the posterior probability density function over healthy tissues and two types of lesions (T1-hypointense and T2-hyperintense) is generated at every voxel. During training, the system explicitly models the spatial variability of the intensity distributions throughout the brain by first segmenting it into distinct anatomical regions and then building regional likelihood distributions for each tissue class based on multimodal magnetic resonance image (MRI) intensities. Local class smoothness is ensured by incorporating neighboring voxel information in the prior probability through Markov random fields. The system is tested on two datasets from real multisite clinical trials consisting of multimodal MRIs from a total of 100 patients with MS. Lesion classification results based on the framework are compared with and without the regional information, as well as with other state-of-the-art methods against the labels from expert manual raters. The metrics for comparison include Dice overlap, sensitivity, and positive predictive rates for both voxel and lesion classifications. Statistically significant improvements in Dice values ( ), for voxel-based and lesion-based sensitivity values ( ), and positive predictive rates ( and respectively) are shown when the proposed method is compared to the method without regional information, and to a widely used method [1]. This holds particularly true in the posterior fossa, an area where classification is very challenging. The proposed method allows us to provide clinicians with accurate tissue labels for T1-hypointense and T2-hyperintense lesions, two types of lesions that differ in appearance and clinical ramifications, and with a confidence level in the classification, which helps clinicians assess the classification results.

Intraoperative optical biopsy for brain tumors using spectro-lifetime properties of intrinsic fluorophores

NASA Astrophysics Data System (ADS)

Vasefi, Fartash; Kittle, David S.; Nie, Zhaojun; Falcone, Christina; Patil, Chirag G.; Chu, Ray M.; Mamelak, Adam N.; Black, Keith L.; Butte, Pramod V.

2016-04-01

We have developed and tested a system for real-time intra-operative optical identification and classification of brain tissues using time-resolved fluorescence spectroscopy (TRFS). A supervised learning algorithm using linear discriminant analysis (LDA) employing selected intrinsic fluorescence decay temporal points in 6 spectral bands was employed to maximize statistical significance difference between training groups. The linear discriminant analysis on in vivo human tissues obtained by TRFS measurements (N = 35) were validated by histopathologic analysis and neuronavigation correlation to pre-operative MRI images. These results demonstrate that TRFS can differentiate between normal cortex, white matter and glioma.

Subject-Specific Sparse Dictionary Learning for Atlas-Based Brain MRI Segmentation.

PubMed

Roy, Snehashis; He, Qing; Sweeney, Elizabeth; Carass, Aaron; Reich, Daniel S; Prince, Jerry L; Pham, Dzung L

2015-09-01

Quantitative measurements from segmentations of human brain magnetic resonance (MR) images provide important biomarkers for normal aging and disease progression. In this paper, we propose a patch-based tissue classification method from MR images that uses a sparse dictionary learning approach and atlas priors. Training data for the method consists of an atlas MR image, prior information maps depicting where different tissues are expected to be located, and a hard segmentation. Unlike most atlas-based classification methods that require deformable registration of the atlas priors to the subject, only affine registration is required between the subject and training atlas. A subject-specific patch dictionary is created by learning relevant patches from the atlas. Then the subject patches are modeled as sparse combinations of learned atlas patches leading to tissue memberships at each voxel. The combination of prior information in an example-based framework enables us to distinguish tissues having similar intensities but different spatial locations. We demonstrate the efficacy of the approach on the application of whole-brain tissue segmentation in subjects with healthy anatomy and normal pressure hydrocephalus, as well as lesion segmentation in multiple sclerosis patients. For each application, quantitative comparisons are made against publicly available state-of-the art approaches.

A software tool for automatic classification and segmentation of 2D/3D medical images

NASA Astrophysics Data System (ADS)

Strzelecki, Michal; Szczypinski, Piotr; Materka, Andrzej; Klepaczko, Artur

2013-02-01

Modern medical diagnosis utilizes techniques of visualization of human internal organs (CT, MRI) or of its metabolism (PET). However, evaluation of acquired images made by human experts is usually subjective and qualitative only. Quantitative analysis of MR data, including tissue classification and segmentation, is necessary to perform e.g. attenuation compensation, motion detection, and correction of partial volume effect in PET images, acquired with PET/MR scanners. This article presents briefly a MaZda software package, which supports 2D and 3D medical image analysis aiming at quantification of image texture. MaZda implements procedures for evaluation, selection and extraction of highly discriminative texture attributes combined with various classification, visualization and segmentation tools. Examples of MaZda application in medical studies are also provided.

Prediction of pathologic staging with magnetic resonance imaging after preoperative chemoradiotherapy in rectal cancer: pooled analysis of KROG 10-01 and 11-02.

PubMed

Lee, Jong Hoon; Jang, Hong Seok; Kim, Jun-Gi; Lee, Myung Ah; Kim, Dae Yong; Kim, Tae Hyun; Oh, Jae Hwan; Park, Sung Chan; Kim, Sun Young; Baek, Ji Yeon; Park, Hee Chul; Kim, Hee Cheol; Nam, Taek-Keun; Chie, Eui Kyu; Jung, Ji-Han; Oh, Seong Taek

2014-10-01

The reported overall accuracy of MRI in predicting the pathologic stage of nonirradiated rectal cancer is high. However, the role of MRI in restaging rectal tumors after neoadjuvant CRT is contentious. Thus, we evaluate the accuracy of restaging magnetic resonance imaging (MRI) for rectal cancer patients who receive preoperative chemoradiotherapy (CRT). We analyzed 150 patients with locally advanced rectal cancer (T3-4N0-2) who had received preoperative CRT. Pre-CRT MRI was performed for local tumor and nodal staging. All patients underwent restaging MRI followed by total mesorectal excision after the end of radiotherapy. The primary endpoint of the present study was to estimate the accuracy of post-CRT MRI as compared with pathologic staging. Pathologic T classification matched the post-CRT MRI findings in 97 (64.7%) of 150 patients. 36 (24.0%) of 150 patients were overstaged in T classification, and the concordance degree was moderate (k=0.33, p<0.01). Pathologic N classification matched the post-CRI MRI findings in 85 (56.6%) of 150 patients. 54 (36.0%) of 150 patients were overstaged in N classification. 26 patients achieved downstaging (ycT0-2N0) on restaging MRI after CRT. 23 (88.5%) of 26 patients who had been downstaged on MRI after CRT were confirmed on the pathological staging, and the concordance degree was good (k=0.72, p<0.01). Restaging MRI has low accuracy for the prediction of the pathologic T and N classifications in rectal cancer patients who received preoperative CRT. The diagnostic accuracy of restaging MRI is relatively high in rectal cancer patients who achieved clinical downstaging after CRT. Copyright © 2014 Elsevier Ireland Ltd. All rights reserved.

A modified method for MRF segmentation and bias correction of MR image with intensity inhomogeneity.

PubMed

Xie, Mei; Gao, Jingjing; Zhu, Chongjin; Zhou, Yan

2015-01-01

Markov random field (MRF) model is an effective method for brain tissue classification, which has been applied in MR image segmentation for decades. However, it falls short of the expected classification in MR images with intensity inhomogeneity for the bias field is not considered in the formulation. In this paper, we propose an interleaved method joining a modified MRF classification and bias field estimation in an energy minimization framework, whose initial estimation is based on k-means algorithm in view of prior information on MRI. The proposed method has a salient advantage of overcoming the misclassifications from the non-interleaved MRF classification for the MR image with intensity inhomogeneity. In contrast to other baseline methods, experimental results also have demonstrated the effectiveness and advantages of our algorithm via its applications in the real and the synthetic MR images.

Can glenoid wear be accurately assessed using x-ray imaging? Evaluating agreement of x-ray and magnetic resonance imaging (MRI) Walch classification.

PubMed

Kopka, Michaela; Fourman, Mitchell; Soni, Ashish; Cordle, Andrew C; Lin, Albert

2017-09-01

The Walch classification is the most recognized means of assessing glenoid wear in preoperative planning for shoulder arthroplasty. This classification relies on advanced imaging, which is more expensive and less practical than plain radiographs. The purpose of this study was to determine whether the Walch classification could be accurately applied to x-ray images compared with magnetic resonance imaging (MRI) as the gold standard. We hypothesized that x-ray images cannot adequately replace advanced imaging in the evaluation of glenoid wear. Preoperative axillary x-ray images and MRI scans of 50 patients assessed for shoulder arthroplasty were independently reviewed by 5 raters. Glenoid wear was individually classified according to the Walch classification using each imaging modality. The raters then collectively reviewed the MRI scans and assigned a consensus classification to serve as the gold standard. The κ coefficient was used to determine interobserver agreement for x-ray images and independent MRI reads, as well as the agreement between x-ray images and consensus MRI. The inter-rater agreement for x-ray images and MRIs was "moderate" (κ = 0.42 and κ = 0.47, respectively) for the 5-category Walch classification (A1, A2, B1, B2, C) and "moderate" (κ = 0.54 and κ = 0.59, respectively) for the 3-category Walch classification (A, B, C). The agreement between x-ray images and consensus MRI was much lower: "fair-to-moderate" (κ = 0.21-0.51) for the 5-category and "moderate" (κ = 0.36-0.60) for the 3-category Walch classification. The inter-rater agreement between x-ray images and consensus MRI is "fair-to-moderate." This is lower than the previously reported reliability of the Walch classification using computed tomography scans. Accordingly, x-ray images are inferior to advanced imaging when assessing glenoid wear. Copyright © 2017 Journal of Shoulder and Elbow Surgery Board of Trustees. Published by Elsevier Inc. All rights reserved.

A hybrid method for classifying cognitive states from fMRI data.

PubMed

Parida, S; Dehuri, S; Cho, S-B; Cacha, L A; Poznanski, R R

2015-09-01

Functional magnetic resonance imaging (fMRI) makes it possible to detect brain activities in order to elucidate cognitive-states. The complex nature of fMRI data requires under-standing of the analyses applied to produce possible avenues for developing models of cognitive state classification and improving brain activity prediction. While many models of classification task of fMRI data analysis have been developed, in this paper, we present a novel hybrid technique through combining the best attributes of genetic algorithms (GAs) and ensemble decision tree technique that consistently outperforms all other methods which are being used for cognitive-state classification. Specifically, this paper illustrates the combined effort of decision-trees ensemble and GAs for feature selection through an extensive simulation study and discusses the classification performance with respect to fMRI data. We have shown that our proposed method exhibits significant reduction of the number of features with clear edge classification accuracy over ensemble of decision-trees.

SU-E-J-219: A Dixon Based Pseudo-CT Generation Method for MR-Only Radiotherapy Treatment Planning of the Pelvis and Head and Neck

DOE Office of Scientific and Technical Information (OSTI.GOV)

Maspero, M.; Meijer, G.J.; Lagendijk, J.J.W.

2015-06-15

Purpose: To develop an image processing method for MRI-based generation of electron density maps, known as pseudo-CT (pCT), without usage of model- or atlas-based segmentation, and to evaluate the method in the pelvic and head-neck region against CT. Methods: CT and MRI scans were obtained from the pelvic region of four patients in supine position using a flat table top only for CT. Stratified CT maps were generated by classifying each voxel based on HU ranges into one of four classes: air, adipose tissue, soft tissue or bone.A hierarchical region-selective algorithm, based on automatic thresholding and clustering, was used tomore » classify tissues from MR Dixon reconstructed fat, In-Phase (IP) and Opposed-Phase (OP) images. First, a body mask was obtained by thresholding the IP image. Subsequently, an automatic threshold on the Dixon fat image differentiated soft and adipose tissue. K-means clustering on IP and OP images resulted in a mask that, via a connected neighborhood analysis, allowing the user to select the components corresponding to bone structures.The pCT was estimated through assignment of bulk HU to the tissue classes. Bone-only Digital Reconstructed Radiographs (DRR) were generated as well. The pCT images were rigidly registered to the stratified CT to allow a volumetric and voxelwise comparison. Moreover, pCTs were also calculated within the head-neck region in two volunteers using the same pipeline. Results: The volumetric comparison resulted in differences <1% for each tissue class. A voxelwise comparison showed a good classification, ranging from 64% to 98%. The primary misclassified classes were adipose/soft tissue and bone/soft tissue. As the patients have been imaged on different table tops, part of the misclassification error can be explained by misregistration. Conclusion: The proposed approach does not rely on an anatomy model providing the flexibility to successfully generate the pCT in two different body sites. This research is founded by ZonMw IMDI Programme, project name: “RASOR sharp: MRI based radiotherapy planning using a single MRI sequence”, project number: 10-104003010.« less

Classification of human coronary atherosclerotic plaques using ex vivo high-resolution multicontrast-weighted MRI compared with histopathology.

PubMed

Li, Tao; Li, Xin; Zhao, Xihai; Zhou, Weihua; Cai, Zulong; Yang, Li; Guo, Aitao; Zhao, Shaohong

2012-05-01

The objective of our study was to evaluate the feasibility of ex vivo high-resolution multicontrast-weighted MRI to accurately classify human coronary atherosclerotic plaques according to the American Heart Association classification. Thirteen human cadaver heart specimens were imaged using high-resolution multicontrast-weighted MR technique (T1-weighted, proton density-weighted, and T2-weighted). All MR images were matched with histopathologic sections according to the landmark of the bifurcation of the left main coronary artery. The sensitivity and specificity of MRI for the classification of plaques were determined, and Cohen's kappa analysis was applied to evaluate the agreement between MRI and histopathology in the classification of atherosclerotic plaques. One hundred eleven MR cross-sectional images obtained perpendicular to the long axis of the proximal left anterior descending artery were successfully matched with the histopathologic sections. For the classification of plaques, the sensitivity and specificity of MRI were as follows: type I-II (near normal), 60% and 100%; type III (focal lipid pool), 80% and 100%; type IV-V (lipid, necrosis, fibrosis), 96.2% and 88.2%; type VI (hemorrhage), 100% and 99.0%; type VII (calcification), 93% and 100%; and type VIII (fibrosis without lipid core), 100% and 99.1%, respectively. Isointensity, which indicates lipid composition on histopathology, was detected on MRI in 48.8% of calcified plaques. Agreement between MRI and histopathology for plaque classification was 0.86 (p < 0.001). Ex vivo high-resolution multicontrast-weighted MRI can accurately classify advanced atherosclerotic plaques in human coronary arteries.

Pairwise Classifier Ensemble with Adaptive Sub-Classifiers for fMRI Pattern Analysis.

PubMed

Kim, Eunwoo; Park, HyunWook

2017-02-01

The multi-voxel pattern analysis technique is applied to fMRI data for classification of high-level brain functions using pattern information distributed over multiple voxels. In this paper, we propose a classifier ensemble for multiclass classification in fMRI analysis, exploiting the fact that specific neighboring voxels can contain spatial pattern information. The proposed method converts the multiclass classification to a pairwise classifier ensemble, and each pairwise classifier consists of multiple sub-classifiers using an adaptive feature set for each class-pair. Simulated and real fMRI data were used to verify the proposed method. Intra- and inter-subject analyses were performed to compare the proposed method with several well-known classifiers, including single and ensemble classifiers. The comparison results showed that the proposed method can be generally applied to multiclass classification in both simulations and real fMRI analyses.

Comparing the MRI-based Goutallier Classification to an experimental quantitative MR spectroscopic fat measurement of the supraspinatus muscle.

PubMed

Gilbert, Fabian; Böhm, Dirk; Eden, Lars; Schmalzl, Jonas; Meffert, Rainer H; Köstler, Herbert; Weng, Andreas M; Ziegler, Dirk

2016-08-22

The Goutallier Classification is a semi quantitative classification system to determine the amount of fatty degeneration in rotator cuff muscles. Although initially proposed for axial computer tomography scans it is currently applied to magnet-resonance-imaging-scans. The role for its clinical use is controversial, as the reliability of the classification has been shown to be inconsistent. The purpose of this study was to compare the semi quantitative MRI-based Goutallier Classification applied by 5 different raters to experimental MR spectroscopic quantitative fat measurement in order to determine the correlation between this classification system and the true extent of fatty degeneration shown by spectroscopy. MRI-scans of 42 patients with rotator cuff tears were examined by 5 shoulder surgeons and were graduated according to the MRI-based Goutallier Classification proposed by Fuchs et al. Additionally the fat/water ratio was measured with MR spectroscopy using the experimental SPLASH technique. The semi quantitative grading according to the Goutallier Classification was statistically correlated with the quantitative measured fat/water ratio using Spearman's rank correlation. Statistical analysis of the data revealed only fair correlation of the Goutallier Classification system and the quantitative fat/water ratio with R = 0.35 (p < 0.05). By dichotomizing the scale the correlation was 0.72. The interobserver and intraobserver reliabilities were substantial with R = 0.62 and R = 0.74 (p < 0.01). The correlation between the semi quantitative MRI based Goutallier Classification system and MR spectroscopic fat measurement is weak. As an adequate estimation of fatty degeneration based on standard MRI may not be possible, quantitative methods need to be considered in order to increase diagnostic safety and thus provide patients with ideal care in regard to the amount of fatty degeneration. Spectroscopic MR measurement may increase the accuracy of the Goutallier classification and thus improve the prediction of clinical results after rotator cuff repair. However, these techniques are currently only available in an experimental setting.

High-resolution 3-T MRI of the triangular fibrocartilage complex in the wrist: injury pattern and MR features.

PubMed

Zhan, Huili; Zhang, Huibo; Bai, Rongjie; Qian, Zhanhua; Liu, Yue; Zhang, Heng; Yin, Yuming

2017-12-01

To investigate if using high-resolution 3-T MRI can identify additional injuries of the triangular fibrocartilage complex (TFCC) beyond the Palmer classification. Eighty-six patients with surgically proven TFCC injury were included in this study. All patients underwent high-resolution 3-T MRI of the injured wrist. The MR imaging features of TFCC were analyzed according to the Palmer classification. According to the Palmer classification, 69 patients could be classified as having Palmer injuries (52 had traumatic tears and 17 had degenerative tears). There were 17 patients whose injuries could not be classified according to the Palmer classification: 13 had volar or dorsal capsular TFC detachment and 4 had a horizontal tear of the articular disk. Using high-resolution 3-T MRI, we have not only found all the TFCC injuries described in the Palmer classification, additional injury types were found in this study, including horizontal tear of the TFC and capsular TFC detachment. We propose the modified Palmer classification and add the injury types that were not included in the original Palmer classification.

Development of a computer aided diagnosis model for prostate cancer classification on multi-parametric MRI

NASA Astrophysics Data System (ADS)

Alfano, R.; Soetemans, D.; Bauman, G. S.; Gibson, E.; Gaed, M.; Moussa, M.; Gomez, J. A.; Chin, J. L.; Pautler, S.; Ward, A. D.

2018-02-01

Multi-parametric MRI (mp-MRI) is becoming a standard in contemporary prostate cancer screening and diagnosis, and has shown to aid physicians in cancer detection. It offers many advantages over traditional systematic biopsy, which has shown to have very high clinical false-negative rates of up to 23% at all stages of the disease. However beneficial, mp-MRI is relatively complex to interpret and suffers from inter-observer variability in lesion localization and grading. Computer-aided diagnosis (CAD) systems have been developed as a solution as they have the power to perform deterministic quantitative image analysis. We measured the accuracy of such a system validated using accurately co-registered whole-mount digitized histology. We trained a logistic linear classifier (LOGLC), support vector machine (SVC), k-nearest neighbour (KNN) and random forest classifier (RFC) in a four part ROI based experiment against: 1) cancer vs. non-cancer, 2) high-grade (Gleason score ≥4+3) vs. low-grade cancer (Gleason score <4+3), 3) high-grade vs. other tissue components and 4) high-grade vs. benign tissue by selecting the classifier with the highest AUC using 1-10 features from forward feature selection. The CAD model was able to classify malignant vs. benign tissue and detect high-grade cancer with high accuracy. Once fully validated, this work will form the basis for a tool that enhances the radiologist's ability to detect malignancies, potentially improving biopsy guidance, treatment selection, and focal therapy for prostate cancer patients, maximizing the potential for cure and increasing quality of life.

Classification of multiple sclerosis patients by latent class analysis of magnetic resonance imaging characteristics.

PubMed

Zwemmer, J N P; Berkhof, J; Castelijns, J A; Barkhof, F; Polman, C H; Uitdehaag, B M J

2006-10-01

Disease heterogeneity is a major issue in multiple sclerosis (MS). Classification of MS patients is usually based on clinical characteristics. More recently, a pathological classification has been presented. While clinical subtypes differ by magnetic resonance imaging (MRI) signature on a group level, a classification of individual MS patients based purely on MRI characteristics has not been presented so far. To investigate whether a restricted classification of MS patients can be made based on a combination of quantitative and qualitative MRI characteristics and to test whether the resulting subgroups are associated with clinical and laboratory characteristics. MRI examinations of the brain and spinal cord of 50 patients were scored for 21 quantitative and qualitative characteristics. Using latent class analysis, subgroups were identified, for whom disease characteristics and laboratory measures were compared. Latent class analysis revealed two subgroups that mainly differed in the extent of lesion confluency and MRI correlates of neuronal loss in the brain. Demographics and disease characteristics were comparable except for cognitive deficits. No correlations with laboratory measures were found. Latent class analysis offers a feasible approach for classifying subgroups of MS patients based on the presence of MRI characteristics. The reproducibility, longitudinal evolution and further clinical or prognostic relevance of the observed classification will have to be explored in a larger and independent sample of patients.

Geometric distortion correction in prostate diffusion-weighted MRI and its effect on quantitative apparent diffusion coefficient analysis.

PubMed

Nketiah, Gabriel; Selnaes, Kirsten M; Sandsmark, Elise; Teruel, Jose R; Krüger-Stokke, Brage; Bertilsson, Helena; Bathen, Tone F; Elschot, Mattijs

2018-05-01

To evaluate the effect of correction for B 0 inhomogeneity-induced geometric distortion in echo-planar diffusion-weighted imaging on quantitative apparent diffusion coefficient (ADC) analysis in multiparametric prostate MRI. Geometric distortion correction was performed in echo-planar diffusion-weighted images (b = 0, 50, 400, 800 s/mm 2 ) of 28 patients, using two b 0 scans with opposing phase-encoding polarities. Histology-matched tumor and healthy tissue volumes of interest delineated on T 2 -weighted images were mapped to the nondistortion-corrected and distortion-corrected data sets by resampling with and without spatial coregistration. The ADC values were calculated on the volume and voxel level. The effect of distortion correction on ADC quantification and tissue classification was evaluated using linear-mixed models and logistic regression, respectively. Without coregistration, the absolute differences in tumor ADC (range: 0.0002-0.189 mm 2 /s×10 -3 (volume level); 0.014-0.493 mm 2 /s×10 -3 (voxel level)) between the nondistortion-corrected and distortion-corrected were significantly associated (P < 0.05) with distortion distance (mean: 1.4 ± 1.3 mm; range: 0.3-5.3 mm). No significant associations were found upon coregistration; however, in patients with high rectal gas residue, distortion correction resulted in improved spatial representation and significantly better classification of healthy versus tumor voxels (P < 0.05). Geometric distortion correction in DWI could improve quantitative ADC analysis in multiparametric prostate MRI. Magn Reson Med 79:2524-2532, 2018. © 2017 International Society for Magnetic Resonance in Medicine. © 2017 International Society for Magnetic Resonance in Medicine.

Automated brain tumour detection and segmentation using superpixel-based extremely randomized trees in FLAIR MRI.

PubMed

Soltaninejad, Mohammadreza; Yang, Guang; Lambrou, Tryphon; Allinson, Nigel; Jones, Timothy L; Barrick, Thomas R; Howe, Franklyn A; Ye, Xujiong

2017-02-01

We propose a fully automated method for detection and segmentation of the abnormal tissue associated with brain tumour (tumour core and oedema) from Fluid- Attenuated Inversion Recovery (FLAIR) Magnetic Resonance Imaging (MRI). The method is based on superpixel technique and classification of each superpixel. A number of novel image features including intensity-based, Gabor textons, fractal analysis and curvatures are calculated from each superpixel within the entire brain area in FLAIR MRI to ensure a robust classification. Extremely randomized trees (ERT) classifier is compared with support vector machine (SVM) to classify each superpixel into tumour and non-tumour. The proposed method is evaluated on two datasets: (1) Our own clinical dataset: 19 MRI FLAIR images of patients with gliomas of grade II to IV, and (2) BRATS 2012 dataset: 30 FLAIR images with 10 low-grade and 20 high-grade gliomas. The experimental results demonstrate the high detection and segmentation performance of the proposed method using ERT classifier. For our own cohort, the average detection sensitivity, balanced error rate and the Dice overlap measure for the segmented tumour against the ground truth are 89.48 %, 6 % and 0.91, respectively, while, for the BRATS dataset, the corresponding evaluation results are 88.09 %, 6 % and 0.88, respectively. This provides a close match to expert delineation across all grades of glioma, leading to a faster and more reproducible method of brain tumour detection and delineation to aid patient management.

Myocardial perfusion quantification using simultaneously acquired 13 NH3 -ammonia PET and dynamic contrast-enhanced MRI in patients at rest and stress.

PubMed

Kunze, Karl P; Nekolla, Stephan G; Rischpler, Christoph; Zhang, Shelley HuaLei; Hayes, Carmel; Langwieser, Nicolas; Ibrahim, Tareq; Laugwitz, Karl-Ludwig; Schwaiger, Markus

2018-04-19

Systematic differences with respect to myocardial perfusion quantification exist between DCE-MRI and PET. Using the potential of integrated PET/MRI, this study was conceived to compare perfusion quantification on the basis of simultaneously acquired 13 NH 3 -ammonia PET and DCE-MRI data in patients at rest and stress. Twenty-nine patients were examined on a 3T PET/MRI scanner. DCE-MRI was implemented in dual-sequence design and additional T 1 mapping for signal normalization. Four different deconvolution methods including a modified version of the Fermi technique were compared against 13 NH 3 -ammonia results. Cohort-average flow comparison yielded higher resting flows for DCE-MRI than for PET and, therefore, significantly lower DCE-MRI perfusion ratios under the common assumption of equal arterial and tissue hematocrit. Absolute flow values were strongly correlated in both slice-average (R 2  = 0.82) and regional (R 2  = 0.7) evaluations. Different DCE-MRI deconvolution methods yielded similar flow result with exception of an unconstrained Fermi method exhibiting outliers at high flows when compared with PET. Thresholds for Ischemia classification may not be directly tradable between PET and MRI flow values. Differences in perfusion ratios between PET and DCE-MRI may be lifted by using stress/rest-specific hematocrit conversion. Proper physiological constraints are advised in model-constrained deconvolution. © 2018 International Society for Magnetic Resonance in Medicine.

[Magnetic resonance semiotics of prostate cancer according to the PI-RADS classification. The clinical diagnostic algorithm of a study].

PubMed

Korobkin, A S; Shariya, M A; Chaban, A S; Voskanvan, G A; Vinarov, A Z

2015-01-01

to elaborate the magnetic resonance imaging (MRI) signs of prostate cancer (PC) in accordance with the PI-RADS classification during multiparametric MRI (mpMRI). A total of 89 men aged 20 to 82 years were examined. A control group consisted of 8 (9%) healthy volunteers younger than 30 years of age with no urological history to obtain control images and MRI plots and 20 (22.5%) men aged 26-76 years, whose morphological changes were inflammatory and hyperplastic. The second age-matched group included 61 (68.5%) patients diagnosed with prostate cancer at morphological examination. A set of studies included digital rectal examination, serum prostate-specific antigen, and transrectal ultrasound-guided prostate biopsy. All the patients underwent prostate mpMRI applying a 3.0 T Achieva MRI scanner (Philips, the Netherlands). The patients have been found to have mpMRI signs that were typical of PC; its MRI semiotics according to the PI-RADS classification is presented. Each mpMRI procedure has been determined to be of importance and informative value in detecting PC. The comprehensive mpMRI approach to diagnosing PC improves the quality and diagnostic value of prostate MRI.

Phenotypic characterization of glioblastoma identified through shape descriptors

NASA Astrophysics Data System (ADS)

Chaddad, Ahmad; Desrosiers, Christian; Toews, Matthew

2016-03-01

This paper proposes quantitatively describing the shape of glioblastoma (GBM) tissue phenotypes as a set of shape features derived from segmentations, for the purposes of discriminating between GBM phenotypes and monitoring tumor progression. GBM patients were identified from the Cancer Genome Atlas, and quantitative MR imaging data were obtained from the Cancer Imaging Archive. Three GBM tissue phenotypes are considered including necrosis, active tumor and edema/invasion. Volumetric tissue segmentations are obtained from registered T1˗weighted (T1˗WI) postcontrast and fluid-attenuated inversion recovery (FLAIR) MRI modalities. Shape features are computed from respective tissue phenotype segmentations, and a Kruskal-Wallis test was employed to select features capable of classification with a significance level of p < 0.05. Several classifier models are employed to distinguish phenotypes, where a leave-one-out cross-validation was performed. Eight features were found statistically significant for classifying GBM phenotypes with p <0.05, orientation is uninformative. Quantitative evaluations show the SVM results in the highest classification accuracy of 87.50%, sensitivity of 94.59% and specificity of 92.77%. In summary, the shape descriptors proposed in this work show high performance in predicting GBM tissue phenotypes. They are thus closely linked to morphological characteristics of GBM phenotypes and could potentially be used in a computer assisted labeling system.

Intra- and interrater reliability of three different MRI grading and classification systems after acute hamstring injuries.

PubMed

Wangensteen, Arnlaug; Tol, Johannes L; Roemer, Frank W; Bahr, Roald; Dijkstra, H Paul; Crema, Michel D; Farooq, Abdulaziz; Guermazi, Ali

2017-04-01

To assess and compare the intra- and interrater reliability of three different MRI grading and classification systems after acute hamstring injury. Male athletes (n=40) with clinical diagnosis of acute hamstring injury and MRI ≤5days were selected from a prospective cohort. Two radiologists independently evaluated the MRIs using standardised scoring form including the modified Peetrons grading system, the Chan acute muscle strain injury classification and the British Athletics Muscle Injury Classification. Intra-and interrater reliability was assessed with linear weighted kappa (κ) or unweighted Cohen's κ and percentage agreement was calculated. We observed 'substantial' to 'almost perfect' intra- (κ range 0.65-1.00) and interrater reliability (κ range 0.77-1.00) with percentage agreement 83-100% and 88-100%, respectively, for severity gradings, overall anatomical sites and overall classifications for the three MRI systems. We observed substantial variability (κ range -0.05 to 1.00) for subcategories within the Chan classification and the British Athletics Muscle Injury Classification, however, the prevalence of positive scorings was low for some subcategories. The modified Peetrons grading system, overall Chan classification and overall British Athletics Muscle Injury Classification demonstrated 'substantial' to 'almost perfect' intra- and interrater reliability when scored by experienced radiologists. The intra- and interrater reliability for the anatomical subcategories within the classifications remains unclear. Copyright © 2017 Elsevier B.V. All rights reserved.

Multimodal Classification of Schizophrenia Patients with MEG and fMRI Data Using Static and Dynamic Connectivity Measures

PubMed Central

Cetin, Mustafa S.; Houck, Jon M.; Rashid, Barnaly; Agacoglu, Oktay; Stephen, Julia M.; Sui, Jing; Canive, Jose; Mayer, Andy; Aine, Cheryl; Bustillo, Juan R.; Calhoun, Vince D.

2016-01-01

Mental disorders like schizophrenia are currently diagnosed by physicians/psychiatrists through clinical assessment and their evaluation of patient's self-reported experiences as the illness emerges. There is great interest in identifying biological markers of prognosis at the onset of illness, rather than relying on the evolution of symptoms across time. Functional network connectivity, which indicates a subject's overall level of “synchronicity” of activity between brain regions, demonstrates promise in providing individual subject predictive power. Many previous studies reported functional connectivity changes during resting-state using only functional magnetic resonance imaging (fMRI). Nevertheless, exclusive reliance on fMRI to generate such networks may limit the inference of the underlying dysfunctional connectivity, which is hypothesized to be a factor in patient symptoms, as fMRI measures connectivity via hemodynamics. Therefore, combination of connectivity assessments using fMRI and magnetoencephalography (MEG), which more directly measures neuronal activity, may provide improved classification of schizophrenia than either modality alone. Moreover, recent evidence indicates that metrics of dynamic connectivity may also be critical for understanding pathology in schizophrenia. In this work, we propose a new framework for extraction of important disease related features and classification of patients with schizophrenia based on using both fMRI and MEG to investigate functional network components in the resting state. Results of this study show that the integration of fMRI and MEG provides important information that captures fundamental characteristics of functional network connectivity in schizophrenia and is helpful for prediction of schizophrenia patient group membership. Combined fMRI/MEG methods, using static functional network connectivity analyses, improved classification accuracy relative to use of fMRI or MEG methods alone (by 15 and 12.45%, respectively), while combined fMRI/MEG methods using dynamic functional network connectivity analyses improved classification up to 5.12% relative to use of fMRI alone and up to 17.21% relative to use of MEG alone. PMID:27807403

A Hybrid Hierarchical Approach for Brain Tissue Segmentation by Combining Brain Atlas and Least Square Support Vector Machine

PubMed Central

Kasiri, Keyvan; Kazemi, Kamran; Dehghani, Mohammad Javad; Helfroush, Mohammad Sadegh

2013-01-01

In this paper, we present a new semi-automatic brain tissue segmentation method based on a hybrid hierarchical approach that combines a brain atlas as a priori information and a least-square support vector machine (LS-SVM). The method consists of three steps. In the first two steps, the skull is removed and the cerebrospinal fluid (CSF) is extracted. These two steps are performed using the toolbox FMRIB's automated segmentation tool integrated in the FSL software (FSL-FAST) developed in Oxford Centre for functional MRI of the brain (FMRIB). Then, in the third step, the LS-SVM is used to segment grey matter (GM) and white matter (WM). The training samples for LS-SVM are selected from the registered brain atlas. The voxel intensities and spatial positions are selected as the two feature groups for training and test. SVM as a powerful discriminator is able to handle nonlinear classification problems; however, it cannot provide posterior probability. Thus, we use a sigmoid function to map the SVM output into probabilities. The proposed method is used to segment CSF, GM and WM from the simulated magnetic resonance imaging (MRI) using Brainweb MRI simulator and real data provided by Internet Brain Segmentation Repository. The semi-automatically segmented brain tissues were evaluated by comparing to the corresponding ground truth. The Dice and Jaccard similarity coefficients, sensitivity and specificity were calculated for the quantitative validation of the results. The quantitative results show that the proposed method segments brain tissues accurately with respect to corresponding ground truth. PMID:24696800

Detection of muscle gap by L-BIA in muscle injuries: clinical prognosis.

PubMed

Nescolarde, L; Yanguas, J; Terricabras, J; Lukaski, H; Alomar, X; Rosell-Ferrer, J; Rodas, G

2017-06-21

Sport-related muscle injury classifications are based basically on imaging criteria such as ultrasound (US) and magnetic resonance imaging (MRI) without consensus because of a lack of clinical prognostics for return-to-play (RTP), which is conditioned upon the severity of the injury, and this in turn with the muscle gap (muscular fibers retraction). Recently, Futbol Club Barcelona's medical department proposed a new muscle injury classification in which muscle gap plays an important role, with the drawback that it is not always possible to identify by MRI. Localized bioimpedance measurement (L-BIA) has emerged as a non-invasive technique for supporting US and MRI to quantify the disrupted soft tissue structure in injured muscles. To correlate the severity of the injury according to the gap with the RTP, through the percent of change in resistance (R), reactance (Xc) and phase-angle (PA) by L-BIA measurements in 22 muscle injuries. After grouping the data according to the muscle gap (by MRI exam), there were significant differences in R between grade 1 and grade 2f (myotendinous or myofascial muscle injury with feather-like appearance), as well as between grade 2f and grade 2g (myotendinous or myofascial muscle injury with feather and gap). The Xc and PA values decrease significantly between each grade (i.e. 1 versus 2f, 1 versus 2g and 2f versus 2g). In addition, the severity of the muscle gap adversely affected the RTP with significant differences observed between 1 and 2g as well as between 2f and 2g. These results show that L-BIA could aid MRI and US in identifying the severity of an injured muscle according to muscle gap and therefore to accurately predict the RTP.

Automated pixel-wise brain tissue segmentation of diffusion-weighted images via machine learning.

PubMed

Ciritsis, Alexander; Boss, Andreas; Rossi, Cristina

2018-04-26

The diffusion-weighted (DW) MR signal sampled over a wide range of b-values potentially allows for tissue differentiation in terms of cellularity, microstructure, perfusion, and T 2 relaxivity. This study aimed to implement a machine learning algorithm for automatic brain tissue segmentation from DW-MRI datasets, and to determine the optimal sub-set of features for accurate segmentation. DWI was performed at 3 T in eight healthy volunteers using 15 b-values and 20 diffusion-encoding directions. The pixel-wise signal attenuation, as well as the trace and fractional anisotropy (FA) of the diffusion tensor, were used as features to train a support vector machine classifier for gray matter, white matter, and cerebrospinal fluid classes. The datasets of two volunteers were used for validation. For each subject, tissue classification was also performed on 3D T 1 -weighted data sets with a probabilistic framework. Confusion matrices were generated for quantitative assessment of image classification accuracy in comparison with the reference method. DWI-based tissue segmentation resulted in an accuracy of 82.1% on the validation dataset and of 82.2% on the training dataset, excluding relevant model over-fitting. A mean Dice coefficient (DSC) of 0.79 ± 0.08 was found. About 50% of the classification performance was attributable to five features (i.e. signal measured at b-values of 5/10/500/1200 s/mm 2 and the FA). This reduced set of features led to almost identical performances for the validation (82.2%) and the training (81.4%) datasets (DSC = 0.79 ± 0.08). Machine learning techniques applied to DWI data allow for accurate brain tissue segmentation based on both morphological and functional information. Copyright © 2018 John Wiley & Sons, Ltd.

Comprehensive 4-stage categorization of bicuspid aortic valve leaflet morphology by cardiac MRI in 386 patients.

PubMed

Murphy, I G; Collins, J; Powell, A; Markl, M; McCarthy, P; Malaisrie, S C; Carr, J C; Barker, A J

2017-08-01

Bicuspid aortic valve (BAV) disease is heterogeneous and related to valve dysfunction and aortopathy. Appropriate follow up and surveillance of patients with BAV may depend on correct phenotypic categorization. There are multiple classification schemes, however a need exists to comprehensively capture commissure fusion, leaflet asymmetry, and valve orifice orientation. Our aim was to develop a BAV classification scheme for use at MRI to ascertain the frequency of different phenotypes and the consistency of BAV classification. The BAV classification scheme builds on the Sievers surgical BAV classification, adding valve orifice orientation, partial leaflet fusion and leaflet asymmetry. A single observer successfully applied this classification to 386 of 398 Cardiac MRI studies. Repeatability of categorization was ascertained with intraobserver and interobserver kappa scores. Sensitivity and specificity of MRI findings was determined from operative reports, where available. Fusion of the right and left leaflets accounted for over half of all cases. Partial leaflet fusion was seen in 46% of patients. Good interobserver agreement was seen for orientation of the valve opening (κ = 0.90), type (κ = 0.72) and presence of partial fusion (κ = 0.83, p < 0.0001). Retrospective review of operative notes showed sensitivity and specificity for orientation (90, 93%) and for Sievers type (73, 87%). The proposed BAV classification schema was assessed by MRI for its reliability to classify valve morphology in addition to illustrating the wide heterogeneity of leaflet size, orifice orientation, and commissural fusion. The classification may be helpful in further understanding the relationship between valve morphology, flow derangement and aortopathy.

Multivariate detrending of fMRI signal drifts for real-time multiclass pattern classification.

PubMed

Lee, Dongha; Jang, Changwon; Park, Hae-Jeong

2015-03-01

Signal drift in functional magnetic resonance imaging (fMRI) is an unavoidable artifact that limits classification performance in multi-voxel pattern analysis of fMRI. As conventional methods to reduce signal drift, global demeaning or proportional scaling disregards regional variations of drift, whereas voxel-wise univariate detrending is too sensitive to noisy fluctuations. To overcome these drawbacks, we propose a multivariate real-time detrending method for multiclass classification that involves spatial demeaning at each scan and the recursive detrending of drifts in the classifier outputs driven by a multiclass linear support vector machine. Experiments using binary and multiclass data showed that the linear trend estimation of the classifier output drift for each class (a weighted sum of drifts in the class-specific voxels) was more robust against voxel-wise artifacts that lead to inconsistent spatial patterns and the effect of online processing than voxel-wise detrending. The classification performance of the proposed method was significantly better, especially for multiclass data, than that of voxel-wise linear detrending, global demeaning, and classifier output detrending without demeaning. We concluded that the multivariate approach using classifier output detrending of fMRI signals with spatial demeaning preserves spatial patterns, is less sensitive than conventional methods to sample size, and increases classification performance, which is a useful feature for real-time fMRI classification. Copyright © 2014 Elsevier Inc. All rights reserved.

Implicit structured sequence learning: an fMRI study of the structural mere-exposure effect

PubMed Central

Folia, Vasiliki; Petersson, Karl Magnus

2014-01-01

In this event-related fMRI study we investigated the effect of 5 days of implicit acquisition on preference classification by means of an artificial grammar learning (AGL) paradigm based on the structural mere-exposure effect and preference classification using a simple right-linear unification grammar. This allowed us to investigate implicit AGL in a proper learning design by including baseline measurements prior to grammar exposure. After 5 days of implicit acquisition, the fMRI results showed activations in a network of brain regions including the inferior frontal (centered on BA 44/45) and the medial prefrontal regions (centered on BA 8/32). Importantly, and central to this study, the inclusion of a naive preference fMRI baseline measurement allowed us to conclude that these fMRI findings were the intrinsic outcomes of the learning process itself and not a reflection of a preexisting functionality recruited during classification, independent of acquisition. Support for the implicit nature of the knowledge utilized during preference classification on day 5 come from the fact that the basal ganglia, associated with implicit procedural learning, were activated during classification, while the medial temporal lobe system, associated with explicit declarative memory, was consistently deactivated. Thus, preference classification in combination with structural mere-exposure can be used to investigate structural sequence processing (syntax) in unsupervised AGL paradigms with proper learning designs. PMID:24550865

Implicit structured sequence learning: an fMRI study of the structural mere-exposure effect.

PubMed

Folia, Vasiliki; Petersson, Karl Magnus

2014-01-01

In this event-related fMRI study we investigated the effect of 5 days of implicit acquisition on preference classification by means of an artificial grammar learning (AGL) paradigm based on the structural mere-exposure effect and preference classification using a simple right-linear unification grammar. This allowed us to investigate implicit AGL in a proper learning design by including baseline measurements prior to grammar exposure. After 5 days of implicit acquisition, the fMRI results showed activations in a network of brain regions including the inferior frontal (centered on BA 44/45) and the medial prefrontal regions (centered on BA 8/32). Importantly, and central to this study, the inclusion of a naive preference fMRI baseline measurement allowed us to conclude that these fMRI findings were the intrinsic outcomes of the learning process itself and not a reflection of a preexisting functionality recruited during classification, independent of acquisition. Support for the implicit nature of the knowledge utilized during preference classification on day 5 come from the fact that the basal ganglia, associated with implicit procedural learning, were activated during classification, while the medial temporal lobe system, associated with explicit declarative memory, was consistently deactivated. Thus, preference classification in combination with structural mere-exposure can be used to investigate structural sequence processing (syntax) in unsupervised AGL paradigms with proper learning designs.

Classification of fMRI independent components using IC-fingerprints and support vector machine classifiers.

PubMed

De Martino, Federico; Gentile, Francesco; Esposito, Fabrizio; Balsi, Marco; Di Salle, Francesco; Goebel, Rainer; Formisano, Elia

2007-01-01

We present a general method for the classification of independent components (ICs) extracted from functional MRI (fMRI) data sets. The method consists of two steps. In the first step, each fMRI-IC is associated with an IC-fingerprint, i.e., a representation of the component in a multidimensional space of parameters. These parameters are post hoc estimates of global properties of the ICs and are largely independent of a specific experimental design and stimulus timing. In the second step a machine learning algorithm automatically separates the IC-fingerprints into six general classes after preliminary training performed on a small subset of expert-labeled components. We illustrate this approach in a multisubject fMRI study employing visual structure-from-motion stimuli encoding faces and control random shapes. We show that: (1) IC-fingerprints are a valuable tool for the inspection, characterization and selection of fMRI-ICs and (2) automatic classifications of fMRI-ICs in new subjects present a high correspondence with those obtained by expert visual inspection of the components. Importantly, our classification procedure highlights several neurophysiologically interesting processes. The most intriguing of which is reflected, with high intra- and inter-subject reproducibility, in one IC exhibiting a transiently task-related activation in the 'face' region of the primary sensorimotor cortex. This suggests that in addition to or as part of the mirror system, somatotopic regions of the sensorimotor cortex are involved in disambiguating the perception of a moving body part. Finally, we show that the same classification algorithm can be successfully applied, without re-training, to fMRI collected using acquisition parameters, stimulation modality and timing considerably different from those used for training.

Classification of cardiac-related artifacts in dynamic contrast breast MRI

NASA Astrophysics Data System (ADS)

Stegbauer, Keith C.; Smith, Justin P.; Niemeyer, Tanya L.; Wood, Chris

2004-05-01

Dynamic contrast breast MRI is becoming an important adjunct in screening women at high risk for breast cancer, determining extent of disease (staging) and monitoring response to therapy. In dynamic contrast breast MRI, regions of rapid contrast uptake indicate increases in vascularity which can be associated with abnormal tissue, sometimes significant for malignant disease. To show these areas of enhancement, subtractions between the pre and post contrast images and maximum intensity projections (MIPs) are computed. Many projections are obscured by normally enhancing anatomy (heart, aorta, pulmonary vessels). Identification of these structures allows their removal from MIPs, which improves image quality, diagnostic utility and the conspicuity of the enhancing regions. In this study, a fully automated classifier is presented which uses the spatial location of enhancing regions to separate those that occur inside the chest wall from those occurring in the tissue of interest (breast, axilla, chest wall). The classifier was trained on 21 studies each acquired at a different institution (699 clusters of pixels), and tested on 7 studies (231 clusters of pixels) that were not part of the training set. Multiple cost functions for training were examined. The measurements for the peak performance of the classifier were sensitivity 97.0%, specificity 99.4%, PPV 99.9%, NPV 78.8%.

Comparative Study of SVM Methods Combined with Voxel Selection for Object Category Classification on fMRI Data

PubMed Central

Song, Sutao; Zhan, Zhichao; Long, Zhiying; Zhang, Jiacai; Yao, Li

2011-01-01

Background Support vector machine (SVM) has been widely used as accurate and reliable method to decipher brain patterns from functional MRI (fMRI) data. Previous studies have not found a clear benefit for non-linear (polynomial kernel) SVM versus linear one. Here, a more effective non-linear SVM using radial basis function (RBF) kernel is compared with linear SVM. Different from traditional studies which focused either merely on the evaluation of different types of SVM or the voxel selection methods, we aimed to investigate the overall performance of linear and RBF SVM for fMRI classification together with voxel selection schemes on classification accuracy and time-consuming. Methodology/Principal Findings Six different voxel selection methods were employed to decide which voxels of fMRI data would be included in SVM classifiers with linear and RBF kernels in classifying 4-category objects. Then the overall performances of voxel selection and classification methods were compared. Results showed that: (1) Voxel selection had an important impact on the classification accuracy of the classifiers: in a relative low dimensional feature space, RBF SVM outperformed linear SVM significantly; in a relative high dimensional space, linear SVM performed better than its counterpart; (2) Considering the classification accuracy and time-consuming holistically, linear SVM with relative more voxels as features and RBF SVM with small set of voxels (after PCA) could achieve the better accuracy and cost shorter time. Conclusions/Significance The present work provides the first empirical result of linear and RBF SVM in classification of fMRI data, combined with voxel selection methods. Based on the findings, if only classification accuracy was concerned, RBF SVM with appropriate small voxels and linear SVM with relative more voxels were two suggested solutions; if users concerned more about the computational time, RBF SVM with relative small set of voxels when part of the principal components were kept as features was a better choice. PMID:21359184

Comparative study of SVM methods combined with voxel selection for object category classification on fMRI data.

PubMed

Song, Sutao; Zhan, Zhichao; Long, Zhiying; Zhang, Jiacai; Yao, Li

2011-02-16

Support vector machine (SVM) has been widely used as accurate and reliable method to decipher brain patterns from functional MRI (fMRI) data. Previous studies have not found a clear benefit for non-linear (polynomial kernel) SVM versus linear one. Here, a more effective non-linear SVM using radial basis function (RBF) kernel is compared with linear SVM. Different from traditional studies which focused either merely on the evaluation of different types of SVM or the voxel selection methods, we aimed to investigate the overall performance of linear and RBF SVM for fMRI classification together with voxel selection schemes on classification accuracy and time-consuming. Six different voxel selection methods were employed to decide which voxels of fMRI data would be included in SVM classifiers with linear and RBF kernels in classifying 4-category objects. Then the overall performances of voxel selection and classification methods were compared. Results showed that: (1) Voxel selection had an important impact on the classification accuracy of the classifiers: in a relative low dimensional feature space, RBF SVM outperformed linear SVM significantly; in a relative high dimensional space, linear SVM performed better than its counterpart; (2) Considering the classification accuracy and time-consuming holistically, linear SVM with relative more voxels as features and RBF SVM with small set of voxels (after PCA) could achieve the better accuracy and cost shorter time. The present work provides the first empirical result of linear and RBF SVM in classification of fMRI data, combined with voxel selection methods. Based on the findings, if only classification accuracy was concerned, RBF SVM with appropriate small voxels and linear SVM with relative more voxels were two suggested solutions; if users concerned more about the computational time, RBF SVM with relative small set of voxels when part of the principal components were kept as features was a better choice.

Multi-class SVM model for fMRI-based classification and grading of liver fibrosis

NASA Astrophysics Data System (ADS)

Freiman, M.; Sela, Y.; Edrei, Y.; Pappo, O.; Joskowicz, L.; Abramovitch, R.

2010-03-01

We present a novel non-invasive automatic method for the classification and grading of liver fibrosis from fMRI maps based on hepatic hemodynamic changes. This method automatically creates a model for liver fibrosis grading based on training datasets. Our supervised learning method evaluates hepatic hemodynamics from an anatomical MRI image and three T2*-W fMRI signal intensity time-course scans acquired during the breathing of air, air-carbon dioxide, and carbogen. It constructs a statistical model of liver fibrosis from these fMRI scans using a binary-based one-against-all multi class Support Vector Machine (SVM) classifier. We evaluated the resulting classification model with the leave-one out technique and compared it to both full multi-class SVM and K-Nearest Neighbor (KNN) classifications. Our experimental study analyzed 57 slice sets from 13 mice, and yielded a 98.2% separation accuracy between healthy and low grade fibrotic subjects, and an overall accuracy of 84.2% for fibrosis grading. These results are better than the existing image-based methods which can only discriminate between healthy and high grade fibrosis subjects. With appropriate extensions, our method may be used for non-invasive classification and progression monitoring of liver fibrosis in human patients instead of more invasive approaches, such as biopsy or contrast-enhanced imaging.

The value of CT and MRI in the classification and surgical decision-making among spine surgeons in thoracolumbar spinal injuries.

PubMed

Rajasekaran, Shanmuganathan; Vaccaro, Alexander R; Kanna, Rishi Mugesh; Schroeder, Gregory D; Oner, Frank Cumhur; Vialle, Luiz; Chapman, Jens; Dvorak, Marcel; Fehlings, Michael; Shetty, Ajoy Prasad; Schnake, Klaus; Maheshwaran, Anupama; Kandziora, Frank

2017-05-01

Although imaging has a major role in evaluation and management of thoracolumbar spinal trauma by spine surgeons, the exact role of computed tomography (CT) and magnetic resonance imaging (MRI) in addition to radiographs for fracture classification and surgical decision-making is unclear. Spine surgeons (n = 41) from around the world classified 30 thoracolumbar fractures. The cases were presented in a three-step approach: first plain radiographs, followed by CT and MRI images. Surgeons were asked to classify according to the AOSpine classification system and choose management in each of the three steps. Surgeons correctly classified 43.4 % of fractures with plain radiographs alone; after, additionally, evaluating CT and MRI images, this percentage increased by further 18.2 and 2.2 %, respectively. AO type A fractures were identified in 51.7 % of fractures with radiographs, while the number of type B fractures increased after CT and MRI. The number of type C fractures diagnosed was constant across the three steps. Agreement between radiographs and CT was fair for A-type (k = 0.31), poor for B-type (k = 0.19), but it was excellent between CT and MRI (k > 0.87). CT and MRI had similar sensitivity in identifying fracture subtypes except that MRI had a higher sensitivity (56.5 %) for B2 fractures (p < 0.001). The need for surgical fixation was deemed present in 72 % based on radiographs alone and increased to 81.7 % with CT images (p < 0.0001). The assessment for need of surgery did not change after an MRI (p = 0.77). For accurate classification, radiographs alone were insufficient except for C-type injuries. CT is mandatory for accurately classifying thoracolumbar fractures. Though MRI did confer a modest gain in sensitivity in B2 injuries, the study does not support the need for routine MRI in patients for classification, assessing instability or need for surgery.

Multi-task linear programming discriminant analysis for the identification of progressive MCI individuals.

PubMed

Yu, Guan; Liu, Yufeng; Thung, Kim-Han; Shen, Dinggang

2014-01-01

Accurately identifying mild cognitive impairment (MCI) individuals who will progress to Alzheimer's disease (AD) is very important for making early interventions. Many classification methods focus on integrating multiple imaging modalities such as magnetic resonance imaging (MRI) and fluorodeoxyglucose positron emission tomography (FDG-PET). However, the main challenge for MCI classification using multiple imaging modalities is the existence of a lot of missing data in many subjects. For example, in the Alzheimer's Disease Neuroimaging Initiative (ADNI) study, almost half of the subjects do not have PET images. In this paper, we propose a new and flexible binary classification method, namely Multi-task Linear Programming Discriminant (MLPD) analysis, for the incomplete multi-source feature learning. Specifically, we decompose the classification problem into different classification tasks, i.e., one for each combination of available data sources. To solve all different classification tasks jointly, our proposed MLPD method links them together by constraining them to achieve the similar estimated mean difference between the two classes (under classification) for those shared features. Compared with the state-of-the-art incomplete Multi-Source Feature (iMSF) learning method, instead of constraining different classification tasks to choose a common feature subset for those shared features, MLPD can flexibly and adaptively choose different feature subsets for different classification tasks. Furthermore, our proposed MLPD method can be efficiently implemented by linear programming. To validate our MLPD method, we perform experiments on the ADNI baseline dataset with the incomplete MRI and PET images from 167 progressive MCI (pMCI) subjects and 226 stable MCI (sMCI) subjects. We further compared our method with the iMSF method (using incomplete MRI and PET images) and also the single-task classification method (using only MRI or only subjects with both MRI and PET images). Experimental results show very promising performance of our proposed MLPD method.

Multi-Task Linear Programming Discriminant Analysis for the Identification of Progressive MCI Individuals

PubMed Central

Yu, Guan; Liu, Yufeng; Thung, Kim-Han; Shen, Dinggang

2014-01-01

Accurately identifying mild cognitive impairment (MCI) individuals who will progress to Alzheimer's disease (AD) is very important for making early interventions. Many classification methods focus on integrating multiple imaging modalities such as magnetic resonance imaging (MRI) and fluorodeoxyglucose positron emission tomography (FDG-PET). However, the main challenge for MCI classification using multiple imaging modalities is the existence of a lot of missing data in many subjects. For example, in the Alzheimer's Disease Neuroimaging Initiative (ADNI) study, almost half of the subjects do not have PET images. In this paper, we propose a new and flexible binary classification method, namely Multi-task Linear Programming Discriminant (MLPD) analysis, for the incomplete multi-source feature learning. Specifically, we decompose the classification problem into different classification tasks, i.e., one for each combination of available data sources. To solve all different classification tasks jointly, our proposed MLPD method links them together by constraining them to achieve the similar estimated mean difference between the two classes (under classification) for those shared features. Compared with the state-of-the-art incomplete Multi-Source Feature (iMSF) learning method, instead of constraining different classification tasks to choose a common feature subset for those shared features, MLPD can flexibly and adaptively choose different feature subsets for different classification tasks. Furthermore, our proposed MLPD method can be efficiently implemented by linear programming. To validate our MLPD method, we perform experiments on the ADNI baseline dataset with the incomplete MRI and PET images from 167 progressive MCI (pMCI) subjects and 226 stable MCI (sMCI) subjects. We further compared our method with the iMSF method (using incomplete MRI and PET images) and also the single-task classification method (using only MRI or only subjects with both MRI and PET images). Experimental results show very promising performance of our proposed MLPD method. PMID:24820966

Breast fat volume measurement using wide-bore 3 T MRI: comparison of traditional mammographic density evaluation with MRI density measurements using automatic segmentation.

PubMed

Petridou, E; Kibiro, M; Gladwell, C; Malcolm, P; Toms, A; Juette, A; Borga, M; Dahlqvist Leinhard, O; Romu, T; Kasmai, B; Denton, E

2017-07-01

To compare magnetic resonance imaging (MRI)-derived breast density measurements using automatic segmentation algorithms with radiologist estimations using the Breast Imaging Reporting and Data Systems (BI-RADS) density classification. Forty women undergoing mammography and dynamic breast MRI as part of their clinical management were recruited. Fat-water separated MRI images derived from a two-point Dixon technique, phase-sensitive reconstruction, and atlas-based segmentation were obtained before and after intravenous contrast medium administration. Breast density was assessed using software from Advanced MR Analytics (AMRA), Linköping, Sweden, with results compared to the widely used four-quartile quantitative BI-RADS scale. The proportion of glandular tissue in the breast on MRI was derived from the AMRA sequence. The mean unenhanced breast density was 0.31±0.22 (mean±SD; left) and 0.29±0.21 (right). Mean breast density on post-contrast images was 0.32±0.19 (left) and 0.32±0.2 (right). There was "almost perfect" correlation between pre- and post-contrast breast density quantification: Spearman's correlation rho=0.98 (95% confidence intervals [CI]: 0.97-0.99; left) and rho=0.99 (95% CI: 0.98-0.99; right). The 95% limits of agreement were -0.11-0.08 (left) and -0.08-0.03 (right). Interobserver reliability for BI-RADS was "substantial": weighted Kappa k=0.8 (95% CI: 0.74-0.87). The Spearman correlation coefficient between BI-RADS and MRI breast density was rho=0.73 (95% CI: 0.60-0.82; left) and rho=0.75 (95% CI: 0.63-0.83; right) which was also "substantial". The AMRA sequence provides a fully automated, reproducible, objective assessment of fibroglandular breast tissue proportion that correlates well with mammographic assessment of breast density with the added advantage of avoidance of ionising radiation. Copyright © 2017 The Royal College of Radiologists. All rights reserved.

Fast Realistic MRI Simulations Based on Generalized Multi-Pool Exchange Tissue Model.

PubMed

Liu, Fang; Velikina, Julia V; Block, Walter F; Kijowski, Richard; Samsonov, Alexey A

2017-02-01

We present MRiLab, a new comprehensive simulator for large-scale realistic MRI simulations on a regular PC equipped with a modern graphical processing unit (GPU). MRiLab combines realistic tissue modeling with numerical virtualization of an MRI system and scanning experiment to enable assessment of a broad range of MRI approaches including advanced quantitative MRI methods inferring microstructure on a sub-voxel level. A flexible representation of tissue microstructure is achieved in MRiLab by employing the generalized tissue model with multiple exchanging water and macromolecular proton pools rather than a system of independent proton isochromats typically used in previous simulators. The computational power needed for simulation of the biologically relevant tissue models in large 3D objects is gained using parallelized execution on GPU. Three simulated and one actual MRI experiments were performed to demonstrate the ability of the new simulator to accommodate a wide variety of voxel composition scenarios and demonstrate detrimental effects of simplified treatment of tissue micro-organization adapted in previous simulators. GPU execution allowed  ∼ 200× improvement in computational speed over standard CPU. As a cross-platform, open-source, extensible environment for customizing virtual MRI experiments, MRiLab streamlines the development of new MRI methods, especially those aiming to infer quantitatively tissue composition and microstructure.

Fast Realistic MRI Simulations Based on Generalized Multi-Pool Exchange Tissue Model

PubMed Central

Velikina, Julia V.; Block, Walter F.; Kijowski, Richard; Samsonov, Alexey A.

2017-01-01

We present MRiLab, a new comprehensive simulator for large-scale realistic MRI simulations on a regular PC equipped with a modern graphical processing unit (GPU). MRiLab combines realistic tissue modeling with numerical virtualization of an MRI system and scanning experiment to enable assessment of a broad range of MRI approaches including advanced quantitative MRI methods inferring microstructure on a sub-voxel level. A flexibl representation of tissue microstructure is achieved in MRiLab by employing the generalized tissue model with multiple exchanging water and macromolecular proton pools rather than a system of independent proton isochromats typically used in previous simulators. The computational power needed for simulation of the biologically relevant tissue models in large 3D objects is gained using parallelized execution on GPU. Three simulated and one actual MRI experiments were performed to demonstrate the ability of the new simulator to accommodate a wide variety of voxel composition scenarios and demonstrate detrimental effects of simplifie treatment of tissue micro-organization adapted in previous simulators. GPU execution allowed ∼200× improvement in computational speed over standard CPU. As a cross-platform, open-source, extensible environment for customizing virtual MRI experiments, MRiLab streamlines the development of new MRI methods, especially those aiming to infer quantitatively tissue composition and microstructure. PMID:28113746

Natural image classification driven by human brain activity

NASA Astrophysics Data System (ADS)

Zhang, Dai; Peng, Hanyang; Wang, Jinqiao; Tang, Ming; Xue, Rong; Zuo, Zhentao

2016-03-01

Natural image classification has been a hot topic in computer vision and pattern recognition research field. Since the performance of an image classification system can be improved by feature selection, many image feature selection methods have been developed. However, the existing supervised feature selection methods are typically driven by the class label information that are identical for different samples from the same class, ignoring with-in class image variability and therefore degrading the feature selection performance. In this study, we propose a novel feature selection method, driven by human brain activity signals collected using fMRI technique when human subjects were viewing natural images of different categories. The fMRI signals associated with subjects viewing different images encode the human perception of natural images, and therefore may capture image variability within- and cross- categories. We then select image features with the guidance of fMRI signals from brain regions with active response to image viewing. Particularly, bag of words features based on GIST descriptor are extracted from natural images for classification, and a sparse regression base feature selection method is adapted to select image features that can best predict fMRI signals. Finally, a classification model is built on the select image features to classify images without fMRI signals. The validation experiments for classifying images from 4 categories of two subjects have demonstrated that our method could achieve much better classification performance than the classifiers built on image feature selected by traditional feature selection methods.

Automated modification and fusion of voxel models to construct body phantoms with heterogeneous breast tissue: Application to MRI simulations.

PubMed

Rispoli, Joseph V; Wright, Steven M; Malloy, Craig R; McDougall, Mary P

2017-01-01

Human voxel models incorporating detailed anatomical features are vital tools for the computational evaluation of electromagnetic (EM) fields within the body. Besides whole-body human voxel models, phantoms representing smaller heterogeneous anatomical features are often employed; for example, localized breast voxel models incorporating fatty and fibroglandular tissues have been developed for a variety of EM applications including mammography simulation and dosimetry, magnetic resonance imaging (MRI), and ultra-wideband microwave imaging. However, considering wavelength effects, electromagnetic modeling of the breast at sub-microwave frequencies necessitates detailed breast phantoms in conjunction with whole-body voxel models. Heterogeneous breast phantoms are sized to fit within radiofrequency coil hardware, modified by voxel-wise extrusion, and fused to whole-body models using voxel-wise, tissue-dependent logical operators. To illustrate the utility of this method, finite-difference time-domain simulations are performed using a whole-body model integrated with a variety of available breast phantoms spanning the standard four tissue density classifications representing the majority of the population. The software library uses a combination of voxel operations to seamlessly size, modify, and fuse eleven breast phantoms to whole-body voxel models. The software is publicly available on GitHub and is linked to the file exchange at MATLAB ® Central. Simulations confirm the proportions of fatty and fibroglandular tissues in breast phantoms have significant yet predictable implications on projected power deposition in tissue. Breast phantoms may be modified and fused to whole-body voxel models using the software presented in this work; user considerations for the open-source software and resultant phantoms are discussed. Furthermore, results indicate simulating breast models as predominantly fatty tissue can considerably underestimate the potential for tissue heating in women with substantial fibroglandular tissue.

Automated modification and fusion of voxel models to construct body phantoms with heterogeneous breast tissue: Application to MRI simulations

PubMed Central

Rispoli, Joseph V.; Wright, Steven M.; Malloy, Craig R.; McDougall, Mary P.

2017-01-01

Background Human voxel models incorporating detailed anatomical features are vital tools for the computational evaluation of electromagnetic (EM) fields within the body. Besides whole-body human voxel models, phantoms representing smaller heterogeneous anatomical features are often employed; for example, localized breast voxel models incorporating fatty and fibroglandular tissues have been developed for a variety of EM applications including mammography simulation and dosimetry, magnetic resonance imaging (MRI), and ultra-wideband microwave imaging. However, considering wavelength effects, electromagnetic modeling of the breast at sub-microwave frequencies necessitates detailed breast phantoms in conjunction with whole-body voxel models. Methods Heterogeneous breast phantoms are sized to fit within radiofrequency coil hardware, modified by voxel-wise extrusion, and fused to whole-body models using voxel-wise, tissue-dependent logical operators. To illustrate the utility of this method, finite-difference time-domain simulations are performed using a whole-body model integrated with a variety of available breast phantoms spanning the standard four tissue density classifications representing the majority of the population. Results The software library uses a combination of voxel operations to seamlessly size, modify, and fuse eleven breast phantoms to whole-body voxel models. The software is publicly available on GitHub and is linked to the file exchange at MATLAB® Central. Simulations confirm the proportions of fatty and fibroglandular tissues in breast phantoms have significant yet predictable implications on projected power deposition in tissue. Conclusions Breast phantoms may be modified and fused to whole-body voxel models using the software presented in this work; user considerations for the open-source software and resultant phantoms are discussed. Furthermore, results indicate simulating breast models as predominantly fatty tissue can considerably underestimate the potential for tissue heating in women with substantial fibroglandular tissue. PMID:28798837

The relevance of MRI for patient modeling in head and neck hyperthermia treatment planning: a comparison of CT and CT-MRI based tissue segmentation on simulated temperature.

PubMed

Verhaart, René F; Fortunati, Valerio; Verduijn, Gerda M; van der Lugt, Aad; van Walsum, Theo; Veenland, Jifke F; Paulides, Margarethus M

2014-12-01

In current clinical practice, head and neck (H&N) hyperthermia treatment planning (HTP) is solely based on computed tomography (CT) images. Magnetic resonance imaging (MRI) provides superior soft-tissue contrast over CT. The purpose of the authors' study is to investigate the relevance of using MRI in addition to CT for patient modeling in H&N HTP. CT and MRI scans were acquired for 11 patients in an immobilization mask. Three observers manually segmented on CT, MRI T1 weighted (MRI-T1w), and MRI T2 weighted (MRI-T2w) images the following thermo-sensitive tissues: cerebrum, cerebellum, brainstem, myelum, sclera, lens, vitreous humor, and the optical nerve. For these tissues that are used for patient modeling in H&N HTP, the interobserver variation of manual tissue segmentation in CT and MRI was quantified with the mean surface distance (MSD). Next, the authors compared the impact of CT and CT and MRI based patient models on the predicted temperatures. For each tissue, the modality was selected that led to the lowest observer variation and inserted this in the combined CT and MRI based patient model (CT and MRI), after a deformable image registration. In addition, a patient model with a detailed segmentation of brain tissues (including white matter, gray matter, and cerebrospinal fluid) was created (CT and MRIdb). To quantify the relevance of MRI based segmentation for H&N HTP, the authors compared the predicted maximum temperatures in the segmented tissues (Tmax) and the corresponding specific absorption rate (SAR) of the patient models based on (1) CT, (2) CT and MRI, and (3) CT and MRIdb. In MRI, a similar or reduced interobserver variation was found compared to CT (maximum of median MSD in CT: 0.93 mm, MRI-T1w: 0.72 mm, MRI-T2w: 0.66 mm). Only for the optical nerve the interobserver variation is significantly lower in CT compared to MRI (median MSD in CT: 0.58 mm, MRI-T1w: 1.27 mm, MRI-T2w: 1.40 mm). Patient models based on CT (Tmax: 38.0 °C) and CT and MRI (Tmax: 38.1 °C) result in similar simulated temperatures, while CT and MRIdb (Tmax: 38.5 °C) resulted in significantly higher temperatures. The SAR corresponding to these temperatures did not differ significantly. Although MR imaging reduces the interobserver variation in most tissues, it does not affect simulated local tissue temperatures. However, the improved soft-tissue contrast provided by MRI allows generating a detailed brain segmentation, which has a strong impact on the predicted local temperatures and hence may improve simulation guided hyperthermia.

The relevance of MRI for patient modeling in head and neck hyperthermia treatment planning: A comparison of CT and CT-MRI based tissue segmentation on simulated temperature

DOE Office of Scientific and Technical Information (OSTI.GOV)

Verhaart, René F., E-mail: r.f.verhaart@erasmusmc.nl; Paulides, Margarethus M.; Fortunati, Valerio

Purpose: In current clinical practice, head and neck (H and N) hyperthermia treatment planning (HTP) is solely based on computed tomography (CT) images. Magnetic resonance imaging (MRI) provides superior soft-tissue contrast over CT. The purpose of the authors’ study is to investigate the relevance of using MRI in addition to CT for patient modeling in H and N HTP. Methods: CT and MRI scans were acquired for 11 patients in an immobilization mask. Three observers manually segmented on CT, MRI T1 weighted (MRI-T1w), and MRI T2 weighted (MRI-T2w) images the following thermo-sensitive tissues: cerebrum, cerebellum, brainstem, myelum, sclera, lens, vitreousmore » humor, and the optical nerve. For these tissues that are used for patient modeling in H and N HTP, the interobserver variation of manual tissue segmentation in CT and MRI was quantified with the mean surface distance (MSD). Next, the authors compared the impact of CT and CT and MRI based patient models on the predicted temperatures. For each tissue, the modality was selected that led to the lowest observer variation and inserted this in the combined CT and MRI based patient model (CT and MRI), after a deformable image registration. In addition, a patient model with a detailed segmentation of brain tissues (including white matter, gray matter, and cerebrospinal fluid) was created (CT and MRI{sub db}). To quantify the relevance of MRI based segmentation for H and N HTP, the authors compared the predicted maximum temperatures in the segmented tissues (T{sub max}) and the corresponding specific absorption rate (SAR) of the patient models based on (1) CT, (2) CT and MRI, and (3) CT and MRI{sub db}. Results: In MRI, a similar or reduced interobserver variation was found compared to CT (maximum of median MSD in CT: 0.93 mm, MRI-T1w: 0.72 mm, MRI-T2w: 0.66 mm). Only for the optical nerve the interobserver variation is significantly lower in CT compared to MRI (median MSD in CT: 0.58 mm, MRI-T1w: 1.27 mm, MRI-T2w: 1.40 mm). Patient models based on CT (T{sub max}: 38.0 °C) and CT and MRI (T{sub max}: 38.1 °C) result in similar simulated temperatures, while CT and MRI{sub db} (T{sub max}: 38.5 °C) resulted in significantly higher temperatures. The SAR corresponding to these temperatures did not differ significantly. Conclusions: Although MR imaging reduces the interobserver variation in most tissues, it does not affect simulated local tissue temperatures. However, the improved soft-tissue contrast provided by MRI allows generating a detailed brain segmentation, which has a strong impact on the predicted local temperatures and hence may improve simulation guided hyperthermia.« less

MRI classification system (MRICS) for children with cerebral palsy: development, reliability, and recommendations.

PubMed

Himmelmann, Kate; Horber, Veronka; De La Cruz, Javier; Horridge, Karen; Mejaski-Bosnjak, Vlatka; Hollody, Katalin; Krägeloh-Mann, Ingeborg

2017-01-01

To develop and evaluate a classification system for magnetic resonance imaging (MRI) findings of children with cerebral palsy (CP) that can be used in CP registers. The classification system was based on pathogenic patterns occurring in different periods of brain development. The MRI classification system (MRICS) consists of five main groups: maldevelopments, predominant white matter injury, predominant grey matter injury, miscellaneous, and normal findings. A detailed manual for the descriptions of these patterns was developed, including test cases (www.scpenetwork.eu/en/my-scpe/rtm/neuroimaging/cp-neuroimaging/). A literature review was performed and MRICS was compared with other classification systems. An exercise was carried out to check applicability and interrater reliability. Professionals working with children with CP or in CP registers were invited to participate in the exercise and chose to classify either 18 MRIs or MRI reports of children with CP. Classification systems in the literature were compatible with MRICS and harmonization possible. Interrater reliability was found to be good overall (k=0.69; 0.54-0.82) among the 41 participants and very good (k=0.81; 0.74-0.92) using the classification based on imaging reports. Surveillance of Cerebral Palsy in Europe (SCPE) proposes the MRICS as a reliable tool. Together with its manual it is simple to apply for CP registers. © 2016 Mac Keith Press.

Multiclass Classification for the Differential Diagnosis on the ADHD Subtypes Using Recursive Feature Elimination and Hierarchical Extreme Learning Machine: Structural MRI Study

PubMed Central

Qureshi, Muhammad Naveed Iqbal; Min, Beomjun; Jo, Hang Joon; Lee, Boreom

2016-01-01

The classification of neuroimaging data for the diagnosis of certain brain diseases is one of the main research goals of the neuroscience and clinical communities. In this study, we performed multiclass classification using a hierarchical extreme learning machine (H-ELM) classifier. We compared the performance of this classifier with that of a support vector machine (SVM) and basic extreme learning machine (ELM) for cortical MRI data from attention deficit/hyperactivity disorder (ADHD) patients. We used 159 structural MRI images of children from the publicly available ADHD-200 MRI dataset. The data consisted of three types, namely, typically developing (TDC), ADHD-inattentive (ADHD-I), and ADHD-combined (ADHD-C). We carried out feature selection by using standard SVM-based recursive feature elimination (RFE-SVM) that enabled us to achieve good classification accuracy (60.78%). In this study, we found the RFE-SVM feature selection approach in combination with H-ELM to effectively enable the acquisition of high multiclass classification accuracy rates for structural neuroimaging data. In addition, we found that the most important features for classification were the surface area of the superior frontal lobe, and the cortical thickness, volume, and mean surface area of the whole cortex. PMID:27500640

Multiclass Classification for the Differential Diagnosis on the ADHD Subtypes Using Recursive Feature Elimination and Hierarchical Extreme Learning Machine: Structural MRI Study.

PubMed

Qureshi, Muhammad Naveed Iqbal; Min, Beomjun; Jo, Hang Joon; Lee, Boreom

2016-01-01

The classification of neuroimaging data for the diagnosis of certain brain diseases is one of the main research goals of the neuroscience and clinical communities. In this study, we performed multiclass classification using a hierarchical extreme learning machine (H-ELM) classifier. We compared the performance of this classifier with that of a support vector machine (SVM) and basic extreme learning machine (ELM) for cortical MRI data from attention deficit/hyperactivity disorder (ADHD) patients. We used 159 structural MRI images of children from the publicly available ADHD-200 MRI dataset. The data consisted of three types, namely, typically developing (TDC), ADHD-inattentive (ADHD-I), and ADHD-combined (ADHD-C). We carried out feature selection by using standard SVM-based recursive feature elimination (RFE-SVM) that enabled us to achieve good classification accuracy (60.78%). In this study, we found the RFE-SVM feature selection approach in combination with H-ELM to effectively enable the acquisition of high multiclass classification accuracy rates for structural neuroimaging data. In addition, we found that the most important features for classification were the surface area of the superior frontal lobe, and the cortical thickness, volume, and mean surface area of the whole cortex.

Improved sparse decomposition based on a smoothed L0 norm using a Laplacian kernel to select features from fMRI data.

PubMed

Zhang, Chuncheng; Song, Sutao; Wen, Xiaotong; Yao, Li; Long, Zhiying

2015-04-30

Feature selection plays an important role in improving the classification accuracy of multivariate classification techniques in the context of fMRI-based decoding due to the "few samples and large features" nature of functional magnetic resonance imaging (fMRI) data. Recently, several sparse representation methods have been applied to the voxel selection of fMRI data. Despite the low computational efficiency of the sparse representation methods, they still displayed promise for applications that select features from fMRI data. In this study, we proposed the Laplacian smoothed L0 norm (LSL0) approach for feature selection of fMRI data. Based on the fast sparse decomposition using smoothed L0 norm (SL0) (Mohimani, 2007), the LSL0 method used the Laplacian function to approximate the L0 norm of sources. Results of the simulated and real fMRI data demonstrated the feasibility and robustness of LSL0 for the sparse source estimation and feature selection. Simulated results indicated that LSL0 produced more accurate source estimation than SL0 at high noise levels. The classification accuracy using voxels that were selected by LSL0 was higher than that by SL0 in both simulated and real fMRI experiment. Moreover, both LSL0 and SL0 showed higher classification accuracy and required less time than ICA and t-test for the fMRI decoding. LSL0 outperformed SL0 in sparse source estimation at high noise level and in feature selection. Moreover, LSL0 and SL0 showed better performance than ICA and t-test for feature selection. Copyright © 2015 Elsevier B.V. All rights reserved.

Linear Discriminant Analysis Achieves High Classification Accuracy for the BOLD fMRI Response to Naturalistic Movie Stimuli

PubMed Central

Mandelkow, Hendrik; de Zwart, Jacco A.; Duyn, Jeff H.

2016-01-01

Naturalistic stimuli like movies evoke complex perceptual processes, which are of great interest in the study of human cognition by functional MRI (fMRI). However, conventional fMRI analysis based on statistical parametric mapping (SPM) and the general linear model (GLM) is hampered by a lack of accurate parametric models of the BOLD response to complex stimuli. In this situation, statistical machine-learning methods, a.k.a. multivariate pattern analysis (MVPA), have received growing attention for their ability to generate stimulus response models in a data-driven fashion. However, machine-learning methods typically require large amounts of training data as well as computational resources. In the past, this has largely limited their application to fMRI experiments involving small sets of stimulus categories and small regions of interest in the brain. By contrast, the present study compares several classification algorithms known as Nearest Neighbor (NN), Gaussian Naïve Bayes (GNB), and (regularized) Linear Discriminant Analysis (LDA) in terms of their classification accuracy in discriminating the global fMRI response patterns evoked by a large number of naturalistic visual stimuli presented as a movie. Results show that LDA regularized by principal component analysis (PCA) achieved high classification accuracies, above 90% on average for single fMRI volumes acquired 2 s apart during a 300 s movie (chance level 0.7% = 2 s/300 s). The largest source of classification errors were autocorrelations in the BOLD signal compounded by the similarity of consecutive stimuli. All classifiers performed best when given input features from a large region of interest comprising around 25% of the voxels that responded significantly to the visual stimulus. Consistent with this, the most informative principal components represented widespread distributions of co-activated brain regions that were similar between subjects and may represent functional networks. In light of these results, the combination of naturalistic movie stimuli and classification analysis in fMRI experiments may prove to be a sensitive tool for the assessment of changes in natural cognitive processes under experimental manipulation. PMID:27065832

Fiber-probe optical spectroscopy discriminates normal brain from focal cortical dysplasia in pediatric subjects

NASA Astrophysics Data System (ADS)

Anand, Suresh; Cicchi, Riccardo; Giordano, Flavio; Conti, Valerio; Buccoliero, Anna Maria; Guerrini, Renzo; Pavone, Francesco S.

2017-02-01

Focal cortical dysplasia (FCD) is an abnormality in the cerebral cortex that is caused by malformations during cortical development. Currently, magnetic resonance imaging (MRI) and electro-corticography (ECoG) are used for detecting FCD. On the downside, MRI is very much insensitive to small malformations in the brain, while ECoG is an invasive and time consuming procedure. Recently, optical techniques were widely exploited as a minimally invasive and quantitative approaches for disease diagnosis. These techniques include fluorescence and Raman spectroscopy. The aim of this investigation is to study the diagnostic performances of optical spectroscopy incorporating fluorescence (at 378 nm and 445 nm excitation wavelengths) and Raman spectroscopy (at 785 nm excitation) for the discrimination of FCD from normal brain in pediatric subjects. The study included 10 normal and 17 FCD tissue sites from 3 normal and 7 FCD samples. The emission spectra of FCD at 378 nm excitation wavelength presented a blue-shifted peak with respect to normal tissue. Prominent spectral differences between normal and FCD tissue were observed at 1298 cm-1, 1302 cm-1, 1445 cm-1 and 1660 cm-1 using Raman spectroscopy. Tissue classification models were developed using a multivariate statistical method, principal component analysis. This study demonstrates that a combined spectroscopic approach can provide a better diagnostic capability for classifying normal and FCD tissues. Further, the implementation of the technology within a fiber probe could open the way for in vivo diagnostics and intra-operative surgical guidance.

Contrast-enhanced computed tomography plus gadolinium-ethoxybenzyl diethylenetriamine pentaacetic acid-enhanced magnetic resonance imaging for gross classification of hepatocellular carcinoma.

PubMed

Chen, Chuang; Zhao, Hui; Fu, Xu; Huang, LuoShun; Tang, Min; Yan, XiaoPeng; Sun, ShiQuan; Jia, WenJun; Mao, Liang; Shi, Jiong; Chen, Jun; He, Jian; Zhu, Jin; Qiu, YuDong

2017-05-02

Accurate gross classification through imaging is critical for determination of hepatocellular carcinoma (HCC) patient prognoses and treatment strategies. The present retrospective study evaluated the utility of contrast-enhanced computed tomography (CE-CT) combined with gadolinium-ethoxybenzyl diethylenetriamine pentaacetic acid-enhanced magnetic resonance imaging (EOB-MRI) for diagnosis and classification of HCCs prior to surgery. Ninety-four surgically resected HCC nodules were classified as simple nodular (SN), SN with extranodular growth (SN-EG), confluent multinodular (CMN), or infiltrative (IF) types. SN-EG, CMN and IF samples were grouped as non-SN. The abilities of the two imaging modalities to differentiate non-SN from SN HCCs were assessed using the EOB-MRI hepatobiliary phase and CE-CT arterial, portal, and equilibrium phases. Areas under the ROC curves for non-SN diagnoses were 0.765 (95% confidence interval [CI]: 0.666-0.846) for CE-CT, 0.877 (95% CI: 0.793-0.936) for EOB-MRI, and 0.908 (95% CI: 0.830-0.958) for CE-CT plus EOB-MRI. Sensitivities, specificities, and accuracies with respect to identification of non-SN tumors of all sizes were 71.4%, 81.6%, and 75.5% for CE-CT; 96.4%, 78.9%, and 89.3% for EOB-MRI; and 98.2%, 84.2%, and 92.5% for CE-CT plus EOB-MRI. These results show that CE-CT combined with EOB-MRI offers a more accurate imaging evaluation for HCC gross classification than either modality alone.

Unsupervised segmentation of brain regions with similar microstructural properties: application to alcoholism.

PubMed

Cosa, Alejandro; Canals, Santiago; Valles-Lluch, Ana; Moratal, David

2013-01-01

In this work, a novel brain MRI segmentation approach evaluates microstructural differences between groups. Going further from the traditional segmentation of brain tissues (white matter -WM-, gray matter -GM- and cerebrospinal fluid -CSF- or a mixture of them), a new way to classify brain areas is proposed using their microstructural MR properties. Eight rats were studied using the proposed methodology identifying regions which present microstructural differences as a consequence on one month of hard alcohol consumption. Differences in relaxation times of the tissues have been found in different brain regions (p<0.05). Furthermore, these changes allowed the automatic classification of the animals based on their drinking history (hit rate of 93.75 % of the cases).

Automated assessment of thigh composition using machine learning for Dixon magnetic resonance images.

PubMed

Yang, Yu Xin; Chong, Mei Sian; Tay, Laura; Yew, Suzanne; Yeo, Audrey; Tan, Cher Heng

2016-10-01

To develop and validate a machine learning based automated segmentation method that jointly analyzes the four contrasts provided by Dixon MRI technique for improved thigh composition segmentation accuracy. The automatic detection of body composition is formulized as a three-class classification issue. Each image voxel in the training dataset is assigned with a correct label. A voxel classifier is trained and subsequently used to predict unseen data. Morphological operations are finally applied to generate volumetric segmented images for different structures. We applied this algorithm on datasets of (1) four contrast images, (2) water and fat images, and (3) unsuppressed images acquired from 190 subjects. The proposed method using four contrasts achieved most accurate and robust segmentation compared to the use of combined fat and water images and the use of unsuppressed image, average Dice coefficients of 0.94 ± 0.03, 0.96 ± 0.03, 0.80 ± 0.03, and 0.97 ± 0.01 has been achieved to bone region, subcutaneous adipose tissue (SAT), inter-muscular adipose tissue (IMAT), and muscle respectively. Our proposed method based on machine learning produces accurate tissue quantification and showed an effective use of large information provided by the four contrast images from Dixon MRI.

Predictive MRI correlates of lesser metatarsophalangeal joint plantar plate tear.

PubMed

Umans, Rachel L; Umans, Benjamin D; Umans, Hilary; Elsinger, Elisabeth

2016-07-01

To identify correlated signs on non-enhanced MRI that might improve diagnostic detection of plantar plate (PP) tear. We performed an IRB-approved, HIPAA-compliant retrospective analysis of 100 non-contrast MRI (50 PP tear, 50 controls). All were anonymized, randomized, and reviewed; 20 were duplicated to assess consistency. One musculoskeletal radiologist evaluated qualitative variables. A trained non-physician performed measurements. Consistency and concordance were assessed. Pearson's Chi-square test was used to test the correlation between qualitative findings and PP tear status. Correlation between measurements and PP status was assessed using t tests and Wilcoxon's rank-sum test (p values < 0.05 considered significant). Classification and regression trees were utilized to identify attributes that, taken together, would consistently distinguish PP tear from controls. Quantitative measurements were highly reproducible (concordance 0.88-0.99). Elevated 2nd MT protrusion, lesser MT supination and rotational divergence of >45° between the 1st-2nd MT axis correlated with PP tear. Pericapsular soft tissue thickening correlated most strongly with PP tear, correctly classifying 95 % of cases and controls. Excluding pericapsular soft tissue thickening, sequential assessment of 2nd toe enthesitis, 2nd flexor tendon subluxation, and splaying of the second and third toes accurately classified PP status in 92 %. Pericapsular soft tissue thickening most strongly correlated with PP tear. For cases in which it might be difficult to distinguish pericapsular fibrosis from neuroma, sequential assessment of 2nd toe enthesitis, flexor tendon subluxation and splaying of the 2nd and 3rd toe is most helpful for optimizing accurate diagnosis of PP tear.

The Effects of Day-to-Day Variability of Physiological Data on Operator Functional State Classification

DTIC Science & Technology

2013-03-01

fMRI data (e.g. Kamitami & Tong, 2005). This approach has been remarkably successful in classifying mental workload in complex tasks (Berka, et al...1991). These previous studies relied upon spectral comparison rather than classification. In previous research examining the stability of fMRI ...chose to focus on electrophysiology, as the collection conditions may be more carefully controlled across days than fMRI and it is more amenable to

Transperineal ultrasonography: First level exam in IBD patients with perianal disease.

PubMed

Terracciano, Fulvia; Scalisi, Giuseppe; Bossa, Fabrizio; Scimeca, Daniela; Biscaglia, Giuseppe; Mangiacotti, Michele; Valvano, Maria Rosa; Perri, Francesco; Simeone, Anna; Andriulli, Angelo

2016-08-01

A pelvic magnetic resonance imaging (MRI) represents the front-line method for evaluating perianal disease in patients with inflammatory bowel disease (IBD). Recently, transperineal ultrasonography (TPUS) has been proposed as a simple, safe, time-sparing and useful diagnostic technique to assess different pathological conditions of the pelvic floor. The aim of this prospective single centre study was to evaluate the accuracy of TPUS versus MRI for the detection and classification of perineal disease in IBD patients. From November 2013 to November 2014, 28 IBD patients underwent either TPUS or MRI. Fistulae and abscesses were classified according to Parks' and AGA's classification methods. A concordance was assessed by k statistics. Overall, 33 fistulae and 8 abscesses were recognized by TPUS (30 and 7 by MRI, respectively). The agreement between TPUS and MRI was 75% according to Parks' classification (k=0.67) and 86% according to AGA classification (k=0.83), while it was 36% (k=0.34) for classifying abscesses. TPUS proved to be as accurate as MRI for detecting superficial and small abscesses and for classifying perianal disease. Both examinations may be performed at the initial presentation of the patient, but TPUS is a cheaper, time-sparing procedure. The optimal use of TPUS might be in follow-up patients. Copyright © 2016 Editrice Gastroenterologica Italiana S.r.l. Published by Elsevier Ltd. All rights reserved.

[MRI of the rotator cuff: evaluation of a new symptomatologic classification].

PubMed

Tavernier, T; Walch, G; Noël, E; Lapra, C; Bochu, M

1995-05-01

The different classifications use for the rotator cuff pathology seem to be incomplete. We propose a new classification with many advantages: 1) Differentiate the tendinopathy between less serious (grade 2A) and serious (grade 2B). 2) Recognize the intra-tendinous cleavage of the infra-spinatus associated with complete tear of the supra-spinatus. 3) Differentiate partial and complete tears of the supra-spinatus. We established this classification after a retrospective study of 42 patients operated on for a rotator cuff pathology. Every case had had a preoperative MRI. This classification is simple, reliable, especially for the associated intra tendinous cleavage.

Cross-sectional imaging of metal-on-metal hip arthroplasties. Can we substitute MARS MRI with CT?

PubMed

Robinson, Elizabeth; Henckel, Johann; Sabah, Shiraz; Satchithananda, Keshthra; Skinner, John; Hart, Alister

2014-12-01

Metal artifact reduction sequence (MARS) MRI is widely advocated for surveillance of metal-on-metal hip arthroplasties (MOM-HAs). However, its use is limited by susceptibility artifact at the prosthesis-bone interface, local availability, patient compliance, and cost (Hayter et al. 2011a). We wanted to determine whether CT is a suitable substitute for MARS MRI in evaluation of the painful MOM-HA. 50 MOM-HA patients (30 female) with unexplained painful prostheses underwent MARS MRI and CT imaging. 2 observers who were blind regarding the clinical data objectively reported the following outcomes: soft tissue lesions (pseudotumors), muscle atrophy, and acetabular and femoral osteolysis. Diagnostic test characteristics were calculated. Pseudotumor was diagnosed in 25 of 50 hips by MARS MRI and in 11 of 50 by CT. Pseudotumors were classified as type 1 (n=2), type 2A (n=17), type 2B (n=4), and type 3 (n=2) by MARS MRI. CT did not permit pseudotumor classification. The sensitivity of CT for diagnosis of pseudotumor was 44% (95% CI: 25-65). CT had "slight" agreement with MARS MRI for quantification of muscle atrophy (κ=0.23, CI: 0.16-0.29; p<0.01). Osteolysis was identified in 15 of 50 patients by CT. 4 of these lesions were identified by MARS MRI. CT was found to be superior to MRI for detection of osteolysis adjacent to MOM-HA, and should be incorporated into diagnostic algorithms. CT was unable to classify and failed to detect many pseudotumors, and it was unreliable for assessment of muscle atrophy. Where MARS MRI is contraindicated or unavailable, CT would be an unsuitable substitute and other modalities such as ultrasound should be considered.

Malakoplakia of the Prostate as a Mimicker of Prostate Cancer on Prostate Health Index and Magnetic Resonance Imaging-Fusion Prostate Biopsy: A Case Report.

PubMed

Heah, Nathaniel H; Tan, Teck Wei; Tan, Yung Khan

2017-01-01

Background: Isolated malakoplakia of the prostate is a rare inflammatory condition that has been clinically mistaken for prostatic malignancies. The development of Prostate Imaging Reporting and Data System (PI-RADS) classifications, and Prostate Health Index (PHI) has led to more accurate diagnosis of clinically significant disease and stratification of patients that may be at risk of prostate cancer. Case Presentation: We present a case of a 75-year-old male who was on follow-up with our hospital for elevated prostate specific antigen (PSA). He was admitted for an episode of urosepsis, which was treated with antibiotics and subsequently underwent further workup and was found to have a raised PHI, as well as a high PI-RADS classification and was later found to have malakoplakia based on histology of prostate tissue obtained during targeted magnetic resonance imaging (MRI)-guided fusion prostate biopsy. Conclusion: To our understanding, this is the first case where a prostate lesion has been labeled as a PI-RADS 5 lesion, with elevated PHI that has subsequently been proven histologically to be malakoplakia. An important possible confounder is the interval between the MRI and the episode of urosepsis and it is well known that urosepsis can affect the PSA and MRI result. We present this case to highlight the potential for a false diagnosis of prostate cancer, in spite of laboratory and radiological findings.

Ensemble support vector machine classification of dementia using structural MRI and mini-mental state examination.

PubMed

Sørensen, Lauge; Nielsen, Mads

2018-05-15

The International Challenge for Automated Prediction of MCI from MRI data offered independent, standardized comparison of machine learning algorithms for multi-class classification of normal control (NC), mild cognitive impairment (MCI), converting MCI (cMCI), and Alzheimer's disease (AD) using brain imaging and general cognition. We proposed to use an ensemble of support vector machines (SVMs) that combined bagging without replacement and feature selection. SVM is the most commonly used algorithm in multivariate classification of dementia, and it was therefore valuable to evaluate the potential benefit of ensembling this type of classifier. The ensemble SVM, using either a linear or a radial basis function (RBF) kernel, achieved multi-class classification accuracies of 55.6% and 55.0% in the challenge test set (60 NC, 60 MCI, 60 cMCI, 60 AD), resulting in a third place in the challenge. Similar feature subset sizes were obtained for both kernels, and the most frequently selected MRI features were the volumes of the two hippocampal subregions left presubiculum and right subiculum. Post-challenge analysis revealed that enforcing a minimum number of selected features and increasing the number of ensemble classifiers improved classification accuracy up to 59.1%. The ensemble SVM outperformed single SVM classifications consistently in the challenge test set. Ensemble methods using bagging and feature selection can improve the performance of the commonly applied SVM classifier in dementia classification. This resulted in competitive classification accuracies in the International Challenge for Automated Prediction of MCI from MRI data. Copyright © 2018 Elsevier B.V. All rights reserved.

Analysis of EEG-fMRI data in focal epilepsy based on automated spike classification and Signal Space Projection.

PubMed

Liston, Adam D; De Munck, Jan C; Hamandi, Khalid; Laufs, Helmut; Ossenblok, Pauly; Duncan, John S; Lemieux, Louis

2006-07-01

Simultaneous acquisition of EEG and fMRI data enables the investigation of the hemodynamic correlates of interictal epileptiform discharges (IEDs) during the resting state in patients with epilepsy. This paper addresses two issues: (1) the semi-automation of IED classification in statistical modelling for fMRI analysis and (2) the improvement of IED detection to increase experimental fMRI efficiency. For patients with multiple IED generators, sensitivity to IED-correlated BOLD signal changes can be improved when the fMRI analysis model distinguishes between IEDs of differing morphology and field. In an attempt to reduce the subjectivity of visual IED classification, we implemented a semi-automated system, based on the spatio-temporal clustering of EEG events. We illustrate the technique's usefulness using EEG-fMRI data from a subject with focal epilepsy in whom 202 IEDs were visually identified and then clustered semi-automatically into four clusters. Each cluster of IEDs was modelled separately for the purpose of fMRI analysis. This revealed IED-correlated BOLD activations in distinct regions corresponding to three different IED categories. In a second step, Signal Space Projection (SSP) was used to project the scalp EEG onto the dipoles corresponding to each IED cluster. This resulted in 123 previously unrecognised IEDs, the inclusion of which, in the General Linear Model (GLM), increased the experimental efficiency as reflected by significant BOLD activations. We have also shown that the detection of extra IEDs is robust in the face of fluctuations in the set of visually detected IEDs. We conclude that automated IED classification can result in more objective fMRI models of IEDs and significantly increased sensitivity.

Usefulness of Ilae 2010 classification in Mexican epilepsy patients.

PubMed

Leyva, Ildefonso Rodríguez; Gómez, Juan Francisco Hernández; Enríquez, Fernando Cortés; Sierra, Juan Francisco Hernández

2017-05-15

Advances in neuroimaging, genomics, and molecular biology have improved the understanding of the pathogenesis of epilepsy. That is why the International League Against Epilepsy (ILAE) has created a new classification system. The present study aims to evaluate the association between epilepsy cases classified by the ILAE 2010 classification proposal, electroencephalography (EEG), and magnetic resonance imaging brain findings (MRI). Prospective cross-sectional design of 277 cases of epilepsy seen at the Epilepsy Clinic, Hospital Central "Dr. Ignacio Morones Prieto", were compared with the ILAE classification based on the etiology and clinical manifestations and their MRI and EEG findings. Cochran, Mantell, Haenzel test with significance p<0.05. MRI findings were associated with the etiology of the ILAE classification. According to EEG findings, the structural-metabolic etiology patients had more dysfunctional reports than genetic or unknown etiology patients (p<0.05). The adoption of the ILAE classification is recommended, as it can provide useful guidance towards the etiology of cases of epilepsy even when brain MRIs and EEGs are not available. Copyright © 2017 Elsevier B.V. All rights reserved.

Event-Related fMRI of Category Learning: Differences in Classification and Feedback Networks

ERIC Educational Resources Information Center

Little, Deborah M.; Shin, Silvia S.; Sisco, Shannon M.; Thulborn, Keith R.

2006-01-01

Eighteen healthy young adults underwent event-related (ER) functional magnetic resonance imaging (fMRI) of the brain while performing a visual category learning task. The specific category learning task required subjects to extract the rules that guide classification of quasi-random patterns of dots into categories. Following each classification…

Comparison of classification methods for voxel-based prediction of acute ischemic stroke outcome following intra-arterial intervention

NASA Astrophysics Data System (ADS)

Winder, Anthony J.; Siemonsen, Susanne; Flottmann, Fabian; Fiehler, Jens; Forkert, Nils D.

2017-03-01

Voxel-based tissue outcome prediction in acute ischemic stroke patients is highly relevant for both clinical routine and research. Previous research has shown that features extracted from baseline multi-parametric MRI datasets have a high predictive value and can be used for the training of classifiers, which can generate tissue outcome predictions for both intravenous and conservative treatments. However, with the recent advent and popularization of intra-arterial thrombectomy treatment, novel research specifically addressing the utility of predictive classi- fiers for thrombectomy intervention is necessary for a holistic understanding of current stroke treatment options. The aim of this work was to develop three clinically viable tissue outcome prediction models using approximate nearest-neighbor, generalized linear model, and random decision forest approaches and to evaluate the accuracy of predicting tissue outcome after intra-arterial treatment. Therefore, the three machine learning models were trained, evaluated, and compared using datasets of 42 acute ischemic stroke patients treated with intra-arterial thrombectomy. Classifier training utilized eight voxel-based features extracted from baseline MRI datasets and five global features. Evaluation of classifier-based predictions was performed via comparison to the known tissue outcome, which was determined in follow-up imaging, using the Dice coefficient and leave-on-patient-out cross validation. The random decision forest prediction model led to the best tissue outcome predictions with a mean Dice coefficient of 0.37. The approximate nearest-neighbor and generalized linear model performed equally suboptimally with average Dice coefficients of 0.28 and 0.27 respectively, suggesting that both non-linearity and machine learning are desirable properties of a classifier well-suited to the intra-arterial tissue outcome prediction problem.

Pattern classification of fMRI data: applications for analysis of spatially distributed cortical networks.

PubMed

Yourganov, Grigori; Schmah, Tanya; Churchill, Nathan W; Berman, Marc G; Grady, Cheryl L; Strother, Stephen C

2014-08-01

The field of fMRI data analysis is rapidly growing in sophistication, particularly in the domain of multivariate pattern classification. However, the interaction between the properties of the analytical model and the parameters of the BOLD signal (e.g. signal magnitude, temporal variance and functional connectivity) is still an open problem. We addressed this problem by evaluating a set of pattern classification algorithms on simulated and experimental block-design fMRI data. The set of classifiers consisted of linear and quadratic discriminants, linear support vector machine, and linear and nonlinear Gaussian naive Bayes classifiers. For linear discriminant, we used two methods of regularization: principal component analysis, and ridge regularization. The classifiers were used (1) to classify the volumes according to the behavioral task that was performed by the subject, and (2) to construct spatial maps that indicated the relative contribution of each voxel to classification. Our evaluation metrics were: (1) accuracy of out-of-sample classification and (2) reproducibility of spatial maps. In simulated data sets, we performed an additional evaluation of spatial maps with ROC analysis. We varied the magnitude, temporal variance and connectivity of simulated fMRI signal and identified the optimal classifier for each simulated environment. Overall, the best performers were linear and quadratic discriminants (operating on principal components of the data matrix) and, in some rare situations, a nonlinear Gaussian naïve Bayes classifier. The results from the simulated data were supported by within-subject analysis of experimental fMRI data, collected in a study of aging. This is the first study that systematically characterizes interactions between analysis model and signal parameters (such as magnitude, variance and correlation) on the performance of pattern classifiers for fMRI. Copyright © 2014 Elsevier Inc. All rights reserved.

Multivariate analysis of fMRI time series: classification and regression of brain responses using machine learning.

PubMed

Formisano, Elia; De Martino, Federico; Valente, Giancarlo

2008-09-01

Machine learning and pattern recognition techniques are being increasingly employed in functional magnetic resonance imaging (fMRI) data analysis. By taking into account the full spatial pattern of brain activity measured simultaneously at many locations, these methods allow detecting subtle, non-strictly localized effects that may remain invisible to the conventional analysis with univariate statistical methods. In typical fMRI applications, pattern recognition algorithms "learn" a functional relationship between brain response patterns and a perceptual, cognitive or behavioral state of a subject expressed in terms of a label, which may assume discrete (classification) or continuous (regression) values. This learned functional relationship is then used to predict the unseen labels from a new data set ("brain reading"). In this article, we describe the mathematical foundations of machine learning applications in fMRI. We focus on two methods, support vector machines and relevance vector machines, which are respectively suited for the classification and regression of fMRI patterns. Furthermore, by means of several examples and applications, we illustrate and discuss the methodological challenges of using machine learning algorithms in the context of fMRI data analysis.

Breast density quantification using magnetic resonance imaging (MRI) with bias field correction: A postmortem study

PubMed Central

Ding, Huanjun; Johnson, Travis; Lin, Muqing; Le, Huy Q.; Ducote, Justin L.; Su, Min-Ying; Molloi, Sabee

2013-01-01

Purpose: Quantification of breast density based on three-dimensional breast MRI may provide useful information for the early detection of breast cancer. However, the field inhomogeneity can severely challenge the computerized image segmentation process. In this work, the effect of the bias field in breast density quantification has been investigated with a postmortem study. Methods: T1-weighted images of 20 pairs of postmortem breasts were acquired on a 1.5 T breast MRI scanner. Two computer-assisted algorithms were used to quantify the volumetric breast density. First, standard fuzzy c-means (FCM) clustering was used on raw images with the bias field present. Then, the coherent local intensity clustering (CLIC) method estimated and corrected the bias field during the iterative tissue segmentation process. Finally, FCM clustering was performed on the bias-field-corrected images produced by CLIC method. The left–right correlation for breasts in the same pair was studied for both segmentation algorithms to evaluate the precision of the tissue classification. Finally, the breast densities measured with the three methods were compared to the gold standard tissue compositions obtained from chemical analysis. The linear correlation coefficient, Pearson's r, was used to evaluate the two image segmentation algorithms and the effect of bias field. Results: The CLIC method successfully corrected the intensity inhomogeneity induced by the bias field. In left–right comparisons, the CLIC method significantly improved the slope and the correlation coefficient of the linear fitting for the glandular volume estimation. The left–right breast density correlation was also increased from 0.93 to 0.98. When compared with the percent fibroglandular volume (%FGV) from chemical analysis, results after bias field correction from both the CLIC the FCM algorithms showed improved linear correlation. As a result, the Pearson's r increased from 0.86 to 0.92 with the bias field correction. Conclusions: The investigated CLIC method significantly increased the precision and accuracy of breast density quantification using breast MRI images by effectively correcting the bias field. It is expected that a fully automated computerized algorithm for breast density quantification may have great potential in clinical MRI applications. PMID:24320536

Breast density quantification using magnetic resonance imaging (MRI) with bias field correction: a postmortem study.

PubMed

Ding, Huanjun; Johnson, Travis; Lin, Muqing; Le, Huy Q; Ducote, Justin L; Su, Min-Ying; Molloi, Sabee

2013-12-01

Quantification of breast density based on three-dimensional breast MRI may provide useful information for the early detection of breast cancer. However, the field inhomogeneity can severely challenge the computerized image segmentation process. In this work, the effect of the bias field in breast density quantification has been investigated with a postmortem study. T1-weighted images of 20 pairs of postmortem breasts were acquired on a 1.5 T breast MRI scanner. Two computer-assisted algorithms were used to quantify the volumetric breast density. First, standard fuzzy c-means (FCM) clustering was used on raw images with the bias field present. Then, the coherent local intensity clustering (CLIC) method estimated and corrected the bias field during the iterative tissue segmentation process. Finally, FCM clustering was performed on the bias-field-corrected images produced by CLIC method. The left-right correlation for breasts in the same pair was studied for both segmentation algorithms to evaluate the precision of the tissue classification. Finally, the breast densities measured with the three methods were compared to the gold standard tissue compositions obtained from chemical analysis. The linear correlation coefficient, Pearson's r, was used to evaluate the two image segmentation algorithms and the effect of bias field. The CLIC method successfully corrected the intensity inhomogeneity induced by the bias field. In left-right comparisons, the CLIC method significantly improved the slope and the correlation coefficient of the linear fitting for the glandular volume estimation. The left-right breast density correlation was also increased from 0.93 to 0.98. When compared with the percent fibroglandular volume (%FGV) from chemical analysis, results after bias field correction from both the CLIC the FCM algorithms showed improved linear correlation. As a result, the Pearson's r increased from 0.86 to 0.92 with the bias field correction. The investigated CLIC method significantly increased the precision and accuracy of breast density quantification using breast MRI images by effectively correcting the bias field. It is expected that a fully automated computerized algorithm for breast density quantification may have great potential in clinical MRI applications.

Pancreatitis-imaging approach

PubMed Central

Busireddy, Kiran K; AlObaidy, Mamdoh; Ramalho, Miguel; Kalubowila, Janaka; Baodong, Liu; Santagostino, Ilaria; Semelka, Richard C

2014-01-01

Pancreatitis is defined as the inflammation of the pancreas and considered the most common pancreatic disease in children and adults. Imaging plays a significant role in the diagnosis, severity assessment, recognition of complications and guiding therapeutic interventions. In the setting of pancreatitis, wider availability and good image quality make multi-detector contrast-enhanced computed tomography (MD-CECT) the most used imaging technique. However, magnetic resonance imaging (MRI) offers diagnostic capabilities similar to those of CT, with additional intrinsic advantages including lack of ionizing radiation and exquisite soft tissue characterization. This article reviews the proposed definitions of revised Atlanta classification for acute pancreatitis, illustrates a wide range of morphologic pancreatic parenchymal and associated peripancreatic changes for different types of acute pancreatitis. It also describes the spectrum of early and late chronic pancreatitis imaging findings and illustrates some of the less common types of chronic pancreatitis, with special emphasis on the role of CT and MRI. PMID:25133027

Classification of EEG abnormalities in partial epilepsy with simultaneous EEG-fMRI recordings.

PubMed

Pedreira, C; Vaudano, A E; Thornton, R C; Chaudhary, U J; Vulliemoz, S; Laufs, H; Rodionov, R; Carmichael, D W; Lhatoo, S D; Guye, M; Quian Quiroga, R; Lemieux, L

2014-10-01

Scalp EEG recordings and the classification of interictal epileptiform discharges (IED) in patients with epilepsy provide valuable information about the epileptogenic network, particularly by defining the boundaries of the "irritative zone" (IZ), and hence are helpful during pre-surgical evaluation of patients with severe refractory epilepsies. The current detection and classification of epileptiform signals essentially rely on expert observers. This is a very time-consuming procedure, which also leads to inter-observer variability. Here, we propose a novel approach to automatically classify epileptic activity and show how this method provides critical and reliable information related to the IZ localization beyond the one provided by previous approaches. We applied Wave_clus, an automatic spike sorting algorithm, for the classification of IED visually identified from pre-surgical simultaneous Electroencephalogram-functional Magnetic Resonance Imagining (EEG-fMRI) recordings in 8 patients affected by refractory partial epilepsy candidate for surgery. For each patient, two fMRI analyses were performed: one based on the visual classification and one based on the algorithmic sorting. This novel approach successfully identified a total of 29 IED classes (compared to 26 for visual identification). The general concordance between methods was good, providing a full match of EEG patterns in 2 cases, additional EEG information in 2 other cases and, in general, covering EEG patterns of the same areas as expert classification in 7 of the 8 cases. Most notably, evaluation of the method with EEG-fMRI data analysis showed hemodynamic maps related to the majority of IED classes representing improved performance than the visual IED classification-based analysis (72% versus 50%). Furthermore, the IED-related BOLD changes revealed by using the algorithm were localized within the presumed IZ for a larger number of IED classes (9) in a greater number of patients than the expert classification (7 and 5, respectively). In contrast, in only one case presented the new algorithm resulted in fewer classes and activation areas. We propose that the use of automated spike sorting algorithms to classify IED provides an efficient tool for mapping IED-related fMRI changes and increases the EEG-fMRI clinical value for the pre-surgical assessment of patients with severe epilepsy. Copyright © 2014 Elsevier Inc. All rights reserved.

Elimination of RF inhomogeneity effects in segmentation.

PubMed

Agus, Onur; Ozkan, Mehmed; Aydin, Kubilay

2007-01-01

There are various methods proposed for the segmentation and analysis of MR images. However the efficiency of these techniques is effected by various artifacts that occur in the imaging system. One of the most encountered problems is the intensity variation across an image. To overcome this problem different methods are used. In this paper we propose a method for the elimination of intensity artifacts in segmentation of MRI images. Inter imager variations are also minimized to produce the same tissue segmentation for the same patient. A well-known multivariate classification algorithm, maximum likelihood is employed to illustrate the enhancement in segmentation.

Evaluation of carotid plaque vulnerability in vivo: Correlation between dynamic contrast-enhanced MRI and MRI-modified AHA classification.

PubMed

Ge, Xiaoqian; Zhou, Zien; Zhao, Huilin; Li, Xiao; Sun, Beibei; Suo, Shiteng; Hackett, Maree L; Wan, Jieqing; Xu, Jianrong; Liu, Xiaosheng

2017-09-01

To noninvasively monitor carotid plaque vulnerability by exploring the relationship between pharmacokinetic parameters (PPs) of dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) and plaque types based on MRI-modified American Heart Association (AHA) classification, as well as to assess the ability of PPs in discrimination between stable and vulnerable plaques suspected on MRI. Of 70 consecutive patients with carotid plaques who volunteered for 3.0T MRI (3D time-of-flight [TOF], T 1 -weighted, T 2 -weighted, 3D magnetization-prepared rapid acquisition gradient-echo [MP-RAGE] and DCE-MRI), 66 participants were available for analysis. After plaque classification according to MRI-modified AHA Lesion-Type (LT), PPs (K trans , k ep , v e , and v p ) of DCE-MRI were measured. The Extended Tofts model was used for calculation of PPs. For participants with multiple carotid plaques, the plaque with the worst MRI-modified AHA LT was chosen for analysis. Correlations between PPs and plaque types and the ability of these parameters to distinguish stable and vulnerable plaques suspected on MRI were assessed. Significant positive correlation between K trans and LT III to VI was found (ρ = 0.532, P < 0.001), as was the correlation between k ep and LT III to VI (ρ = 0.409, P < 0.001). Stable and vulnerable plaques suspected on MRI could potentially be distinguished by K trans (sensitivity 83%, specificity 100%) and k ep (sensitivity 77%, specificity 91%). K trans and k ep from DCE-MRI can provide quantitative information to monitor plaque vulnerability in vivo and differentiate vulnerable plaques suspected on MRI from stable ones. These two parameters could be adopted as imaging biomarkers for plaque characterization and risk stratification. 1 Technical Efficacy: Stage 2 J. MAGN. RESON. IMAGING 2017;46:870-876. © 2017 International Society for Magnetic Resonance in Medicine.

Unsupervised MRI segmentation of brain tissues using a local linear model and level set.

PubMed

Rivest-Hénault, David; Cheriet, Mohamed

2011-02-01

Real-world magnetic resonance imaging of the brain is affected by intensity nonuniformity (INU) phenomena which makes it difficult to fully automate the segmentation process. This difficult task is accomplished in this work by using a new method with two original features: (1) each brain tissue class is locally modeled using a local linear region representative, which allows us to account for the INU in an implicit way and to more accurately position the region's boundaries; and (2) the region models are embedded in the level set framework, so that the spatial coherence of the segmentation can be controlled in a natural way. Our new method has been tested on the ground-truthed Internet Brain Segmentation Repository (IBSR) database and gave promising results, with Tanimoto indexes ranging from 0.61 to 0.79 for the classification of the white matter and from 0.72 to 0.84 for the gray matter. To our knowledge, this is the first time a region-based level set model has been used to perform the segmentation of real-world MRI brain scans with convincing results. Copyright © 2011 Elsevier Inc. All rights reserved.

Efficacy of thigh volume ratios assessed via stereovision body imaging as a predictor of visceral adipose tissue measured by magnetic resonance imaging

PubMed Central

Lee, Jane J; Freeland-Graves, Jeanne H; Pepper, M Reese; Yu, Wurong; Xu, Bugao

2014-01-01

Objectives The research examined the efficacy of regional volumes of thigh ratios assessed by stereovision body imaging (SBI) as a predictor of visceral adipose tissue measured by magnetic resonance imaging (MRI). Body measurements obtained via SBI also were utilized to explore disparities of body size and shape in men and women. Method 121 participants were measured for total/regional body volumes and ratios via SBI and abdominal subcutaneous and visceral adipose tissue areas by MRI. Results Thigh to torso and thigh to abdomen-hip volume ratios were the most reliable parameters to predict the accumulation of visceral adipose tissue depots compared to other body measurements. Thigh volume in relation to torso [odds ratios (OR) 0.44] and abdomen-hip (OR 0.41) volumes were negatively associated with increased risks of greater visceral adipose tissue depots, even after controlling for age, gender, and body mass index (BMI). Irrespective of BMI classification, men exhibited greater total body (80.95L vs. 72.41L), torso (39.26L vs. 34.13L), and abdomen-hip (29.01L vs. 25.85L) volumes than women. Women had higher thigh volumes (4.93L vs. 3.99L) and lower-body volume ratios [thigh to total body (0.07 vs. 0.05), thigh to torso (0.15 vs. 0.11), and thigh to abdomen-hip (0.20 vs. 0.15); p<0.05]. Conclusions The unique parameters of the volumes of thigh in relation to torso and abdomen-hip, by SBI were highly effective in predicting visceral adipose tissue deposition. The SBI provided an efficient method for determining body size and shape in men and women via total and regional body volumes and ratios. PMID:25645428

Knee cartilage extraction and bone-cartilage interface analysis from 3D MRI data sets

NASA Astrophysics Data System (ADS)

Tamez-Pena, Jose G.; Barbu-McInnis, Monica; Totterman, Saara

2004-05-01

This works presents a robust methodology for the analysis of the knee joint cartilage and the knee bone-cartilage interface from fused MRI sets. The proposed approach starts by fusing a set of two 3D MR images the knee. Although the proposed method is not pulse sequence dependent, the first sequence should be programmed to achieve good contrast between bone and cartilage. The recommended second pulse sequence is one that maximizes the contrast between cartilage and surrounding soft tissues. Once both pulse sequences are fused, the proposed bone-cartilage analysis is done in four major steps. First, an unsupervised segmentation algorithm is used to extract the femur, the tibia, and the patella. Second, a knowledge based feature extraction algorithm is used to extract the femoral, tibia and patellar cartilages. Third, a trained user corrects cartilage miss-classifications done by the automated extracted cartilage. Finally, the final segmentation is the revisited using an unsupervised MAP voxel relaxation algorithm. This final segmentation has the property that includes the extracted bone tissue as well as all the cartilage tissue. This is an improvement over previous approaches where only the cartilage was segmented. Furthermore, this approach yields very reproducible segmentation results in a set of scan-rescan experiments. When these segmentations were coupled with a partial volume compensated surface extraction algorithm the volume, area, thickness measurements shows precisions around 2.6%

Enhancing the discrimination accuracy between metastases, gliomas and meningiomas on brain MRI by volumetric textural features and ensemble pattern recognition methods.

PubMed

Georgiadis, Pantelis; Cavouras, Dionisis; Kalatzis, Ioannis; Glotsos, Dimitris; Athanasiadis, Emmanouil; Kostopoulos, Spiros; Sifaki, Koralia; Malamas, Menelaos; Nikiforidis, George; Solomou, Ekaterini

2009-01-01

Three-dimensional (3D) texture analysis of volumetric brain magnetic resonance (MR) images has been identified as an important indicator for discriminating among different brain pathologies. The purpose of this study was to evaluate the efficiency of 3D textural features using a pattern recognition system in the task of discriminating benign, malignant and metastatic brain tissues on T1 postcontrast MR imaging (MRI) series. The dataset consisted of 67 brain MRI series obtained from patients with verified and untreated intracranial tumors. The pattern recognition system was designed as an ensemble classification scheme employing a support vector machine classifier, specially modified in order to integrate the least squares features transformation logic in its kernel function. The latter, in conjunction with using 3D textural features, enabled boosting up the performance of the system in discriminating metastatic, malignant and benign brain tumors with 77.14%, 89.19% and 93.33% accuracy, respectively. The method was evaluated using an external cross-validation process; thus, results might be considered indicative of the generalization performance of the system to "unseen" cases. The proposed system might be used as an assisting tool for brain tumor characterization on volumetric MRI series.

Characterization of Cerebral White Matter Properties Using Quantitative Magnetic Resonance Imaging Stains

PubMed Central

Hurley, Samuel A.; Samsonov, Alexey A.; Adluru, Nagesh; Hosseinbor, Ameer Pasha; Mossahebi, Pouria; Tromp, Do P.M.; Zakszewski, Elizabeth; Field, Aaron S.

2011-01-01

Abstract The image contrast in magnetic resonance imaging (MRI) is highly sensitive to several mechanisms that are modulated by the properties of the tissue environment. The degree and type of contrast weighting may be viewed as image filters that accentuate specific tissue properties. Maps of quantitative measures of these mechanisms, akin to microstructural/environmental-specific tissue stains, may be generated to characterize the MRI and physiological properties of biological tissues. In this article, three quantitative MRI (qMRI) methods for characterizing white matter (WM) microstructural properties are reviewed. All of these measures measure complementary aspects of how water interacts with the tissue environment. Diffusion MRI, including diffusion tensor imaging, characterizes the diffusion of water in the tissues and is sensitive to the microstructural density, spacing, and orientational organization of tissue membranes, including myelin. Magnetization transfer imaging characterizes the amount and degree of magnetization exchange between free water and macromolecules like proteins found in the myelin bilayers. Relaxometry measures the MRI relaxation constants T1 and T2, which in WM have a component associated with the water trapped in the myelin bilayers. The conduction of signals between distant brain regions occurs primarily through myelinated WM tracts; thus, these methods are potential indicators of pathology and structural connectivity in the brain. This article provides an overview of the qMRI stain mechanisms, acquisition and analysis strategies, and applications for these qMRI stains. PMID:22432902

Posterior medial meniscus root ligament lesions: MRI classification and associated findings.

PubMed

Choi, Ja-Young; Chang, Eric Y; Cunha, Guilherme M; Tafur, Monica; Statum, Sheronda; Chung, Christine B

2014-12-01

The purposes of this study were to determine the prevalence of altered MRI appearances of "posterior medial meniscus root ligament (PMMRL)" lesions, introduce a classification of lesion types, and report associated findings. We retrospectively reviewed 419 knee MRI studies to identify the presence of PMMRL lesions. Classification was established on the basis of lesions encountered. The medial compartment was assessed for medial meniscal tears in the meniscus proper, medial meniscal extrusion, insertional PMMRL osseous changes, regional synovitis, osteoarthritis, insufficiency fracture, and cruciate ligament abnormality. PMMRL abnormalities occurred in 28.6% (120/419) of the studies: degeneration, 14.3% (60/419) and tear, 14.3% (60/419). Our classification system included degeneration and tearing. Tearing was categorized as partial or complete with delineation of the point of failure as entheseal, midsubstance, or junction to meniscus. Of all tears, 93.3% (56/60) occurred at the meniscal junction. Univariate analysis revealed significant differences between the knees with and without PMMRL lesions in age, medial meniscal tear, medial meniscal extrusion, insertional PMMRL osseous change, regional synovitis, osteoarthritis, insufficiency fracture (p=0.017), and cruciate ligament degeneration (p<0.001). PMMRL lesions are commonly detected in symptomatic patients. We have introduced an MRI classification system. PMMRL lesions are significantly associated with age, medial meniscal tears, medial meniscal extrusion, insertional PMMRL osseous change, regional synovitis, osteoarthritis, insufficiency fracture, and cruciate ligament degeneration.

[MRI and CT-scan in presumed benign ovarian tumors].

PubMed

Thomassin-Naggara, I; Bazot, M

2013-12-01

Radiological examinations are required for the assessment of complex or indeterminate ovarian masses, mainly using MRI and CT-scan. MRI provides better tissue characterization than Doppler ultrasound or CT-scan (LE2). Pelvic MRI is recommended in case of an indeterminate or complex ovarian ultrasonographic mass (grade B). The protocol of a pelvic MRI should include morphological T1 and T2 sequences (grade B). In case of solid portion, perfusion and diffusion sequences are recommended (grade C). In case of doubt about the diagnosis of ovarian origin, pelvic MRI is preferred over the CT-scan (grade C). MRI is the technique of choice for the difference between functional and organic ovarian lesion diagnosis (grade C). It can be useful in case of clinical diagnostic uncertainty between polycystic ovary syndrome and ovarian hyperstimulation and multilocular ovarian tumor syndrome (grade C). No MRI classification for ovarian masses is currently validated. The establishment of a presumption of risk of malignancy is required in a MRI report of adnexal mass with if possible a guidance on the histological diagnosis. In the absence of clinical or sonographic diagnosis, pelvic CT-scan is recommended in the context of acute painful pelvic mass in non-pregnant patients (grade C). It specifies the anomalies and allows the differential diagnosis with digestive and urinary diseases (LE4). Given the lack of data in the literature, the precautionary principle must be applied to the realization of a pelvic MRI in a pregnant patient. A risk-benefit balance should be evaluated case by case by the clinician and the radiologist and information should be given to the patient. In an emergency situation during pregnancy, pelvic MRI is an alternative to CT-scan for the exploration of acute pelvic pain in case of uncertain sonographic diagnosis (grade C). Copyright © 2013. Published by Elsevier Masson SAS.

High-resolution 3 T MRI of traumatic and degenerative triangular fibrocartilage complex (TFCC) abnormalities using Palmer and Outerbridge classifications.

PubMed

Nozaki, T; Rafijah, G; Yang, L; Ueno, T; Horiuchi, S; Hitt, D; Yoshioka, H

2017-10-01

To investigate the usefulness of high-resolution 3 T magnetic resonance imaging (MRI) for the evaluation of traumatic and degenerative triangular fibrocartilage complex (TFCC) abnormalities among three groups: patients presenting with wrist pain who were (a) younger than age 50 years or (b) age 50 or older (PT<50 and PT≥50, respectively), and (c) asymptomatic controls who were younger than age 50 years (AC). High-resolution 3 T MRI was evaluated retrospectively in 96 patients, including 47 PT<50, 38 PT≥50, and 11 AC. Two board-certified radiologists reviewed the MRI images independently. MRI features of TFCC injury were analysed according to the Palmer classification, and cartilage degeneration around the TFCC was evaluated using the Outerbridge classification. Differences in MRI findings among these groups were detected using chi-square test. Cohen's kappa was calculated to assess interobserver and intra-observer reliability. The incidence of Palmer class 1A, 1C and 1D traumatic TFCC injury was significantly (p<0.05) higher in PT≥50 than in PT<50 (class 1A: 47.4% versus 27.7%, class 1C: 31.6% versus 12.8%, and class 1D: 21.1% versus 2.1%). Likewise, MRI findings of TFCC degeneration were observed more frequently in PT≥50 than in PT<50 (p<0.01). Outerbridge grade 2 or higher cartilage degeneration was significantly (p<0.01) more frequently seen in PT≥50 than in PT<50 (55.3% versus 17% in the lunate, 28.9% versus 4.3% in the triquetrum, 73.7% versus 12.8% in the ulna). High-resolution wrist MRI at 3 T enables detailed evaluation of TFCC traumatic injury and degenerative changes using the Palmer and Outerbridge classifications, with good or excellent interobserver and intra-observer reliability. Copyright © 2017 The Royal College of Radiologists. Published by Elsevier Ltd. All rights reserved.

Assessment of MRI Issues at 3 Tesla for a New Metallic Tissue Marker

PubMed Central

Cronenweth, Charlotte M.; Shellock, Frank G.

2015-01-01

Purpose. To assess the MRI issues at 3 Tesla for a metallic tissue marker used to localize removal areas of tissue abnormalities. Materials and Methods. A newly designed, metallic tissue marker (Achieve Marker, CareFusion, Vernon Hills, IL) used to mark biopsy sites, particularly in breasts, was assessed for MRI issues which included standardized tests to determine magnetic field interactions (i.e., translational attraction and torque), MRI-related heating, and artifacts at 3 Tesla. Temperature changes were determined for the marker using a gelled-saline-filled phantom. MRI was performed at a relatively high specific absorption rate (whole body averaged SAR, 2.9-W/kg). MRI artifacts were evaluated using T1-weighted, spin echo and gradient echo pulse sequences. Results. The marker displayed minimal magnetic field interactions (2-degree deflection angle and no torque). MRI-related heating was only 0.1°C above background heating (i.e., the heating without the tissue marker present). Artifacts seen as localized signal loss were relatively small in relation to the size and shape of the marker. Conclusions. Based on the findings, the new metallic tissue marker is acceptable or “MR Conditional” (using current labeling terminology) for a patient undergoing an MRI procedure at 3 Tesla or less. PMID:26266051

Co-trained convolutional neural networks for automated detection of prostate cancer in multi-parametric MRI.

PubMed

Yang, Xin; Liu, Chaoyue; Wang, Zhiwei; Yang, Jun; Min, Hung Le; Wang, Liang; Cheng, Kwang-Ting Tim

2017-12-01

Multi-parameter magnetic resonance imaging (mp-MRI) is increasingly popular for prostate cancer (PCa) detection and diagnosis. However, interpreting mp-MRI data which typically contains multiple unregistered 3D sequences, e.g. apparent diffusion coefficient (ADC) and T2-weighted (T2w) images, is time-consuming and demands special expertise, limiting its usage for large-scale PCa screening. Therefore, solutions to computer-aided detection of PCa in mp-MRI images are highly desirable. Most recent advances in automated methods for PCa detection employ a handcrafted feature based two-stage classification flow, i.e. voxel-level classification followed by a region-level classification. This work presents an automated PCa detection system which can concurrently identify the presence of PCa in an image and localize lesions based on deep convolutional neural network (CNN) features and a single-stage SVM classifier. Specifically, the developed co-trained CNNs consist of two parallel convolutional networks for ADC and T2w images respectively. Each network is trained using images of a single modality in a weakly-supervised manner by providing a set of prostate images with image-level labels indicating only the presence of PCa without priors of lesions' locations. Discriminative visual patterns of lesions can be learned effectively from clutters of prostate and surrounding tissues. A cancer response map with each pixel indicating the likelihood to be cancerous is explicitly generated at the last convolutional layer of the network for each modality. A new back-propagated error E is defined to enforce both optimized classification results and consistent cancer response maps for different modalities, which help capture highly representative PCa-relevant features during the CNN feature learning process. The CNN features of each modality are concatenated and fed into a SVM classifier. For images which are classified to contain cancers, non-maximum suppression and adaptive thresholding are applied to the corresponding cancer response maps for PCa foci localization. Evaluation based on 160 patient data with 12-core systematic TRUS-guided prostate biopsy as the reference standard demonstrates that our system achieves a sensitivity of 0.46, 0.92 and 0.97 at 0.1, 1 and 10 false positives per normal/benign patient which is significantly superior to two state-of-the-art CNN-based methods (Oquab et al., 2015; Zhou et al., 2015) and 6-core systematic prostate biopsies. Copyright © 2017 Elsevier B.V. All rights reserved.

Comparative Approach of MRI-Based Brain Tumor Segmentation and Classification Using Genetic Algorithm.

PubMed

Bahadure, Nilesh Bhaskarrao; Ray, Arun Kumar; Thethi, Har Pal

2018-01-17

The detection of a brain tumor and its classification from modern imaging modalities is a primary concern, but a time-consuming and tedious work was performed by radiologists or clinical supervisors. The accuracy of detection and classification of tumor stages performed by radiologists is depended on their experience only, so the computer-aided technology is very important to aid with the diagnosis accuracy. In this study, to improve the performance of tumor detection, we investigated comparative approach of different segmentation techniques and selected the best one by comparing their segmentation score. Further, to improve the classification accuracy, the genetic algorithm is employed for the automatic classification of tumor stage. The decision of classification stage is supported by extracting relevant features and area calculation. The experimental results of proposed technique are evaluated and validated for performance and quality analysis on magnetic resonance brain images, based on segmentation score, accuracy, sensitivity, specificity, and dice similarity index coefficient. The experimental results achieved 92.03% accuracy, 91.42% specificity, 92.36% sensitivity, and an average segmentation score between 0.82 and 0.93 demonstrating the effectiveness of the proposed technique for identifying normal and abnormal tissues from brain MR images. The experimental results also obtained an average of 93.79% dice similarity index coefficient, which indicates better overlap between the automated extracted tumor regions with manually extracted tumor region by radiologists.

A novel segmentation approach for implementation of MRAC in head PET/MRI employing Short-TE MRI and 2-point Dixon method in a fuzzy C-means framework

NASA Astrophysics Data System (ADS)

Khateri, Parisa; Rad, Hamidreza Saligheh; Jafari, Amir Homayoun; Ay, Mohammad Reza

2014-01-01

Quantitative PET image reconstruction requires an accurate map of attenuation coefficients of the tissue under investigation at 511 keV (μ-map), and in order to correct the emission data for attenuation. The use of MRI-based attenuation correction (MRAC) has recently received lots of attention in the scientific literature. One of the major difficulties facing MRAC has been observed in the areas where bone and air collide, e.g. ethmoidal sinuses in the head area. Bone is intrinsically not detectable by conventional MRI, making it difficult to distinguish air from bone. Therefore, development of more versatile MR sequences to label the bone structure, e.g. ultra-short echo-time (UTE) sequences, certainly plays a significant role in novel methodological developments. However, long acquisition time and complexity of UTE sequences limit its clinical applications. To overcome this problem, we developed a novel combination of Short-TE (ShTE) pulse sequence to detect bone signal with a 2-point Dixon technique for water-fat discrimination, along with a robust image segmentation method based on fuzzy clustering C-means (FCM) to segment the head area into four classes of air, bone, soft tissue and adipose tissue. The imaging protocol was set on a clinical 3 T Tim Trio and also 1.5 T Avanto (Siemens Medical Solution, Erlangen, Germany) employing a triple echo time pulse sequence in the head area. The acquisition parameters were as follows: TE1/TE2/TE3=0.98/4.925/6.155 ms, TR=8 ms, FA=25 on the 3 T system, and TE1/TE2/TE3=1.1/2.38/4.76 ms, TR=16 ms, FA=18 for the 1.5 T system. The second and third echo-times belonged to the Dixon decomposition to distinguish soft and adipose tissues. To quantify accuracy, sensitivity and specificity of the bone segmentation algorithm, resulting classes of MR-based segmented bone were compared with the manual segmented one by our expert neuro-radiologist. Results for both 3 T and 1.5 T systems show that bone segmentation applied in several slices yields average accuracy, sensitivity and specificity higher than 90%. Results indicate that FCM is an appropriate technique for tissue classification in the sinusoidal area where there is air-bone interface. Furthermore, using Dixon method, fat and brain tissues were successfully separated.

Multiclass fMRI data decoding and visualization using supervised self-organizing maps.

PubMed

Hausfeld, Lars; Valente, Giancarlo; Formisano, Elia

2014-08-01

When multivariate pattern decoding is applied to fMRI studies entailing more than two experimental conditions, a most common approach is to transform the multiclass classification problem into a series of binary problems. Furthermore, for decoding analyses, classification accuracy is often the only outcome reported although the topology of activation patterns in the high-dimensional features space may provide additional insights into underlying brain representations. Here we propose to decode and visualize voxel patterns of fMRI datasets consisting of multiple conditions with a supervised variant of self-organizing maps (SSOMs). Using simulations and real fMRI data, we evaluated the performance of our SSOM-based approach. Specifically, the analysis of simulated fMRI data with varying signal-to-noise and contrast-to-noise ratio suggested that SSOMs perform better than a k-nearest-neighbor classifier for medium and large numbers of features (i.e. 250 to 1000 or more voxels) and similar to support vector machines (SVMs) for small and medium numbers of features (i.e. 100 to 600voxels). However, for a larger number of features (>800voxels), SSOMs performed worse than SVMs. When applied to a challenging 3-class fMRI classification problem with datasets collected to examine the neural representation of three human voices at individual speaker level, the SSOM-based algorithm was able to decode speaker identity from auditory cortical activation patterns. Classification performances were similar between SSOMs and other decoding algorithms; however, the ability to visualize decoding models and underlying data topology of SSOMs promotes a more comprehensive understanding of classification outcomes. We further illustrated this visualization ability of SSOMs with a re-analysis of a dataset examining the representation of visual categories in the ventral visual cortex (Haxby et al., 2001). This analysis showed that SSOMs could retrieve and visualize topography and neighborhood relations of the brain representation of eight visual categories. We conclude that SSOMs are particularly suited for decoding datasets consisting of more than two classes and are optimally combined with approaches that reduce the number of voxels used for classification (e.g. region-of-interest or searchlight approaches). Copyright © 2014. Published by Elsevier Inc.

Automatic Denoising of Functional MRI Data: Combining Independent Component Analysis and Hierarchical Fusion of Classifiers

PubMed Central

Salimi-Khorshidi, Gholamreza; Douaud, Gwenaëlle; Beckmann, Christian F; Glasser, Matthew F; Griffanti, Ludovica; Smith, Stephen M

2014-01-01

Many sources of fluctuation contribute to the fMRI signal, and this makes identifying the effects that are truly related to the underlying neuronal activity difficult. Independent component analysis (ICA) - one of the most widely used techniques for the exploratory analysis of fMRI data - has shown to be a powerful technique in identifying various sources of neuronally-related and artefactual fluctuation in fMRI data (both with the application of external stimuli and with the subject “at rest”). ICA decomposes fMRI data into patterns of activity (a set of spatial maps and their corresponding time series) that are statistically independent and add linearly to explain voxel-wise time series. Given the set of ICA components, if the components representing “signal” (brain activity) can be distinguished form the “noise” components (effects of motion, non-neuronal physiology, scanner artefacts and other nuisance sources), the latter can then be removed from the data, providing an effective cleanup of structured noise. Manual classification of components is labour intensive and requires expertise; hence, a fully automatic noise detection algorithm that can reliably detect various types of noise sources (in both task and resting fMRI) is desirable. In this paper, we introduce FIX (“FMRIB’s ICA-based X-noiseifier”), which provides an automatic solution for denoising fMRI data via accurate classification of ICA components. For each ICA component FIX generates a large number of distinct spatial and temporal features, each describing a different aspect of the data (e.g., what proportion of temporal fluctuations are at high frequencies). The set of features is then fed into a multi-level classifier (built around several different Classifiers). Once trained through the hand-classification of a sufficient number of training datasets, the classifier can then automatically classify new datasets. The noise components can then be subtracted from (or regressed out of) the original data, to provide automated cleanup. On conventional resting-state fMRI (rfMRI) single-run datasets, FIX achieved about 95% overall accuracy. On high-quality rfMRI data from the Human Connectome Project, FIX achieves over 99% classification accuracy, and as a result is being used in the default rfMRI processing pipeline for generating HCP connectomes. FIX is publicly available as a plugin for FSL. PMID:24389422

Improving the Performance of the Prony Method Using a Wavelet Domain Filter for MRI Denoising

PubMed Central

Lentini, Marianela; Paluszny, Marco

2014-01-01

The Prony methods are used for exponential fitting. We use a variant of the Prony method for abnormal brain tissue detection in sequences of T 2 weighted magnetic resonance images. Here, MR images are considered to be affected only by Rician noise, and a new wavelet domain bilateral filtering process is implemented to reduce the noise in the images. This filter is a modification of Kazubek's algorithm and we use synthetic images to show the ability of the new procedure to suppress noise and compare its performance with respect to the original filter, using quantitative and qualitative criteria. The tissue classification process is illustrated using a real sequence of T 2 MR images, and the filter is applied to each image before using the variant of the Prony method. PMID:24834108

Improving the performance of the prony method using a wavelet domain filter for MRI denoising.

PubMed

Jaramillo, Rodney; Lentini, Marianela; Paluszny, Marco

2014-01-01

The Prony methods are used for exponential fitting. We use a variant of the Prony method for abnormal brain tissue detection in sequences of T 2 weighted magnetic resonance images. Here, MR images are considered to be affected only by Rician noise, and a new wavelet domain bilateral filtering process is implemented to reduce the noise in the images. This filter is a modification of Kazubek's algorithm and we use synthetic images to show the ability of the new procedure to suppress noise and compare its performance with respect to the original filter, using quantitative and qualitative criteria. The tissue classification process is illustrated using a real sequence of T 2 MR images, and the filter is applied to each image before using the variant of the Prony method.

PET/MRI of metabolic activity in osteoarthritis: A feasibility study.

PubMed

Kogan, Feliks; Fan, Audrey P; McWalter, Emily J; Oei, Edwin H G; Quon, Andrew; Gold, Garry E

2017-06-01

To evaluate positron emission tomography / magnetic resonance imaging (PET/MRI) knee imaging to detect and characterize osseous metabolic abnormalities and correlate PET radiotracer uptake with osseous abnormalities and cartilage degeneration observed on MRI. Both knees of 22 subjects with knee pain or injury were scanned at one timepoint, without gadolinium, on a hybrid 3.0T PET-MRI system following injection of 18 F-fluoride or 18 F-fluorodeoxyglucose (FDG). A musculoskeletal radiologist identified volumes of interest (VOIs) around bone abnormalities on MR images and scored bone marrow lesions (BMLs) and osteophytes using a MOAKS scoring system. Cartilage appearance adjacent to bone abnormalities was graded with MRI-modified Outerbridge classifications. On PET standardized uptake values (SUV) maps, VOIs with SUV greater than 5 times the SUV in normal-appearing bone were identified as high-uptake VOI (VOI High ). Differences in 18 F-fluoride uptake between bone abnormalities, BML, and osteophyte grades and adjacent cartilage grades on MRI were identified using Mann-Whitney U-tests. SUV max in all subchondral bone lesions (BML, osteophytes, sclerosis) was significantly higher than that of normal-appearing bone on MRI (P < 0.001 for all). Of the 172 high-uptake regions on 18 F-fluoride PET, 63 (37%) corresponded to normal-appearing subchondral bone on MRI. Furthermore, many small grade 1 osteophytes (40 of 82 [49%]), often described as the earliest signs of osteoarthritis (OA), did not show high uptake. Lastly, PET SUV max in subchondral bone adjacent to grade 0 cartilage was significantly lower compared to that of grades 1-2 (P < 0.05) and grades 3-4 cartilage (P < 0.001). PET/MRI can simultaneously assess multiple early metabolic and morphologic markers of knee OA across multiple tissues in the joint. Our findings suggest that PET/MR may detect metabolic abnormalities in subchondral bone, which appear normal on MRI. 2 Technical Efficacy: Stage 1 J. MAGN. RESON. IMAGING 2017;45:1736-1745. © 2016 International Society for Magnetic Resonance in Medicine.

[Magnetic resonance imaging in facial injuries and digital fusion CT/MRI].

PubMed

Kozakiewicz, Marcin; Olszycki, Marek; Arkuszewski, Piotr; Stefańczyk, Ludomir

2006-01-01

Magnetic resonance images [MRI] and their digital fusion with computed tomography [CT] data, observed in patients affected with facial injuries, are presented in this study. The MR imaging of 12 posttraumatic patients was performed in the same plains as their previous CT scans. Evaluation focused on quality of the facial soft tissues depicting, which was unsatisfactory in CT. Using the own "Dental Studio" programme the digital fusion of the both modalities was performed. Pathologic dislocations and injures of facial soft tissues are visualized better in MRI than in CT examination. Especially MRI properly reveals disturbances in intraorbital soft structures. MRI-based assessment is valuable in patients affected with facial soft tissues injuries, especially in case of orbita/sinuses hernia. Fusion CT/MRI scans allows to evaluate simultaneously bone structure and soft tissues of the same region.

Optimized statistical parametric mapping for partial-volume-corrected amyloid positron emission tomography in patients with Alzheimer's disease and Lewy body dementia

NASA Astrophysics Data System (ADS)

Oh, Jungsu S.; Kim, Jae Seung; Chae, Sun Young; Oh, Minyoung; Oh, Seung Jun; Cha, Seung Nam; Chang, Ho-Jong; Lee, Chong Sik; Lee, Jae Hong

2017-03-01

We present an optimized voxelwise statistical parametric mapping (SPM) of partial-volume (PV)-corrected positron emission tomography (PET) of 11C Pittsburgh Compound B (PiB), incorporating the anatomical precision of magnetic resonance image (MRI) and amyloid β (A β) burden-specificity of PiB PET. First, we applied region-based partial-volume correction (PVC), termed the geometric transfer matrix (GTM) method, to PiB PET, creating MRI-based lobar parcels filled with mean PiB uptakes. Then, we conducted a voxelwise PVC by multiplying the original PET by the ratio of a GTM-based PV-corrected PET to a 6-mm-smoothed PV-corrected PET. Finally, we conducted spatial normalizations of the PV-corrected PETs onto the study-specific template. As such, we increased the accuracy of the SPM normalization and the tissue specificity of SPM results. Moreover, lobar smoothing (instead of whole-brain smoothing) was applied to increase the signal-to-noise ratio in the image without degrading the tissue specificity. Thereby, we could optimize a voxelwise group comparison between subjects with high and normal A β burdens (from 10 patients with Alzheimer's disease, 30 patients with Lewy body dementia, and 9 normal controls). Our SPM framework outperformed than the conventional one in terms of the accuracy of the spatial normalization (85% of maximum likelihood tissue classification volume) and the tissue specificity (larger gray matter, and smaller cerebrospinal fluid volume fraction from the SPM results). Our SPM framework optimized the SPM of a PV-corrected A β PET in terms of anatomical precision, normalization accuracy, and tissue specificity, resulting in better detection and localization of A β burdens in patients with Alzheimer's disease and Lewy body dementia.

Individual Patient Diagnosis of AD and FTD via High-Dimensional Pattern Classification of MRI

PubMed Central

Davatzikos, C.; Resnick, S. M.; Wu, X.; Parmpi, P.; Clark, C. M.

2008-01-01

The purpose of this study is to determine the diagnostic accuracy of MRI-based high-dimensional pattern classification in differentiating between patients with Alzheimer’s Disease (AD), Frontotemporal Dementia (FTD), and healthy controls, on an individual patient basis. MRI scans of 37 patients with AD and 37 age-matched cognitively normal elderly individuals, as well as 12 patients with FTD and 12 age-matched cognitively normal elderly individuals, were analyzed using voxel-based analysis and high-dimensional pattern classification. Diagnostic sensitivity and specificity of spatial patterns of regional brain atrophy found to be characteristic of AD and FTD were determined via cross-validation and via split-sample methods. Complex spatial patterns of relatively reduced brain volumes were identified, including temporal, orbitofrontal, parietal and cingulate regions, which were predominantly characteristic of either AD or FTD. These patterns provided 100% diagnostic accuracy, when used to separate AD or FTD from healthy controls. The ability to correctly distinguish AD from FTD averaged 84.3%. All estimates of diagnostic accuracy were determined via cross-validation. In conclusion, AD- and FTD-specific patterns of brain atrophy can be detected with high accuracy using high-dimensional pattern classification of MRI scans obtained in a typical clinical setting. PMID:18474436

The maximum entropy method of moments and Bayesian probability theory

NASA Astrophysics Data System (ADS)

Bretthorst, G. Larry

2013-08-01

The problem of density estimation occurs in many disciplines. For example, in MRI it is often necessary to classify the types of tissues in an image. To perform this classification one must first identify the characteristics of the tissues to be classified. These characteristics might be the intensity of a T1 weighted image and in MRI many other types of characteristic weightings (classifiers) may be generated. In a given tissue type there is no single intensity that characterizes the tissue, rather there is a distribution of intensities. Often this distributions can be characterized by a Gaussian, but just as often it is much more complicated. Either way, estimating the distribution of intensities is an inference problem. In the case of a Gaussian distribution, one must estimate the mean and standard deviation. However, in the Non-Gaussian case the shape of the density function itself must be inferred. Three common techniques for estimating density functions are binned histograms [1, 2], kernel density estimation [3, 4], and the maximum entropy method of moments [5, 6]. In the introduction, the maximum entropy method of moments will be reviewed. Some of its problems and conditions under which it fails will be discussed. Then in later sections, the functional form of the maximum entropy method of moments probability distribution will be incorporated into Bayesian probability theory. It will be shown that Bayesian probability theory solves all of the problems with the maximum entropy method of moments. One gets posterior probabilities for the Lagrange multipliers, and, finally, one can put error bars on the resulting estimated density function.

Frontoparietal Priority Maps as Biomarkers for mTBI

DTIC Science & Technology

2015-10-01

preliminary data analysis is underway. 15. SUBJECT TERMS mTBI, fMRI , DTI, psychophysics, vision, convergence insufficiency 16. SECURITY CLASSIFICATION OF...biomarkers and behavioral measures of visual performance in veterans who have and have not experienced mTBI. KEYWORDS mTBI fMRI DTI psychophysics...MRI protocol prepared 8 Delayed to month 15 due to recruitment delays. Major Task 5: acquire MRI measures, which include DTI and fMRI Complete

Fast and effective characterization of 3D region of interest in medical image data

NASA Astrophysics Data System (ADS)

Kontos, Despina; Megalooikonomou, Vasileios

2004-05-01

We propose a framework for detecting, characterizing and classifying spatial Regions of Interest (ROIs) in medical images, such as tumors and lesions in MRI or activation regions in fMRI. A necessary step prior to classification is efficient extraction of discriminative features. For this purpose, we apply a characterization technique especially designed for spatial ROIs. The main idea of this technique is to extract a k-dimensional feature vector using concentric spheres in 3D (or circles in 2D) radiating out of the ROI's center of mass. These vectors form characterization signatures that can be used to represent the initial ROIs. We focus on classifying fMRI ROIs obtained from a study that explores neuroanatomical correlates of semantic processing in Alzheimer's disease (AD). We detect a ROI highly associated with AD and apply the feature extraction technique with different experimental settings. We seek to distinguish control from patient samples. We study how classification can be performed using the extracted signatures as well as how different experimental parameters affect classification accuracy. The obtained classification accuracy ranged from 82% to 87% (based on the selected ROI) suggesting that the proposed classification framework can be potentially useful in supporting medical decision-making.

Integrated 68Gallium Labelled Prostate-Specific Membrane Antigen-11 Positron Emission Tomography/Magnetic Resonance Imaging Enhances Discriminatory Power of Multi-Parametric Prostate Magnetic Resonance Imaging.

PubMed

Al-Bayati, Mohammad; Grueneisen, Johannes; Lütje, Susanne; Sawicki, Lino M; Suntharalingam, Saravanabavaan; Tschirdewahn, Stephan; Forsting, Michael; Rübben, Herbert; Herrmann, Ken; Umutlu, Lale; Wetter, Axel

2018-01-01

To evaluate diagnostic accuracy of integrated 68Gallium labelled prostate-specific membrane antigen (68Ga-PSMA)-11 positron emission tomography (PET)/MRI in patients with primary prostate cancer (PCa) as compared to multi-parametric MRI. A total of 22 patients with recently diagnosed primary PCa underwent clinically indicated 68Ga-PSMA-11 PET/CT for initial staging followed by integrated 68Ga-PSMA-11 PET/MRI. Images of multi-parametric magnetic resonance imaging (mpMRI), PET and PET/MRI were evaluated separately by applying Prostate Imaging Reporting and Data System (PIRADSv2) for mpMRI and a 5-point Likert scale for PET and PET/MRI. Results were compared with pathology reports of biopsy or resection. Statistical analyses including receiver operating characteristics analysis were performed to compare the diagnostic performance of mpMRI, PET and PET/MRI. PET and integrated PET/MRI demonstrated a higher diagnostic accuracy than mpMRI (area under the curve: mpMRI: 0.679, PET and PET/MRI: 0.951). The proportion of equivocal results (PIRADS 3 and Likert 3) was considerably higher in mpMRI than in PET and PET/MRI. In a notable proportion of equivocal PIRADS results, PET led to a correct shift towards higher suspicion of malignancy and enabled correct lesion classification. Integrated 68Ga-PSMA-11 PET/MRI demonstrates higher diagnostic accuracy than mpMRI and is particularly valuable in tumours with equivocal results from PIRADS classification. © 2018 S. Karger AG, Basel.

Spatially aggregated multiclass pattern classification in functional MRI using optimally selected functional brain areas.

PubMed

Zheng, Weili; Ackley, Elena S; Martínez-Ramón, Manel; Posse, Stefan

2013-02-01

In previous works, boosting aggregation of classifier outputs from discrete brain areas has been demonstrated to reduce dimensionality and improve the robustness and accuracy of functional magnetic resonance imaging (fMRI) classification. However, dimensionality reduction and classification of mixed activation patterns of multiple classes remain challenging. In the present study, the goals were (a) to reduce dimensionality by combining feature reduction at the voxel level and backward elimination of optimally aggregated classifiers at the region level, (b) to compare region selection for spatially aggregated classification using boosting and partial least squares regression methods and (c) to resolve mixed activation patterns using probabilistic prediction of individual tasks. Brain activation maps from interleaved visual, motor, auditory and cognitive tasks were segmented into 144 functional regions. Feature selection reduced the number of feature voxels by more than 50%, leaving 95 regions. The two aggregation approaches further reduced the number of regions to 30, resulting in more than 75% reduction of classification time and misclassification rates of less than 3%. Boosting and partial least squares (PLS) were compared to select the most discriminative and the most task correlated regions, respectively. Successful task prediction in mixed activation patterns was feasible within the first block of task activation in real-time fMRI experiments. This methodology is suitable for sparsifying activation patterns in real-time fMRI and for neurofeedback from distributed networks of brain activation. Copyright © 2013 Elsevier Inc. All rights reserved.

Assessment of three different software systems in the evaluation of dynamic MRI of the breast.

PubMed

Kurz, K D; Steinhaus, D; Klar, V; Cohnen, M; Wittsack, H J; Saleh, A; Mödder, U; Blondin, D

2009-02-01

The aim was to compare the diagnostic performance and handling of dynamic contrast-enhanced MRI of the breast with two commercial software solutions ("CADstream" and "3TP") and one self-developed software system ("Mammatool"). Identical data sets of dynamic breast MRI from 21 patients were evaluated retrospectively with all three software systems. The exams were classified according to the BI-RADS classification. The number of lesions in the parametric mapping was compared to histology or follow-up of more than 2 years. In addition, 25 quality criteria were judged by 3 independent investigators with a score from 0 to 5. Statistical analysis was performed to document the quality ranking of the different software systems. There were 9 invasive carcinomas, one pure DCIS, one papilloma, one radial scar, three histologically proven changes due to mastopathy, one adenosis and two fibroadenomas. Additionally two patients with enhancing parenchyma followed with MRI for more than 3 years and one scar after breast conserving therapy were included. All malignant lesions were classified as BI-RADS 4 or 5 using all software systems and showed significant enhancement in the parametric mapping. "CADstream" showed the best score on subjective quality criteria. "3TP" showed the lowest number of false-positive results. "Mammatool" produced the lowest number of benign tissues indicated with parametric overlay. All three software programs tested were adequate for sensitive and efficient assessment of dynamic MRI of the breast. Improvements in specificity may be achievable.

Voxel-wise prostate cell density prediction using multiparametric magnetic resonance imaging and machine learning.

PubMed

Sun, Yu; Reynolds, Hayley M; Wraith, Darren; Williams, Scott; Finnegan, Mary E; Mitchell, Catherine; Murphy, Declan; Haworth, Annette

2018-04-26

There are currently no methods to estimate cell density in the prostate. This study aimed to develop predictive models to estimate prostate cell density from multiparametric magnetic resonance imaging (mpMRI) data at a voxel level using machine learning techniques. In vivo mpMRI data were collected from 30 patients before radical prostatectomy. Sequences included T2-weighted imaging, diffusion-weighted imaging and dynamic contrast-enhanced imaging. Ground truth cell density maps were computed from histology and co-registered with mpMRI. Feature extraction and selection were performed on mpMRI data. Final models were fitted using three regression algorithms including multivariate adaptive regression spline (MARS), polynomial regression (PR) and generalised additive model (GAM). Model parameters were optimised using leave-one-out cross-validation on the training data and model performance was evaluated on test data using root mean square error (RMSE) measurements. Predictive models to estimate voxel-wise prostate cell density were successfully trained and tested using the three algorithms. The best model (GAM) achieved a RMSE of 1.06 (± 0.06) × 10 3 cells/mm 2 and a relative deviation of 13.3 ± 0.8%. Prostate cell density can be quantitatively estimated non-invasively from mpMRI data using high-quality co-registered data at a voxel level. These cell density predictions could be used for tissue classification, treatment response evaluation and personalised radiotherapy.

Combining 5-Aminolevulinic Acid Fluorescence and Intraoperative Magnetic Resonance Imaging in Glioblastoma Surgery: A Histology-Based Evaluation.

PubMed

Hauser, Sonja B; Kockro, Ralf A; Actor, Bertrand; Sarnthein, Johannes; Bernays, René-Ludwig

2016-04-01

Glioblastoma resection guided by 5-aminolevulinic acid (5-ALA) fluorescence and intraoperative magnetic resonance imaging (iMRI) may improve surgical results and prolong survival. To evaluate 5-ALA fluorescence combined with subsequent low-field iMRI for resection control in glioblastoma surgery. Fourteen patients with suspected glioblastoma suitable for complete resection of contrast-enhancing portions were enrolled. The surgery was carried out using 5-ALA-induced fluorescence and frameless navigation. Areas suspicious for tumor underwent biopsy. After complete resection of fluorescent tissue, low-field iMRI was performed. Areas suspicious for tumor remnant underwent biopsy under navigation guidance and were resected. The histological analysis was blinded. In 13 of 14 cases, the diagnosis was glioblastoma multiforme. One lymphoma and 1 case without fluorescence were excluded. In 11 of 12 operations, residual contrast enhancement on iMRI was found after complete resection of 5-ALA fluorescent tissue. In 1 case, the iMRI enhancement was in an eloquent area and did not undergo a biopsy. The 28 biopsies of areas suspicious for tumor on iMRI in the remaining 10 cases showed tumor in 39.3%, infiltration zone in 25%, reactive central nervous system tissue in 32.1%, and normal brain in 3.6%. Ninety-three fluorescent and 24 non-fluorescent tissue samples collected before iMRI contained tumor in 95.7% and 87.5%, respectively. 5-ALA fluorescence-guided resection may leave some glioblastoma tissue undetected. MRI might detect areas suspicious for tumor even after complete resection of all fluorescent tissue; however, due to the limited accuracy of iMRI in predicting tumor remnant (64.3%), resection of this tissue has to be considered with caution in eloquent regions.

Detecting stripe artifacts in ultrasound images.

PubMed

Maciak, Adam; Kier, Christian; Seidel, Günter; Meyer-Wiethe, Karsten; Hofmann, Ulrich G

2009-10-01

Brain perfusion diseases such as acute ischemic stroke are detectable through computed tomography (CT)-/magnetic resonance imaging (MRI)-based methods. An alternative approach makes use of ultrasound imaging. In this low-cost bedside method, noise and artifacts degrade the imaging process. Especially stripe artifacts show a similar signal behavior compared to acute stroke or brain perfusion diseases. This document describes how stripe artifacts can be detected and eliminated in ultrasound images obtained through harmonic imaging (HI). On the basis of this new method, both proper identification of areas with critically reduced brain tissue perfusion and classification between brain perfusion defects and ultrasound stripe artifacts are made possible.

Bayesian reconstruction and use of anatomical a priori information for emission tomography

DOE Office of Scientific and Technical Information (OSTI.GOV)

Bowsher, J.E.; Johnson, V.E.; Turkington, T.G.

1996-10-01

A Bayesian method is presented for simultaneously segmenting and reconstructing emission computed tomography (ECT) images and for incorporating high-resolution, anatomical information into those reconstructions. The anatomical information is often available from other imaging modalities such as computed tomography (CT) or magnetic resonance imaging (MRI). The Bayesian procedure models the ECT radiopharmaceutical distribution as consisting of regions, such that radiopharmaceutical activity is similar throughout each region. It estimates the number of regions, the mean activity of each region, and the region classification and mean activity of each voxel. Anatomical information is incorporated by assigning higher prior probabilities to ECT segmentations inmore » which each ECT region stays within a single anatomical region. This approach is effective because anatomical tissue type often strongly influences radiopharmaceutical uptake. The Bayesian procedure is evaluated using physically acquired single-photon emission computed tomography (SPECT) projection data and MRI for the three-dimensional (3-D) Hoffman brain phantom. A clinically realistic count level is used. A cold lesion within the brain phantom is created during the SPECT scan but not during the MRI to demonstrate that the estimation procedure can detect ECT structure that is not present anatomically.« less

Concurrent multiscale imaging with magnetic resonance imaging and optical coherence tomography

NASA Astrophysics Data System (ADS)

Liang, Chia-Pin; Yang, Bo; Kim, Il Kyoon; Makris, George; Desai, Jaydev P.; Gullapalli, Rao P.; Chen, Yu

2013-04-01

We develop a novel platform based on a tele-operated robot to perform high-resolution optical coherence tomography (OCT) imaging under continuous large field-of-view magnetic resonance imaging (MRI) guidance. Intra-operative MRI (iMRI) is a promising guidance tool for high-precision surgery, but it may not have sufficient resolution or contrast to visualize certain small targets. To address these limitations, we develop an MRI-compatible OCT needle probe, which is capable of providing microscale tissue architecture in conjunction with macroscale MRI tissue morphology in real time. Coregistered MRI/OCT images on ex vivo chicken breast and human brain tissues demonstrate that the complementary imaging scales and contrast mechanisms have great potential to improve the efficiency and the accuracy of iMRI procedure.

Neural and Behavioral Sequelae of Blast-Related Traumatic Brain Injury

DTIC Science & Technology

2012-11-01

testing and advanced MRI techniques [task-activated functional MRI (fMRI) and diffusion tensor imaging ( DTI )] to gain a comprehensive understanding of... DTI fiber tracking) and neurobehavioral testing (computerized assessment and standard neuropsychological testing) on 60 chronic trauma patients: 15...data analysis. 15. SUBJECT TERMS Blast-related traumatic brain injury (TBI), fMRI, DTI , cognition 16. SECURITY CLASSIFICATION OF: 17. LIMITATION

Identifying Autism from Resting-State fMRI Using Long Short-Term Memory Networks.

PubMed

Dvornek, Nicha C; Ventola, Pamela; Pelphrey, Kevin A; Duncan, James S

2017-09-01

Functional magnetic resonance imaging (fMRI) has helped characterize the pathophysiology of autism spectrum disorders (ASD) and carries promise for producing objective biomarkers for ASD. Recent work has focused on deriving ASD biomarkers from resting-state functional connectivity measures. However, current efforts that have identified ASD with high accuracy were limited to homogeneous, small datasets, while classification results for heterogeneous, multi-site data have shown much lower accuracy. In this paper, we propose the use of recurrent neural networks with long short-term memory (LSTMs) for classification of individuals with ASD and typical controls directly from the resting-state fMRI time-series. We used the entire large, multi-site Autism Brain Imaging Data Exchange (ABIDE) I dataset for training and testing the LSTM models. Under a cross-validation framework, we achieved classification accuracy of 68.5%, which is 9% higher than previously reported methods that used fMRI data from the whole ABIDE cohort. Finally, we presented interpretation of the trained LSTM weights, which highlight potential functional networks and regions that are known to be implicated in ASD.

Identifying Autism from Resting-State fMRI Using Long Short-Term Memory Networks

PubMed Central

Dvornek, Nicha C.; Ventola, Pamela; Pelphrey, Kevin A.; Duncan, James S.

2017-01-01

Functional magnetic resonance imaging (fMRI) has helped characterize the pathophysiology of autism spectrum disorders (ASD) and carries promise for producing objective biomarkers for ASD. Recent work has focused on deriving ASD biomarkers from resting-state functional connectivity measures. However, current efforts that have identified ASD with high accuracy were limited to homogeneous, small datasets, while classification results for heterogeneous, multi-site data have shown much lower accuracy. In this paper, we propose the use of recurrent neural networks with long short-term memory (LSTMs) for classification of individuals with ASD and typical controls directly from the resting-state fMRI time-series. We used the entire large, multi-site Autism Brain Imaging Data Exchange (ABIDE) I dataset for training and testing the LSTM models. Under a cross-validation framework, we achieved classification accuracy of 68.5%, which is 9% higher than previously reported methods that used fMRI data from the whole ABIDE cohort. Finally, we presented interpretation of the trained LSTM weights, which highlight potential functional networks and regions that are known to be implicated in ASD. PMID:29104967

MRI assessment of local acute radiation syndrome.

PubMed

Weber-Donat, G; Amabile, J-C; Lahutte-Auboin, M; Potet, J; Baccialone, J; Bey, E; Teriitehau, C; Laroche, P

2012-12-01

To describe local acute radiation syndrome and its radiological imaging characteristics. We performed a retrospective study of patients who had suffered skin and deeper radiation damage who were investigated by magnetic resonance imaging (MRI). We compared the clinical findings, C-reactive protein (CRP) levels and MRI results. A total of 22 MRI examinations were performed between 2005 and 2010 in 7 patients; 6 patients had increased CRP levels and MRI abnormalities. They were treated by surgery and local cellular therapy. One patient had no CRP or MRI abnormalities, and had a spontaneous good outcome. Eighteen abnormal MR examinations demonstrated high STIR signal and/or abnormal enhancement in the dermis and muscle tissues. Three MRI examinations demonstrated skeletal abnormalities, consistent with radionecrosis. The four normal MRI examinations were associated only with minor clinical manifestations such as pain and pigmentation disorders. MRI seems to be a useful and promising imaging investigation in radiation burns management i.e. initial lesion evaluation, treatment evaluation and complication diagnosis. MRI findings correlated perfectly with clinical stage and no false negative examinations were obtained. In particular, the association between normal MRI and low CRP level seems to be related to good outcome without specific treatment. Local acute radiation syndrome (radioepidermitis) mainly affects the skin and superficial tissues. MRI findings correspond with clinical stage (with a strong negative predictive value). MRI outperformed X-ray examination for the diagnosis of bone radionecrosis. Diffusion-weighted imaging shows low ADC in bone and soft tissue necrosis. Perfusion sequence allows assessment of tissue microcirculation impairment.

Assessment of sexual orientation using the hemodynamic brain response to visual sexual stimuli.

PubMed

Ponseti, Jorge; Granert, Oliver; Jansen, Olav; Wolff, Stephan; Mehdorn, Hubertus; Bosinski, Hartmut; Siebner, Hartwig

2009-06-01

The assessment of sexual orientation is of importance to the diagnosis and treatment of sex offenders and paraphilic disorders. Phallometry is considered gold standard in objectifying sexual orientation, yet this measurement has been criticized because of its intrusiveness and limited reliability. To evaluate whether the spatial response pattern to sexual stimuli as revealed by a change in blood oxygen level-dependent (BOLD) signal can be used for individual classification of sexual orientation. We used a preexisting functional MRI (fMRI) data set that had been acquired in a nonclinical sample of 12 heterosexual men and 14 homosexual men. During fMRI, participants were briefly exposed to pictures of same-sex and opposite-sex genitals. Data analysis involved four steps: (i) differences in the BOLD response to female and male sexual stimuli were calculated for each subject; (ii) these contrast images were entered into a group analysis to calculate whole-brain difference maps between homosexual and heterosexual participants; (iii) a single expression value was computed for each subject expressing its correspondence to the group result; and (iv) based on these expression values, Fisher's linear discriminant analysis and the kappa-nearest neighbor classification method were used to predict the sexual orientation of each subject. Sensitivity and specificity of the two classification methods in predicting individual sexual orientation. Both classification methods performed well in predicting individual sexual orientation with a mean accuracy of >85% (Fisher's linear discriminant analysis: 92% sensitivity, 85% specificity; kappa-nearest neighbor classification: 88% sensitivity, 92% specificity). Despite the small sample size, the functional response patterns of the brain to sexual stimuli contained sufficient information to predict individual sexual orientation with high accuracy. These results suggest that fMRI-based classification methods hold promise for the diagnosis of paraphilic disorders (e.g., pedophilia).

[Feasibility study of dynamic contrast enhanced magnetic resonance imaging qualitative diagnosis of musculoskeletal tumors].

PubMed

Zhang, J; Zuo, P L; Cheng, K B; Yu, A H; Cheng, X G

2016-04-18

To investigate the feasibility of dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) parameters in differentiating musculoskeletal tumors with different behaviours of pathological findings before therapy. A total of 34 subjects of musculoskeletal tumors were involved in this retrospective analysis. DCE-MRI was performed using a fat-saturated 3D VIBE (volumetric interpolated breath-hold exam) imaging sequence with following parameters: FA, 10 degree; TR/TE, 5.6/2.4 ms; slice thickness, 4.0 mm with no intersection gap; field of view, 310 mm×213 mm; matrix, 256×178; voxel size, 1.2 mm×1.2 mm×4.0 mm; parallel imaging acceleration factor. The actuation time for the DCE-MRI sequence was 255 s with a temporal resolution of 5 s and 40 image volumes. Using pathological results as a gold standard, tumors were divided into benign, borderline and malignant tumors. Toft's model was used for calculation of K(trans) (volume transfer constant), Ve (extravascular extracellular space distribute volume per unit tissue volume) and Kep (microvascular permeability reflux constant). Those parameters were compared between the lesions and the control tissues using paired t tests. The one-way analysis of variance was used to assess the difference among benign, borderline and malignant tumors. P values <0.05 difference was statistically significant. Based on the WHO Classification of Tumours of Soft Tissue and Bone(2012) criteria, 34 patients were divided into three groups: 11 for benign tumors, 12 for borderline tumors, and 11 for malignancies. Compared with control tissues, K(trans) and Kep showed no difference, but Ve was increased in benign tumors, Kep showed no difference, but K(trans) and Ve were increased in borderline tumors,K(trans), Kep and Ve were increased in malignant tumors. K(trans) (P<0.001) and Kep (P<0.01) were significantly higher in malignant tumors than in benign and borderline tumors, but did not show any difference between benign tumors and borderline tumors. Ve was significantly higher in malignant tumors than in benign (P<0.05), but did not show any difference between malignant and borderline tumors, benign tumors and borderline tumors (P>0.05). DCE-MRI technique is useful to evaluate the pathological behaviour of musculoskeletal tumors. The quantitative analysis of DCE parameters in conjunction with conventional MR images can improve the accuracy of musculoskeletal tumor qualitative analysis.

In vivo magnetic resonance imaging of type I collagen scaffold in rat: improving visualization of bladder and subcutaneous implants.

PubMed

Sun, Yi; Geutjes, Paul; Oosterwijk, Egbert; Heerschap, Arend

2014-12-01

Noninvasive monitoring of implanted scaffolds is important to understand their behavior and role in tissue engineering, in particular to follow their degradation and interaction with host tissue. Magnetic resonance imaging (MRI) is well suited for this goal, but its application is often hampered by the low contrast of scaffolds that are prepared from biomaterials such as type I collagen. The aim of this study was to test iron oxide particles incorporation in improving their MRI contrasts, and to follow their degradation and tissue interactions. Scaffolds with and without iron oxide particles were implanted either subcutaneously or on the bladder of rats. At predetermined time points, in vivo MRI were obtained and tissues were then harvested for histology analysis and transmission electron microscopy. The result showed that the incorporation of iron oxide particles improved MRI contrast of the implants, providing information on their location, shapes, and degradation. Second, the host tissue reaction to the type I collagen implants could be observed in both MRI and histology. Finally, MRI also revealed that the degradation and host tissue reaction of iron particles-loaded scaffolds differed between subcutaneous and bladder implantation, which was substantiated by histology.

Comparison of Contrast-Enhanced Ultrasound and Gadolinium-Ethoxybenzyl-Diethylenetriamine Pentaacetic Acid-Enhanced MRI for the Diagnosis of Macroscopic Type of Hepatocellular Carcinoma.

PubMed

Iwamoto, Takayuki; Imai, Yasuharu; Kogita, Sachiyo; Igura, Takumi; Sawai, Yoshiyuki; Fukuda, Kazuto; Yamaguchi, Yoshitaka; Matsumoto, Yasushi; Nakahara, Masanori; Morimoto, Osakuni; Seki, Yasushi; Ohashi, Hiroshi; Fujita, Norihiko; Kudo, Masatoshi; Takehara, Tetsuo

We compared the efficacy of contrast-enhanced ultrasound sonography (CEUS) with sonazoid and gadolinium-ethoxybenzyl-diethylenetriamine pentaacetic acid (Gd-EOB-DTPA)-enhanced MRI for the assessment of macroscopic classification of nodular hepatocellular carcinoma (HCC). Seventy-seven consecutive patients with 79 surgically resected HCCs who underwent both preoperative CEUS and Gd-EOB-DTPA-enhanced MRI were enrolled in this retrospective study. Based on the macroscopic diagnosis of resected specimens, nodules were categorized into the simple nodular (SN) and non-SN type HCC. Two hepatologists independently assessed image datasets of the post-vascular phase of CEUS and hepatobiliary phase of Gd-EOB-DTPA-enhanced MRI to compare their diagnostic performance. Gd-EOB-DTPA-enhanced MRI enabled the evaluation of macroscopic classification in a significantly larger number of nodules than CEUS (78/79 (98.7%) vs. 70/79 (88.6%), p < 0.05). Of 70 nodules that could be evaluated by both modalities, 41 and 29 nodules were pathologically categorized as SN and non-SN, respectively. The areas under the receiver operating characteristic curve (AUC) for non-SN did not differ between CEUS and Gd-EOB-DTPA-enhanced MRI (reader 1: 0.748 for CEUS, 0.808 for MRI; reader 2: 0.759 for CEUS, 0.787 for MRI). The AUC of combined CEUS and Gd-EOB-DTPA-enhanced MRI for SN HCC was 0.855 (reader 1) and 0.824 (reader 2), indicating higher AUC values for the combined modalities. The diagnostic performance for macroscopic classification of nodular HCC of CEUS was comparable with that of Gd-EOB-DTPA-enhanced MRI, although some HCCs could not be evaluated by CEUS owing to lower detectability. The combination of the 2 modalities had a more accurate diagnostic performance. © 2016 S. Karger AG, Basel.

Use of Magnetic Resonance Imaging as Well as Clinical Disease Activity in the Clinical Classification of Multiple Sclerosis and Assessment of Its Course

PubMed Central

Dhib-Jalbut, Suhayl; Dowling, Peter; Durelli, Luca; Ford, Corey; Giovannoni, Gavin; Halper, June; Harris, Colleen; Herbert, Joseph; Li, David; Lincoln, John A.; Lisak, Robert; Lublin, Fred D.; Lucchinetti, Claudia F.; Moore, Wayne; Naismith, Robert T.; Oehninger, Carlos; Simon, Jack; Sormani, Maria Pia

2012-01-01

It has recently been suggested that the Lublin-Reingold clinical classification of multiple sclerosis (MS) be modified to include the use of magnetic resonance imaging (MRI). An international consensus conference sponsored by the Consortium of Multiple Sclerosis Centers (CMSC) was held from March 5 to 7, 2010, to review the available evidence on the need for such modification of the Lublin-Reingold criteria and whether the addition of MRI or other biomarkers might lead to a better understanding of MS pathophysiology and disease course over time. The conference participants concluded that evidence of new MRI gadolinium-enhancing (Gd+) T1-weighted lesions and unequivocally new or enlarging T2-weighted lesions (subclinical activity, subclinical relapses) should be added to the clinical classification of MS in distinguishing relapsing inflammatory from progressive forms of the disease. The consensus was that these changes to the classification system would provide more rigorous definitions and categorization of MS course, leading to better insights as to the evolution and treatment of MS. PMID:24453741

Plexiform neurofibroma tissue classification

NASA Astrophysics Data System (ADS)

Weizman, L.; Hoch, L.; Ben Sira, L.; Joskowicz, L.; Pratt, L.; Constantini, S.; Ben Bashat, D.

2011-03-01

Plexiform Neurofibroma (PN) is a major complication of NeuroFibromatosis-1 (NF1), a common genetic disease that involving the nervous system. PNs are peripheral nerve sheath tumors extending along the length of the nerve in various parts of the body. Treatment decision is based on tumor volume assessment using MRI, which is currently time consuming and error prone, with limited semi-automatic segmentation support. We present in this paper a new method for the segmentation and tumor mass quantification of PN from STIR MRI scans. The method starts with a user-based delineation of the tumor area in a single slice and automatically detects the PN lesions in the entire image based on the tumor connectivity. Experimental results on seven datasets yield a mean volume overlap difference of 25% as compared to manual segmentation by expert radiologist with a mean computation and interaction time of 12 minutes vs. over an hour for manual annotation. Since the user interaction in the segmentation process is minimal, our method has the potential to successfully become part of the clinical workflow.

Co-occurrence of Local Anisotropic Gradient Orientations (CoLlAGe): A new radiomics descriptor.

PubMed

Prasanna, Prateek; Tiwari, Pallavi; Madabhushi, Anant

2016-11-22

In this paper, we introduce a new radiomic descriptor, Co-occurrence of Local Anisotropic Gradient Orientations (CoLlAGe) for capturing subtle differences between benign and pathologic phenotypes which may be visually indistinguishable on routine anatomic imaging. CoLlAGe seeks to capture and exploit local anisotropic differences in voxel-level gradient orientations to distinguish similar appearing phenotypes. CoLlAGe involves assigning every image voxel an entropy value associated with the co-occurrence matrix of gradient orientations computed around every voxel. The hypothesis behind CoLlAGe is that benign and pathologic phenotypes even though they may appear similar on anatomic imaging, will differ in their local entropy patterns, in turn reflecting subtle local differences in tissue microarchitecture. We demonstrate CoLlAGe's utility in three clinically challenging classification problems: distinguishing (1) radiation necrosis, a benign yet confounding effect of radiation treatment, from recurrent tumors on T1-w MRI in 42 brain tumor patients, (2) different molecular sub-types of breast cancer on DCE-MRI in 65 studies and (3) non-small cell lung cancer (adenocarcinomas) from benign fungal infection (granulomas) on 120 non-contrast CT studies. For each of these classification problems, CoLlAGE in conjunction with a random forest classifier outperformed state of the art radiomic descriptors (Haralick, Gabor, Histogram of Gradient Orientations).

Hippocampus shape analysis for temporal lobe epilepsy detection in magnetic resonance imaging

NASA Astrophysics Data System (ADS)

Kohan, Zohreh; Azmi, Reza

2016-03-01

There are evidences in the literature that Temporal Lobe Epilepsy (TLE) causes some lateralized atrophy and deformation on hippocampus and other substructures of the brain. Magnetic Resonance Imaging (MRI), due to high-contrast soft tissue imaging, is one of the most popular imaging modalities being used in TLE diagnosis and treatment procedures. Using an algorithm to help clinicians for better and more effective shape deformations analysis could improve the diagnosis and treatment of the disease. In this project our purpose is to design, implement and test a classification algorithm for MRIs based on hippocampal asymmetry detection using shape and size-based features. Our method consisted of two main parts; (1) shape feature extraction, and (2) image classification. We tested 11 different shape and size features and selected four of them that detect the asymmetry in hippocampus significantly in a randomly selected subset of the dataset. Then, we employed a support vector machine (SVM) classifier to classify the remaining images of the dataset to normal and epileptic images using our selected features. The dataset contains 25 patient images in which 12 cases were used as a training set and the rest 13 cases for testing the performance of classifier. We measured accuracy, specificity and sensitivity of, respectively, 76%, 100%, and 70% for our algorithm. The preliminary results show that using shape and size features for detecting hippocampal asymmetry could be helpful in TLE diagnosis in MRI.

MRI of articular cartilage at microscopic resolution

PubMed Central

Xia, Y.

2013-01-01

This review briefly summarises some of the definitive studies of articular cartilage by microscopic MRI (µMRI) that were conducted with the highest spatial resolutions. The article has four major sections. The first section introduces the cartilage tissue, MRI and µMRI, and the concept of image contrast in MRI. The second section describes the characteristic profiles of three relaxation times (T1, T2 and T1ρ) and self-diffusion in healthy articular cartilage. The third section discusses several factors that can influence the visualisation of articular cartilage and the detection of cartilage lesion by MRI and µMRI. These factors include image resolution, image analysis strategies, visualisation of the total tissue, topographical variations of the tissue properties, surface fibril ambiguity, deformation of the articular cartilage, and cartilage lesion. The final section justifies the values of multidisciplinary imaging that correlates MRI with other technical modalities, such as optical imaging. Rather than an exhaustive review to capture all activities in the literature, the studies cited in this review are merely illustrative. PMID:23610697

Understanding Magnetic Resonance Imaging of Knee Cartilage Repair: A Focus on Clinical Relevance.

PubMed

Hayashi, Daichi; Li, Xinning; Murakami, Akira M; Roemer, Frank W; Trattnig, Siegfried; Guermazi, Ali

2017-06-01

The aims of this review article are (a) to describe the principles of morphologic and compositional magnetic resonance imaging (MRI) techniques relevant for the imaging of knee cartilage repair surgery and their application to longitudinal studies and (b) to illustrate the clinical relevance of pre- and postsurgical MRI with correlation to intraoperative images. First, MRI sequences that can be applied for imaging of cartilage repair tissue in the knee are described, focusing on comparison of 2D and 3D fast spin echo and gradient recalled echo sequences. Imaging features of cartilage repair tissue are then discussed, including conventional (morphologic) MRI and compositional MRI techniques. More specifically, imaging techniques for specific cartilage repair surgery techniques as described above, as well as MRI-based semiquantitative scoring systems for the knee cartilage repair tissue-MR Observation of Cartilage Repair Tissue and Cartilage Repair OA Knee Score-are explained. Then, currently available surgical techniques are reviewed, including marrow stimulation, osteochondral autograft, osteochondral allograft, particulate cartilage allograft, autologous chondrocyte implantation, and others. Finally, ongoing research efforts and future direction of cartilage repair tissue imaging are discussed.

A Comparison of Supervised Machine Learning Algorithms and Feature Vectors for MS Lesion Segmentation Using Multimodal Structural MRI

PubMed Central

Sweeney, Elizabeth M.; Vogelstein, Joshua T.; Cuzzocreo, Jennifer L.; Calabresi, Peter A.; Reich, Daniel S.; Crainiceanu, Ciprian M.; Shinohara, Russell T.

2014-01-01

Machine learning is a popular method for mining and analyzing large collections of medical data. We focus on a particular problem from medical research, supervised multiple sclerosis (MS) lesion segmentation in structural magnetic resonance imaging (MRI). We examine the extent to which the choice of machine learning or classification algorithm and feature extraction function impacts the performance of lesion segmentation methods. As quantitative measures derived from structural MRI are important clinical tools for research into the pathophysiology and natural history of MS, the development of automated lesion segmentation methods is an active research field. Yet, little is known about what drives performance of these methods. We evaluate the performance of automated MS lesion segmentation methods, which consist of a supervised classification algorithm composed with a feature extraction function. These feature extraction functions act on the observed T1-weighted (T1-w), T2-weighted (T2-w) and fluid-attenuated inversion recovery (FLAIR) MRI voxel intensities. Each MRI study has a manual lesion segmentation that we use to train and validate the supervised classification algorithms. Our main finding is that the differences in predictive performance are due more to differences in the feature vectors, rather than the machine learning or classification algorithms. Features that incorporate information from neighboring voxels in the brain were found to increase performance substantially. For lesion segmentation, we conclude that it is better to use simple, interpretable, and fast algorithms, such as logistic regression, linear discriminant analysis, and quadratic discriminant analysis, and to develop the features to improve performance. PMID:24781953

A comparison of supervised machine learning algorithms and feature vectors for MS lesion segmentation using multimodal structural MRI.

PubMed

Sweeney, Elizabeth M; Vogelstein, Joshua T; Cuzzocreo, Jennifer L; Calabresi, Peter A; Reich, Daniel S; Crainiceanu, Ciprian M; Shinohara, Russell T

2014-01-01

Machine learning is a popular method for mining and analyzing large collections of medical data. We focus on a particular problem from medical research, supervised multiple sclerosis (MS) lesion segmentation in structural magnetic resonance imaging (MRI). We examine the extent to which the choice of machine learning or classification algorithm and feature extraction function impacts the performance of lesion segmentation methods. As quantitative measures derived from structural MRI are important clinical tools for research into the pathophysiology and natural history of MS, the development of automated lesion segmentation methods is an active research field. Yet, little is known about what drives performance of these methods. We evaluate the performance of automated MS lesion segmentation methods, which consist of a supervised classification algorithm composed with a feature extraction function. These feature extraction functions act on the observed T1-weighted (T1-w), T2-weighted (T2-w) and fluid-attenuated inversion recovery (FLAIR) MRI voxel intensities. Each MRI study has a manual lesion segmentation that we use to train and validate the supervised classification algorithms. Our main finding is that the differences in predictive performance are due more to differences in the feature vectors, rather than the machine learning or classification algorithms. Features that incorporate information from neighboring voxels in the brain were found to increase performance substantially. For lesion segmentation, we conclude that it is better to use simple, interpretable, and fast algorithms, such as logistic regression, linear discriminant analysis, and quadratic discriminant analysis, and to develop the features to improve performance.

Neural and Behavioral Sequelae of Blast-Related Traumatic Brain Injury

DTIC Science & Technology

2012-09-01

fMRI, DTI , cognition 16. SECURITY CLASSIFICATION OF: 17. LIMITATION OF ABSTRACT 18. NUMBER OF PAGES 19a. NAME OF RESPONSIBLE PERSON USAMRMC a...techniques [task-activated functional MRI (fMRI) and diffusion tensor imaging ( DTI )] to gain a comprehensive understanding of the neural changes...orthopedic injuries. We accomplished this goal by conducting advanced neuroimaging (task-activated fMRI and DTI fiber tracking) and neurobehavioral

Probabilistic brain tissue segmentation in neonatal magnetic resonance imaging.

PubMed

Anbeek, Petronella; Vincken, Koen L; Groenendaal, Floris; Koeman, Annemieke; van Osch, Matthias J P; van der Grond, Jeroen

2008-02-01

A fully automated method has been developed for segmentation of four different structures in the neonatal brain: white matter (WM), central gray matter (CEGM), cortical gray matter (COGM), and cerebrospinal fluid (CSF). The segmentation algorithm is based on information from T2-weighted (T2-w) and inversion recovery (IR) scans. The method uses a K nearest neighbor (KNN) classification technique with features derived from spatial information and voxel intensities. Probabilistic segmentations of each tissue type were generated. By applying thresholds on these probability maps, binary segmentations were obtained. These final segmentations were evaluated by comparison with a gold standard. The sensitivity, specificity, and Dice similarity index (SI) were calculated for quantitative validation of the results. High sensitivity and specificity with respect to the gold standard were reached: sensitivity >0.82 and specificity >0.9 for all tissue types. Tissue volumes were calculated from the binary and probabilistic segmentations. The probabilistic segmentation volumes of all tissue types accurately estimated the gold standard volumes. The KNN approach offers valuable ways for neonatal brain segmentation. The probabilistic outcomes provide a useful tool for accurate volume measurements. The described method is based on routine diagnostic magnetic resonance imaging (MRI) and is suitable for large population studies.

The clinical outcomes of deep gray matter injury in children with cerebral palsy in relation with brain magnetic resonance imaging.

PubMed

Choi, Ja Young; Choi, Yoon Seong; Rha, Dong-Wook; Park, Eun Sook

2016-08-01

In the present study we investigated the nature and extent of clinical outcomes using various classifications and analyzed the relationship between brain magnetic resonance imaging (MRI) findings and the extent of clinical outcomes in children with cerebral palsy (CP) with deep gray matter injury. The deep gray matter injuries of 69 children were classified into hypoxic ischemic encephalopathy (HIE) and kernicterus patterns. HIE patterns were divided into four groups (I-IV) based on severity. Functional classification was investigated using the gross motor function classification system-expanded and revised, manual ability classification system, communication function classification system, and tests of cognitive function, and other associated problems. The severity of HIE pattern on brain MRI was strongly correlated with the severity of clinical outcomes in these various domains. Children with a kernicterus pattern showed a wide range of clinical outcomes in these areas. Children with severe HIE are at high risk of intellectual disability (ID) or epilepsy and children with a kernicterus pattern are at risk of hearing impairment and/or ID. Grading severity of HIE pattern on brain MRI is useful for predicting overall outcomes. The clinical outcomes of children with a kernicterus pattern range widely from mild to severe. Delineation of the clinical outcomes of children with deep gray matter injury, which are a common abnormal brain MRI finding in children with CP, is necessary. The present study provides clinical outcomes for various domains in children with deep gray matter injury on brain MRI. The deep gray matter injuries were divided into two major groups; HIE and kernicterus patterns. Our study showed that severity of HIE pattern on brain MRI was strongly associated with the severity of impairments in gross motor function, manual ability, communication function, and cognition. These findings suggest that severity of HIE pattern can be useful for predicting the severity of impairments. Conversely, children with a kernicterus pattern showed a wide range of clinical outcomes in various domains. Children with severe HIE pattern are at high risk of ID or epilepsy and children with kernicterus pattern are at risk of hearing impairment or ID. The strength of our study was the assessment of clinical outcomes after 3 years of age using standardized classification systems in various domains in children with deep gray matter injury. Copyright © 2016 Elsevier Ltd. All rights reserved.

Magnetic resonance imaging of intraoral hard and soft tissues using an intraoral coil and FLASH sequences.

PubMed

Flügge, Tabea; Hövener, Jan-Bernd; Ludwig, Ute; Eisenbeiss, Anne-Kathrin; Spittau, Björn; Hennig, Jürgen; Schmelzeisen, Rainer; Nelson, Katja

2016-12-01

To ascertain the feasibility of MRI as a non-ionizing protocol for routine dentomaxillofacial diagnostic imaging. Wireless coils were used for MRI of intraoral hard and soft tissues. FLASH MRI was applied in vivo with a mandible voxel size of 250 × 250 × 500 μm 3 , FOV of 64 × 64 × 28 mm 3 and acquisition time of 3:57 min and with a maxilla voxel size of 350 μm 3 and FOV of 34 cm 3 in 6:40 min. Ex vivo imaging was performed in 4:38 min, with a resolution of 200 μm 3 and FOV of 36.5 cm 3 . Cone beam (CB) CT of the mandible and subjects were acquired. MRI was compared to CBCT and histological sections. Deviations were calculated with intraclass correlation coefficient (ICC) and coefficient of variation (c v ). A high congruence between CBCT, MRI and specimens was demonstrated. Hard and soft tissues including dental pulp, periodontium, gingiva, cancellous bone and mandibular canal contents were adequately displayed with MRI. Imaging of select intraoral tissues was achieved using custom MRI protocols with an easily applicable intraoral coil in a clinically acceptable acquisition time. Comparison with CBCT and histological sections helped demonstrate dimensional accuracy of the MR images. The course of the mandibular canal was accurately displayed with CBCT and MRI. • MRI is a clinically available diagnostic tool in dentistry • Intraoral hard and soft tissues can be imaged with a high resolution with MRI • The dimensional accuracy of MRI is comparable to cone beam CT.

In vitro assessment of MRI issues at 3-Tesla for a breast tissue expander with a remote port.

PubMed

Linnemeyer, Hannah; Shellock, Frank G; Ahn, Christina Y

2014-04-01

A patient with a breast tissue expander may require a diagnostic assessment using magnetic resonance imaging (MRI). To ensure patient safety, this type of implant must undergo in vitro MRI testing using proper techniques. Therefore, this investigation evaluated MRI issues (i.e., magnetic field interactions, heating, and artifacts) at 3-Tesla for a breast tissue expander with a remote port. A breast tissue expander with a remote port (Integra Breast Tissue Expander, Model 3612-06 with Standard Remote Port, PMT Corporation, Chanhassen, MN) underwent evaluation for magnetic field interactions (translational attraction and torque), MRI-related heating, and artifacts using standardized techniques. Heating was evaluated by placing the implant in a gelled-saline-filled phantom and MRI was performed using a transmit/receive RF body coil at an MR system reported, whole body averaged specific absorption rate of 2.9-W/kg. Artifacts were characterized using T1-weighted and GRE pulse sequences. Magnetic field interactions were not substantial and, thus, will not pose a hazard to a patient in a 3-Tesla or less MRI environment. The highest temperature rise was 1.7°C, which is physiologically inconsequential. Artifacts were large in relation to the remote port and metal connector of the implant but will only present problems if the MR imaging area of interest is where these components are located. A patient with this breast tissue expander with a remote port may safely undergo MRI at 3-Tesla or less under the conditions used for this investigation. These findings are the first reported at 3-Tesla for a tissue expander. Copyright © 2014 Elsevier Inc. All rights reserved.

Estimation of gas and tissue lung volumes by MRI: functional approach of lung imaging.

PubMed

Qanadli, S D; Orvoen-Frija, E; Lacombe, P; Di Paola, R; Bittoun, J; Frija, G

1999-01-01

The purpose of this work was to assess the accuracy of MRI for the determination of lung gas and tissue volumes. Fifteen healthy subjects underwent MRI of the thorax and pulmonary function tests [vital capacity (VC) and total lung capacity (TLC)] in the supine position. MR examinations were performed at inspiration and expiration. Lung volumes were measured by a previously validated technique on phantoms. Both individual and total lung volumes and capacities were calculated. MRI total vital capacity (VC(MRI)) was compared with spirometric vital capacity (VC(SP)). Capacities were correlated to lung volumes. Tissue volume (V(T)) was estimated as the difference between the total lung volume at full inspiration and the TLC. No significant difference was seen between VC(MRI) and VC(SP). Individual capacities were well correlated (r = 0.9) to static volume at full inspiration. The V(T) was estimated to be 836+/-393 ml. This preliminary study demonstrates that MRI can accurately estimate lung gas and tissue volumes. The proposed approach appears well suited for functional imaging of the lung.

Editorial Commentary: Single-Image Slice Magnetic Resonance Imaging Assessments Do Not Predict 3-Dimensional Muscle Volume.

PubMed

Brand, Jefferson C

2016-01-01

No single-image magnetic resonance imaging (MRI) assessment-Goutallier classification, Fuchs classification, or cross-sectional area-is predictive of whole-muscle volume or fatty atrophy of the supraspinatus or infraspinatus. Rather, 3-dimensional MRI measurement of whole-muscle volume and fat-free muscle volume is required and is associated with shoulder strength, which is clinically relevant. Three-dimensional MRI may represent a new gold standard for assessment of the rotator cuff musculature using imaging and may help to predict the feasibility of repair of a rotator cuff tear as well as the postoperative outcome. Unfortunately, 3-dimensional MRI assessment of muscle volume is labor intensive and is not widely available for clinical use. Copyright © 2016 Arthroscopy Association of North America. Published by Elsevier Inc. All rights reserved.

Individual classification of Alzheimer's disease with diffusion magnetic resonance imaging.

PubMed

Schouten, Tijn M; Koini, Marisa; Vos, Frank de; Seiler, Stephan; Rooij, Mark de; Lechner, Anita; Schmidt, Reinhold; Heuvel, Martijn van den; Grond, Jeroen van der; Rombouts, Serge A R B

2017-05-15

Diffusion magnetic resonance imaging (MRI) is a powerful non-invasive method to study white matter integrity, and is sensitive to detect differences in Alzheimer's disease (AD) patients. Diffusion MRI may be able to contribute towards reliable diagnosis of AD. We used diffusion MRI to classify AD patients (N=77), and controls (N=173). We use different methods to extract information from the diffusion MRI data. First, we use the voxel-wise diffusion tensor measures that have been skeletonised using tract based spatial statistics. Second, we clustered the voxel-wise diffusion measures with independent component analysis (ICA), and extracted the mixing weights. Third, we determined structural connectivity between Harvard Oxford atlas regions with probabilistic tractography, as well as graph measures based on these structural connectivity graphs. Classification performance for voxel-wise measures ranged between an AUC of 0.888, and 0.902. The ICA-clustered measures ranged between an AUC of 0.893, and 0.920. The AUC for the structural connectivity graph was 0.900, while graph measures based upon this graph ranged between an AUC of 0.531, and 0.840. All measures combined with a sparse group lasso resulted in an AUC of 0.896. Overall, fractional anisotropy clustered into ICA components was the best performing measure. These findings may be useful for future incorporation of diffusion MRI into protocols for AD classification, or as a starting point for early detection of AD using diffusion MRI. Copyright © 2017 Elsevier Inc. All rights reserved.

Connective tissue of cervical carcinoma xenografts: associations with tumor hypoxia and interstitial fluid pressure and its assessment by DCE-MRI and DW-MRI.

PubMed

Hompland, Tord; Ellingsen, Christine; Galappathi, Kanthi; Rofstad, Einar K

2014-01-01

Abstract Background. A high fraction of stroma in malignant tissues is associated with tumor progression, metastasis, and poor prognosis. Possible correlations between the stromal and physiologic microenvironments of tumors and the potential of dynamic contrast-enhanced (DCE) and diffusion-weighted (DW) magnetic resonance imaging (MRI) in quantification of the stromal microenvironment were investigated in this study. Material and methods. CK-160 cervical carcinoma xenografts were used as preclinical tumor model. A total of 43 tumors were included in the study, and of these tumors, 17 were used to search for correlations between the stromal and physiologic microenvironments, 11 were subjected to DCE-MRI, and 15 were subjected to DW-MRI. DCE-MRI and DW-MRI were carried out at 1.5 T with a clinical MR scanner and a slotted tube resonator transceiver coil constructed for mice. Fraction of connective tissue (CTFCol) and fraction of hypoxic tissue (HFPim) were determined by immunohistochemistry. A Millar SPC 320 catheter was used to measure tumor interstitial fluid pressure (IFP). Results. CTFCol showed a positive correlation to IFP and an inverse correlation to HFPim. The apparent diffusion coefficient assessed by DW-MRI was inversely correlated to CTFCol, whereas no correlation was found between DCE-MRI-derived parameters and CTFCol. Conclusion. DW-MRI is a potentially useful method for characterizing the stromal microenvironment of tumors.

Automatic classification of schizophrenia using resting-state functional language network via an adaptive learning algorithm

NASA Astrophysics Data System (ADS)

Zhu, Maohu; Jie, Nanfeng; Jiang, Tianzi

2014-03-01

A reliable and precise classification of schizophrenia is significant for its diagnosis and treatment of schizophrenia. Functional magnetic resonance imaging (fMRI) is a novel tool increasingly used in schizophrenia research. Recent advances in statistical learning theory have led to applying pattern classification algorithms to access the diagnostic value of functional brain networks, discovered from resting state fMRI data. The aim of this study was to propose an adaptive learning algorithm to distinguish schizophrenia patients from normal controls using resting-state functional language network. Furthermore, here the classification of schizophrenia was regarded as a sample selection problem where a sparse subset of samples was chosen from the labeled training set. Using these selected samples, which we call informative vectors, a classifier for the clinic diagnosis of schizophrenia was established. We experimentally demonstrated that the proposed algorithm incorporating resting-state functional language network achieved 83.6% leaveone- out accuracy on resting-state fMRI data of 27 schizophrenia patients and 28 normal controls. In contrast with KNearest- Neighbor (KNN), Support Vector Machine (SVM) and l1-norm, our method yielded better classification performance. Moreover, our results suggested that a dysfunction of resting-state functional language network plays an important role in the clinic diagnosis of schizophrenia.

Differentiation of malignant from benign soft tissue tumours: use of additive qualitative and quantitative diffusion-weighted MR imaging to standard MR imaging at 3.0 T.

PubMed

Lee, So-Yeon; Jee, Won-Hee; Jung, Joon-Yong; Park, Michael Y; Kim, Sun-Ki; Jung, Chan-Kwon; Chung, Yang-Guk

2016-03-01

To determine the added value of diffusion-weighted imaging (DWI) to standard magnetic resonance imaging (MRI) to differentiate malignant from benign soft tissue tumours at 3.0 T. 3.0 T MR images including DWI in 63 patients who underwent surgery for soft tissue tumours were retrospectively analyzed. Two readers independently interpreted MRI for the presence of malignancy in two steps: standard MRI alone, standard MRI and DWI with qualitative and quantitative analysis combined. There were 34 malignant and 29 non-malignant soft tissue tumours. In qualitative analysis, hyperintensity relative to skeletal muscle was more frequent in malignant than benign tumours on DWI (P=0.003). In quantitative analysis, ADCs of malignant tumours were significantly lower than those of non-malignant tumours (P≤0.002): 759±385 vs. 1188±423 μm(2)/sec minimum ADC value, 941±440 vs. 1310±440 μm(2)/sec average ADC value. The mean sensitivity, specificity and accuracy of both readers were 96%, 72%, and 85% on standard MRI alone and 97%, 90%, and 94% on standard MRI with DWI. The addition of DWI to standard MRI improves the diagnostic accuracy for differentiation of malignant from benign soft tissue tumours at 3.0 T. DWI has added value for differentiating malignant from benign soft tissue tumours. Addition of DWI to standard MRI at 3.0 T improves the diagnostic accuracy. Measurements of both ADC min within solid portion and ADC av are helpful.

Magnetic resonance imaging characteristics of nonthermal irreversible electroporation in vegetable tissue.

PubMed

Hjouj, Mohammad; Rubinsky, Boris

2010-07-01

We introduce and characterize the use of MRI for studying nonthermal irreversible electroporation (NTIRE) in a vegetative tissue model. NTIRE is a new minimally invasive surgical technique for tissue ablation in which microsecond, high electric-field pulses form nanoscale defects in the cell membrane that lead to cell death. Clinical NTIRE sequences were applied to a potato tuber tissue model. The potato is used for NTIRE studies because cell damage is readily visible with optical means through a natural oxidation process of released intracellular enzymes (polyphenol oxidase) and the formation of brown-black melanins. MRI sequences of the treated area were taken at various times before and after NTIRE and compared with photographic images. A comparison was made between T1W, T2W, FLAIR and STIR MRIs of NTIRE and photographic images. Some MRI sequences show changes in areas treated by irreversible electroporation. T1W and FLAIR produce brighter images of the treated areas. In contrast, the signal was lost from the treated area when a suppression technique, STIR, was used. There was similarity between optical photographic images of the treated tissue and MRIs of the same areas. This is the first study to characterize MRI of NTIRE in vegetative tissue. We find that NTIRE produces changes in vegetative tissue that can be imaged by certain MRI sequences. This could make MRI an effective tool to study the fundamentals of NTIRE in nonanimal tissue.

Symmetry-based detection and diagnosis of DCIS in breast MRI

NASA Astrophysics Data System (ADS)

Srikantha, Abhilash; Harz, Markus T.; Newstead, Gillian; Wang, Lei; Platel, Bram; Hegenscheid, Katrin; Mann, Ritse M.; Hahn, Horst K.; Peitgen, Heinz-Otto

2013-02-01

The delineation and diagnosis of non-mass-like lesions, most notably DCIS (ductal carcinoma in situ), is among the most challenging tasks in breast MRI reading. Even for human observers, DCIS is not always easy to diferentiate from patterns of active parenchymal enhancement or from benign alterations of breast tissue. In this light, it is no surprise that CADe/CADx approaches often completely fail to classify DCIS. Of the several approaches that have tried to devise such computer aid, none achieve performances similar to mass detection and classification in terms of sensitivity and specificity. In our contribution, we show a novel approach to combine a newly proposed metric of anatomical breast symmetry calculated on subtraction images of dynamic contrast-enhanced (DCE) breast MRI, descriptive kinetic parameters, and lesion candidate morphology to achieve performances comparable to computer-aided methods used for masses. We have based the development of the method on DCE MRI data of 18 DCIS cases with hand-annotated lesions, complemented by DCE-MRI data of nine normal cases. We propose a novel metric to quantify the symmetry of contralateral breasts and derive a strong indicator for potentially malignant changes from this metric. Also, we propose a novel metric for the orientation of a finding towards a fix point (the nipple). Our combined scheme then achieves a sensitivity of 89% with a specificity of 78%, matching CAD results for breast MRI on masses. The processing pipeline is intended to run on a CAD server, hence we designed all processing to be automated and free of per-case parameters. We expect that the detection results of our proposed non-mass aimed algorithm will complement other CAD algorithms, or ideally be joined with them in a voting scheme.

Focal liver lesions segmentation and classification in nonenhanced T2-weighted MRI.

PubMed

Gatos, Ilias; Tsantis, Stavros; Karamesini, Maria; Spiliopoulos, Stavros; Karnabatidis, Dimitris; Hazle, John D; Kagadis, George C

2017-07-01

To automatically segment and classify focal liver lesions (FLLs) on nonenhanced T2-weighted magnetic resonance imaging (MRI) scans using a computer-aided diagnosis (CAD) algorithm. 71 FLLs (30 benign lesions, 19 hepatocellular carcinomas, and 22 metastases) on T2-weighted MRI scans were delineated by the proposed CAD scheme. The FLL segmentation procedure involved wavelet multiscale analysis to extract accurate edge information and mean intensity values for consecutive edges computed using horizontal and vertical analysis that were fed into the subsequent fuzzy C-means algorithm for final FLL border extraction. Texture information for each extracted lesion was derived using 42 first- and second-order textural features from grayscale value histogram, co-occurrence, and run-length matrices. Twelve morphological features were also extracted to capture any shape differentiation between classes. Feature selection was performed with stepwise multilinear regression analysis that led to a reduced feature subset. A multiclass Probabilistic Neural Network (PNN) classifier was then designed and used for lesion classification. PNN model evaluation was performed using the leave-one-out (LOO) method and receiver operating characteristic (ROC) curve analysis. The mean overlap between the automatically segmented FLLs and the manual segmentations performed by radiologists was 0.91 ± 0.12. The highest classification accuracies in the PNN model for the benign, hepatocellular carcinoma, and metastatic FLLs were 94.1%, 91.4%, and 94.1%, respectively, with sensitivity/specificity values of 90%/97.3%, 89.5%/92.2%, and 90.9%/95.6% respectively. The overall classification accuracy for the proposed system was 90.1%. Our diagnostic system using sophisticated FLL segmentation and classification algorithms is a powerful tool for routine clinical MRI-based liver evaluation and can be a supplement to contrast-enhanced MRI to prevent unnecessary invasive procedures. © 2017 American Association of Physicists in Medicine.

Efficacy of thigh volume ratios assessed via stereovision body imaging as a predictor of visceral adipose tissue measured by magnetic resonance imaging.

PubMed

Lee, Jane J; Freeland-Graves, Jeanne H; Pepper, M Reese; Yu, Wurong; Xu, Bugao

2015-01-01

The research examined the efficacy of regional volumes of thigh ratios assessed by stereovision body imaging (SBI) as a predictor of visceral adipose tissue measured by magnetic resonance imaging (MRI). Body measurements obtained via SBI also were utilized to explore disparities of body size and shape in men and women. One hundred twenty-one participants were measured for total/regional body volumes and ratios via SBI and abdominal subcutaneous and visceral adipose tissue areas by MRI. Thigh to torso and thigh to abdomen-hip volume ratios were the most reliable parameters to predict the accumulation of visceral adipose tissue depots compared to other body measurements. Thigh volume in relation to torso [odds ratios (OR) 0.44] and abdomen-hip (OR 0.41) volumes were negatively associated with increased risks of greater visceral adipose tissue depots, even after controlling for age, gender, and body mass index (BMI). Irrespective of BMI classification, men exhibited greater total body (80.95L vs. 72.41L), torso (39.26L vs. 34.13L), and abdomen-hip (29.01L vs. 25.85L) volumes than women. Women had higher thigh volumes (4.93L vs. 3.99L) and lower-body volume ratios [thigh to total body (0.07 vs. 0.05), thigh to torso (0.15 vs. 0.11), and thigh to abdomen-hip (0.20 vs. 0.15); P < 0.05]. The unique parameters of the volumes of thigh in relation to torso and abdomen-hip, by SBI were highly effective in predicting visceral adipose tissue deposition. The SBI provided an efficient method for determining body size and shape in men and women via total and regional body volumes and ratios. Am. J. Hum. Biol. 27:445-457, 2015. © 2015 Wiley Periodicals, Inc. © 2015 Wiley Periodicals, Inc.

Magnetic Resonance Imaging of Adipose Tissue in Metabolic Dysfunction.

PubMed

Franz, Daniela; Syväri, Jan; Weidlich, Dominik; Baum, Thomas; Rummeny, Ernst J; Karampinos, Dimitrios C

2018-06-06

 Adipose tissue has become an increasingly important tissue target in medicine. It plays a central role in the storage and release of energy throughout the human body and has recently gained interest for its endocrinologic function. Magnetic resonance imaging (MRI) is an established method for quantitative direct evaluation of adipose tissue distribution, and is used increasingly as the modality of choice for metabolic phenotyping. The purpose of this review was the identification and presentation of the currently available literature on MRI of adipose tissue in metabolic dysfunction.  A PubMed (http://www.ncbi.nlm.nih.gov/pubmed) keyword search up to August 2017 without starting date limitation was performed and reference lists of relevant articles were searched.  MRI provides excellent tools for the evaluation of adipose tissue distribution and further characterization of the tissue. Standard as well as newly developed MRI techniques allow a risk stratification for the development of metabolic dysfunction and enable monitoring without the use of ionizing radiation or contrast material.   · Different types of adipose tissue play a crucial role in various types of metabolic dysfunction.. · Magnetic resonance imaging (MRI) is an excellent tool for noninvasive adipose tissue evaluation with respect to distribution, composition and metabolic activity.. · Both standard and newly developed MRI techniques can be used for risk stratification for the development of metabolic dysfunction and allow monitoring without the use of ionizing radiation or contrast material.. · Franz D, Syväri J, Weidlich D et al. Magnetic Resonance Imaging of Adipose Tissue in Metabolic Dysfunction. Fortschr Röntgenstr 2018; DOI: 10.1055/a-0612-8006. © Georg Thieme Verlag KG Stuttgart · New York.

Machine learning classification with confidence: application of transductive conformal predictors to MRI-based diagnostic and prognostic markers in depression.

PubMed

Nouretdinov, Ilia; Costafreda, Sergi G; Gammerman, Alexander; Chervonenkis, Alexey; Vovk, Vladimir; Vapnik, Vladimir; Fu, Cynthia H Y

2011-05-15

There is rapidly accumulating evidence that the application of machine learning classification to neuroimaging measurements may be valuable for the development of diagnostic and prognostic prediction tools in psychiatry. However, current methods do not produce a measure of the reliability of the predictions. Knowing the risk of the error associated with a given prediction is essential for the development of neuroimaging-based clinical tools. We propose a general probabilistic classification method to produce measures of confidence for magnetic resonance imaging (MRI) data. We describe the application of transductive conformal predictor (TCP) to MRI images. TCP generates the most likely prediction and a valid measure of confidence, as well as the set of all possible predictions for a given confidence level. We present the theoretical motivation for TCP, and we have applied TCP to structural and functional MRI data in patients and healthy controls to investigate diagnostic and prognostic prediction in depression. We verify that TCP predictions are as accurate as those obtained with more standard machine learning methods, such as support vector machine, while providing the additional benefit of a valid measure of confidence for each prediction. Copyright © 2010 Elsevier Inc. All rights reserved.

68Ga-PSMA-11 PET/CT in Newly Diagnosed Carcinoma of the Prostate: Correlation of Intraprostatic PSMA Uptake with Several Clinical Parameters.

PubMed

Koerber, Stefan A; Utzinger, Maximilian T; Kratochwil, Clemens; Kesch, Claudia; Haefner, Matthias F; Katayama, Sonja; Mier, Walter; Iagaru, Andrei H; Herfarth, Klaus; Haberkorn, Uwe; Debus, Juergen; Giesel, Frederik L

2017-12-01

68 Ga-prostate-specific membrane antigen (PSMA) PET/CT is a promising diagnostic tool for patients with prostate cancer. Our study evaluates SUVs in benign prostate tissue and malignant, intraprostatic tumor lesions and correlates results with several clinical parameters. Methods: One hundred four men with newly diagnosed prostate carcinoma and no previous therapy were included in this study. SUV max was measured and correlated with biopsy findings and MRI. Afterward, data were compared with current prostate-specific antigen (PSA) values, Gleason score (GS), and d'Amico risk classification. Results: In this investigation a mean SUV max of 1.88 ± 0.44 in healthy prostate tissue compared with 10.77 ± 8.45 in malignant prostate lesions ( P < 0.001) was observed. Patients with higher PSA, higher GS, and higher d'Amico risk score had statistically significant higher PSMA uptake on PET/CT ( P < 0.001 each). Conclusion: PSMA PET/CT is well suited for detecting the intraprostatic malignant lesion in patients with newly diagnosed prostate cancer. Our findings indicate a significant correlation of PSMA uptake with PSA, GS, and risk classification according to the d'Amico scale. © 2017 by the Society of Nuclear Medicine and Molecular Imaging.

Random forest feature selection, fusion and ensemble strategy: Combining multiple morphological MRI measures to discriminate among healhy elderly, MCI, cMCI and alzheimer's disease patients: From the alzheimer's disease neuroimaging initiative (ADNI) database.

PubMed

Dimitriadis, S I; Liparas, Dimitris; Tsolaki, Magda N

2018-05-15

In the era of computer-assisted diagnostic tools for various brain diseases, Alzheimer's disease (AD) covers a large percentage of neuroimaging research, with the main scope being its use in daily practice. However, there has been no study attempting to simultaneously discriminate among Healthy Controls (HC), early mild cognitive impairment (MCI), late MCI (cMCI) and stable AD, using features derived from a single modality, namely MRI. Based on preprocessed MRI images from the organizers of a neuroimaging challenge, 3 we attempted to quantify the prediction accuracy of multiple morphological MRI features to simultaneously discriminate among HC, MCI, cMCI and AD. We explored the efficacy of a novel scheme that includes multiple feature selections via Random Forest from subsets of the whole set of features (e.g. whole set, left/right hemisphere etc.), Random Forest classification using a fusion approach and ensemble classification via majority voting. From the ADNI database, 60 HC, 60 MCI, 60 cMCI and 60 CE were used as a training set with known labels. An extra dataset of 160 subjects (HC: 40, MCI: 40, cMCI: 40 and AD: 40) was used as an external blind validation dataset to evaluate the proposed machine learning scheme. In the second blind dataset, we succeeded in a four-class classification of 61.9% by combining MRI-based features with a Random Forest-based Ensemble Strategy. We achieved the best classification accuracy of all teams that participated in this neuroimaging competition. The results demonstrate the effectiveness of the proposed scheme to simultaneously discriminate among four groups using morphological MRI features for the very first time in the literature. Hence, the proposed machine learning scheme can be used to define single and multi-modal biomarkers for AD. Copyright © 2017 Elsevier B.V. All rights reserved.

International recommendation for a comprehensive neuropathologic workup of epilepsy surgery brain tissue: A consensus Task Force report from the ILAE Commission on Diagnostic Methods.

PubMed

Blümcke, Ingmar; Aronica, Eleonora; Miyata, Hajime; Sarnat, Harvey B; Thom, Maria; Roessler, Karl; Rydenhag, Bertil; Jehi, Lara; Krsek, Pavel; Wiebe, Samuel; Spreafico, Roberto

2016-03-01

Epilepsy surgery is an effective treatment in many patients with drug-resistant focal epilepsies. An early decision for surgical therapy is facilitated by a magnetic resonance imaging (MRI)-visible brain lesion congruent with the electrophysiologically abnormal brain region. Recent advances in the pathologic diagnosis and classification of epileptogenic brain lesions are helpful for clinical correlation, outcome stratification, and patient management. However, application of international consensus classification systems to common epileptic pathologies (e.g., focal cortical dysplasia [FCD] and hippocampal sclerosis [HS]) necessitates standardized protocols for neuropathologic workup of epilepsy surgery specimens. To this end, the Task Force of Neuropathology from the International League Against Epilepsy (ILAE) Commission on Diagnostic Methods developed a consensus standard operational procedure for tissue inspection, distribution, and processing. The aims are to provide a systematic framework for histopathologic workup, meeting minimal standards and maximizing current and future opportunities for morphofunctional correlations and molecular studies for both clinical care and research. Whenever feasible, anatomically intact surgical specimens are desirable to enable systematic analysis in selective hippocampectomies, temporal lobe resections, and lesional or nonlesional neocortical samples. Correct orientation of sample and the sample's relation to neurophysiologically aberrant sites requires good communication between pathology and neurosurgical teams. Systematic tissue sampling of 5-mm slabs along a defined anatomic axis and application of a limited immunohistochemical panel will ensure a reliable differential diagnosis of main pathologies encountered in epilepsy surgery. Wiley Periodicals, Inc. © 2016 International League Against Epilepsy.

Attributed graph distance measure for automatic detection of attention deficit hyperactive disordered subjects.

PubMed

Dey, Soumyabrata; Rao, A Ravishankar; Shah, Mubarak

2014-01-01

Attention Deficit Hyperactive Disorder (ADHD) is getting a lot of attention recently for two reasons. First, it is one of the most commonly found childhood disorders and second, the root cause of the problem is still unknown. Functional Magnetic Resonance Imaging (fMRI) data has become a popular tool for the analysis of ADHD, which is the focus of our current research. In this paper we propose a novel framework for the automatic classification of the ADHD subjects using their resting state fMRI (rs-fMRI) data of the brain. We construct brain functional connectivity networks for all the subjects. The nodes of the network are constructed with clusters of highly active voxels and edges between any pair of nodes represent the correlations between their average fMRI time series. The activity level of the voxels are measured based on the average power of their corresponding fMRI time-series. For each node of the networks, a local descriptor comprising of a set of attributes of the node is computed. Next, the Multi-Dimensional Scaling (MDS) technique is used to project all the subjects from the unknown graph-space to a low dimensional space based on their inter-graph distance measures. Finally, the Support Vector Machine (SVM) classifier is used on the low dimensional projected space for automatic classification of the ADHD subjects. Exhaustive experimental validation of the proposed method is performed using the data set released for the ADHD-200 competition. Our method shows promise as we achieve impressive classification accuracies on the training (70.49%) and test data sets (73.55%). Our results reveal that the detection rates are higher when classification is performed separately on the male and female groups of subjects.

Can we improve accuracy and reliability of MRI interpretation in children with optic pathway glioma? Proposal for a reproducible imaging classification.

PubMed

Lambron, Julien; Rakotonjanahary, Josué; Loisel, Didier; Frampas, Eric; De Carli, Emilie; Delion, Matthieu; Rialland, Xavier; Toulgoat, Frédérique

2016-02-01

Magnetic resonance (MR) images from children with optic pathway glioma (OPG) are complex. We initiated this study to evaluate the accuracy of MR imaging (MRI) interpretation and to propose a simple and reproducible imaging classification for MRI. We randomly selected 140 MRIs from among 510 MRIs performed on 104 children diagnosed with OPG in France from 1990 to 2004. These images were reviewed independently by three radiologists (F.T., 15 years of experience in neuroradiology; D.L., 25 years of experience in pediatric radiology; and J.L., 3 years of experience in radiology) using a classification derived from the Dodge and modified Dodge classifications. Intra- and interobserver reliabilities were assessed using the Bland-Altman method and the kappa coefficient. These reviews allowed the definition of reliable criteria for MRI interpretation. The reviews showed intraobserver variability and large discrepancies among the three radiologists (kappa coefficient varying from 0.11 to 1). These variabilities were too large for the interpretation to be considered reproducible over time or among observers. A consensual analysis, taking into account all observed variabilities, allowed the development of a definitive interpretation protocol. Using this revised protocol, we observed consistent intra- and interobserver results (kappa coefficient varying from 0.56 to 1). The mean interobserver difference for the solid portion of the tumor with contrast enhancement was 0.8 cm(3) (limits of agreement = -16 to 17). We propose simple and precise rules for improving the accuracy and reliability of MRI interpretation for children with OPG. Further studies will be necessary to investigate the possible prognostic value of this approach.

Classification of autistic individuals and controls using cross-task characterization of fMRI activity

PubMed Central

Chanel, Guillaume; Pichon, Swann; Conty, Laurence; Berthoz, Sylvie; Chevallier, Coralie; Grèzes, Julie

2015-01-01

Multivariate pattern analysis (MVPA) has been applied successfully to task-based and resting-based fMRI recordings to investigate which neural markers distinguish individuals with autistic spectrum disorders (ASD) from controls. While most studies have focused on brain connectivity during resting state episodes and regions of interest approaches (ROI), a wealth of task-based fMRI datasets have been acquired in these populations in the last decade. This calls for techniques that can leverage information not only from a single dataset, but from several existing datasets that might share some common features and biomarkers. We propose a fully data-driven (voxel-based) approach that we apply to two different fMRI experiments with social stimuli (faces and bodies). The method, based on Support Vector Machines (SVMs) and Recursive Feature Elimination (RFE), is first trained for each experiment independently and each output is then combined to obtain a final classification output. Second, this RFE output is used to determine which voxels are most often selected for classification to generate maps of significant discriminative activity. Finally, to further explore the clinical validity of the approach, we correlate phenotypic information with obtained classifier scores. The results reveal good classification accuracy (range between 69% and 92.3%). Moreover, we were able to identify discriminative activity patterns pertaining to the social brain without relying on a priori ROI definitions. Finally, social motivation was the only dimension which correlated with classifier scores, suggesting that it is the main dimension captured by the classifiers. Altogether, we believe that the present RFE method proves to be efficient and may help identifying relevant biomarkers by taking advantage of acquired task-based fMRI datasets in psychiatric populations. PMID:26793434

Brain Decoding-Classification of Hand Written Digits from fMRI Data Employing Bayesian Networks

PubMed Central

Yargholi, Elahe'; Hossein-Zadeh, Gholam-Ali

2016-01-01

We are frequently exposed to hand written digits 0–9 in today's modern life. Success in decoding-classification of hand written digits helps us understand the corresponding brain mechanisms and processes and assists seriously in designing more efficient brain–computer interfaces. However, all digits belong to the same semantic category and similarity in appearance of hand written digits makes this decoding-classification a challenging problem. In present study, for the first time, augmented naïve Bayes classifier is used for classification of functional Magnetic Resonance Imaging (fMRI) measurements to decode the hand written digits which took advantage of brain connectivity information in decoding-classification. fMRI was recorded from three healthy participants, with an age range of 25–30. Results in different brain lobes (frontal, occipital, parietal, and temporal) show that utilizing connectivity information significantly improves decoding-classification and capability of different brain lobes in decoding-classification of hand written digits were compared to each other. In addition, in each lobe the most contributing areas and brain connectivities were determined and connectivities with short distances between their endpoints were recognized to be more efficient. Moreover, data driven method was applied to investigate the similarity of brain areas in responding to stimuli and this revealed both similarly active areas and active mechanisms during this experiment. Interesting finding was that during the experiment of watching hand written digits, there were some active networks (visual, working memory, motor, and language processing), but the most relevant one to the task was language processing network according to the voxel selection. PMID:27468261

Association between pathology and texture features of multi parametric MRI of the prostate

NASA Astrophysics Data System (ADS)

Kuess, Peter; Andrzejewski, Piotr; Nilsson, David; Georg, Petra; Knoth, Johannes; Susani, Martin; Trygg, Johan; Helbich, Thomas H.; Polanec, Stephan H.; Georg, Dietmar; Nyholm, Tufve

2017-10-01

The role of multi-parametric (mp)MRI in the diagnosis and treatment of prostate cancer has increased considerably. An alternative to visual inspection of mpMRI is the evaluation using histogram-based (first order statistics) parameters and textural features (second order statistics). The aims of the present work were to investigate the relationship between benign and malignant sub-volumes of the prostate and textures obtained from mpMR images. The performance of tumor prediction was investigated based on the combination of histogram-based and textural parameters. Subsequently, the relative importance of mpMR images was assessed and the benefit of additional imaging analyzed. Finally, sub-structures based on the PI-RADS classification were investigated as potential regions to automatically detect maligned lesions. Twenty-five patients who received mpMRI prior to radical prostatectomy were included in the study. The imaging protocol included T2, DWI, and DCE. Delineation of tumor regions was performed based on pathological information. First and second order statistics were derived from each structure and for all image modalities. The resulting data were processed with multivariate analysis, using PCA (principal component analysis) and OPLS-DA (orthogonal partial least squares discriminant analysis) for separation of malignant and healthy tissue. PCA showed a clear difference between tumor and healthy regions in the peripheral zone for all investigated images. The predictive ability of the OPLS-DA models increased for all image modalities when first and second order statistics were combined. The predictive value reached a plateau after adding ADC and T2, and did not increase further with the addition of other image information. The present study indicates a distinct difference in the signatures between malign and benign prostate tissue. This is an absolute prerequisite for automatic tumor segmentation, but only the first step in that direction. For the specific identified signature, DCE did not add complementary information to T2 and ADC maps.

Brain tumor segmentation based on local independent projection-based classification.

PubMed

Huang, Meiyan; Yang, Wei; Wu, Yao; Jiang, Jun; Chen, Wufan; Feng, Qianjin

2014-10-01

Brain tumor segmentation is an important procedure for early tumor diagnosis and radiotherapy planning. Although numerous brain tumor segmentation methods have been presented, enhancing tumor segmentation methods is still challenging because brain tumor MRI images exhibit complex characteristics, such as high diversity in tumor appearance and ambiguous tumor boundaries. To address this problem, we propose a novel automatic tumor segmentation method for MRI images. This method treats tumor segmentation as a classification problem. Additionally, the local independent projection-based classification (LIPC) method is used to classify each voxel into different classes. A novel classification framework is derived by introducing the local independent projection into the classical classification model. Locality is important in the calculation of local independent projections for LIPC. Locality is also considered in determining whether local anchor embedding is more applicable in solving linear projection weights compared with other coding methods. Moreover, LIPC considers the data distribution of different classes by learning a softmax regression model, which can further improve classification performance. In this study, 80 brain tumor MRI images with ground truth data are used as training data and 40 images without ground truth data are used as testing data. The segmentation results of testing data are evaluated by an online evaluation tool. The average dice similarities of the proposed method for segmenting complete tumor, tumor core, and contrast-enhancing tumor on real patient data are 0.84, 0.685, and 0.585, respectively. These results are comparable to other state-of-the-art methods.

Diagnostic Classification of Schizophrenia Patients on the Basis of Regional Reward-Related fMRI Signal Patterns

PubMed Central

Koch, Stefan P.; Hägele, Claudia; Haynes, John-Dylan; Heinz, Andreas; Schlagenhauf, Florian; Sterzer, Philipp

2015-01-01

Functional neuroimaging has provided evidence for altered function of mesolimbic circuits implicated in reward processing, first and foremost the ventral striatum, in patients with schizophrenia. While such findings based on significant group differences in brain activations can provide important insights into the pathomechanisms of mental disorders, the use of neuroimaging results from standard univariate statistical analysis for individual diagnosis has proven difficult. In this proof of concept study, we tested whether the predictive accuracy for the diagnostic classification of schizophrenia patients vs. healthy controls could be improved using multivariate pattern analysis (MVPA) of regional functional magnetic resonance imaging (fMRI) activation patterns for the anticipation of monetary reward. With a searchlight MVPA approach using support vector machine classification, we found that the diagnostic category could be predicted from local activation patterns in frontal, temporal, occipital and midbrain regions, with a maximal cluster peak classification accuracy of 93% for the right pallidum. Region-of-interest based MVPA for the ventral striatum achieved a maximal cluster peak accuracy of 88%, whereas the classification accuracy on the basis of standard univariate analysis reached only 75%. Moreover, using support vector regression we could additionally predict the severity of negative symptoms from ventral striatal activation patterns. These results show that MVPA can be used to substantially increase the accuracy of diagnostic classification on the basis of task-related fMRI signal patterns in a regionally specific way. PMID:25799236

Diagnostic value of MRI signs in differentiating Ewing sarcoma from osteomyelitis.

PubMed

Kasalak, Ömer; Overbosch, Jelle; Adams, Hugo Ja; Dammann, Amelie; Dierckx, Rudi Ajo; Jutte, Paul C; Kwee, Thomas C

2018-01-01

Background The value of magnetic resonance imaging (MRI) signs in differentiating Ewing sarcoma from osteomyelitis has not be thoroughly investigated. Purpose To investigate the value of various MRI signs in differentiating Ewing sarcoma from osteomyelitis. Material and Methods Forty-one patients who underwent MRI because of a bone lesion of unknown nature with a differential diagnosis that included both Ewing sarcoma and osteomyelitis were included. Two observers assessed several MRI signs, including the transition zone of the bone lesion, the presence of a soft-tissue mass, intramedullary and extramedullary fat globules, and the penumbra sign. Results Diagnostic accuracies for discriminating Ewing sarcoma from osteomyelitis were 82.4% and 79.4% for the presence of a soft-tissue mass, and 64.7% and 58.8% for a sharp transition zone of the bone lesion, for readers 1 and 2 respectively. Inter-observer agreement with regard to the presence of a soft-tissue mass and the transition zone of the bone lesion were moderate (κ = 0.470) and fair (κ = 0.307), respectively. Areas under the receiver operating characteristic curve of the diameter of the soft-tissue mass (if present) were 0.829 and 0.833, for readers 1 and 2 respectively. Mean inter-observer difference in soft-tissue mass diameter measurement ± limits of agreement was 35.0 ± 75.0 mm. Diagnostic accuracies of all other MRI signs were all < 50%. Conclusion Presence and size of a soft-tissue mass, and sharpness of the transition zone, are useful MRI signs to differentiate Ewing sarcoma from osteomyelitis, but inter-observer agreement is relatively low. Other MRI signs are of no value in this setting.

Instrumentation and method for measuring NIR light absorbed in tissue during MR imaging in medical NIRS measurements

NASA Astrophysics Data System (ADS)

Myllylä, Teemu S.; Sorvoja, Hannu S. S.; Nikkinen, Juha; Tervonen, Osmo; Kiviniemi, Vesa; Myllylä, Risto A.

2011-07-01

Our goal is to provide a cost-effective method for examining human tissue, particularly the brain, by the simultaneous use of functional magnetic resonance imaging (fMRI) and near-infrared spectroscopy (NIRS). Due to its compatibility requirements, MRI poses a demanding challenge for NIRS measurements. This paper focuses particularly on presenting the instrumentation and a method for the non-invasive measurement of NIR light absorbed in human tissue during MR imaging. One practical method to avoid disturbances in MR imaging involves using long fibre bundles to enable conducting the measurements at some distance from the MRI scanner. This setup serves in fact a dual purpose, since also the NIRS device will be less disturbed by the MRI scanner. However, measurements based on long fibre bundles suffer from light attenuation. Furthermore, because one of our primary goals was to make the measuring method as cost-effective as possible, we used high-power light emitting diodes instead of more expensive lasers. The use of LEDs, however, limits the maximum output power which can be extracted to illuminate the tissue. To meet these requirements, we improved methods of emitting light sufficiently deep into tissue. We also show how to measure NIR light of a very small power level that scatters from the tissue in the MRI environment, which is characterized by strong electromagnetic interference. In this paper, we present the implemented instrumentation and measuring method and report on test measurements conducted during MRI scanning. These measurements were performed in MRI operating rooms housing 1.5 Tesla-strength closed MRI scanners (manufactured by GE) in the Dept. of Diagnostic Radiology at the Oulu University Hospital.

Predicting decisions in human social interactions using real-time fMRI and pattern classification.

PubMed

Hollmann, Maurice; Rieger, Jochem W; Baecke, Sebastian; Lützkendorf, Ralf; Müller, Charles; Adolf, Daniela; Bernarding, Johannes

2011-01-01

Negotiation and trade typically require a mutual interaction while simultaneously resting in uncertainty which decision the partner ultimately will make at the end of the process. Assessing already during the negotiation in which direction one's counterpart tends would provide a tremendous advantage. Recently, neuroimaging techniques combined with multivariate pattern classification of the acquired data have made it possible to discriminate subjective states of mind on the basis of their neuronal activation signature. However, to enable an online-assessment of the participant's mind state both approaches need to be extended to a real-time technique. By combining real-time functional magnetic resonance imaging (fMRI) and online pattern classification techniques, we show that it is possible to predict human behavior during social interaction before the interacting partner communicates a specific decision. Average accuracy reached approximately 70% when we predicted online the decisions of volunteers playing the ultimatum game, a well-known paradigm in economic game theory. Our results demonstrate the successful online analysis of complex emotional and cognitive states using real-time fMRI, which will enable a major breakthrough for social fMRI by providing information about mental states of partners already during the mutual interaction. Interestingly, an additional whole brain classification across subjects confirmed the online results: anterior insula, ventral striatum, and lateral orbitofrontal cortex, known to act in emotional self-regulation and reward processing for adjustment of behavior, appeared to be strong determinants of later overt behavior in the ultimatum game. Using whole brain classification we were also able to discriminate between brain processes related to subjective emotional and motivational states and brain processes related to the evaluation of objective financial incentives.

Three-dimensional histology: tools and application to quantitative assessment of cell-type distribution in rabbit heart

PubMed Central

Burton, Rebecca A.B.; Lee, Peter; Casero, Ramón; Garny, Alan; Siedlecka, Urszula; Schneider, Jürgen E.; Kohl, Peter; Grau, Vicente

2014-01-01

Aims Cardiac histo-anatomical organization is a major determinant of function. Changes in tissue structure are a relevant factor in normal and disease development, and form targets of therapeutic interventions. The purpose of this study was to test tools aimed to allow quantitative assessment of cell-type distribution from large histology and magnetic resonance imaging- (MRI) based datasets. Methods and results Rabbit heart fixation during cardioplegic arrest and MRI were followed by serial sectioning of the whole heart and light-microscopic imaging of trichrome-stained tissue. Segmentation techniques developed specifically for this project were applied to segment myocardial tissue in the MRI and histology datasets. In addition, histology slices were segmented into myocytes, connective tissue, and undefined. A bounding surface, containing the whole heart, was established for both MRI and histology. Volumes contained in the bounding surface (called ‘anatomical volume’), as well as that identified as containing any of the above tissue categories (called ‘morphological volume’), were calculated. The anatomical volume was 7.8 cm3 in MRI, and this reduced to 4.9 cm3 after histological processing, representing an ‘anatomical’ shrinkage by 37.2%. The morphological volume decreased by 48% between MRI and histology, highlighting the presence of additional tissue-level shrinkage (e.g. an increase in interstitial cleft space). The ratio of pixels classified as containing myocytes to pixels identified as non-myocytes was roughly 6:1 (61.6 vs. 9.8%; the remaining fraction of 28.6% was ‘undefined’). Conclusion Qualitative and quantitative differentiation between myocytes and connective tissue, using state-of-the-art high-resolution serial histology techniques, allows identification of cell-type distribution in whole-heart datasets. Comparison with MRI illustrates a pronounced reduction in anatomical and morphological volumes during histology processing. PMID:25362175

Human immunodeficiency virus atropy induces modification of subcutaneous adipose tissue architecture: in vivo visualization by high-resolution magnetic resonance imaging.

PubMed

Josse, G; Gensanne, D; Aquilina, C; Bernard, J; Saint-Martory, C; Lagarde, J M; Schmitt, A M

2009-04-01

Human immunodeficiency virus (HIV) infection generally induces lipodystrophy. For targeted treatment a better understanding of its development is necessary. The utility of high-resolution magnetic resonance imaging (MRI) is explored. The present study presents a way to visualize the adipose tissue architecture in vivo and to inspect modifications associated with the atrophy. High-resolution MRI scans with surface coils were performed on the calf and at the lumbar region of three groups of patients: HIV patients with lipoatrophy, HIV patients without lipoatrophy and healthy volunteers. All patients underwent a clinical examination. In addition, dual energy X-ray absorptiometry (DEXA) measurements were taken. On the MRI scans adipose tissue thickness and adipose nodule size were measured. Results High-resolution MRI enabled identification of a clear disorganization of adipose tissue in patients with lipoatrophy. In addition, these patients presented a very small adipose tissue thickness on the calf and a very small nodule size. led to the hypothesis that adipose tissue disorganization appears before changes in DEXA measurements or clinically visible modifications. High-resolution MRI enabled visualization in vivo of precise changes in tissue organization due to HIV lipoatrophy. This imaging technique should be very informative for better monitoring of the atrophy.

Biomedical Applications of Sodium MRI In Vivo

PubMed Central

Madelin, Guillaume; Regatte, Ravinder R.

2013-01-01

In this article, we present an up-to-date overview of the potential biomedical applications of sodium MRI in vivo. Sodium MRI is a subject of increasing interest in translational imaging research as it can give some direct and quantitative biochemical information on the tissue viability, cell integrity and function, and therefore not only help the diagnosis but also the prognosis of diseases and treatment outcomes. It has already been applied in vivo in most of human tissues, such as brain for stroke or tumor detection and therapeutic response, in breast cancer, in articular cartilage, in muscle and in kidney, and it was shown in some studies that it could provide very useful new information not available through standard proton MRI. However, this technique is still very challenging due to the low detectable sodium signal in biological tissue with MRI and hardware/software limitations of the clinical scanners. The article is divided in three parts: (1) the role of sodium in biological tissues, (2) a short review on sodium magnetic resonance, and (3) a review of some studies on sodium MRI on different organs/diseases to date. PMID:23722972

Image segmentation and 3D visualization for MRI mammography

NASA Astrophysics Data System (ADS)

Li, Lihua; Chu, Yong; Salem, Angela F.; Clark, Robert A.

2002-05-01

MRI mammography has a number of advantages, including the tomographic, and therefore three-dimensional (3-D) nature, of the images. It allows the application of MRI mammography to breasts with dense tissue, post operative scarring, and silicon implants. However, due to the vast quantity of images and subtlety of difference in MR sequence, there is a need for reliable computer diagnosis to reduce the radiologist's workload. The purpose of this work was to develop automatic breast/tissue segmentation and visualization algorithms to aid physicians in detecting and observing abnormalities in breast. Two segmentation algorithms were developed: one for breast segmentation, the other for glandular tissue segmentation. In breast segmentation, the MRI image is first segmented using an adaptive growing clustering method. Two tracing algorithms were then developed to refine the breast air and chest wall boundaries of breast. The glandular tissue segmentation was performed using an adaptive thresholding method, in which the threshold value was spatially adaptive using a sliding window. The 3D visualization of the segmented 2D slices of MRI mammography was implemented under IDL environment. The breast and glandular tissue rendering, slicing and animation were displayed.

Body Imaging

NASA Technical Reports Server (NTRS)

1990-01-01

Magnetic Resonance Imaging (MRI) and Computer-aided Tomography (CT) images are often complementary. In most cases, MRI is good for viewing soft tissue but not bone, while CT images are good for bone but not always good for soft tissue discrimination. Physicians and engineers in the Department of Radiology at the University of Michigan Hospitals are developing a technique for combining the best features of MRI and CT scans to increase the accuracy of discriminating one type of body tissue from another. One of their research tools is a computer program called HICAP. The program can be used to distinguish between healthy and diseased tissue in body images.

Advanced Pediatric Brain Imaging Research and Training Program

DTIC Science & Technology

2014-10-01

death and disability in children. Recent advances in pediatric magnetic resonance imaging ( MRI ) techniques are revolutionizing our understanding of... MRI , brain injury. 16. SECURITY CLASSIFICATION OF: 17. LIMITATION OF ABSTRACT 18. NUMBER OF PAGES 19a. NAME OF RESPONSIBLE PERSON USAMRMC a...principles of pediatric brain injury and recovery following injury, as well as the clinical application of sophisticated MRI techniques that are

Resting State fMRI Functional Connectivity-Based Classification Using a Convolutional Neural Network Architecture

PubMed Central

Meszlényi, Regina J.; Buza, Krisztian; Vidnyánszky, Zoltán

2017-01-01

Machine learning techniques have become increasingly popular in the field of resting state fMRI (functional magnetic resonance imaging) network based classification. However, the application of convolutional networks has been proposed only very recently and has remained largely unexplored. In this paper we describe a convolutional neural network architecture for functional connectome classification called connectome-convolutional neural network (CCNN). Our results on simulated datasets and a publicly available dataset for amnestic mild cognitive impairment classification demonstrate that our CCNN model can efficiently distinguish between subject groups. We also show that the connectome-convolutional network is capable to combine information from diverse functional connectivity metrics and that models using a combination of different connectivity descriptors are able to outperform classifiers using only one metric. From this flexibility follows that our proposed CCNN model can be easily adapted to a wide range of connectome based classification or regression tasks, by varying which connectivity descriptor combinations are used to train the network. PMID:29089883

Resting State fMRI Functional Connectivity-Based Classification Using a Convolutional Neural Network Architecture.

PubMed

Meszlényi, Regina J; Buza, Krisztian; Vidnyánszky, Zoltán

2017-01-01

Machine learning techniques have become increasingly popular in the field of resting state fMRI (functional magnetic resonance imaging) network based classification. However, the application of convolutional networks has been proposed only very recently and has remained largely unexplored. In this paper we describe a convolutional neural network architecture for functional connectome classification called connectome-convolutional neural network (CCNN). Our results on simulated datasets and a publicly available dataset for amnestic mild cognitive impairment classification demonstrate that our CCNN model can efficiently distinguish between subject groups. We also show that the connectome-convolutional network is capable to combine information from diverse functional connectivity metrics and that models using a combination of different connectivity descriptors are able to outperform classifiers using only one metric. From this flexibility follows that our proposed CCNN model can be easily adapted to a wide range of connectome based classification or regression tasks, by varying which connectivity descriptor combinations are used to train the network.

Clinical, imaging, and immunohistochemical characteristics of focal cortical dysplasia Type II extratemporal epilepsies in children: analyses of an institutional case series.

PubMed

Knerlich-Lukoschus, Friederike; Connolly, Mary B; Hendson, Glenda; Steinbok, Paul; Dunham, Christopher

2017-02-01

OBJECTIVE Focal cortical dysplasia (FCD) Type II is divided into 2 subgroups based on the absence (IIA) or presence (IIB) of balloon cells. In particular, extratemporal FCD Type IIA and IIB is not completely understood in terms of clinical, imaging, biological, and neuropathological differences. The aim of the authors was to analyze distinctions between these 2 formal entities and address clinical, MRI, and immunohistochemical features of extratemporal epilepsies in children. METHODS Cases formerly classified as Palmini FCD Type II nontemporal epilepsies were identified through the prospectively maintained epilepsy database at the British Columbia Children's Hospital in Vancouver, Canada. Clinical data, including age of seizure onset, age at surgery, seizure type(s) and frequency, affected brain region(s), intraoperative electrocorticographic findings, and outcome defined by Engel's classification were obtained for each patient. Preoperative and postoperative MRI results were reevaluated. H & E-stained tissue sections were reevaluated by using the 2011 International League Against Epilepsy classification system and additional immunostaining for standard cellular markers (neuronal nuclei, neurofilament, glial fibrillary acidic protein, CD68). Two additional established markers of pathology in epilepsy resection, namely, CD34 and α-B crystallin, were applied. RESULTS Seven nontemporal FCD Type IIA and 7 Type B cases were included. Patients with FCD Type IIA presented with an earlier age of epilepsy onset and slightly better Engel outcome. Radiology distinguished FCD Types IIA and IIB, in that Type IIB presented more frequently with characteristic cortical alterations. Nonphosphorylated neurofilament protein staining confirmed dysplastic cells in dyslaminated areas. The white-gray matter junction was focally blurred in patients with FCD Type IIB. α-B crystallin highlighted glial cells in the white matter and subpial layer with either of the 2 FCD Type II subtypes and balloon cells in patients with FCD Type IIB. α-B crystallin positivity proved to be a valuable tool for confirming the histological diagnosis of FCD Type IIB in specimens with rare balloon cells or difficult section orientation. Distinct nonendothelial cellular CD34 staining was found exclusively in tissue from patients with MRI-positive FCD Type IIB. CONCLUSIONS Extratemporal FCD Types IIA and IIB in the pediatric age group exhibited imaging and immunohistochemical characteristics; cellular immunoreactivity to CD34 emerged as an especially potential surrogate marker for lesional FCD Type IIB, providing additional evidence that FCD Types IIA and IIB might differ in their etiology and biology. Although the sample number in this study was small, the results further support the theory that postoperative outcome-defined by Engel's classification-is multifactorial and determined by not only histology but also the extent of the initial lesion, its location in eloquent areas, intraoperative electrocorticographic findings, and achieved resection grade.

Performance assessment of automated tissue characterization for prostate H and E stained histopathology

NASA Astrophysics Data System (ADS)

DiFranco, Matthew D.; Reynolds, Hayley M.; Mitchell, Catherine; Williams, Scott; Allan, Prue; Haworth, Annette

2015-03-01

Reliable automated prostate tumor detection and characterization in whole-mount histology images is sought in many applications, including post-resection tumor staging and as ground-truth data for multi-parametric MRI interpretation. In this study, an ensemble-based supervised classification algorithm for high-resolution histology images was trained on tile-based image features including histogram and gray-level co-occurrence statistics. The algorithm was assessed using different combinations of H and E prostate slides from two separate medical centers and at two different magnifications (400x and 200x), with the aim of applying tumor classification models to new data. Slides from both datasets were annotated by expert pathologists in order to identify homogeneous cancerous and non-cancerous tissue regions of interest, which were then categorized as (1) low-grade tumor (LG-PCa), including Gleason 3 and high-grade prostatic intraepithelial neoplasia (HG-PIN), (2) high-grade tumor (HG-PCa), including various Gleason 4 and 5 patterns, or (3) non-cancerous, including benign stroma and benign prostatic hyperplasia (BPH). Classification models for both LG-PCa and HG-PCa were separately trained using a support vector machine (SVM) approach, and per-tile tumor prediction maps were generated from the resulting ensembles. Results showed high sensitivity for predicting HG-PCa with an AUC up to 0.822 using training data from both medical centres, while LG-PCa showed a lower sensitivity of 0.763 with the same training data. Visual inspection of cancer probability heatmaps from 9 patients showed that 17/19 tumors were detected, and HG-PCa generally reported less false positives than LG-PCa.

Prostate tissue ablation with MRI guided transurethral therapeutic ultrasound and intraoperative assessment of the integrity of the neurovascular bundle

NASA Astrophysics Data System (ADS)

Sammet, Steffen; Partanen, Ari; Yousuf, Ambereen; Wardrip, Craig; Niekrasz, Marek; Antic, Tatjana; Razmaria, Aria; Sokka, Sham; Karczmar, Gregory; Oto, Aytekin

2017-03-01

OBJECTIVES: Evaluation of the precision of prostate tissue ablation with MRI guided therapeuticultrasound by intraoperative objective assessment of the neurovascular bundle in canines in-vivo. METHODS: In this ongoing IACUC approved study, eight male canines were scanned in a clinical 3T Achieva MRI scanner (Philips) before, during, and after ultrasound therapy with a prototype MR-guided ultrasound therapy system (Philips). The system includes a therapy console to plan treatment, to calculate real-time temperature maps, and to control ultrasound exposures with temperature feedback. Atransurethral ultrasound applicator with eight transducer elements was used to ablate canine prostate tissue in-vivo. Ablated prostate tissue volumes were compared to the prescribed target volumes to evaluate technical effectiveness. The ablated volumes determined by MRI (T1, T2, diffusion, dynamic contrast enhanced and 240 CEM43 thermal dose maps) were compared to H&E stained histological slides afterprostatectomy. Potential nerve damage of the neurovascular bundle was objectively assessed intraoperativelyduring prostatectomy with a CaverMap Surgical Aid nerve stimulator (Blue Torch Medical Technologies). RESULTS: Transurethral MRI -guided ultrasound therapy can effectively ablate canine prostate tissue invivo. Coronal MR-imaging confirmed the correct placement of the HIFU transducer. MRI temperature maps were acquired during HIFU treatment, and subsequently used for calculating thermal dose. Prescribed target volumes corresponded to the 240 CEM43 thermal dose maps during HIFU treatment in all canines. Ablated volumes on high resolution anatomical, diffusion weighted, and contrast enhanced MR images matched corresponding histological slides after prostatectomy. MRI guidance with realtime temperature monitoring showed no damage to surrounding tissues, especially to the neurovascular bundle (assessed intra-operatively with a nerve stimulator) or to the rectum wall. CONCLUSIONS: Our study demonstrates the effectiveness and precision of transurethral ultrasound ablation of prostatic tissue in canines with MRI monitoring and guidance. The canine prostate is an excellent model for the human prostate with similar anatomical characteristics and diseases. MRI guidance with real-time, intraoperative temperature monitoring reduces the risk of damaging critical surrounding anatomical structures in ultrasound therapy of the prostate.

Soft tissue recurrence of giant cell tumor of the bone: Prevalence and radiographic features.

PubMed

Xu, Leilei; Jin, Jing; Hu, Annan; Xiong, Jin; Wang, Dongmei; Sun, Qi; Wang, Shoufeng

2017-11-01

Recurrence of giant cell tumor of bone (GCTB) in the soft tissue is rarely seen in the clinical practice. This study aims to determine the prevalence of soft tissue recurrence of GCTB, and to characterize its radiographic features. A total of 291 patients treated by intralesional curettage for histologically diagnosed GCTB were reviewed. 6 patients were identified to have the recurrence of GCTB in the soft tissue, all of whom had undergone marginal resection of the lesion. Based on the x-ray, CT and MRI imaging, the radiographic features of soft tissue recurrence were classified into 3 types. Type I was defined as soft tissue recurrence with peripheral ossification, type II was defined as soft tissue recurrence with central ossification, and type III was defined as pure soft tissue recurrence without ossification. Demographic data including period of recurrence and follow-up duration after the second surgery were recorded for these 6 patients. Musculoskeletal Tumor Society (MSTS) scoring system was used to evaluate functional outcomes. The overall recurrence rate was 2.1% (6/291). The mean interval between initial surgery and recurrence was 11.3 ± 4.1 months (range, 5-17). The recurrence lesions were located in the thigh of 2 patients, in the forearm of 2 patients and in the leg of the other 2 patients. According to the classification system mentioned above, 2 patients were classified with type I, 1 as type II and 3 as type III. After the marginal excision surgery, all patients were consistently followed up for a mean period of 13.4 ± 5.3 months (range, 6-19), with no recurrence observed at the final visit. All the patients were satisfied with the surgical outcome. According to the MSTS scale, the mean postoperative functional score was 28.0 ± 1.2 (range, 26-29). The classification of soft tissue recurrence of GCTB may be helpful for the surgeon to select the appropriate imaging procedure to detect the recurrence. In addition, the marginal resection can produce a favorable outcome for the patients.

The brain MRI classification problem from wavelets perspective

NASA Astrophysics Data System (ADS)

Bendib, Mohamed M.; Merouani, Hayet F.; Diaba, Fatma

2015-02-01

Haar and Daubechies 4 (DB4) are the most used wavelets for brain MRI (Magnetic Resonance Imaging) classification. The former is simple and fast to compute while the latter is more complex and offers a better resolution. This paper explores the potential of both of them in performing Normal versus Pathological discrimination on the one hand, and Multiclassification on the other hand. The Whole Brain Atlas is used as a validation database, and the Random Forest (RF) algorithm is employed as a learning approach. The achieved results are discussed and statistically compared.

Adipose Tissue Quantification by Imaging Methods: A Proposed Classification

PubMed Central

Shen, Wei; Wang, ZiMian; Punyanita, Mark; Lei, Jianbo; Sinav, Ahmet; Kral, John G.; Imielinska, Celina; Ross, Robert; Heymsfield, Steven B.

2007-01-01

Recent advances in imaging techniques and understanding of differences in the molecular biology of adipose tissue has rendered classical anatomy obsolete, requiring a new classification of the topography of adipose tissue. Adipose tissue is one of the largest body compartments, yet a classification that defines specific adipose tissue depots based on their anatomic location and related functions is lacking. The absence of an accepted taxonomy poses problems for investigators studying adipose tissue topography and its functional correlates. The aim of this review was to critically examine the literature on imaging of whole body and regional adipose tissue and to create the first systematic classification of adipose tissue topography. Adipose tissue terminology was examined in over 100 original publications. Our analysis revealed inconsistencies in the use of specific definitions, especially for the compartment termed “visceral” adipose tissue. This analysis leads us to propose an updated classification of total body and regional adipose tissue, providing a well-defined basis for correlating imaging studies of specific adipose tissue depots with molecular processes. PMID:12529479

Accurate classification of brain gliomas by discriminate dictionary learning based on projective dictionary pair learning of proton magnetic resonance spectra.

PubMed

Adebileje, Sikiru Afolabi; Ghasemi, Keyvan; Aiyelabegan, Hammed Tanimowo; Saligheh Rad, Hamidreza

2017-04-01

Proton magnetic resonance spectroscopy is a powerful noninvasive technique that complements the structural images of cMRI, which aids biomedical and clinical researches, by identifying and visualizing the compositions of various metabolites within the tissues of interest. However, accurate classification of proton magnetic resonance spectroscopy is still a challenging issue in clinics due to low signal-to-noise ratio, overlapping peaks of metabolites, and the presence of background macromolecules. This paper evaluates the performance of a discriminate dictionary learning classifiers based on projective dictionary pair learning method for brain gliomas proton magnetic resonance spectroscopy spectra classification task, and the result were compared with the sub-dictionary learning methods. The proton magnetic resonance spectroscopy data contain a total of 150 spectra (74 healthy, 23 grade II, 23 grade III, and 30 grade IV) from two databases. The datasets from both databases were first coupled together, followed by column normalization. The Kennard-Stone algorithm was used to split the datasets into its training and test sets. Performance comparison based on the overall accuracy, sensitivity, specificity, and precision was conducted. Based on the overall accuracy of our classification scheme, the dictionary pair learning method was found to outperform the sub-dictionary learning methods 97.78% compared with 68.89%, respectively. Copyright © 2016 John Wiley & Sons, Ltd. Copyright © 2016 John Wiley & Sons, Ltd.

Intraoperative MRI-guided resection of focal cortical dysplasia in pediatric patients: technique and outcomes.

PubMed

Sacino, Matthew F; Ho, Cheng-Ying; Murnick, Jonathan; Tsuchida, Tammy; Magge, Suresh N; Keating, Robert F; Gaillard, William D; Oluigbo, Chima O

2016-06-01

OBJECTIVE Previous meta-analysis has demonstrated that the most important factor in seizure freedom following surgery for focal cortical dysplasia (FCD) is completeness of resection. However, intraoperative detection of epileptogenic dysplastic cortical tissue remains a challenge, potentially leading to a partial resection and the need for reoperation. The objective of this study was to determine the role of intraoperative MRI (iMRI) in the intraoperative detection and localization of FCD as well as its impact on surgical decision making, completeness of resection, and seizure control outcomes. METHODS The authors retrospectively reviewed the medical records of pediatric patients who underwent iMRI-assisted resection of FCD at the Children's National Health System between January 2014 and April 2015. Data reviewed included demographics, length of surgery, details of iMRI acquisition, postoperative seizure freedom, and complications. Postsurgical seizure outcome was assessed utilizing the Engel Epilepsy Surgery Outcome Scale. RESULTS Twelve consecutive pediatric patients (8 females and 4 males) underwent iMRI-guided resection of FCD lesions. The mean age at the time of surgery was 8.8 years ± 1.6 years (range 0.7 to 18.8 years), and the mean duration of follow up was 3.5 months ± 1.0 month. The mean age at seizure onset was 2.8 years ± 1.0 year (range birth to 9.0 years). Two patients had Type 1 FCD, 5 patients had Type 2A FCD, 2 patients had Type 2B FCD, and 3 patients had FCD of undetermined classification. iMRI findings impacted intraoperative surgical decision making in 5 (42%) of the 12 patients, who then underwent further exploration of the resection cavity. At the time of the last postoperative follow-up, 11 (92%) of the 12 patients were seizure free (Engel Class I). No patients underwent reoperation following iMRI-guided surgery. CONCLUSIONS iMRI-guided resection of FCD in pediatric patients precluded the need for repeat surgery. Furthermore, it resulted in the achievement of complete resection in all the patients, leading to a high rate of postoperative seizure freedom.

Added Value of Fetal MRI in the Evaluation of Fetal Anomalies of the Corpus Callosum: A Retrospective Analysis of 78 Cases.

PubMed

Manevich-Mazor, Mirra; Weissmann-Brenner, Alina; Bar Yosef, Omer; Hoffmann, Chen; Mazor, Roei David; Mosheva, Mariela; Achiron, Reuven Ryszard; Katorza, Eldad

2018-06-07

 To evaluate the added value of fetal MRI to ultrasound in detecting and specifying callosal anomalies, and its impact on clinical decision making.  Fetuses with a sonographic diagnosis of an anomalous corpus callosum (CC) who underwent a subsequent fetal brain MRI between 2010 and 2015 were retrospectively evaluated and classified according to the severity of the findings. The findings detected on ultrasound were compared to those detected on MRI. An analysis was performed to assess whether fetal MRI altered the group classification, and thus the management of these pregnancies.  78 women were recruited following sonographic diagnoses of either complete or partial callosal agenesis, short, thin or thick CC. Normal MRI studies were obtained inµ19 cases (24 %). Among these, all children available for follow-up received an adequate adaptive score in their Vineland II adaptive behavior scale assessment. Analysis of the concordance between US and MRI demonstrated a substantial level of agreement for complete callosal agenesis (kappa: 0.742), moderate agreement for thin CC (kappa: 0.418) and fair agreement for all other callosal anomalies. Comparison between US and MRI-based mild/severe findings classifications revealed that MRI contributed to a change in the management for 28 fetuses (35.9 %), mostly (25 fetuses, 32.1 %) in favor of pregnancy preservation.  Fetal MRI effectively detects callosal anomalies and enables satisfactory validation of the presence or absence of callosal anomalies identified by ultrasound and adds valuable data that improves clinical decision making. © Georg Thieme Verlag KG Stuttgart · New York.

Task-specific feature extraction and classification of fMRI volumes using a deep neural network initialized with a deep belief network: Evaluation using sensorimotor tasks

PubMed Central

Jang, Hojin; Plis, Sergey M.; Calhoun, Vince D.; Lee, Jong-Hwan

2016-01-01

Feedforward deep neural networks (DNN), artificial neural networks with multiple hidden layers, have recently demonstrated a record-breaking performance in multiple areas of applications in computer vision and speech processing. Following the success, DNNs have been applied to neuroimaging modalities including functional/structural magnetic resonance imaging (MRI) and positron-emission tomography data. However, no study has explicitly applied DNNs to 3D whole-brain fMRI volumes and thereby extracted hidden volumetric representations of fMRI that are discriminative for a task performed as the fMRI volume was acquired. Our study applied fully connected feedforward DNN to fMRI volumes collected in four sensorimotor tasks (i.e., left-hand clenching, right-hand clenching, auditory attention, and visual stimulus) undertaken by 12 healthy participants. Using a leave-one-subject-out cross-validation scheme, a restricted Boltzmann machine-based deep belief network was pretrained and used to initialize weights of the DNN. The pretrained DNN was fine-tuned while systematically controlling weight-sparsity levels across hidden layers. Optimal weight-sparsity levels were determined from a minimum validation error rate of fMRI volume classification. Minimum error rates (mean ± standard deviation; %) of 6.9 (± 3.8) were obtained from the three-layer DNN with the sparsest condition of weights across the three hidden layers. These error rates were even lower than the error rates from the single-layer network (9.4 ± 4.6) and the two-layer network (7.4 ± 4.1). The estimated DNN weights showed spatial patterns that are remarkably task-specific, particularly in the higher layers. The output values of the third hidden layer represented distinct patterns/codes of the 3D whole-brain fMRI volume and encoded the information of the tasks as evaluated from representational similarity analysis. Our reported findings show the ability of the DNN to classify a single fMRI volume based on the extraction of hidden representations of fMRI volumes associated with tasks across multiple hidden layers. Our study may be beneficial to the automatic classification/diagnosis of neuropsychiatric and neurological diseases and prediction of disease severity and recovery in (pre-) clinical settings using fMRI volumes without requiring an estimation of activation patterns or ad hoc statistical evaluation. PMID:27079534

Task-specific feature extraction and classification of fMRI volumes using a deep neural network initialized with a deep belief network: Evaluation using sensorimotor tasks.

PubMed

Jang, Hojin; Plis, Sergey M; Calhoun, Vince D; Lee, Jong-Hwan

2017-01-15

Feedforward deep neural networks (DNNs), artificial neural networks with multiple hidden layers, have recently demonstrated a record-breaking performance in multiple areas of applications in computer vision and speech processing. Following the success, DNNs have been applied to neuroimaging modalities including functional/structural magnetic resonance imaging (MRI) and positron-emission tomography data. However, no study has explicitly applied DNNs to 3D whole-brain fMRI volumes and thereby extracted hidden volumetric representations of fMRI that are discriminative for a task performed as the fMRI volume was acquired. Our study applied fully connected feedforward DNN to fMRI volumes collected in four sensorimotor tasks (i.e., left-hand clenching, right-hand clenching, auditory attention, and visual stimulus) undertaken by 12 healthy participants. Using a leave-one-subject-out cross-validation scheme, a restricted Boltzmann machine-based deep belief network was pretrained and used to initialize weights of the DNN. The pretrained DNN was fine-tuned while systematically controlling weight-sparsity levels across hidden layers. Optimal weight-sparsity levels were determined from a minimum validation error rate of fMRI volume classification. Minimum error rates (mean±standard deviation; %) of 6.9 (±3.8) were obtained from the three-layer DNN with the sparsest condition of weights across the three hidden layers. These error rates were even lower than the error rates from the single-layer network (9.4±4.6) and the two-layer network (7.4±4.1). The estimated DNN weights showed spatial patterns that are remarkably task-specific, particularly in the higher layers. The output values of the third hidden layer represented distinct patterns/codes of the 3D whole-brain fMRI volume and encoded the information of the tasks as evaluated from representational similarity analysis. Our reported findings show the ability of the DNN to classify a single fMRI volume based on the extraction of hidden representations of fMRI volumes associated with tasks across multiple hidden layers. Our study may be beneficial to the automatic classification/diagnosis of neuropsychiatric and neurological diseases and prediction of disease severity and recovery in (pre-) clinical settings using fMRI volumes without requiring an estimation of activation patterns or ad hoc statistical evaluation. Copyright © 2016 Elsevier Inc. All rights reserved.

MR imaging of the traumatic triangular fibrocartilaginous complex tear

PubMed Central

Griffith, James F.; Fung, Cindy S. Y.; Lee, Ryan K. L.; Tong, Cina S. L.; Wong, Clara W. Y.; Tse, Wing Lim; Ho, Pak Cheong

2017-01-01

Triangular fibrocartilage complex is a major stabilizer of the distal radioulnar joint (DRUJ). However, triangular fibrocartilage complex (TFCC) tear is difficult to be diagnosed on MRI for its intrinsic small and thin structure with complex anatomy. The purpose of this article is to review the anatomy of TFCC, state of art MRI imaging technique, normal appearance and features of tear on MRI according to the Palmar’s classification. Atypical tear and limitations of MRI in diagnosis of TFCC tear are also discussed. PMID:28932701

Magnetic Resonance Safety

PubMed Central

Sammet, Steffen

2016-01-01

Magnetic Resonance Imaging (MRI) has a superior soft-tissue contrast compared to other radiological imaging modalities and its physiological and functional applications have led to a significant increase in MRI scans worldwide. A comprehensive MRI safety training to protect patients and other healthcare workers from potential bio-effects and risks of the magnetic fields in an MRI suite is therefore essential. The knowledge of the purpose of safety zones in an MRI suite as well as MRI appropriateness criteria is important for all healthcare professionals who will work in the MRI environment or refer patients for MRI scans. The purpose of this article is to give an overview of current magnetic resonance safety guidelines and discuss the safety risks of magnetic fields in an MRI suite including forces and torque of ferromagnetic objects, tissue heating, peripheral nerve stimulation and hearing damages. MRI safety and compatibility of implanted devices, MRI scans during pregnancy and the potential risks of MRI contrast agents will also be discussed and a comprehensive MRI safety training to avoid fatal accidents in an MRI suite will be presented. PMID:26940331

Hybrid PET/MR imaging in two sarcoma patients - clinical benefits and implications for future trials.

PubMed

Partovi, Sasan; Kohan, Andres A; Zipp, Lisa; Faulhaber, Peter; Kosmas, Christos; Ros, Pablo R; Robbin, Mark R

2014-01-01

PET/MRI is an evolving hybrid imaging modality which combines the inherent strengths of MRIs soft-tissue and contrast resolution and PETs functional metabolic capabilities. Bone and soft-tissue sarcoma are a relatively rare tumor entity, relying on MRI for local staging and often on PET/CT for lymph node involvement and metastatic spread evaluation. The purpose of this article is to demonstrate the successful use of PET/MRI in two sarcoma patients. We also use these patients as a starting point to discuss how PET/MRI might be of value in sarcoma. Among its potential benefits are: superior TNM staging than either modality alone, decreased radiation dose, more sensitive and specific follow-up and better assessment of treatment response. These potentials need to be investigated in future PET/MRI soft-tissue sarcoma trials.

Ultrasound of the coracoclavicular ligaments in the acute phase of an acromioclavicular disjonction: Comparison of radiographic, ultrasound and MRI findings.

PubMed

Faruch Bilfeld, Marie; Lapègue, Franck; Chiavassa Gandois, Hélène; Bayol, Marie Aurélie; Bonnevialle, Nicolas; Sans, Nicolas

2017-02-01

Acromioclavicular joint injuries are typically diagnosed by clinical and radiographic assessment with the Rockwood classification, which is crucial for treatment planning. The purpose of this study was to describe how the ultrasound findings of acromioclavicular joint injury compare with radiography and MRI findings. Forty-seven patients with suspected unilateral acromioclavicular joint injury after acute trauma were enrolled in this prospective study. All patients underwent digital radiography, ultrasound and 3T MRI. A modified Rockwood classification was used to evaluate the coracoclavicular ligaments. The classifications of acromioclavicular joint injuries diagnosed with radiography, ultrasound and MRI were compared. MRI was used as the gold standard. The agreement between the ultrasound and MRI findings was very good, with a correlation coefficient of 0.83 (95 % CI: 0.72-0.90; p < 0.0001). Ultrasound detected coracoclavicular ligament injuries with a sensitivity of 88.9 %, specificity of 90.0 %, positive predictive value of 92.3 % and negative predictive value of 85.7 %. The agreement between the ultrasound and radiography findings was poor, with a correlation coefficient of 0.69 (95 % CI: 0.51-0.82; p < 0.0001). Ultrasound is an effective examination for the diagnostic work-up of lesions of the coracoclavicular ligaments in the acute phase of an acromioclavicular injury. • Ultrasound is appropriate for acute acromioclavicular trauma due to its accessibility. • Ultrasound contributes to the diagnostic work-up of acute lesions of the coracoclavicular ligaments. • Ultrasound is appropriate in patients likely to benefit from surgical treatment. • Ultrasound could be a supplement to standard radiography in acute acromioclavicular trauma.

Molecular classification of patients with grade II/III glioma using quantitative MRI characteristics.

PubMed

Bahrami, Naeim; Hartman, Stephen J; Chang, Yu-Hsuan; Delfanti, Rachel; White, Nathan S; Karunamuni, Roshan; Seibert, Tyler M; Dale, Anders M; Hattangadi-Gluth, Jona A; Piccioni, David; Farid, Nikdokht; McDonald, Carrie R

2018-06-02

Molecular markers of WHO grade II/III glioma are known to have important prognostic and predictive implications and may be associated with unique imaging phenotypes. The purpose of this study is to determine whether three clinically relevant molecular markers identified in gliomas-IDH, 1p/19q, and MGMT status-show distinct quantitative MRI characteristics on FLAIR imaging. Sixty-one patients with grade II/III gliomas who had molecular data and MRI available prior to radiation were included. Quantitative MRI features were extracted that measured tissue heterogeneity (homogeneity and pixel correlation) and FLAIR border distinctiveness (edge contrast; EC). T-tests were conducted to determine whether patients with different genotypes differ across the features. Logistic regression with LASSO regularization was used to determine the optimal combination of MRI and clinical features for predicting molecular subtypes. Patients with IDH wildtype tumors showed greater signal heterogeneity (p = 0.001) and lower EC (p = 0.008) within the FLAIR region compared to IDH mutant tumors. Among patients with IDH mutant tumors, 1p/19q co-deleted tumors had greater signal heterogeneity (p = 0.002) and lower EC (p = 0.005) compared to 1p/19q intact tumors. MGMT methylated tumors showed lower EC (p = 0.03) compared to the unmethylated group. The combination of FLAIR border distinctness, heterogeneity, and pixel correlation optimally classified tumors by IDH status. Quantitative imaging characteristics of FLAIR heterogeneity and border pattern in grade II/III gliomas may provide unique information for determining molecular status at time of initial diagnostic imaging, which may then guide subsequent surgical and medical management.

Deriving stable multi-parametric MRI radiomic signatures in the presence of inter-scanner variations: survival prediction of glioblastoma via imaging pattern analysis and machine learning techniques

NASA Astrophysics Data System (ADS)

Rathore, Saima; Bakas, Spyridon; Akbari, Hamed; Shukla, Gaurav; Rozycki, Martin; Davatzikos, Christos

2018-02-01

There is mounting evidence that assessment of multi-parametric magnetic resonance imaging (mpMRI) profiles can noninvasively predict survival in many cancers, including glioblastoma. The clinical adoption of mpMRI as a prognostic biomarker, however, depends on its applicability in a multicenter setting, which is hampered by inter-scanner variations. This concept has not been addressed in existing studies. We developed a comprehensive set of within-patient normalized tumor features such as intensity profile, shape, volume, and tumor location, extracted from multicenter mpMRI of two large (npatients=353) cohorts, comprising the Hospital of the University of Pennsylvania (HUP, npatients=252, nscanners=3) and The Cancer Imaging Archive (TCIA, npatients=101, nscanners=8). Inter-scanner harmonization was conducted by normalizing the tumor intensity profile, with that of the contralateral healthy tissue. The extracted features were integrated by support vector machines to derive survival predictors. The predictors' generalizability was evaluated within each cohort, by two cross-validation configurations: i) pooled/scanner-agnostic, and ii) across scanners (training in multiple scanners and testing in one). The median survival in each configuration was used as a cut-off to divide patients in long- and short-survivors. Accuracy (ACC) for predicting long- versus short-survivors, for these configurations was ACCpooled=79.06% and ACCpooled=84.7%, ACCacross=73.55% and ACCacross=74.76%, in HUP and TCIA datasets, respectively. The hazard ratio at 95% confidence interval was 3.87 (2.87-5.20, P<0.001) and 6.65 (3.57-12.36, P<0.001) for HUP and TCIA datasets, respectively. Our findings suggest that adequate data normalization coupled with machine learning classification allows robust prediction of survival estimates on mpMRI acquired by multiple scanners.

Consideration of the effects of intense tissue heating on the RF electromagnetic fields during MRI: simulations for MRgFUS in the hip

NASA Astrophysics Data System (ADS)

Xuegang Xin, Sherman; Gu, Shiyong; Carluccio, Giuseppe; Collins, Christopher M.

2015-01-01

Due to the strong dependence of tissue electrical properties on temperature, it is important to consider the potential effects of intense tissue heating on the RF electromagnetic fields during MRI, as can occur in MR-guided focused ultrasound surgery. In principle, changes of the RF electromagnetic fields could affect both efficacy of RF pulses, and the MRI-induced RF heating (SAR) pattern. In this study, the equilibrium temperature distribution in a whole-body model with 2 mm resolution before and during intense tissue heating up to 60 °C at the target region was calculated. Temperature-dependent electric properties of tissues were assigned to the model to establish a temperature-dependent electromagnetic whole-body model in a 3T MRI system. The results showed maximum changes in conductivity, permittivity, ≤ft|\\mathbf{B}1+\\right|, and SAR of about 25%, 6%, 2%, and 20%, respectively. Though the B1 field and SAR distributions are both temperature-dependent, the potential harm to patients due to higher SARs is expected to be minimal and the effects on the B1 field distribution should have minimal effect on images from basic MRI sequences.

Cross-classification of musical and vocal emotions in the auditory cortex.

PubMed

Paquette, Sébastien; Takerkart, Sylvain; Saget, Shinji; Peretz, Isabelle; Belin, Pascal

2018-05-09

Whether emotions carried by voice and music are processed by the brain using similar mechanisms has long been investigated. Yet neuroimaging studies do not provide a clear picture, mainly due to lack of control over stimuli. Here, we report a functional magnetic resonance imaging (fMRI) study using comparable stimulus material in the voice and music domains-the Montreal Affective Voices and the Musical Emotional Bursts-which include nonverbal short bursts of happiness, fear, sadness, and neutral expressions. We use a multivariate emotion-classification fMRI analysis involving cross-timbre classification as a means of comparing the neural mechanisms involved in processing emotional information in the two domains. We find, for affective stimuli in the violin, clarinet, or voice timbres, that local fMRI patterns in the bilateral auditory cortex and upper premotor regions support above-chance emotion classification when training and testing sets are performed within the same timbre category. More importantly, classifier performance generalized well across timbre in cross-classifying schemes, albeit with a slight accuracy drop when crossing the voice-music boundary, providing evidence for a shared neural code for processing musical and vocal emotions, with possibly a cost for the voice due to its evolutionary significance. © 2018 New York Academy of Sciences.

Inter-reader reproducibility of dynamic contrast-enhanced magnetic resonance imaging in patients with non-small cell lung cancer treated with bevacizumab and erlotinib.

PubMed

van den Boogaart, Vivian E M; de Lussanet, Quido G; Houben, Ruud M A; de Ruysscher, Dirk; Groen, Harry J M; Marcus, J Tim; Smit, Egbert F; Dingemans, Anne-Marie C; Backes, Walter H

2016-03-01

Objectives When evaluating anti-tumor treatment response by dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) it is necessary to assure its validity and reproducibility. This has not been well addressed in lung tumors. Therefore we have evaluated the inter-reader reproducibility of response classification by DCE-MRI in patients with non-small cell lung cancer (NSCLC) treated with bevacizumab and erlotinib enrolled in a multicenter trial. Twenty-one patients were scanned before and 3 weeks after start of treatment with DCE-MRI in a multicenter trial. The scans were evaluated by two independent readers. The primary lung tumor was used for response assessment. Responses were assessed in terms of relative changes in tumor mean trans endothelial transfer rate (K(trans)) and its heterogeneity in terms of the spatial standard deviation. Reproducibility was expressed by the inter-reader variability, intra-class correlation coefficient (ICC) and dichotomous response classification. The inter-reader variability and ICC for the relative K(trans) were 5.8% and 0.930, respectively. For tumor heterogeneity the inter-reader variability and ICC were 0.017 and 0.656, respectively. For the two readers the response classification for relative K(trans) was concordant in 20 of 21 patients (k=0.90, p<0.0001) and for tumor heterogeneity in 19 of 21 patients (k=0.80, p<0.0001). Strong agreement was seen with regard to the inter-reader variability and reproducibility of response classification by the two readers of lung cancer DCE-MRI scans. Copyright © 2015 Elsevier Ireland Ltd. All rights reserved.

Tissue-Point Motion Tracking in the Tongue from Cine MRI and Tagged MRI

ERIC Educational Resources Information Center

Woo, Jonghye; Stone, Maureen; Suo, Yuanming; Murano, Emi Z.; Prince, Jerry L.

2014-01-01

Purpose: Accurate tissue motion tracking within the tongue can help professionals diagnose and treat vocal tract--related disorders, evaluate speech quality before and after surgery, and conduct various scientific studies. The authors compared tissue tracking results from 4 widely used deformable registration (DR) methods applied to cine magnetic…

Tissue classification for laparoscopic image understanding based on multispectral texture analysis

NASA Astrophysics Data System (ADS)

Zhang, Yan; Wirkert, Sebastian J.; Iszatt, Justin; Kenngott, Hannes; Wagner, Martin; Mayer, Benjamin; Stock, Christian; Clancy, Neil T.; Elson, Daniel S.; Maier-Hein, Lena

2016-03-01

Intra-operative tissue classification is one of the prerequisites for providing context-aware visualization in computer-assisted minimally invasive surgeries. As many anatomical structures are difficult to differentiate in conventional RGB medical images, we propose a classification method based on multispectral image patches. In a comprehensive ex vivo study we show (1) that multispectral imaging data is superior to RGB data for organ tissue classification when used in conjunction with widely applied feature descriptors and (2) that combining the tissue texture with the reflectance spectrum improves the classification performance. Multispectral tissue analysis could thus evolve as a key enabling technique in computer-assisted laparoscopy.

Diffusion MRI at 25: Exploring brain tissue structure and function

PubMed Central

Bihan, Denis Le; Johansen-Berg, Heidi

2013-01-01

Diffusion MRI (or dMRI) came into existence in the mid-1980s. During the last 25 years, diffusion MRI has been extraordinarily successful (with more than 300,000 entries on Google Scholar for diffusion MRI). Its main clinical domain of application has been neurological disorders, especially for the management of patients with acute stroke. It is also rapidly becoming a standard for white matter disorders, as diffusion tensor imaging (DTI) can reveal abnormalities in white matter fiber structure and provide outstanding maps of brain connectivity. The ability to visualize anatomical connections between different parts of the brain, non-invasively and on an individual basis, has emerged as a major breakthrough for neurosciences. The driving force of dMRI is to monitor microscopic, natural displacements of water molecules that occur in brain tissues as part of the physical diffusion process. Water molecules are thus used as a probe that can reveal microscopic details about tissue architecture, either normal or in a diseased state. PMID:22120012

Ultrahigh field MRI in clinical neuroimmunology: a potential contribution to improved diagnostics and personalised disease management.

PubMed

Sinnecker, Tim; Kuchling, Joseph; Dusek, Petr; Dörr, Jan; Niendorf, Thoralf; Paul, Friedemann; Wuerfel, Jens

2015-01-01

Conventional magnetic resonance imaging (MRI) at 1.5 Tesla (T) is limited by modest spatial resolution and signal-to-noise ratio (SNR), impeding the identification and classification of inflammatory central nervous system changes in current clinical practice. Gaining from enhanced susceptibility effects and improved SNR, ultrahigh field MRI at 7 T depicts inflammatory brain lesions in great detail. This review summarises recent reports on 7 T MRI in neuroinflammatory diseases and addresses the question as to whether ultrahigh field MRI may eventually improve clinical decision-making and personalised disease management.

A fuzzy integral method based on the ensemble of neural networks to analyze fMRI data for cognitive state classification across multiple subjects.

PubMed

Cacha, L A; Parida, S; Dehuri, S; Cho, S-B; Poznanski, R R

2016-12-01

The huge number of voxels in fMRI over time poses a major challenge to for effective analysis. Fast, accurate, and reliable classifiers are required for estimating the decoding accuracy of brain activities. Although machine-learning classifiers seem promising, individual classifiers have their own limitations. To address this limitation, the present paper proposes a method based on the ensemble of neural networks to analyze fMRI data for cognitive state classification for application across multiple subjects. Similarly, the fuzzy integral (FI) approach has been employed as an efficient tool for combining different classifiers. The FI approach led to the development of a classifiers ensemble technique that performs better than any of the single classifier by reducing the misclassification, the bias, and the variance. The proposed method successfully classified the different cognitive states for multiple subjects with high accuracy of classification. Comparison of the performance improvement, while applying ensemble neural networks method, vs. that of the individual neural network strongly points toward the usefulness of the proposed method.

Consistency of signal intensity and T2* in frozen ex vivo heart muscle, kidney, and liver tissue.

PubMed

Kaye, Elena A; Josan, Sonal; Lu, Aiming; Rosenberg, Jarrett; Daniel, Bruce L; Pauly, Kim Butts

2010-03-01

To investigate tissue dependence of the MRI-based thermometry in frozen tissue by quantification and comparison of signal intensity and T2* of ex vivo frozen tissue of three different types: heart muscle, kidney, and liver. Tissue samples were frozen and imaged on a 0.5 Tesla MRI scanner with ultrashort echo time (UTE) sequence. Signal intensity and T2* were determined as the temperature of the tissue samples was decreased from room temperature to approximately -40 degrees C. Statistical analysis was performed for (-20 degrees C, -5 degrees C) temperature interval. The findings of this study demonstrate that signal intensity and T2* are consistent across three types of tissue for (-20 degrees C, -5 degrees C) temperature interval. Both parameters can be used to calculate a single temperature calibration curve for all three types of tissue and potentially in the future serve as a foundation for tissue-independent MRI-based thermometry.

An Automated Method for Identifying Artifact in Independent Component Analysis of Resting-State fMRI

PubMed Central

Bhaganagarapu, Kaushik; Jackson, Graeme D.; Abbott, David F.

2013-01-01

An enduring issue with data-driven analysis and filtering methods is the interpretation of results. To assist, we present an automatic method for identification of artifact in independent components (ICs) derived from functional MRI (fMRI). The method was designed with the following features: does not require temporal information about an fMRI paradigm; does not require the user to train the algorithm; requires only the fMRI images (additional acquisition of anatomical imaging not required); is able to identify a high proportion of artifact-related ICs without removing components that are likely to be of neuronal origin; can be applied to resting-state fMRI; is automated, requiring minimal or no human intervention. We applied the method to a MELODIC probabilistic ICA of resting-state functional connectivity data acquired in 50 healthy control subjects, and compared the results to a blinded expert manual classification. The method identified between 26 and 72% of the components as artifact (mean 55%). About 0.3% of components identified as artifact were discordant with the manual classification; retrospective examination of these ICs suggested the automated method had correctly identified these as artifact. We have developed an effective automated method which removes a substantial number of unwanted noisy components in ICA analyses of resting-state fMRI data. Source code of our implementation of the method is available. PMID:23847511

Automatic classification of patients with idiopathic Parkinson's disease and progressive supranuclear palsy using diffusion MRI datasets

NASA Astrophysics Data System (ADS)

Talai, Sahand; Boelmans, Kai; Sedlacik, Jan; Forkert, Nils D.

2017-03-01

Parkinsonian syndromes encompass a spectrum of neurodegenerative diseases, which can be classified into various subtypes. The differentiation of these subtypes is typically conducted based on clinical criteria. Due to the overlap of intra-syndrome symptoms, the accurate differential diagnosis based on clinical guidelines remains a challenge with failure rates up to 25%. The aim of this study is to present an image-based classification method of patients with Parkinson's disease (PD) and patients with progressive supranuclear palsy (PSP), an atypical variant of PD. Therefore, apparent diffusion coefficient (ADC) parameter maps were calculated based on diffusion-tensor magnetic resonance imaging (MRI) datasets. Mean ADC values were determined in 82 brain regions using an atlas-based approach. The extracted mean ADC values for each patient were then used as features for classification using a linear kernel support vector machine classifier. To increase the classification accuracy, a feature selection was performed, which resulted in the top 17 attributes to be used as the final input features. A leave-one-out cross validation based on 56 PD and 21 PSP subjects revealed that the proposed method is capable of differentiating PD and PSP patients with an accuracy of 94.8%. In conclusion, the classification of PD and PSP patients based on ADC features obtained from diffusion MRI datasets is a promising new approach for the differentiation of Parkinsonian syndromes in the broader context of decision support systems.

Breast cancer Ki67 expression preoperative discrimination by DCE-MRI radiomics features

NASA Astrophysics Data System (ADS)

Ma, Wenjuan; Ji, Yu; Qin, Zhuanping; Guo, Xinpeng; Jian, Xiqi; Liu, Peifang

2018-02-01

To investigate whether quantitative radiomics features extracted from dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) are associated with Ki67 expression of breast cancer. In this institutional review board approved retrospective study, we collected 377 cases Chinese women who were diagnosed with invasive breast cancer in 2015. This cohort included 53 low-Ki67 expression (Ki67 proliferation index less than 14%) and 324 cases with high-Ki67 expression (Ki67 proliferation index more than 14%). A binary-classification of low- vs. high- Ki67 expression was performed. A set of 52 quantitative radiomics features, including morphological, gray scale statistic, and texture features, were extracted from the segmented lesion area. Three most common machine learning classification methods, including Naive Bayes, k-Nearest Neighbor and support vector machine with Gaussian kernel, were employed for the classification and the least absolute shrink age and selection operator (LASSO) method was used to select most predictive features set for the classifiers. Classification performance was evaluated by the area under receiver operating characteristic curve (AUC), accuracy, sensitivity and specificity. The model that used Naive Bayes classification method achieved the best performance than the other two methods, yielding 0.773 AUC value, 0.757 accuracy, 0.777 sensitivity and 0.769 specificity. Our study showed that quantitative radiomics imaging features of breast tumor extracted from DCE-MRI are associated with breast cancer Ki67 expression. Future larger studies are needed in order to further evaluate the findings.

Usefulness of combining gadolinium-ethoxybenzyl-diethylenetriamine pentaacetic acid-enhanced magnetic resonance imaging and contrast-enhanced ultrasound for diagnosing the macroscopic classification of small hepatocellular carcinoma.

PubMed

Kobayashi, Tomoki; Aikata, Hiroshi; Hatooka, Masahiro; Morio, Kei; Morio, Reona; Kan, Hiromi; Fujino, Hatsue; Fukuhara, Takayuki; Masaki, Keiichi; Ohno, Atsushi; Naeshiro, Noriaki; Nakahara, Takashi; Honda, Yohji; Murakami, Eisuke; Kawaoka, Tomokazu; Tsuge, Masataka; Hiramatsu, Akira; Imamura, Michio; Kawakami, Yoshiiku; Hyogo, Hideyuki; Takahashi, Shoichi; Chayama, Kazuaki

2015-11-01

Non-simple nodules in hepatocellular carcinoma (HCC) correlate with poor prognosis. Therefore, we examined the diagnostic ability of gadolinium-ethoxybenzyl-diethylenetriamine pentaacetic acid-enhanced magnetic resonance imaging (EOB-MRI) and contrast-enhanced ultrasound (CEUS) for diagnosing the macroscopic classification of small HCCs. A total of 85 surgically resected nodules (≤30 mm) were analyzed. HCCs were pathologically classified as simple nodular (SN) and non-SN. By evaluating hepatobiliary phase (HBP) of EOB-MRI and Kupffer phase of CEUS, the diagnostic abilities of both modalities to correctly distinguish between SN and non-SN were compared. Forty-six nodules were diagnosed as SN and the remaining 39 nodules as non-SN. The area under the ROC curve (AUROCs, 95% confidence interval) for the diagnosis of non-SN were EOB-MRI, 0.786 (0.682-0.890): CEUS, 0.784 (0.679-0.889), in combination, 0.876 (0.792-0.959). The sensitivity, specificity, and accuracy were 64.1%, 95.7%, and 81.2% in EOB-MRI, 56.4%, 97.8%, and 78.8% in CEUS, and 84.6%, 95.7%, and 90.6% in combination, respectively. High diagnostic ability was obtained when diagnosed in both modalities combined. The sensitivity was especially statistically significant compared to CEUS. Combined diagnosis by EOB-MRI and CEUS can provide high-quality imaging assessment for determining non-SN in small HCCs. • Non-SN has a higher frequency of MVI and intrahepatic metastasis than SN. • Macroscopic classification is useful to choose the treatment strategy for small HCCs. • Diagnostic ability for macroscopic findings of EOB-MRI and CEUS were statistically equal. • The diagnosis of macroscopic findings by individual modality has limitations. • Combined diagnosis of EOB-MRI and CEUS provides high diagnostic ability.

Performance of a Machine Learning Classifier of Knee MRI Reports in Two Large Academic Radiology Practices: A Tool to Estimate Diagnostic Yield.

PubMed

Hassanpour, Saeed; Langlotz, Curtis P; Amrhein, Timothy J; Befera, Nicholas T; Lungren, Matthew P

2017-04-01

The purpose of this study is to evaluate the performance of a natural language processing (NLP) system in classifying a database of free-text knee MRI reports at two separate academic radiology practices. An NLP system that uses terms and patterns in manually classified narrative knee MRI reports was constructed. The NLP system was trained and tested on expert-classified knee MRI reports from two major health care organizations. Radiology reports were modeled in the training set as vectors, and a support vector machine framework was used to train the classifier. A separate test set from each organization was used to evaluate the performance of the system. We evaluated the performance of the system both within and across organizations. Standard evaluation metrics, such as accuracy, precision, recall, and F1 score (i.e., the weighted average of the precision and recall), and their respective 95% CIs were used to measure the efficacy of our classification system. The accuracy for radiology reports that belonged to the model's clinically significant concept classes after training data from the same institution was good, yielding an F1 score greater than 90% (95% CI, 84.6-97.3%). Performance of the classifier on cross-institutional application without institution-specific training data yielded F1 scores of 77.6% (95% CI, 69.5-85.7%) and 90.2% (95% CI, 84.5-95.9%) at the two organizations studied. The results show excellent accuracy by the NLP machine learning classifier in classifying free-text knee MRI reports, supporting the institution-independent reproducibility of knee MRI report classification. Furthermore, the machine learning classifier performed well on free-text knee MRI reports from another institution. These data support the feasibility of multiinstitutional classification of radiologic imaging text reports with a single machine learning classifier without requiring institution-specific training data.

Anatomical and functional assessment of brown adipose tissue by magnetic resonance imaging.

PubMed

Chen, Y Iris; Cypess, Aaron M; Sass, Christina A; Brownell, Anna-Liisa; Jokivarsi, Kimmo T; Kahn, C Ronald; Kwong, Kenneth K

2012-07-01

Brown adipose tissue (BAT) is the primary tissue responsible for nonshivering thermogenesis in mammals. The amount of BAT and its level of activation help regulate the utilization of excessive calories for thermogenesis as opposed to storage in white adipose tissue (WAT) which would lead to weight gain. Over the past several years, BAT activity in vivo has been primarily assessed by positron emission tomography-computed tomography (PET-CT) scan using 2-[18F]-fluoro-2-deoxy-D-glucose (18F-FDG) to measure glucose utilization associated with BAT mitochondrial respiration. In this study, we demonstrate the feasibility of mapping and estimating BAT volume and metabolic function in vivo in rats at a 9.4T magnetic resonance imaging (MRI) scanner using sequences available from clinical MR scanners. Based on the morphological characteristics of BAT, we measured the volume distribution of BAT with MRI sequences that have strong fat-water contrast. We also investigated BAT volume by utilizing spin-echo MRI sequences. The in vivo MRI-estimated BAT volumes were correlated with direct measurement of BAT mass from dissected samples. Using MRI, we also were able to map hemodynamic responses to changes in BAT metabolism induced pharmacologically by β3-adrenergic receptor agonist, CL-316,243 and compare this to BAT activity in response to CL-316,243 assessed by PET 18F-FDG. In conclusion, we demonstrate the feasibility of measuring BAT volume and function in vivo using routine MRI sequences. The MRI measurement of BAT volume is consistent with quantitative measurement of the tissue ex vivo.

Improved Hardware for Higher Spatial Resolution Strain-ENCoded (SENC) Breast MRI for Strain Measurements

PubMed Central

Harouni, Ahmed A.; Hossain, Jakir; Jacobs, Michael A.; Osman, Nael F.

2012-01-01

Introduction Early detection of breast lesions using mammography has resulted in lower mortality-rates. However, some breast lesions are mammography occult and magnetic resonance imaging (MRI) is recommended, but has lower specificity. It is possible to achieve higher specificity by using Strain-ENCoded (SENC) MRI and/or magnetic resonance elastography(MRE). SENC breast MRI can measure the strain properties of breast tissue. Similarly, MRE is used to measure elasticity (i.e., shear stiffness) of different tissue compositions interrogating the tissue mechanical properties. Reports have shown that malignant tumors are 3–13 times stiffer than normal tissue and benign tumors. Methods We have developed a Strain-ENCoded (SENC) breast hardware device capable of periodically compressing the breast, thus allowing for longer scanning time and measuring the strain characteristics of breast tissue. This hardware enabled us to use SENC MRI with high spatial resolution (1×1×5mm3) instead of Fast SENC(FSENC). Simple controls and multiple safety measures were added to ensure accurate, repeatable and safe in-vivo experiments. Results Phantom experiments showed that SENC breast MRI has higher SNR and CNR than FSENC under different scanning resolutions. Finally, the SENC breast device reproducibility measurements resulted in a difference of less than one mm with a 1% strain difference. Conclusion SENC breast MR images have higher SNR and CNR than FSENC images. Thus, combining SENC breast strain measurements with diagnostic breast MRI to differentiate benign from malignant lesions could potentially increase the specificity of diagnosis in the clinical setting. PMID:21440464

Accuracy of magnetic resonance based susceptibility measurements

NASA Astrophysics Data System (ADS)

Erdevig, Hannah E.; Russek, Stephen E.; Carnicka, Slavka; Stupic, Karl F.; Keenan, Kathryn E.

2017-05-01

Magnetic Resonance Imaging (MRI) is increasingly used to map the magnetic susceptibility of tissue to identify cerebral microbleeds associated with traumatic brain injury and pathological iron deposits associated with neurodegenerative diseases such as Parkinson's and Alzheimer's disease. Accurate measurements of susceptibility are important for determining oxygen and iron content in blood vessels and brain tissue for use in noninvasive clinical diagnosis and treatment assessments. Induced magnetic fields with amplitude on the order of 100 nT, can be detected using MRI phase images. The induced field distributions can then be inverted to obtain quantitative susceptibility maps. The focus of this research was to determine the accuracy of MRI-based susceptibility measurements using simple phantom geometries and to compare the susceptibility measurements with magnetometry measurements where SI-traceable standards are available. The susceptibilities of paramagnetic salt solutions in cylindrical containers were measured as a function of orientation relative to the static MRI field. The observed induced fields as a function of orientation of the cylinder were in good agreement with simple models. The MRI susceptibility measurements were compared with SQUID magnetometry using NIST-traceable standards. MRI can accurately measure relative magnetic susceptibilities while SQUID magnetometry measures absolute magnetic susceptibility. Given the accuracy of moment measurements of tissue mimicking samples, and the need to look at small differences in tissue properties, the use of existing NIST standard reference materials to calibrate MRI reference structures is problematic and better reference materials are required.

MRI for transformation of preserved organs and their pathologies into digital formats for medical education and creation of a virtual pathology museum. A pilot study.

PubMed

Venkatesh, S K; Wang, G; Seet, J E; Teo, L L S; Chong, V F H

2013-03-01

To evaluate the feasibility of magnetic resonance imaging (MRI) for the transformation of preserved organs and their disease entities into digital formats for medical education and creation of a virtual museum. MRI of selected 114 pathology specimen jars representing different organs and their diseases was performed using a 3 T MRI machine with two or more MRI sequences including three-dimensional (3D) T1-weighted (T1W), 3D-T2W, 3D-FLAIR (fluid attenuated inversion recovery), fat-water separation (DIXON), and gradient-recalled echo (GRE) sequences. Qualitative assessment of MRI for depiction of disease and internal anatomy was performed. Volume rendering was performed on commercially available workstations. The digital images, 3D models, and photographs of specimens were archived into a workstation serving as a virtual pathology museum. MRI was successfully performed on all specimens. The 3D-T1W and 3D-T2W sequences demonstrated the best contrast between normal and pathological tissues. The digital material is a useful aid for understanding disease by giving insights into internal structural changes not apparent on visual inspection alone. Volume rendering produced vivid 3D models with better contrast between normal tissue and diseased tissue compared to real specimens or their photographs in some cases. The digital library provides good illustration material for radiological-pathological correlation by enhancing pathological anatomy and information on nature and signal characteristics of tissues. In some specimens, the MRI appearance may be different from corresponding organ and disease in vivo due to dead tissue and changes induced by prolonged contact with preservative fluid. MRI of pathology specimens is feasible and provides excellent images for education and creating a virtual pathology museum that can serve as permanent record of digital material for self-directed learning, improving teaching aids, and radiological-pathological correlation. Copyright © 2012 The Royal College of Radiologists. Published by Elsevier Ltd. All rights reserved.

Foundation and methodologies in computer-aided diagnosis systems for breast cancer detection.

PubMed

Jalalian, Afsaneh; Mashohor, Syamsiah; Mahmud, Rozi; Karasfi, Babak; Saripan, M Iqbal B; Ramli, Abdul Rahman B

2017-01-01

Breast cancer is the most prevalent cancer that affects women all over the world. Early detection and treatment of breast cancer could decline the mortality rate. Some issues such as technical reasons, which related to imaging quality and human error, increase misdiagnosis of breast cancer by radiologists. Computer-aided detection systems (CADs) are developed to overcome these restrictions and have been studied in many imaging modalities for breast cancer detection in recent years. The CAD systems improve radiologists' performance in finding and discriminating between the normal and abnormal tissues. These procedures are performed only as a double reader but the absolute decisions are still made by the radiologist. In this study, the recent CAD systems for breast cancer detection on different modalities such as mammography, ultrasound, MRI, and biopsy histopathological images are introduced. The foundation of CAD systems generally consist of four stages: Pre-processing, Segmentation, Feature extraction, and Classification. The approaches which applied to design different stages of CAD system are summarised. Advantages and disadvantages of different segmentation, feature extraction and classification techniques are listed. In addition, the impact of imbalanced datasets in classification outcomes and appropriate methods to solve these issues are discussed. As well as, performance evaluation metrics for various stages of breast cancer detection CAD systems are reviewed.

Foundation and methodologies in computer-aided diagnosis systems for breast cancer detection

PubMed Central

Jalalian, Afsaneh; Mashohor, Syamsiah; Mahmud, Rozi; Karasfi, Babak; Saripan, M. Iqbal B.; Ramli, Abdul Rahman B.

2017-01-01

Breast cancer is the most prevalent cancer that affects women all over the world. Early detection and treatment of breast cancer could decline the mortality rate. Some issues such as technical reasons, which related to imaging quality and human error, increase misdiagnosis of breast cancer by radiologists. Computer-aided detection systems (CADs) are developed to overcome these restrictions and have been studied in many imaging modalities for breast cancer detection in recent years. The CAD systems improve radiologists' performance in finding and discriminating between the normal and abnormal tissues. These procedures are performed only as a double reader but the absolute decisions are still made by the radiologist. In this study, the recent CAD systems for breast cancer detection on different modalities such as mammography, ultrasound, MRI, and biopsy histopathological images are introduced. The foundation of CAD systems generally consist of four stages: Pre-processing, Segmentation, Feature extraction, and Classification. The approaches which applied to design different stages of CAD system are summarised. Advantages and disadvantages of different segmentation, feature extraction and classification techniques are listed. In addition, the impact of imbalanced datasets in classification outcomes and appropriate methods to solve these issues are discussed. As well as, performance evaluation metrics for various stages of breast cancer detection CAD systems are reviewed. PMID:28435432

Differentiating between bipolar and unipolar depression in functional and structural MRI studies.

PubMed

Han, Kyu-Man; De Berardis, Domenico; Fornaro, Michele; Kim, Yong-Ku

2018-03-28

Distinguishing depression in bipolar disorder (BD) from unipolar depression (UD) solely based on clinical clues is difficult, which has led to the exploration of promising neural markers in neuroimaging measures for discriminating between BD depression and UD. In this article, we review structural and functional magnetic resonance imaging (MRI) studies that directly compare UD and BD depression based on neuroimaging modalities including functional MRI studies on regional brain activation or functional connectivity, structural MRI on gray or white matter morphology, and pattern classification analyses using a machine learning approach. Numerous studies have reported distinct functional and structural alterations in emotion- or reward-processing neural circuits between BD depression and UD. Different activation patterns in neural networks including the amygdala, anterior cingulate cortex (ACC), prefrontal cortex (PFC), and striatum during emotion-, reward-, or cognition-related tasks have been reported between BD and UD. A stronger functional connectivity pattern in BD was pronounced in default mode and in frontoparietal networks and brain regions including the PFC, ACC, parietal and temporal regions, and thalamus compared to UD. Gray matter volume differences in the ACC, hippocampus, amygdala, and dorsolateral prefrontal cortex (DLPFC) have been reported between BD and UD, along with a thinner DLPFC in BD compared to UD. BD showed reduced integrity in the anterior part of the corpus callosum and posterior cingulum compared to UD. Several studies performed pattern classification analysis using structural and functional MRI data to distinguish between UD and BD depression using a supervised machine learning approach, which yielded a moderate level of accuracy in classification. Copyright © 2018 Elsevier Inc. All rights reserved.

3D MRI Modeling of Thin and Spatially Complex Soft Tissue Structures without Shrinkage: Lamprey Myosepta as an Example.

PubMed

Wood, Bradley M; Jia, Guang; Carmichael, Owen; McKlveen, Kevin; Homberger, Dominique G

2018-05-12

3D imaging techniques enable the non-destructive analysis and modeling of complex structures. Among these, MRI exhibits good soft tissue contrast, but is currently less commonly used for non-clinical research than x-ray CT, even though the latter requires contrast-staining that shrinks and distorts soft tissues. When the objective is the creation of a realistic and complete 3D model of soft tissue structures, MRI data are more demanding to acquire and visualize and require extensive post-processing because they comprise non-cubic voxels with dimensions that represent a trade-off between tissue contrast and image resolution. Therefore, thin soft tissue structures with complex spatial configurations are not always visible in a single MRI dataset, so that standard segmentation techniques are not sufficient for their complete visualization. By using the example of the thin and spatially complex connective tissue myosepta in lampreys, we developed a workflow protocol for the selection of the appropriate parameters for the acquisition of MRI data and for the visualization and 3D modeling of soft tissue structures. This protocol includes a novel recursive segmentation technique for supplementing missing data in one dataset with data from another dataset to produce realistic and complete 3D models. Such 3D models are needed for the modeling of dynamic processes, such as the biomechanics of fish locomotion. However, our methodology is applicable to the visualization of any thin soft tissue structures with complex spatial configurations, such as fasciae, aponeuroses, and small blood vessels and nerves, for clinical research and the further exploration of tensegrity. This article is protected by copyright. All rights reserved. © 2018 Wiley Periodicals, Inc.

Decoding of Ankle Flexion and Extension from Cortical Current Sources Estimated from Non-invasive Brain Activity Recording Methods.

PubMed

Mejia Tobar, Alejandra; Hyoudou, Rikiya; Kita, Kahori; Nakamura, Tatsuhiro; Kambara, Hiroyuki; Ogata, Yousuke; Hanakawa, Takashi; Koike, Yasuharu; Yoshimura, Natsue

2017-01-01

The classification of ankle movements from non-invasive brain recordings can be applied to a brain-computer interface (BCI) to control exoskeletons, prosthesis, and functional electrical stimulators for the benefit of patients with walking impairments. In this research, ankle flexion and extension tasks at two force levels in both legs, were classified from cortical current sources estimated by a hierarchical variational Bayesian method, using electroencephalography (EEG) and functional magnetic resonance imaging (fMRI) recordings. The hierarchical prior for the current source estimation from EEG was obtained from activated brain areas and their intensities from an fMRI group (second-level) analysis. The fMRI group analysis was performed on regions of interest defined over the primary motor cortex, the supplementary motor area, and the somatosensory area, which are well-known to contribute to movement control. A sparse logistic regression method was applied for a nine-class classification (eight active tasks and a resting control task) obtaining a mean accuracy of 65.64% for time series of current sources, estimated from the EEG and the fMRI signals using a variational Bayesian method, and a mean accuracy of 22.19% for the classification of the pre-processed of EEG sensor signals, with a chance level of 11.11%. The higher classification accuracy of current sources, when compared to EEG classification accuracy, was attributed to the high number of sources and the different signal patterns obtained in the same vertex for different motor tasks. Since the inverse filter estimation for current sources can be done offline with the present method, the present method is applicable to real-time BCIs. Finally, due to the highly enhanced spatial distribution of current sources over the brain cortex, this method has the potential to identify activation patterns to design BCIs for the control of an affected limb in patients with stroke, or BCIs from motor imagery in patients with spinal cord injury.

Multiparametric MRI characterization and prediction in autism spectrum disorder using graph theory and machine learning.

PubMed

Zhou, Yongxia; Yu, Fang; Duong, Timothy

2014-01-01

This study employed graph theory and machine learning analysis of multiparametric MRI data to improve characterization and prediction in autism spectrum disorders (ASD). Data from 127 children with ASD (13.5±6.0 years) and 153 age- and gender-matched typically developing children (14.5±5.7 years) were selected from the multi-center Functional Connectome Project. Regional gray matter volume and cortical thickness increased, whereas white matter volume decreased in ASD compared to controls. Small-world network analysis of quantitative MRI data demonstrated decreased global efficiency based on gray matter cortical thickness but not with functional connectivity MRI (fcMRI) or volumetry. An integrative model of 22 quantitative imaging features was used for classification and prediction of phenotypic features that included the autism diagnostic observation schedule, the revised autism diagnostic interview, and intelligence quotient scores. Among the 22 imaging features, four (caudate volume, caudate-cortical functional connectivity and inferior frontal gyrus functional connectivity) were found to be highly informative, markedly improving classification and prediction accuracy when compared with the single imaging features. This approach could potentially serve as a biomarker in prognosis, diagnosis, and monitoring disease progression.

Predictive sparse modeling of fMRI data for improved classification, regression, and visualization using the k-support norm.

PubMed

Belilovsky, Eugene; Gkirtzou, Katerina; Misyrlis, Michail; Konova, Anna B; Honorio, Jean; Alia-Klein, Nelly; Goldstein, Rita Z; Samaras, Dimitris; Blaschko, Matthew B

2015-12-01

We explore various sparse regularization techniques for analyzing fMRI data, such as the ℓ1 norm (often called LASSO in the context of a squared loss function), elastic net, and the recently introduced k-support norm. Employing sparsity regularization allows us to handle the curse of dimensionality, a problem commonly found in fMRI analysis. In this work we consider sparse regularization in both the regression and classification settings. We perform experiments on fMRI scans from cocaine-addicted as well as healthy control subjects. We show that in many cases, use of the k-support norm leads to better predictive performance, solution stability, and interpretability as compared to other standard approaches. We additionally analyze the advantages of using the absolute loss function versus the standard squared loss which leads to significantly better predictive performance for the regularization methods tested in almost all cases. Our results support the use of the k-support norm for fMRI analysis and on the clinical side, the generalizability of the I-RISA model of cocaine addiction. Copyright © 2015 Elsevier Ltd. All rights reserved.

Common component classification: what can we learn from machine learning?

PubMed

Anderson, Ariana; Labus, Jennifer S; Vianna, Eduardo P; Mayer, Emeran A; Cohen, Mark S

2011-05-15

Machine learning methods have been applied to classifying fMRI scans by studying locations in the brain that exhibit temporal intensity variation between groups, frequently reporting classification accuracy of 90% or better. Although empirical results are quite favorable, one might doubt the ability of classification methods to withstand changes in task ordering and the reproducibility of activation patterns over runs, and question how much of the classification machines' power is due to artifactual noise versus genuine neurological signal. To examine the true strength and power of machine learning classifiers we create and then deconstruct a classifier to examine its sensitivity to physiological noise, task reordering, and across-scan classification ability. The models are trained and tested both within and across runs to assess stability and reproducibility across conditions. We demonstrate the use of independent components analysis for both feature extraction and artifact removal and show that removal of such artifacts can reduce predictive accuracy even when data has been cleaned in the preprocessing stages. We demonstrate how mistakes in the feature selection process can cause the cross-validation error seen in publication to be a biased estimate of the testing error seen in practice and measure this bias by purposefully making flawed models. We discuss other ways to introduce bias and the statistical assumptions lying behind the data and model themselves. Finally we discuss the complications in drawing inference from the smaller sample sizes typically seen in fMRI studies, the effects of small or unbalanced samples on the Type 1 and Type 2 error rates, and how publication bias can give a false confidence of the power of such methods. Collectively this work identifies challenges specific to fMRI classification and methods affecting the stability of models. Copyright © 2010 Elsevier Inc. All rights reserved.

Noninvasive Assessment of Tissue Heating During Cardiac Radiofrequency Ablation Using MRI Thermography

PubMed Central

Kolandaivelu, Aravindan; Zviman, Menekhem M.; Castro, Valeria; Lardo, Albert C.; Berger, Ronald D.; Halperin, Henry R.

2010-01-01

Background Failure to achieve properly localized, permanent tissue destruction is a common cause of arrhythmia recurrence after cardiac ablation. Current methods of assessing lesion size and location during cardiac radiofrequency ablation are unreliable or not suited for repeated assessment during the procedure. MRI thermography could be used to delineate permanent ablation lesions because tissue heating above 50°C is the cause of permanent tissue destruction during radiofrequency ablation. However, image artifacts caused by cardiac motion, the ablation electrode, and radiofrequency ablation currently pose a challenge to MRI thermography in the heart. In the current study, we sought to demonstrate the feasibility of MRI thermography during cardiac ablation. Methods and Results An MRI-compatible electrophysiology catheter and filtered radiofrequency ablation system was used to perform ablation in the left ventricle of 6 mongrel dogs in a 1.5-T MRI system. Fast gradient-echo imaging was performed before and during radiofrequency ablation, and thermography images were derived from the preheating and postheating images. Lesion extent by thermography was within 20% of the gross pathology lesion. Conclusions MR thermography appears to be a promising technique for monitoring lesion formation and may allow for more accurate placement and titration of ablation, possibly reducing arrhythmia recurrences. PMID:20657028

Dental MRI using wireless intraoral coils

NASA Astrophysics Data System (ADS)

Ludwig, Ute; Eisenbeiss, Anne-Katrin; Scheifele, Christian; Nelson, Katja; Bock, Michael; Hennig, Jürgen; von Elverfeldt, Dominik; Herdt, Olga; Flügge, Tabea; Hövener, Jan-Bernd

2016-03-01

Currently, the gold standard for dental imaging is projection radiography or cone-beam computed tomography (CBCT). These methods are fast and cost-efficient, but exhibit poor soft tissue contrast and expose the patient to ionizing radiation (X-rays). The need for an alternative imaging modality e.g. for soft tissue management has stimulated a rising interest in dental magnetic resonance imaging (MRI) which provides superior soft tissue contrast. Compared to X-ray imaging, however, so far the spatial resolution of MRI is lower and the scan time is longer. In this contribution, we describe wireless, inductively-coupled intraoral coils whose local sensitivity enables high resolution MRI of dental soft tissue. In comparison to CBCT, a similar image quality with complementary contrast was obtained ex vivo. In-vivo, a voxel size of the order of 250•250•500 μm3 was achieved in 4 min only. Compared to dental MRI acquired with clinical equipment, the quality of the images was superior in the sensitive volume of the coils and is expected to improve the planning of interventions and monitoring thereafter. This method may enable a more accurate dental diagnosis and avoid unnecessary interventions, improving patient welfare and bringing MRI a step closer to becoming a radiation-free alternative for dental imaging.

TU-G-201-02: An MRI Simulator From Proposal to Operation

DOE Office of Scientific and Technical Information (OSTI.GOV)

Cao, Y.

2015-06-15

This session will update therapeutic physicists on technological advancements and radiation oncology features of commercial CT, MRI, and PET/CT imaging systems. Also described are physicists’ roles in every stage of equipment selection, purchasing, and operation, including defining specifications, evaluating vendors, making recommendations, and optimal and safe use of imaging equipment in radiation oncology environment. The first presentation defines important terminology of CT and PET/CT followed by a review of latest innovations, such as metal artifact reduction, statistical iterative reconstruction, radiation dose management, tissue classification by dual energy CT and spectral CT, improvement in spatial resolution and sensitivity in PET, andmore » potentials of PET/MR. We will also discuss important technical specifications and items in CT and PET/CT purchasing quotes and their impacts. The second presentation will focus on key components in the request for proposal for a MRI simulator and how to evaluate vendor proposals. MRI safety issues in radiation Oncology, including MRI scanner Zones (4-zone design), will be discussed. Basic MR terminologies, important functionalities, and advanced features, which are relevant to radiation therapy, will be discussed. In the third presentation, justification of imaging systems for radiation oncology, considerations in room design and construction in a RO department, shared use with diagnostic radiology, staffing needs and training, clinical/research use cases and implementation, will be discussed. The emphasis will be on understanding and bridging the differences between diagnostic and radiation oncology installations, building consensus amongst stakeholders for purchase and use, and integrating imaging technologies into the radiation oncology environment. Learning Objectives: Learn the latest innovations of major imaging systems relevant to radiation therapy Be able to describe important technical specifications of CT, MRI, and PET/CT Understand the process of budget request, equipment justification, comparisons of technical specifications, site visits, vendor selection, and contract development.« less

White Paper: Interventional MRI: Current Status and Potential for Development Considering Economic Perspectives, Part 2: Liver and Other Applications in Oncology.

PubMed

Barkhausen, Jörg; Kahn, Thomas; Krombach, Gabriele A; Kuhl, Christiane K; Lotz, Joachim; Maintz, David; Ricke, Jens; Schönberg, Stefan O; Vogl, Thomas J; Wacker, Frank K

2017-11-01

Background  MRI is attractive for guiding and monitoring interventional procedures due to its high intrinsic soft tissue contrast and the possibility to measure flow and cardiac function. Methods  Technical solutions have been developed for all procedural steps including imaging guidance, MR-safe catheters and instruments and patient monitoring. This has led to widening of the clinical applications. Interventional MRI is becoming increasingly important for the treatment of patients suffering from malignant diseases. The detectability of masses and consequently their accessibility for biopsy is higher, compared to other modalities, due to the high intrinsic soft tissue contrast of MRI. Temperature-dependent sequences allow for minimally invasive and tissue-sparing ablation (A-0 ablation). Conclusion  Interventional MRI has become established in the clinical routine for a variety of indications, including biopsies and tumor ablation. Since the economic requirement of covering costs by reimbursement is met and interventional MRI decreases the mortality and morbidity of interventional procedures, broader application of interventional MRI can be expected in the clinical routine in the future. Key points   · Particularly for the treatment of oncological patients, interventional MRI is superior to other methods with respect to minimal invasiveness and tissue protection due to the ability to exactly determine tumor borders and to visualize and control the size of the ablation area on the basis of MR temperature measurement.. · Due to the better visualization of targets and the effects of ablation in tissue, interventional MRI can lower the mortality and morbidity associated with these interventions for many indications.. · The complex comparison of costs and reimbursement shows that this application can be performed in a cost-covering manner and broader application can be expected in the future.. Citation Format · Barkhausen J, Kahn T, Krombach GA et al. White Paper: Interventional MRI: Current Status and Potential for Development Considering Economic Perspectives, Part 2: Liver and Other Applications in Oncology. Fortschr Röntgenstr 2017; 189: 1047 - 1054. © Georg Thieme Verlag KG Stuttgart · New York.

Cupping artifact correction and automated classification for high-resolution dedicated breast CT images.

PubMed

Yang, Xiaofeng; Wu, Shengyong; Sechopoulos, Ioannis; Fei, Baowei

2012-10-01

To develop and test an automated algorithm to classify the different tissues present in dedicated breast CT images. The original CT images are first corrected to overcome cupping artifacts, and then a multiscale bilateral filter is used to reduce noise while keeping edge information on the images. As skin and glandular tissues have similar CT values on breast CT images, morphologic processing is used to identify the skin mask based on its position information. A modified fuzzy C-means (FCM) classification method is then used to classify breast tissue as fat and glandular tissue. By combining the results of the skin mask with the FCM, the breast tissue is classified as skin, fat, and glandular tissue. To evaluate the authors' classification method, the authors use Dice overlap ratios to compare the results of the automated classification to those obtained by manual segmentation on eight patient images. The correction method was able to correct the cupping artifacts and improve the quality of the breast CT images. For glandular tissue, the overlap ratios between the authors' automatic classification and manual segmentation were 91.6% ± 2.0%. A cupping artifact correction method and an automatic classification method were applied and evaluated for high-resolution dedicated breast CT images. Breast tissue classification can provide quantitative measurements regarding breast composition, density, and tissue distribution.

Cupping artifact correction and automated classification for high-resolution dedicated breast CT images

PubMed Central

Yang, Xiaofeng; Wu, Shengyong; Sechopoulos, Ioannis; Fei, Baowei

2012-01-01

Purpose: To develop and test an automated algorithm to classify the different tissues present in dedicated breast CT images. Methods: The original CT images are first corrected to overcome cupping artifacts, and then a multiscale bilateral filter is used to reduce noise while keeping edge information on the images. As skin and glandular tissues have similar CT values on breast CT images, morphologic processing is used to identify the skin mask based on its position information. A modified fuzzy C-means (FCM) classification method is then used to classify breast tissue as fat and glandular tissue. By combining the results of the skin mask with the FCM, the breast tissue is classified as skin, fat, and glandular tissue. To evaluate the authors’ classification method, the authors use Dice overlap ratios to compare the results of the automated classification to those obtained by manual segmentation on eight patient images. Results: The correction method was able to correct the cupping artifacts and improve the quality of the breast CT images. For glandular tissue, the overlap ratios between the authors’ automatic classification and manual segmentation were 91.6% ± 2.0%. Conclusions: A cupping artifact correction method and an automatic classification method were applied and evaluated for high-resolution dedicated breast CT images. Breast tissue classification can provide quantitative measurements regarding breast composition, density, and tissue distribution. PMID:23039675

Registration of 3D ultrasound computer tomography and MRI for evaluation of tissue correspondences

NASA Astrophysics Data System (ADS)

Hopp, T.; Dapp, R.; Zapf, M.; Kretzek, E.; Gemmeke, H.; Ruiter, N. V.

2015-03-01

3D Ultrasound Computer Tomography (USCT) is a new imaging method for breast cancer diagnosis. In the current state of development it is essential to correlate USCT with a known imaging modality like MRI to evaluate how different tissue types are depicted. Due to different imaging conditions, e.g. with the breast subject to buoyancy in USCT, a direct correlation is demanding. We present a 3D image registration method to reduce positioning differences and allow direct side-by-side comparison of USCT and MRI volumes. It is based on a two-step approach including a buoyancy simulation with a biomechanical model and free form deformations using cubic B-Splines for a surface refinement. Simulation parameters are optimized patient-specifically in a simulated annealing scheme. The method was evaluated with in-vivo datasets resulting in an average registration error below 5mm. Correlating tissue structures can thereby be located in the same or nearby slices in both modalities and three-dimensional non-linear deformations due to the buoyancy are reduced. Image fusion of MRI volumes and USCT sound speed volumes was performed for intuitive display. By applying the registration to data of our first in-vivo study with the KIT 3D USCT, we could correlate several tissue structures in MRI and USCT images and learn how connective tissue, carcinomas and breast implants observed in the MRI are depicted in the USCT imaging modes.

MR Imaging Based Treatment Planning for Radiotherapy of Prostate Cancer

DTIC Science & Technology

2008-02-01

Radiotherapy, MR-based treatment planning, dosimetry, Monte Carlo dose verification, Prostate Cancer, MRI -based DRRs 16. SECURITY CLASSIFICATION...AcQPlan system Version 5 was used for the study , which is capable of performing dose calculation on both CT and MRI . A four field 3D conformal planning...prostate motion studies for 3DCRT and IMRT of prostate cancer; (2) to investigate and improve the accuracy of MRI -based treatment planning dose calculation

Whole-brain spectroscopic MRI biomarkers identify infiltrating margins in glioblastoma patients

PubMed Central

Cordova, James S.; Shu, Hui-Kuo G.; Liang, Zhongxing; Gurbani, Saumya S.; Cooper, Lee A. D.; Holder, Chad A.; Olson, Jeffrey J.; Kairdolf, Brad; Schreibmann, Eduard; Neill, Stewart G.; Hadjipanayis, Constantinos G.; Shim, Hyunsuk

2016-01-01

Background The standard of care for glioblastoma (GBM) is maximal safe resection followed by radiation therapy with chemotherapy. Currently, contrast-enhanced MRI is used to define primary treatment volumes for surgery and radiation therapy. However, enhancement does not identify the tumor entirely, resulting in limited local control. Proton spectroscopic MRI (sMRI), a method reporting endogenous metabolism, may better define the tumor margin. Here, we develop a whole-brain sMRI pipeline and validate sMRI metrics with quantitative measures of tumor infiltration. Methods Whole-brain sMRI metabolite maps were coregistered with surgical planning MRI and imported into a neuronavigation system to guide tissue sampling in GBM patients receiving 5-aminolevulinic acid fluorescence-guided surgery. Samples were collected from regions with metabolic abnormalities in a biopsy-like fashion before bulk resection. Tissue fluorescence was measured ex vivo using a hand-held spectrometer. Tissue samples were immunostained for Sox2 and analyzed to quantify the density of staining cells using a novel digital pathology image analysis tool. Correlations among sMRI markers, Sox2 density, and ex vivo fluorescence were evaluated. Results Spectroscopic MRI biomarkers exhibit significant correlations with Sox2-positive cell density and ex vivo fluorescence. The choline to N-acetylaspartate ratio showed significant associations with each quantitative marker (Pearson's ρ = 0.82, P < .001 and ρ = 0.36, P < .0001, respectively). Clinically, sMRI metabolic abnormalities predated contrast enhancement at sites of tumor recurrence and exhibited an inverse relationship with progression-free survival. Conclusions As it identifies tumor infiltration and regions at high risk for recurrence, sMRI could complement conventional MRI to improve local control in GBM patients. PMID:26984746

Biomechanical factors and physical examination findings in osteoarthritis of the knee: associations with tissue abnormalities assessed by conventional radiography and high-resolution 3.0 Tesla magnetic resonance imaging.

PubMed

Knoop, Jesper; Dekker, Joost; Klein, Jan-Paul; van der Leeden, Marike; van der Esch, Martin; Reiding, Dick; Voorneman, Ramon E; Gerritsen, Martijn; Roorda, Leo D; Steultjens, Martijn P M; Lems, Willem F

2012-10-05

We aimed to explore the associations between knee osteoarthritis (OA)-related tissue abnormalities assessed by conventional radiography (CR) and by high-resolution 3.0 Tesla magnetic resonance imaging (MRI), as well as biomechanical factors and findings from physical examination in patients with knee OA. This was an explorative cross-sectional study of 105 patients with knee OA. Index knees were imaged using CR and MRI. Multiple features from CR and MRI (cartilage, osteophytes, bone marrow lesions, effusion and synovitis) were related to biomechanical factors (quadriceps and hamstrings muscle strength, proprioceptive accuracy and varus-valgus laxity) and physical examination findings (bony tenderness, crepitus, bony enlargement and palpable warmth), using multivariable regression analyses. Quadriceps weakness was associated with cartilage integrity, effusion, synovitis (all detected by MRI) and CR-detected joint space narrowing. Knee joint laxity was associated with MRI-detected cartilage integrity, CR-detected joint space narrowing and osteophyte formation. Multiple tissue abnormalities including cartilage integrity, osteophytes and effusion, but only those detected by MRI, were found to be associated with physical examination findings such as crepitus. We observed clinically relevant findings, including a significant association between quadriceps weakness and both effusion and synovitis, detected by MRI. Inflammation was detected in over one-third of the participants, emphasizing the inflammatory component of OA and a possible important role for anti-inflammatory therapies in knee OA. In general, OA-related tissue abnormalities of the knee, even those detected by MRI, were found to be discordant with biomechanical and physical examination features.

MULTIMODAL CLASSIFICATION OF DEMENTIA USING FUNCTIONAL DATA, ANATOMICAL FEATURES AND 3D INVARIANT SHAPE DESCRIPTORS

PubMed Central

Mikhno, Arthur; Nuevo, Pablo Martinez; Devanand, Davangere P.; Parsey, Ramin V.; Laine, Andrew F.

2013-01-01

Multimodality classification of Alzheimer’s disease (AD) and its prodromal stage, Mild Cognitive Impairment (MCI), is of interest to the medical community. We improve on prior classification frameworks by incorporating multiple features from MRI and PET data obtained with multiple radioligands, fluorodeoxyglucose (FDG) and Pittsburg compound B (PIB). We also introduce a new MRI feature, invariant shape descriptors based on 3D Zernike moments applied to the hippocampus region. Classification performance is evaluated on data from 17 healthy controls (CTR), 22 MCI, and 17 AD subjects. Zernike significantly outperforms volume, accuracy (Zernike to volume): CTR/AD (90.7% to 71.6%), CTR/MCI (76.2% to 60.0%), MCI/AD (84.3% to 65.5%). Zernike also provides comparable and complementary performance to PET. Optimal accuracy is achieved when Zernike and PET features are combined (accuracy, specificity, sensitivity), CTR/AD (98.8%, 99.5%, 98.1%), CTR/MCI (84.3%, 82.9%, 85.9%) and MCI/AD (93.3%, 93.6%, 93.3%). PMID:24576927

MULTIMODAL CLASSIFICATION OF DEMENTIA USING FUNCTIONAL DATA, ANATOMICAL FEATURES AND 3D INVARIANT SHAPE DESCRIPTORS.

PubMed

Mikhno, Arthur; Nuevo, Pablo Martinez; Devanand, Davangere P; Parsey, Ramin V; Laine, Andrew F

2012-01-01

Multimodality classification of Alzheimer's disease (AD) and its prodromal stage, Mild Cognitive Impairment (MCI), is of interest to the medical community. We improve on prior classification frameworks by incorporating multiple features from MRI and PET data obtained with multiple radioligands, fluorodeoxyglucose (FDG) and Pittsburg compound B (PIB). We also introduce a new MRI feature, invariant shape descriptors based on 3D Zernike moments applied to the hippocampus region. Classification performance is evaluated on data from 17 healthy controls (CTR), 22 MCI, and 17 AD subjects. Zernike significantly outperforms volume, accuracy (Zernike to volume): CTR/AD (90.7% to 71.6%), CTR/MCI (76.2% to 60.0%), MCI/AD (84.3% to 65.5%). Zernike also provides comparable and complementary performance to PET. Optimal accuracy is achieved when Zernike and PET features are combined (accuracy, specificity, sensitivity), CTR/AD (98.8%, 99.5%, 98.1%), CTR/MCI (84.3%, 82.9%, 85.9%) and MCI/AD (93.3%, 93.6%, 93.3%).

Precise Inference and Characterization of Structural Organization (PICASO) of tissue from molecular diffusion

PubMed Central

Ning, Lipeng; Özarslan, Evren; Westin, Carl-Fredrik; Rathi, Yogesh

2017-01-01

Inferring the microstructure of complex media from the diffusive motion of molecules is a challenging problem in diffusion physics. In this paper, we introduce a novel representation of diffusion MRI (dMRI) signal from tissue with spatially-varying diffusivity using a diffusion disturbance function. This disturbance function contains information about the (intra-voxel) spatial fluctuations in diffusivity due to restrictions, hindrances and tissue heterogeneity of the underlying tissue substrate. We derive the short- and long-range disturbance coefficients from this disturbance function to characterize the tissue structure and organization. Moreover, we provide an exact relation between the disturbance coefficients and the time-varying moments of the diffusion propagator, as well as their relation to specific tissue microstructural information such as the intra-axonal volume fraction and the apparent axon radius. The proposed approach is quite general and can model dMRI signal for any type of gradient sequence (rectangular, oscillating, etc.) without using the Gaussian phase approximation. The relevance of the proposed PICASO model is explored using Monte-Carlo simulations and in-vivo dMRI data. The results show that the estimated disturbance coefficients can distinguish different types of microstructural organization of axons. PMID:27751940

Precise Inference and Characterization of Structural Organization (PICASO) of tissue from molecular diffusion.

PubMed

Ning, Lipeng; Özarslan, Evren; Westin, Carl-Fredrik; Rathi, Yogesh

2017-02-01

Inferring the microstructure of complex media from the diffusive motion of molecules is a challenging problem in diffusion physics. In this paper, we introduce a novel representation of diffusion MRI (dMRI) signal from tissue with spatially-varying diffusivity using a diffusion disturbance function. This disturbance function contains information about the (intra-voxel) spatial fluctuations in diffusivity due to restrictions, hindrances and tissue heterogeneity of the underlying tissue substrate. We derive the short- and long-range disturbance coefficients from this disturbance function to characterize the tissue structure and organization. Moreover, we provide an exact relation between the disturbance coefficients and the time-varying moments of the diffusion propagator, as well as their relation to specific tissue microstructural information such as the intra-axonal volume fraction and the apparent axon radius. The proposed approach is quite general and can model dMRI signal for any type of gradient sequence (rectangular, oscillating, etc.) without using the Gaussian phase approximation. The relevance of the proposed PICASO model is explored using Monte-Carlo simulations and in-vivo dMRI data. The results show that the estimated disturbance coefficients can distinguish different types of microstructural organization of axons. Copyright © 2016 Elsevier Inc. All rights reserved.

Custom fit 3D-printed brain holders for comparison of histology with MRI in marmosets.

PubMed

Guy, Joseph R; Sati, Pascal; Leibovitch, Emily; Jacobson, Steven; Silva, Afonso C; Reich, Daniel S

2016-01-15

MRI has the advantage of sampling large areas of tissue and locating areas of interest in 3D space in both living and ex vivo systems, whereas histology has the ability to examine thin slices of ex vivo tissue with high detail and specificity. Although both are valuable tools, it is currently difficult to make high-precision comparisons between MRI and histology due to large differences inherent to the techniques. A method combining the advantages would be an asset to understanding the pathological correlates of MRI. 3D-printed brain holders were used to maintain marmoset brains in the same orientation during acquisition of ex vivo MRI and pathologic cutting of the tissue. The results of maintaining this same orientation show that sub-millimeter, discrete neuropathological features in marmoset brain consistently share size, shape, and location between histology and ex vivo MRI, which facilitates comparison with serial imaging acquired in vivo. Existing methods use computational approaches sensitive to data input in order to warp histologic images to match large-scale features on MRI, but the new method requires no warping of images, due to a preregistration accomplished in the technique, and is insensitive to data formatting and artifacts in both MRI and histology. The simple method of using 3D-printed brain holders to match brain orientation during pathologic sectioning and MRI acquisition enables rapid and precise comparison of small features seen on MRI to their underlying histology. Published by Elsevier B.V.

Correlations between quantitative fat–water magnetic resonance imaging and computed tomography in human subcutaneous white adipose tissue

PubMed Central

Gifford, Aliya; Walker, Ronald C.; Towse, Theodore F.; Brian Welch, E.

2015-01-01

Abstract. Beyond estimation of depot volumes, quantitative analysis of adipose tissue properties could improve understanding of how adipose tissue correlates with metabolic risk factors. We investigated whether the fat signal fraction (FSF) derived from quantitative fat–water magnetic resonance imaging (MRI) scans at 3.0 T correlates to CT Hounsfield units (HU) of the same tissue. These measures were acquired in the subcutaneous white adipose tissue (WAT) at the umbilical level of 21 healthy adult subjects. A moderate correlation exists between MRI- and CT-derived WAT values for all subjects, R2=0.54, p<0.0001, with a slope of −2.6, (95% CI [−3.3,−1.8]), indicating that a decrease of 1 HU equals a mean increase of 0.38% FSF. We demonstrate that FSF estimates obtained using quantitative fat–water MRI techniques correlate with CT HU values in subcutaneous WAT, and therefore, MRI-based FSF could be used as an alternative to CT HU for assessing metabolic risk factors. PMID:26702407

Quantitative DWI implemented after DCE-MRI yields increased specificity for BI-RADS 3 and 4 breast lesions.

PubMed

Dijkstra, Hildebrand; Dorrius, Monique D; Wielema, Mirjam; Pijnappel, Ruud M; Oudkerk, Matthijs; Sijens, Paul E

2016-12-01

To assess if specificity can be increased when semiautomated breast lesion analysis of quantitative diffusion-weighted imaging (DWI) is implemented after dynamic contrast-enhanced (DCE-) magnetic resonance imaging (MRI) in the workup of BI-RADS 3 and 4 breast lesions larger than 1 cm. In all, 120 consecutive patients (mean-age, 48 years; age range, 23-75 years) with 139 breast lesions (≥1 cm) were examined (2010-2014) with 1.5T DCE-MRI and DWI (b = 0, 50, 200, 500, 800, 1000 s/mm 2 ) and the BI-RADS classification and histopathology were obtained. For each lesion malignancy was excluded using voxelwise semiautomated breast lesion analysis based on previously defined thresholds for the apparent diffusion coefficient (ADC) and the three intravoxel incoherent motion (IVIM) parameters: molecular diffusion (D slow ), microperfusion (D fast ), and the fraction of D fast (f fast ). The sensitivity (Se), specificity (Sp), and negative predictive value (NPV) based on only IVIM parameters combined in parallel (D slow , D fast , and f fast ), or the ADC or the BI-RADS classification by DCE-MRI were compared. Subsequently, the Se, Sp, and NPV of the combination of the BI-RADS classification by DCE-MRI followed by the IVIM parameters in parallel (or the ADC) were compared. In all, 23 of 139 breast lesions were benign. Se and Sp of DCE-MRI was 100% and 30.4% (NPV = 100%). Se and Sp of IVIM parameters in parallel were 92.2% and 52.2% (NPV = 57.1%) and for the ADC 95.7% and 17.4%, respectively (NPV = 44.4%). In all, 26 of 139 lesions were classified as BI-RADS 3 (n = 7) or BI-RADS 4 (n = 19). DCE-MRI combined with ADC (Se = 99.1%, Sp = 34.8%) or IVIM (Se = 99.1%, Sp = 56.5%) did significantly improve (P = 0.016) Sp of DCE-MRI alone for workup of BI-RADS 3 and 4 lesions (NPV = 92.9%). Quantitative DWI has a lower NPV compared to DCE-MRI for evaluation of breast lesions and may therefore not be able to replace DCE-MRI; when implemented after DCE-MRI as problem solver for BI-RADS 3 and 4 lesions, the combined specificity improves significantly. J. Magn. Reson. Imaging 2016;44:1642-1649. © 2016 International Society for Magnetic Resonance in Medicine.

Non-invasive imaging of transplanted human neural stem cells and ECM scaffold remodeling in the stroke-damaged rat brain by 19F- and diffusion-MRI

PubMed Central

Bible, Ellen; Dell’Acqua, Flavio; Solanky, Bhavana; Balducci, Anthony; Crapo, Peter; Badylak, Stephen F.; Ahrens, Eric T.; Modo, Michel

2012-01-01

Transplantation of human neural stem cells (hNSCs) is emerging as a viable treatment for stroke related brain injury. However, intraparenchymal grafts do not regenerate lost tissue, but rather integrate into the host parenchyma without significantly affecting the lesion cavity. Providing a structural support for the delivered cells appears important for cell based therapeutic approaches. The non-invasive monitoring of therapeutic methods would provide valuable information regarding therapeutic strategies but remains a challenge. Labeling transplanted cells with metal-based 1H-magnetic resonance imaging (MRI) contrast agents affects the visualization of the lesion cavity. Herein, we demonstrate that a 19F-MRI contrast agent can adequately monitor the distribution of transplanted cells, whilst allowing an evaluation of the lesion cavity and the formation of new tissue on 1H-MRI scans. Twenty percent of cells labeled with the 19F-agent were of host origin, potentially reflecting the re-uptake of label from dead transplanted cells. Both T2- and diffusion-weighted MRI scans indicated that transplantation of hNSCs suspended in a gel form of a xenogeneic extracellular matrix (ECM) bioscaffold resulted in uniformly distributed cells throughout the lesion cavity. However, diffusion MRI indicated that the injected materials did not yet establish diffusion barriers (i.e. cellular network, fiber tracts) normally found within striatal tissue. The ECM bioscaffold therefore provides an important support to hNSCs for the creation of de novo tissue and multi-nuclei MRI represents an adept method for the visualization of some aspects of this process. However, significant developments of both the transplantation paradigm, as well as regenerative imaging, are required to successfully create new tissue in the lesion cavity and to monitor this process non-invasively. PMID:22244696

Simulation of brain tumors in MR images for evaluation of segmentation efficacy.

PubMed

Prastawa, Marcel; Bullitt, Elizabeth; Gerig, Guido

2009-04-01

Obtaining validation data and comparison metrics for segmentation of magnetic resonance images (MRI) are difficult tasks due to the lack of reliable ground truth. This problem is even more evident for images presenting pathology, which can both alter tissue appearance through infiltration and cause geometric distortions. Systems for generating synthetic images with user-defined degradation by noise and intensity inhomogeneity offer the possibility for testing and comparison of segmentation methods. Such systems do not yet offer simulation of sufficiently realistic looking pathology. This paper presents a system that combines physical and statistical modeling to generate synthetic multi-modal 3D brain MRI with tumor and edema, along with the underlying anatomical ground truth, Main emphasis is placed on simulation of the major effects known for tumor MRI, such as contrast enhancement, local distortion of healthy tissue, infiltrating edema adjacent to tumors, destruction and deformation of fiber tracts, and multi-modal MRI contrast of healthy tissue and pathology. The new method synthesizes pathology in multi-modal MRI and diffusion tensor imaging (DTI) by simulating mass effect, warping and destruction of white matter fibers, and infiltration of brain tissues by tumor cells. We generate synthetic contrast enhanced MR images by simulating the accumulation of contrast agent within the brain. The appearance of the the brain tissue and tumor in MRI is simulated by synthesizing texture images from real MR images. The proposed method is able to generate synthetic ground truth and synthesized MR images with tumor and edema that exhibit comparable segmentation challenges to real tumor MRI. Such image data sets will find use in segmentation reliability studies, comparison and validation of different segmentation methods, training and teaching, or even in evaluating standards for tumor size like the RECIST criteria (response evaluation criteria in solid tumors).

MRI differentiation of low-grade from high-grade appendicular chondrosarcoma.

PubMed

Douis, Hassan; Singh, Leanne; Saifuddin, Asif

2014-01-01

To identify magnetic resonance imaging (MRI) features which differentiate low-grade chondral lesions (atypical cartilaginous tumours/grade 1 chondrosarcoma) from high-grade chondrosarcomas (grade 2, grade 3 and dedifferentiated chondrosarcoma) of the major long bones. We identified all patients treated for central atypical cartilaginous tumours and central chondrosarcoma of major long bones (humerus, femur, tibia) over a 13-year period. The MRI studies were assessed for the following features: bone marrow oedema, soft tissue oedema, bone expansion, cortical thickening, cortical destruction, active periostitis, soft tissue mass and tumour length. The MRI-features were compared with the histopathological tumour grading using univariate, multivariate logistic regression and receiver operating characteristic curve (ROC) analyses. One hundred and seventy-nine tumours were included in this retrospective study. There were 28 atypical cartilaginous tumours, 79 grade 1 chondrosarcomas, 36 grade 2 chondrosarcomas, 13 grade 3 chondrosarcomas and 23 dedifferentiated chondrosarcomas. Multivariate analysis demonstrated that bone expansion (P = 0.001), active periostitis (P = 0.001), soft tissue mass (P < 0.001) and tumour length (P < 0.001) were statistically significant differentiating factors between low-grade and high-grade chondral lesions with an area under the ROC curve of 0.956. On MRI, bone expansion, active periostitis, soft tissue mass and tumour length can reliably differentiate high-grade chondrosarcomas from low-grade chondral lesions of the major long bones. • Accurate differentiation of low-grade from high-grade chondrosarcomas is essential before surgery • MRI can reliably differentiate high-grade from low-grade chondrosarcomas of long bone • Differentiating features are bone expansion, periostitis, soft tissue mass and tumour length • Presence of these four MRI features demonstrated a diagnostic accuracy (AUC) of 95.6 % • The findings may result in more accurate diagnosis before definitive surgery.

Tumor segmentation of multi-echo MR T2-weighted images with morphological operators

NASA Astrophysics Data System (ADS)

Torres, W.; Martín-Landrove, M.; Paluszny, M.; Figueroa, G.; Padilla, G.

2009-02-01

In the present work an automatic brain tumor segmentation procedure based on mathematical morphology is proposed. The approach considers sequences of eight multi-echo MR T2-weighted images. The relaxation time T2 characterizes the relaxation of water protons in the brain tissue: white matter, gray matter, cerebrospinal fluid (CSF) or pathological tissue. Image data is initially regularized by the application of a log-convex filter in order to adjust its geometrical properties to those of noiseless data, which exhibits monotonously decreasing convex behavior. Finally the regularized data is analyzed by means of an 8-dimensional morphological eccentricity filter. In a first stage, the filter was used for the spatial homogenization of the tissues in the image, replacing each pixel by the most representative pixel within its structuring element, i.e. the one which exhibits the minimum total distance to all members in the structuring element. On the filtered images, the relaxation time T2 is estimated by means of least square regression algorithm and the histogram of T2 is determined. The T2 histogram was partitioned using the watershed morphological operator; relaxation time classes were established and used for tissue classification and segmentation of the image. The method was validated on 15 sets of MRI data with excellent results.

Migraine classification using magnetic resonance imaging resting-state functional connectivity data.

PubMed

Chong, Catherine D; Gaw, Nathan; Fu, Yinlin; Li, Jing; Wu, Teresa; Schwedt, Todd J

2017-08-01

Background This study used machine-learning techniques to develop discriminative brain-connectivity biomarkers from resting-state functional magnetic resonance neuroimaging ( rs-fMRI) data that distinguish between individual migraine patients and healthy controls. Methods This study included 58 migraine patients (mean age = 36.3 years; SD = 11.5) and 50 healthy controls (mean age = 35.9 years; SD = 11.0). The functional connections of 33 seeded pain-related regions were used as input for a brain classification algorithm that tested the accuracy of determining whether an individual brain MRI belongs to someone with migraine or to a healthy control. Results The best classification accuracy using a 10-fold cross-validation method was 86.1%. Resting functional connectivity of the right middle temporal, posterior insula, middle cingulate, left ventromedial prefrontal and bilateral amygdala regions best discriminated the migraine brain from that of a healthy control. Migraineurs with longer disease durations were classified more accurately (>14 years; 96.7% accuracy) compared to migraineurs with shorter disease durations (≤14 years; 82.1% accuracy). Conclusions Classification of migraine using rs-fMRI provides insights into pain circuits that are altered in migraine and could potentially contribute to the development of a new, noninvasive migraine biomarker. Migraineurs with longer disease burden were classified more accurately than migraineurs with shorter disease burden, potentially indicating that disease duration leads to reorganization of brain circuitry.

Structural MRI-based detection of Alzheimer's disease using feature ranking and classification error.

PubMed

Beheshti, Iman; Demirel, Hasan; Farokhian, Farnaz; Yang, Chunlan; Matsuda, Hiroshi

2016-12-01

This paper presents an automatic computer-aided diagnosis (CAD) system based on feature ranking for detection of Alzheimer's disease (AD) using structural magnetic resonance imaging (sMRI) data. The proposed CAD system is composed of four systematic stages. First, global and local differences in the gray matter (GM) of AD patients compared to the GM of healthy controls (HCs) are analyzed using a voxel-based morphometry technique. The aim is to identify significant local differences in the volume of GM as volumes of interests (VOIs). Second, the voxel intensity values of the VOIs are extracted as raw features. Third, the raw features are ranked using a seven-feature ranking method, namely, statistical dependency (SD), mutual information (MI), information gain (IG), Pearson's correlation coefficient (PCC), t-test score (TS), Fisher's criterion (FC), and the Gini index (GI). The features with higher scores are more discriminative. To determine the number of top features, the estimated classification error based on training set made up of the AD and HC groups is calculated, with the vector size that minimized this error selected as the top discriminative feature. Fourth, the classification is performed using a support vector machine (SVM). In addition, a data fusion approach among feature ranking methods is introduced to improve the classification performance. The proposed method is evaluated using a data-set from ADNI (130 AD and 130 HC) with 10-fold cross-validation. The classification accuracy of the proposed automatic system for the diagnosis of AD is up to 92.48% using the sMRI data. An automatic CAD system for the classification of AD based on feature-ranking method and classification errors is proposed. In this regard, seven-feature ranking methods (i.e., SD, MI, IG, PCC, TS, FC, and GI) are evaluated. The optimal size of top discriminative features is determined by the classification error estimation in the training phase. The experimental results indicate that the performance of the proposed system is comparative to that of state-of-the-art classification models. Copyright © 2016 Elsevier Ireland Ltd. All rights reserved.

Optimization image of magnetic resonance imaging (MRI) T2 fast spin echo (FSE) with variation echo train length (ETL) on the rupture tendon achilles case

NASA Astrophysics Data System (ADS)

Muzamil, Akhmad; Haries Firmansyah, Achmad

2017-05-01

The research was done the optimization image of Magnetic Resonance Imaging (MRI) T2 Fast Spin Echo (FSE) with variation Echo Train Length (ETL) on the Rupture Tendon Achilles case. This study aims to find the variations Echo Train Length (ETL) from the results of ankle’s MRI image and find out how the value of Echo Train Length (ETL) works on the MRI ankle to produce optimal image. In this research, the used ETL variations were 12 and 20 with the interval 2 on weighting T2 FSE sagittal. The study obtained the influence of Echo Train Length (ETL) on the quality of ankle MRI image sagittal using T2 FSE weighting and analyzed in 25 images of five patients. The data analysis has done quantitatively with the Region of Interest (ROI) directly on computer MRI image planes which conducted statistical tests Signal to Noise Ratio (SNR) and Contras to Noise Ratio (CNR). The Signal to Noise Ratio (SNR) was the highest finding on fat tissue, while the Contras to Noise Ratio (CNR) on the Tendon-Fat tissue with ETL 12 found in two patients. The statistics test showed the significant SNR value of the 0.007 (p<0.05) of Tendon tissue, 0.364 (p>0.05) of the Fat, 0.912 (p>0.05) of the Fibula, and 0.436 (p>0.05) of the Heel Bone. For the contrast to noise ratio (CNR) of the Tendon-FAT tissue was about 0.041 (p>0.05). The results of the study showed that ETL variation with T2 FSE sagittal weighting had difference at Tendon tissue and Tendon-Fat tissue for MRI imaging quality. SNR and CNR were an important aspect on imaging optimization process to give the diagnose information.

Haptic fMRI: using classification to quantify task-correlated noise during goal-directed reaching motions.

PubMed

Menon, Samir; Quigley, Paul; Yu, Michelle; Khatib, Oussama

2014-01-01

Neuroimaging artifacts in haptic functional magnetic resonance imaging (Haptic fMRI) experiments have the potential to induce spurious fMRI activation where there is none, or to make neural activation measurements appear correlated across brain regions when they are actually not. Here, we demonstrate that performing three-dimensional goal-directed reaching motions while operating Haptic fMRI Interface (HFI) does not create confounding motion artifacts. To test for artifacts, we simultaneously scanned a subject's brain with a customized soft phantom placed a few centimeters away from the subject's left motor cortex. The phantom captured task-related motion and haptic noise, but did not contain associated neural activation measurements. We quantified the task-related information present in fMRI measurements taken from the brain and the phantom by using a linear max-margin classifier to predict whether raw time series data could differentiate between motion planning or reaching. fMRI measurements in the phantom were uninformative (2σ, 45-73%; chance=50%), while those in primary motor, visual, and somatosensory cortex accurately classified task-conditions (2σ, 90-96%). We also localized artifacts due to the haptic interface alone by scanning a stand-alone fBIRN phantom, while an operator performed haptic tasks outside the scanner's bore with the interface at the same location. The stand-alone phantom had lower temporal noise and had similar mean classification but a tighter distribution (bootstrap Gaussian fit) than the brain phantom. Our results suggest that any fMRI measurement artifacts for Haptic fMRI reaching experiments are dominated by actual neural responses.

Computed tomography synthesis from magnetic resonance images in the pelvis using multiple random forests and auto-context features

NASA Astrophysics Data System (ADS)

Andreasen, Daniel; Edmund, Jens M.; Zografos, Vasileios; Menze, Bjoern H.; Van Leemput, Koen

2016-03-01

In radiotherapy treatment planning that is only based on magnetic resonance imaging (MRI), the electron density information usually obtained from computed tomography (CT) must be derived from the MRI by synthesizing a so-called pseudo CT (pCT). This is a non-trivial task since MRI intensities are neither uniquely nor quantitatively related to electron density. Typical approaches involve either a classification or regression model requiring specialized MRI sequences to solve intensity ambiguities, or an atlas-based model necessitating multiple registrations between atlases and subject scans. In this work, we explore a machine learning approach for creating a pCT of the pelvic region from conventional MRI sequences without using atlases. We use a random forest provided with information about local texture, edges and spatial features derived from the MRI. This helps to solve intensity ambiguities. Furthermore, we use the concept of auto-context by sequentially training a number of classification forests to create and improve context features, which are finally used to train a regression forest for pCT prediction. We evaluate the pCT quality in terms of the voxel-wise error and the radiologic accuracy as measured by water-equivalent path lengths. We compare the performance of our method against two baseline pCT strategies, which either set all MRI voxels in the subject equal to the CT value of water, or in addition transfer the bone volume from the real CT. We show an improved performance compared to both baseline pCTs suggesting that our method may be useful for MRI-only radiotherapy.

Early classification of Alzheimer's disease using hippocampal texture from structural MRI

NASA Astrophysics Data System (ADS)

Zhao, Kun; Ding, Yanhui; Wang, Pan; Dou, Xuejiao; Zhou, Bo; Yao, Hongxiang; An, Ningyu; Zhang, Yongxin; Zhang, Xi; Liu, Yong

2017-03-01

Convergent evidence has been collected to support that Alzheimer's disease (AD) is associated with reduction in hippocampal volume based on anatomical magnetic resonance imaging (MRI) and impaired functional connectivity based on functional MRI. Radiomics texture analysis has been previously successfully used to identify MRI biomarkers of several diseases, including AD, mild cognitive impairment and multiple sclerosis. In this study, our goal was to determine if MRI hippocampal textures, including the intensity, shape, texture and wavelet features, could be served as an MRI biomarker of AD. For this purpose, the texture marker was trained and evaluated from MRI data of 48 AD and 39 normal samples. The result highlights the presence of hippocampal texture abnormalities in AD, and the possibility that texture may serve as a neuroimaging biomarker for AD.

What does magnetic resonance imaging add to the prenatal ultrasound diagnosis of facial clefts?

PubMed

Mailáth-Pokorny, M; Worda, C; Krampl-Bettelheim, E; Watzinger, F; Brugger, P C; Prayer, D

2010-10-01

Ultrasound is the modality of choice for prenatal detection of cleft lip and palate. Because its accuracy in detecting facial clefts, especially isolated clefts of the secondary palate, can be limited, magnetic resonance imaging (MRI) is used as an additional method for assessing the fetus. The aim of this study was to investigate the role of fetal MRI in the prenatal diagnosis of facial clefts. Thirty-four pregnant women with a mean gestational age of 26 (range, 19-34) weeks underwent in utero MRI, after ultrasound examination had identified either a facial cleft (n = 29) or another suspected malformation (micrognathia (n = 1), cardiac defect (n = 1), brain anomaly (n = 2) or diaphragmatic hernia (n = 1)). The facial cleft was classified postnatally and the diagnoses were compared with the previous ultrasound findings. There were 11 (32.4%) cases with cleft of the primary palate alone, 20 (58.8%) clefts of the primary and secondary palate and three (8.8%) isolated clefts of the secondary palate. In all cases the primary and secondary palate were visualized successfully with MRI. Ultrasound imaging could not detect five (14.7%) facial clefts and misclassified 15 (44.1%) facial clefts. The MRI classification correlated with the postnatal/postmortem diagnosis. In our hands MRI allows detailed prenatal evaluation of the primary and secondary palate. By demonstrating involvement of the palate, MRI provides better detection and classification of facial clefts than does ultrasound alone. Copyright © 2010 ISUOG. Published by John Wiley & Sons, Ltd.

Latent feature representation with stacked auto-encoder for AD/MCI diagnosis

PubMed Central

Lee, Seong-Whan

2014-01-01

Recently, there have been great interests for computer-aided diagnosis of Alzheimer’s disease (AD) and its prodromal stage, mild cognitive impairment (MCI). Unlike the previous methods that considered simple low-level features such as gray matter tissue volumes from MRI, and mean signal intensities from PET, in this paper, we propose a deep learning-based latent feature representation with a stacked auto-encoder (SAE). We believe that there exist latent non-linear complicated patterns inherent in the low-level features such as relations among features. Combining the latent information with the original features helps build a robust model in AD/MCI classification, with high diagnostic accuracy. Furthermore, thanks to the unsupervised characteristic of the pre-training in deep learning, we can benefit from the target-unrelated samples to initialize parameters of SAE, thus finding optimal parameters in fine-tuning with the target-related samples, and further enhancing the classification performances across four binary classification problems: AD vs. healthy normal control (HC), MCI vs. HC, AD vs. MCI, and MCI converter (MCI-C) vs. MCI non-converter (MCI-NC). In our experiments on ADNI dataset, we validated the effectiveness of the proposed method, showing the accuracies of 98.8, 90.7, 83.7, and 83.3 % for AD/HC, MCI/HC, AD/MCI, and MCI-C/MCI-NC classification, respectively. We believe that deep learning can shed new light on the neuroimaging data analysis, and our work presented the applicability of this method to brain disease diagnosis. PMID:24363140

DOE Office of Scientific and Technical Information (OSTI.GOV)

Kowalchik, Kristin V.; Vallow, Laura A., E-mail: vallow.laura@mayo.edu; McDonough, Michelle

Purpose: To study the utility of preoperative breast MRI for partial breast irradiation (PBI) patient selection, using multivariable analysis of significant risk factors to create a classification rule. Methods and Materials: Between 2002 and 2009, 712 women with newly diagnosed breast cancer underwent preoperative bilateral breast MRI at Mayo Clinic Florida. Of this cohort, 566 were retrospectively deemed eligible for PBI according to the National Surgical Adjuvant Breast and Bowel Project Protocol B-39 inclusion criteria using physical examination, mammogram, and/or ultrasound. Magnetic resonance images were then reviewed to determine their impact on patient eligibility. The patient and tumor characteristics weremore » evaluated to determine risk factors for altered PBI eligibility after MRI and to create a classification rule. Results: Of the 566 patients initially eligible for PBI, 141 (25%) were found ineligible because of pathologically proven MRI findings. Magnetic resonance imaging detected additional ipsilateral breast cancer in 118 (21%). Of these, 62 (11%) had more extensive disease than originally noted before MRI, and 64 (11%) had multicentric disease. Contralateral breast cancer was detected in 28 (5%). Four characteristics were found to be significantly associated with PBI ineligibility after MRI on multivariable analysis: premenopausal status (P=.021), detection by palpation (P<.001), first-degree relative with a history of breast cancer (P=.033), and lobular histology (P=.002). Risk factors were assigned a score of 0-2. The risk of altered PBI eligibility from MRI based on number of risk factors was 0:18%; 1:22%; 2:42%; 3:65%. Conclusions: Preoperative bilateral breast MRI altered the PBI recommendations for 25% of women. Women who may undergo PBI should be considered for breast MRI, especially those with lobular histology or with 2 or more of the following risk factors: premenopausal, detection by palpation, and first-degree relative with a history of breast cancer.« less

Assessment of gunshot bullet injuries with the use of magnetic resonance imaging.

PubMed

Hess, U; Harms, J; Schneider, A; Schleef, M; Ganter, C; Hannig, C

2000-10-01

Magnetic resonance imaging (MRI) is rarely used for preoperative assessment of shotgun injuries because of concerns of displacing the possibly ferromagnetic foreign body within the surrounding tissue. A total of 56 different projectiles underwent MRI testing for ferromagnetism and imaging quality in vitro and in pig carcasses with a commercially available 1.5-MRI scan. Image quality was compared with that of computed tomographic scans. Projectiles with ferromagnetic properties can be distinguished easily from nonferromagnetic ones by pretesting the motion of an identical projectile within the MRI coil. When ferromagnetic projectiles were excluded, MRI yielded the more precise images compared with other imaging techniques. Projectile localization and associated soft tissue injuries were visualized without artifacts in all cases. When ferromagnetic foreign bodies are excluded by pretesting their properties within the MRI with a comparative projectile, MRI portends an excellent imaging procedure for assessing the extent of injury and planning the removal by surgery.

Intra- and inter-observer agreement in MRI assessment of rotator cuff healing using the Sugaya classification 10years after surgery.

PubMed

Niglis, L; Collin, P; Dosch, J-C; Meyer, N; Kempf, J-F

2017-10-01

The long-term outcomes of rotator cuff repair are unclear. Recurrent tears are common, although their reported frequency varies depending on the type and interpretation challenges of the imaging method used. The primary objective of this study was to assess the intra- and inter-observer reproducibility of the MRI assessment of rotator cuff repair using the Sugaya classification 10years after surgery. The secondary objective was to determine whether poor reproducibility, if found, could be improved by using a simplified yet clinically relevant classification. Our hypothesis was that reproducibility was limited but could be improved by simplifying the classification. In a retrospective study, we assessed intra- and inter-observer agreement in interpreting 49 magnetic resonance imaging (MRI) scans performed 10years after rotator cuff repair. These 49 scans were taken at random among 609 cases that underwent re-evaluation, with imaging, for the 2015 SoFCOT symposium on 10-year and 20-year clinical and anatomical outcomes of rotator cuff repair for full-thickness tears. Each of three observers read each of the 49 scans on two separate occasions. At each reading, they assessed the supra-spinatus tendon according to the Sugaya classification in five types. Intra-observer agreement for the Sugaya type was substantial (κ=0.64) but inter-observer agreement was only fair (κ=0.39). Agreement improved when the five Sugaya types were collapsed into two categories (1-2-3 and 4-5) (intra-observer κ=0.74 and inter-observer κ=0.68). Using the Sugaya classification to assess post-operative rotator cuff healing was associated with substantial intra-observer and fair inter-observer agreement. A simpler classification into two categories improved agreement while remaining clinically relevant. II, prospective randomised low-power study. Copyright © 2017 Elsevier Masson SAS. All rights reserved.

A dual model HU conversion from MRI intensity values within and outside of bone segment for MRI-based radiotherapy treatment planning of prostate cancer

DOE Office of Scientific and Technical Information (OSTI.GOV)

Korhonen, Juha, E-mail: juha.p.korhonen@hus.fi; Department of Oncology, Helsinki University Central Hospital, POB-180, 00029 HUS; Kapanen, Mika

2014-01-15

Purpose: The lack of electron density information in magnetic resonance images (MRI) poses a major challenge for MRI-based radiotherapy treatment planning (RTP). In this study the authors convert MRI intensity values into Hounsfield units (HUs) in the male pelvis and thus enable accurate MRI-based RTP for prostate cancer patients with varying tissue anatomy and body fat contents. Methods: T{sub 1}/T{sub 2}*-weighted MRI intensity values and standard computed tomography (CT) image HUs in the male pelvis were analyzed using image data of 10 prostate cancer patients. The collected data were utilized to generate a dual model HU conversion technique from MRImore » intensity values of the single image set separately within and outside of contoured pelvic bones. Within the bone segment local MRI intensity values were converted to HUs by applying a second-order polynomial model. This model was tuned for each patient by two patient-specific adjustments: MR signal normalization to correct shifts in absolute intensity level and application of a cutoff value to accurately represent low density bony tissue HUs. For soft tissues, such as fat and muscle, located outside of the bone contours, a threshold-based segmentation method without requirements for any patient-specific adjustments was introduced to convert MRI intensity values into HUs. The dual model HU conversion technique was implemented by constructing pseudo-CT images for 10 other prostate cancer patients. The feasibility of these images for RTP was evaluated by comparing HUs in the generated pseudo-CT images with those in standard CT images, and by determining deviations in MRI-based dose distributions compared to those in CT images with 7-field intensity modulated radiation therapy (IMRT) with the anisotropic analytical algorithm and 360° volumetric-modulated arc therapy (VMAT) with the Voxel Monte Carlo algorithm. Results: The average HU differences between the constructed pseudo-CT images and standard CT images of each test patient ranged from −2 to 5 HUs and from 22 to 78 HUs in soft and bony tissues, respectively. The average local absolute value differences were 11 HUs in soft tissues and 99 HUs in bones. The planning target volume doses (volumes 95%, 50%, 5%) in the pseudo-CT images were within 0.8% compared to those in CT images in all of the 20 treatment plans. The average deviation was 0.3%. With all the test patients over 94% (IMRT) and 92% (VMAT) of dose points within body (lower than 10% of maximum dose suppressed) passed the 1 mm and 1% 2D gamma index criterion. The statistical tests (t- and F-tests) showed significantly improved (p ≤ 0.05) HU and dose calculation accuracies with the soft tissue conversion method instead of homogeneous representation of these tissues in MRI-based RTP images. Conclusions: This study indicates that it is possible to construct high quality pseudo-CT images by converting the intensity values of a single MRI series into HUs in the male pelvis, and to use these images for accurate MRI-based prostate RTP dose calculations.« less

The acellular matrix (ACM) for bladder tissue engineering: A quantitative magnetic resonance imaging study.

PubMed

Cheng, Hai-Ling Margaret; Loai, Yasir; Beaumont, Marine; Farhat, Walid A

2010-08-01

Bladder acellular matrices (ACMs) derived from natural tissue are gaining increasing attention for their role in tissue engineering and regeneration. Unlike conventional scaffolds based on biodegradable polymers or gels, ACMs possess native biomechanical and many acquired biologic properties. Efforts to optimize ACM-based scaffolds are ongoing and would be greatly assisted by a noninvasive means to characterize scaffold properties and monitor interaction with cells. MRI is well suited to this role, but research with MRI for scaffold characterization has been limited. This study presents initial results from quantitative MRI measurements for bladder ACM characterization and investigates the effects of incorporating hyaluronic acid, a natural biomaterial useful in tissue-engineering and regeneration. Measured MR relaxation times (T(1), T(2)) and diffusion coefficient were consistent with increased water uptake and glycosaminoglycan content observed on biochemistry in hyaluronic acid ACMs. Multicomponent MRI provided greater specificity, with diffusion data showing an acellular environment and T(2) components distinguishing the separate effects of increased glycosaminoglycans and hydration. These results suggest that quantitative MRI may provide useful information on matrix composition and structure, which is valuable in guiding further development using bladder ACMs for organ regeneration and in strategies involving the use of hyaluronic acid.

[From Brownian motion to mind imaging: diffusion MRI].

PubMed

Le Bihan, Denis

2006-11-01

The success of diffusion MRI, which was introduced in the mid 1980s is deeply rooted in the powerful concept that during their random, diffusion-driven movements water molecules probe tissue structure at a microscopic scale well beyond the usual image resolution. The observation of these movements thus provides valuable information on the structure and the geometric organization of tissues. The most successful application of diffusion MRI has been in brain ischemia, following the discovery that water diffusion drops at a very early stage of the ischemic event. Diffusion MRI provides some patients with the opportunity to receive suitable treatment at a very acute stage when brain tissue might still be salvageable. On the other hand, diffusion is modulated by the spatial orientation of large bundles of myelinated axons running in parallel through in brain white matter. This feature can be exploited to map out the orientation in space of the white matter tracks and to visualize the connections between different parts of the brain on an individual basis. Furthermore, recent data suggest that diffusion MRI may also be used to visualize rapid dynamic tissue changes, such as neuronal swelling, associated with cortical activation, offering a new and direct approach to brain functional imaging.

Non-negative matrix factorization in texture feature for classification of dementia with MRI data

NASA Astrophysics Data System (ADS)

Sarwinda, D.; Bustamam, A.; Ardaneswari, G.

2017-07-01

This paper investigates applications of non-negative matrix factorization as feature selection method to select the features from gray level co-occurrence matrix. The proposed approach is used to classify dementia using MRI data. In this study, texture analysis using gray level co-occurrence matrix is done to feature extraction. In the feature extraction process of MRI data, we found seven features from gray level co-occurrence matrix. Non-negative matrix factorization selected three features that influence of all features produced by feature extractions. A Naïve Bayes classifier is adapted to classify dementia, i.e. Alzheimer's disease, Mild Cognitive Impairment (MCI) and normal control. The experimental results show that non-negative factorization as feature selection method able to achieve an accuracy of 96.4% for classification of Alzheimer's and normal control. The proposed method also compared with other features selection methods i.e. Principal Component Analysis (PCA).

Automated discrimination of dementia spectrum disorders using extreme learning machine and structural T1 MRI features.

PubMed

Jongin Kim; Boreom Lee

2017-07-01

The classification of neuroimaging data for the diagnosis of Alzheimer's Disease (AD) is one of the main research goals of the neuroscience and clinical fields. In this study, we performed extreme learning machine (ELM) classifier to discriminate the AD, mild cognitive impairment (MCI) from normal control (NC). We compared the performance of ELM with that of a linear kernel support vector machine (SVM) for 718 structural MRI images from Alzheimer's Disease Neuroimaging Initiative (ADNI) database. The data consisted of normal control, MCI converter (MCI-C), MCI non-converter (MCI-NC), and AD. We employed SVM-based recursive feature elimination (RFE-SVM) algorithm to find the optimal subset of features. In this study, we found that the RFE-SVM feature selection approach in combination with ELM shows the superior classification accuracy to that of linear kernel SVM for structural T1 MRI data.

Paranasal sinuses and nasopharynx CT and MRI.

PubMed

Sievers, K W; Greess, H; Baum, U; Dobritz, M; Lenz, M

2000-03-01

Neoplastic disease of the nose, paranasal sinuses, the nasopharynx and the parapharyngeal space requires thorough assessment of location and extent in order to plan appropriate treatment. CT allows the deep soft tissue planes to be evaluated and provides a complement to the physical examination. It is especially helpful in regions involving thin bony structures (paranasal sinuses, orbita); here CT performs better than MRI. MRI possesses many advantages over other imaging modalities caused by its excellent tissue contrast. In evaluating regions involving predominantly soft tissue structures (ec nasopharynx and parapharyngeal space) MRI is superior to CT. The possibility to obtain strictly consecutive volume data sets with spiral CT or 3D MRI offer excellent perspectives to visualize the data via 2D or 3D postprocessing. Because head and neck tumors reside in a complex area, having a 3D model of the anatomical features may assist in the delineation of pathology. Data sets may be transferred directly into computer systems and thus be used in computer assisted surgery.

Magnetic resonance imaging of the submandibular-sublingual complex.

PubMed

Sbarbati, A; Baldassarri, A; Leclercq, F; Merigo, F; Antonakis, K; Boicelli, A

1994-01-01

The submandibular-sublingual complex (SSC) was studied in vivo by magnetic resonance imaging (MRI) at 4.7 and 7.05 Tesla in rat and mouse. A correlation was found between histology and MRI signal. The mainly mucous sublingual gland emitted a more intense signal than the mainly serous submandibular gland. Ventral to the glands, cutis, subcutaneous adipose tissue and two planes of muscular tissue separated by connective laminae were visible in vivo. Autopsy and histology confirmed the in vivo description provided by MRI. The reactivity of the salivary system after pharmacological stimulation was studied in mice at 7.05 Tesla. Stimulation of salivary secretion by pilocarpine nitrate injected in the subcutaneous space ventrally to the SSC resulted in an augmentation of the salivary liquid visible in the oral cavity by MRI. The diffusion of pilocarpine nitrate in the connective tissue located ventrally the SSC and in the glandular parenchyma was also followed in vivo. These results show that MRI is a potentially useful tool for studying the salivary glands in vivo.

An automated method for identifying artifact in independent component analysis of resting-state FMRI.

PubMed

Bhaganagarapu, Kaushik; Jackson, Graeme D; Abbott, David F

2013-01-01

An enduring issue with data-driven analysis and filtering methods is the interpretation of results. To assist, we present an automatic method for identification of artifact in independent components (ICs) derived from functional MRI (fMRI). The method was designed with the following features: does not require temporal information about an fMRI paradigm; does not require the user to train the algorithm; requires only the fMRI images (additional acquisition of anatomical imaging not required); is able to identify a high proportion of artifact-related ICs without removing components that are likely to be of neuronal origin; can be applied to resting-state fMRI; is automated, requiring minimal or no human intervention. We applied the method to a MELODIC probabilistic ICA of resting-state functional connectivity data acquired in 50 healthy control subjects, and compared the results to a blinded expert manual classification. The method identified between 26 and 72% of the components as artifact (mean 55%). About 0.3% of components identified as artifact were discordant with the manual classification; retrospective examination of these ICs suggested the automated method had correctly identified these as artifact. We have developed an effective automated method which removes a substantial number of unwanted noisy components in ICA analyses of resting-state fMRI data. Source code of our implementation of the method is available.

Alzheimer Classification Using a Minimum Spanning Tree of High-Order Functional Network on fMRI Dataset

PubMed Central

Guo, Hao; Liu, Lei; Chen, Junjie; Xu, Yong; Jie, Xiang

2017-01-01

Functional magnetic resonance imaging (fMRI) is one of the most useful methods to generate functional connectivity networks of the brain. However, conventional network generation methods ignore dynamic changes of functional connectivity between brain regions. Previous studies proposed constructing high-order functional connectivity networks that consider the time-varying characteristics of functional connectivity, and a clustering method was performed to decrease computational cost. However, random selection of the initial clustering centers and the number of clusters negatively affected classification accuracy, and the network lost neurological interpretability. Here we propose a novel method that introduces the minimum spanning tree method to high-order functional connectivity networks. As an unbiased method, the minimum spanning tree simplifies high-order network structure while preserving its core framework. The dynamic characteristics of time series are not lost with this approach, and the neurological interpretation of the network is guaranteed. Simultaneously, we propose a multi-parameter optimization framework that involves extracting discriminative features from the minimum spanning tree high-order functional connectivity networks. Compared with the conventional methods, our resting-state fMRI classification method based on minimum spanning tree high-order functional connectivity networks greatly improved the diagnostic accuracy for Alzheimer's disease. PMID:29249926

Classifying MCI Subtypes in Community-Dwelling Elderly Using Cross-Sectional and Longitudinal MRI-Based Biomarkers

PubMed Central

Guan, Hao; Liu, Tao; Jiang, Jiyang; Tao, Dacheng; Zhang, Jicong; Niu, Haijun; Zhu, Wanlin; Wang, Yilong; Cheng, Jian; Kochan, Nicole A.; Brodaty, Henry; Sachdev, Perminder; Wen, Wei

2017-01-01

Amnestic MCI (aMCI) and non-amnestic MCI (naMCI) are considered to differ in etiology and outcome. Accurately classifying MCI into meaningful subtypes would enable early intervention with targeted treatment. In this study, we employed structural magnetic resonance imaging (MRI) for MCI subtype classification. This was carried out in a sample of 184 community-dwelling individuals (aged 73–85 years). Cortical surface based measurements were computed from longitudinal and cross-sectional scans. By introducing a feature selection algorithm, we identified a set of discriminative features, and further investigated the temporal patterns of these features. A voting classifier was trained and evaluated via 10 iterations of cross-validation. The best classification accuracies achieved were: 77% (naMCI vs. aMCI), 81% (aMCI vs. cognitively normal (CN)) and 70% (naMCI vs. CN). The best results for differentiating aMCI from naMCI were achieved with baseline features. Hippocampus, amygdala and frontal pole were found to be most discriminative for classifying MCI subtypes. Additionally, we observed the dynamics of classification of several MRI biomarkers. Learning the dynamics of atrophy may aid in the development of better biomarkers, as it may track the progression of cognitive impairment. PMID:29085292

[New ASAS criteria for the diagnosis of spondyloarthritis: diagnosing sacroiliitis by magnetic resonance imaging].

PubMed

Banegas Illescas, M E; López Menéndez, C; Rozas Rodríguez, M L; Fernández Quintero, R M

2014-01-01

Radiographic sacroiliitis has been included in the diagnostic criteria for spondyloarthropathies since the Rome criteria were defined in 1961. However, in the last ten years, magnetic resonance imaging (MRI) has proven more sensitive in the evaluation of the sacroiliac joints in patients with suspected spondyloarthritis and symptoms of sacroiliitis; MRI has proven its usefulness not only for diagnosis of this disease, but also for the follow-up of the disease and response to treatment in these patients. In 2009, The Assessment of SpondyloArthritis international Society (ASAS) developed a new set of criteria for classifying and diagnosing patients with spondyloarthritis; one important development with respect to previous classifications is the inclusion of MRI positive for sacroiliitis as a major diagnostic criterion. This article focuses on the radiologic part of the new classification. We describe and illustrate the different alterations that can be seen on MRI in patients with sacroiliitis, pointing out the limitations of the technique and diagnostic pitfalls. Copyright © 2013 SERAM. Published by Elsevier Espana. All rights reserved.

Fabrication of Custom-Shaped Grafts for Cartilage Regeneration

PubMed Central

Koo, Seungbum; Hargreaves, Brian A.; Gold, Garry E.; Dragoo, Jason L.

2011-01-01

Transplantation of engineered cartilage grafts is a promising method to treat diseased articular cartilage. The interfacial areas between the graft and the native tissues play an important role in the successful integration of the graft to adjacent native tissues. The purposes of the study were to create a custom shaped graft through 3D tissue shape reconstruction and rapid-prototype molding methods using MRI data, and to test the accuracy of the custom shaped graft against the original anatomical defect. An iatrogenic defect on the distal femur was identified with a 1.5 Tesla MRI and its shape was reconstructed into a three-dimensional (3D) computer model by processing the 3D MRI data. First, the accuracy of the MRI-derived 3D model was tested against a laser-scan based 3D model of the defect. A custom-shaped polyurethane graft was fabricated from the laser-scan based 3D model by creating custom molds through computer aided design and rapid-prototyping methods. The polyurethane tissue was laser-scanned again to calculate the accuracy of this process compared to the original defect. The volumes of the defect models from MRI and laser-scan were 537 mm3 and 405 mm3, respectively, implying that the MRI model was 33% larger than the laser-scan model. The average (±SD) distance deviation of the exterior surface of the MRI model from the laser-scan model was 0.4±0.4 mm. The custom-shaped tissue created from the molds was qualitatively very similar to the original shape of the defect. The volume of the custom-shaped cartilage tissue was 463 mm3 which was 15% larger than the laser-scan model. The average (±SD) distance deviation between the two models was 0.04±0.19 mm. Custom-shaped engineered grafts can be fabricated from standard sequence 3-D MRI data with the use of CAD and rapid-prototyping technology, which may help solve the interfacial problem between native cartilage and graft, if the grafts are custom made for the specific defect. The major source of error in fabricating a 3D custom shaped cartilage graft appears to be the accuracy of a MRI data itself; however, the precision of the model is expected to increase by the utilization of advanced MR sequences with higher magnet strengths. PMID:21058268

Temporal development of near-native functional properties and correlations with qMRI in self-assembling fibrocartilage treated with exogenous lysyl oxidase homolog 2.

PubMed

Hadidi, Pasha; Cissell, Derek D; Hu, Jerry C; Athanasiou, Kyriacos A

2017-12-01

Advances in cartilage tissue engineering have led to constructs with mechanical integrity and biochemical composition increasingly resembling that of native tissues. In particular, collagen cross-linking with lysyl oxidase has been used to significantly enhance the mechanical properties of engineered neotissues. In this study, development of collagen cross-links over time, and correlations with tensile properties, were examined in self-assembling neotissues. Additionally, quantitative MRI metrics were examined in relation to construct mechanical properties as well as pyridinoline cross-link content and other engineered tissue components. Scaffold-free meniscus fibrocartilage was cultured in the presence of exogenous lysyl oxidase, and assessed at multiple time points over 8weeks starting from the first week of culture. Engineered constructs demonstrated a 9.9-fold increase in pyridinoline content, reaching 77% of native tissue values, after 8weeks of culture. Additionally, engineered tissues reached 66% of the Young's modulus in the radial direction of native tissues. Further, collagen cross-links were found to correlate with tensile properties, contributing 67% of the tensile strength of engineered neocartilages. Finally, examination of quantitative MRI metrics revealed several correlations with mechanical and biochemical properties of engineered constructs. This study displays the importance of culture duration for collagen cross-link formation, and demonstrates the potential of quantitative MRI in investigating properties of engineered cartilages. This is the first study to demonstrate near-native cross-link content in an engineered tissue, and the first study to quantify pyridinoline cross-link development over time in a self-assembling tissue. Additionally, this work shows the relative contributions of collagen and pyridinoline to the tensile properties of collagenous tissue for the first time. Furthermore, this is the first investigation to identify a relationship between qMRI metrics and the pyridinoline cross-link content of an engineered collagenous tissue. Copyright © 2017 Acta Materialia Inc. Published by Elsevier Ltd. All rights reserved.

Accuracy of automated classification of major depressive disorder as a function of symptom severity.

PubMed

Ramasubbu, Rajamannar; Brown, Matthew R G; Cortese, Filmeno; Gaxiola, Ismael; Goodyear, Bradley; Greenshaw, Andrew J; Dursun, Serdar M; Greiner, Russell

2016-01-01

Growing evidence documents the potential of machine learning for developing brain based diagnostic methods for major depressive disorder (MDD). As symptom severity may influence brain activity, we investigated whether the severity of MDD affected the accuracies of machine learned MDD-vs-Control diagnostic classifiers. Forty-five medication-free patients with DSM-IV defined MDD and 19 healthy controls participated in the study. Based on depression severity as determined by the Hamilton Rating Scale for Depression (HRSD), MDD patients were sorted into three groups: mild to moderate depression (HRSD 14-19), severe depression (HRSD 20-23), and very severe depression (HRSD ≥ 24). We collected functional magnetic resonance imaging (fMRI) data during both resting-state and an emotional-face matching task. Patients in each of the three severity groups were compared against controls in separate analyses, using either the resting-state or task-based fMRI data. We use each of these six datasets with linear support vector machine (SVM) binary classifiers for identifying individuals as patients or controls. The resting-state fMRI data showed statistically significant classification accuracy only for the very severe depression group (accuracy 66%, p = 0.012 corrected), while mild to moderate (accuracy 58%, p = 1.0 corrected) and severe depression (accuracy 52%, p = 1.0 corrected) were only at chance. With task-based fMRI data, the automated classifier performed at chance in all three severity groups. Binary linear SVM classifiers achieved significant classification of very severe depression with resting-state fMRI, but the contribution of brain measurements may have limited potential in differentiating patients with less severe depression from healthy controls.

Machine-learning in grading of gliomas based on multi-parametric magnetic resonance imaging at 3T.

PubMed

Citak-Er, Fusun; Firat, Zeynep; Kovanlikaya, Ilhami; Ture, Ugur; Ozturk-Isik, Esin

2018-06-15

The objective of this study was to assess the contribution of multi-parametric (mp) magnetic resonance imaging (MRI) quantitative features in the machine learning-based grading of gliomas with a multi-region-of-interests approach. Forty-three patients who were newly diagnosed as having a glioma were included in this study. The patients were scanned prior to any therapy using a standard brain tumor magnetic resonance (MR) imaging protocol that included T1 and T2-weighted, diffusion-weighted, diffusion tensor, MR perfusion and MR spectroscopic imaging. Three different regions-of-interest were drawn for each subject to encompass tumor, immediate tumor periphery, and distant peritumoral edema/normal. The normalized mp-MRI features were used to build machine-learning models for differentiating low-grade gliomas (WHO grades I and II) from high grades (WHO grades III and IV). In order to assess the contribution of regional mp-MRI quantitative features to the classification models, a support vector machine-based recursive feature elimination method was applied prior to classification. A machine-learning model based on support vector machine algorithm with linear kernel achieved an accuracy of 93.0%, a specificity of 86.7%, and a sensitivity of 96.4% for the grading of gliomas using ten-fold cross validation based on the proposed subset of the mp-MRI features. In this study, machine-learning based on multiregional and multi-parametric MRI data has proven to be an important tool in grading glial tumors accurately even in this limited patient population. Future studies are needed to investigate the use of machine learning algorithms for brain tumor classification in a larger patient cohort. Copyright © 2018. Published by Elsevier Ltd.

Signal enhancement ratio (SER) quantified from breast DCE-MRI and breast cancer risk

NASA Astrophysics Data System (ADS)

Wu, Shandong; Kurland, Brenda F.; Berg, Wendie A.; Zuley, Margarita L.; Jankowitz, Rachel C.; Sumkin, Jules; Gur, David

2015-03-01

Breast magnetic resonance imaging (MRI) is recommended as an adjunct to mammography for women who are considered at elevated risk of developing breast cancer. As a key component of breast MRI, dynamic contrast-enhanced MRI (DCE-MRI) uses a contrast agent to provide high intensity contrast between breast tissues, making it sensitive to tissue composition and vascularity. Breast DCE-MRI characterizes certain physiologic properties of breast tissue that are potentially related to breast cancer risk. Studies have shown that increased background parenchymal enhancement (BPE), which is the contrast enhancement occurring in normal cancer-unaffected breast tissues in post-contrast sequences, predicts increased breast cancer risk. Signal enhancement ratio (SER) computed from pre-contrast and post-contrast sequences in DCE-MRI measures change in signal intensity due to contrast uptake over time and is a measure of contrast enhancement kinetics. SER quantified in breast tumor has been shown potential as a biomarker for characterizing tumor response to treatments. In this work we investigated the relationship between quantitative measures of SER and breast cancer risk. A pilot retrospective case-control study was performed using a cohort of 102 women, consisting of 51 women who had diagnosed with unilateral breast cancer and 51 matched controls (by age and MRI date) with a unilateral biopsy-proven benign lesion. SER was quantified using fully-automated computerized algorithms and three SER-derived quantitative volume measures were compared between the cancer cases and controls using logistic regression analysis. Our preliminary results showed that SER is associated with breast cancer risk, after adjustment for the Breast Imaging Reporting and Data System (BI-RADS)-based mammographic breast density measures. This pilot study indicated that SER has potential for use as a risk factor for breast cancer risk assessment in women at elevated risk of developing breast cancer.

Regression and statistical shape model based substitute CT generation for MRI alone external beam radiation therapy from standard clinical MRI sequences.

PubMed

Ghose, Soumya; Greer, Peter B; Sun, Jidi; Pichler, Peter; Rivest-Henault, David; Mitra, Jhimli; Richardson, Haylea; Wratten, Chris; Martin, Jarad; Arm, Jameen; Best, Leah; Dowling, Jason A

2017-10-27

In MR only radiation therapy planning, generation of the tissue specific HU map directly from the MRI would eliminate the need of CT image acquisition and may improve radiation therapy planning. The aim of this work is to generate and validate substitute CT (sCT) scans generated from standard T2 weighted MR pelvic scans in prostate radiation therapy dose planning. A Siemens Skyra 3T MRI scanner with laser bridge, flat couch and pelvic coil mounts was used to scan 39 patients scheduled for external beam radiation therapy for localized prostate cancer. For sCT generation a whole pelvis MRI (1.6 mm 3D isotropic T2w SPACE sequence) was acquired. Patients received a routine planning CT scan. Co-registered whole pelvis CT and T2w MRI pairs were used as training images. Advanced tissue specific non-linear regression models to predict HU for the fat, muscle, bladder and air were created from co-registered CT-MRI image pairs. On a test case T2w MRI, the bones and bladder were automatically segmented using a novel statistical shape and appearance model, while other soft tissues were separated using an Expectation-Maximization based clustering model. The CT bone in the training database that was most 'similar' to the segmented bone was then transformed with deformable registration to create the sCT component of the test case T2w MRI bone tissue. Predictions for the bone, air and soft tissue from the separate regression models were successively combined to generate a whole pelvis sCT. The change in monitor units between the sCT-based plans relative to the gold standard CT plan for the same IMRT dose plan was found to be [Formula: see text] (mean  ±  standard deviation) for 39 patients. The 3D Gamma pass rate was [Formula: see text] (2 mm/2%). The novel hybrid model is computationally efficient, generating an sCT in 20 min from standard T2w images for prostate cancer radiation therapy dose planning and DRR generation.

Regression and statistical shape model based substitute CT generation for MRI alone external beam radiation therapy from standard clinical MRI sequences

NASA Astrophysics Data System (ADS)

Ghose, Soumya; Greer, Peter B.; Sun, Jidi; Pichler, Peter; Rivest-Henault, David; Mitra, Jhimli; Richardson, Haylea; Wratten, Chris; Martin, Jarad; Arm, Jameen; Best, Leah; Dowling, Jason A.

2017-11-01

In MR only radiation therapy planning, generation of the tissue specific HU map directly from the MRI would eliminate the need of CT image acquisition and may improve radiation therapy planning. The aim of this work is to generate and validate substitute CT (sCT) scans generated from standard T2 weighted MR pelvic scans in prostate radiation therapy dose planning. A Siemens Skyra 3T MRI scanner with laser bridge, flat couch and pelvic coil mounts was used to scan 39 patients scheduled for external beam radiation therapy for localized prostate cancer. For sCT generation a whole pelvis MRI (1.6 mm 3D isotropic T2w SPACE sequence) was acquired. Patients received a routine planning CT scan. Co-registered whole pelvis CT and T2w MRI pairs were used as training images. Advanced tissue specific non-linear regression models to predict HU for the fat, muscle, bladder and air were created from co-registered CT-MRI image pairs. On a test case T2w MRI, the bones and bladder were automatically segmented using a novel statistical shape and appearance model, while other soft tissues were separated using an Expectation-Maximization based clustering model. The CT bone in the training database that was most ‘similar’ to the segmented bone was then transformed with deformable registration to create the sCT component of the test case T2w MRI bone tissue. Predictions for the bone, air and soft tissue from the separate regression models were successively combined to generate a whole pelvis sCT. The change in monitor units between the sCT-based plans relative to the gold standard CT plan for the same IMRT dose plan was found to be 0.3%+/-0.9% (mean  ±  standard deviation) for 39 patients. The 3D Gamma pass rate was 99.8+/-0.00 (2 mm/2%). The novel hybrid model is computationally efficient, generating an sCT in 20 min from standard T2w images for prostate cancer radiation therapy dose planning and DRR generation.

The first study on therapeutic efficacies of a vascular disrupting agent CA4P among primary hepatocellular carcinomas with a full spectrum of differentiation and vascularity: Correlation of MRI-microangiography-histopathology in rats.

PubMed

Liu, Yewei; De Keyzer, Frederik; Wang, Yixing; Wang, Fengna; Feng, Yuanbo; Chen, Feng; Yu, Jie; Liu, Jianjun; Song, Shaoli; Swinnen, Johan; Bormans, Guy; Oyen, Raymond; Huang, Gang; Ni, Yicheng

2018-04-29

To better inform the next clinical trials of vascular disrupting agent Combretastatin-A4-phosphate (CA4P) in patients with hepatic malignancies, this preclinical study aimed at evaluating CA4P therapeutic efficacy in rats with primary hepatocellular carcinomas (HCCs) of a full spectrum of differentiation and vascularity by magnetic resonance imaging (MRI), microangiography and histopathology. Ninety-six HCCs were raised in 25 rats by diethylnitrosamine gavage. Tumor growth was monitored by T2-/T1-weighted-MRI (T2WI, T1WI) using a 3.0T scanner. Early vascular response and later intratumoral necrosis were detected by dynamic-contrast-enhanced (DCE) MRI and diffusion-weighted-imaging (DWI) before, 1h and 12h after CA4P iv-administration. In-vivo MRI-findings were validated by postmortem-techniques. Multi-parametric MRI revealed rapid CA4P-induced tumor vascular shutdown within 1h, followed by variable intratumoral necrosis at 12h. Tumor volumes decreased by 10% at 1h (P<0.05), but resumed at 12h. Correlations of semi-quantitative DCE parameter initial-area-under-the-gadolinium-curve (IAUGC30) with histopathology proved partial vascular closure and compensational reopening (P<0.05). The higher grades of vascularity prevented those residual tumor tissues from CA4P-caused ischemic necrosis. By histopathology using a 4-scale cellular-differentiation criteria and a 4-grade tumor-vascularity classification, percentage of CA4P-induced necrosis negatively correlated with HCC differentiation (r=-0.404, P<0.001) and tumor vascularity (r=-0.370, P<0.001). Ordinal-logistic-regression helped to predict early tumor responses to CA4P in terms of tumoral differentiation and vascularity. This study demonstrated that CA4P could induce vascular shutdown in primary HCCs within 1h, resulting in various degrees of tumor necrosis at 12h. MRI as a real-time imaging biomarker may help to define tumor vascularity and differentiation and further to predict CA4P therapeutic outcomes. This article is protected by copyright. All rights reserved. © 2018 UICC.

Impact of selective use of breast MRI on surgical decision-making in women with newly diagnosed operable breast cancer.

PubMed

Brennan, Meagan E; McKessar, Merran; Snook, Kylie; Burgess, Ian; Spillane, Andrew J

2017-04-01

This study evaluated the impact of breast MRI on surgical planning in selected cases of breast malignancy (invasive cancer or DCIS). MRI was used when there was ambiguity on clinical and/or conventional imaging assessment. Consecutive women with breast malignancy undergoing breast MRI were included. Clinical, mammogram and ultrasound findings and surgical plan before and after MRI were recorded. MRI findings and histopathology results were documented and the impact of MRI on treatment planning was evaluated. MRI was performed in 181/1416 (12.8%) cases (invasive cancer 155/1219 (12.7%), DCIS 26/197 (13.2%)). Indications for MRI were: clinically dense breast tissue difficult to assess (n = 66; 36.5%), discordant clinical/conventional imaging assessment (n = 61; 33.7%), invasive lobular carcinoma in clinically dense breast tissue (n = 22; 12.2%), palpable/mass-forming DCIS (n = 11; 6.1%); other (n = 19; 10.5%). The recall rate for assessment of additional lesions was 35% (63/181). Additional biopsy-proven malignancy was found in 11/29 (37.9%) ipsilateral breast recalls and 8/34 (23.5%) contralateral breast recalls. MRI detected contralateral malignancy (unsuspected on conventional imaging) in 5/179 (2.8%). The additional information from MRI changed management in 69/181 (38.1%), with more unilateral surgery (wider excision or mastectomy) in 53/181 (29.3%), change to bilateral surgery in 12/181 (6.6%), less surgery in 4/181 (2.2%). Clinical examination estimated histological size within 20 mm in 57%, conventional imaging in 55% and MRI in 71%. MRI was most likely to show concordance with histopathology in the 'discordant assessment' and 'invasive lobular' groups and less likely for 'challenging clinically dense breast tissue.' MRI changed management in 69/181 (38.1%). Copyright © 2017 Elsevier Ltd. All rights reserved.

[Contribution of MRI to the preoperative evaluation of rotator cuff tears].

PubMed

Gagey, N; Desmoineaux, P; Gagey, O; Idy-Peretti, I; Mazas, F

1991-01-01

The authors report a series of 38 patients who had been examined by MRI and then operated for a rotator cuff syndrome. The correlation between the description of the cuff lesions after MRI and the surgical observations were excellent for 37 patients. In one case MRI showed a false image of tear of the supra spinatus m. on its anterior edge. This was due to a bad knowledge of the anatomy of the muscle and tendon and to a poor orientation of the frontal cut plane. This study was completed with MRI and anatomic study of 12 non embalmed cadaveric shoulders. The results showed that MRI was very sensitive (0.93) and specific (0.94) for the diagnosis of rotator cuff tears. MRI allowed also to show partial tears of the tendons of the rotator cuff. The authors propose a MRI classification of cuff lesions which permits to establish a good surgical planning.

Perspectives on Machine Learning for Classification of Schizotypy Using fMRI Data.

PubMed

Madsen, Kristoffer H; Krohne, Laerke G; Cai, Xin-Lu; Wang, Yi; Chan, Raymond C K

2018-03-15

Functional magnetic resonance imaging is capable of estimating functional activation and connectivity in the human brain, and lately there has been increased interest in the use of these functional modalities combined with machine learning for identification of psychiatric traits. While these methods bear great potential for early diagnosis and better understanding of disease processes, there are wide ranges of processing choices and pitfalls that may severely hamper interpretation and generalization performance unless carefully considered. In this perspective article, we aim to motivate the use of machine learning schizotypy research. To this end, we describe common data processing steps while commenting on best practices and procedures. First, we introduce the important role of schizotypy to motivate the importance of reliable classification, and summarize existing machine learning literature on schizotypy. Then, we describe procedures for extraction of features based on fMRI data, including statistical parametric mapping, parcellation, complex network analysis, and decomposition methods, as well as classification with a special focus on support vector classification and deep learning. We provide more detailed descriptions and software as supplementary material. Finally, we present current challenges in machine learning for classification of schizotypy and comment on future trends and perspectives.

Image-guided tissue engineering of anatomically shaped implants via MRI and micro-CT using injection molding.

PubMed

Ballyns, Jeffery J; Gleghorn, Jason P; Niebrzydowski, Vicki; Rawlinson, Jeremy J; Potter, Hollis G; Maher, Suzanne A; Wright, Timothy M; Bonassar, Lawrence J

2008-07-01

This study demonstrates for the first time the development of engineered tissues based on anatomic geometries derived from widely used medical imaging modalities such as computed tomography (CT) and magnetic resonance imaging (MRI). Computer-aided design and tissue injection molding techniques have demonstrated the ability to generate living implants of complex geometry. Due to its complex geometry, the meniscus of the knee was used as an example of this technique's capabilities. MRI and microcomputed tomography (microCT) were used to design custom-printed molds that enabled the generation of anatomically shaped constructs that retained shape throughout 8 weeks of culture. Engineered constructs showed progressive tissue formation indicated by increases in extracellular matrix content and mechanical properties. The paradigm of interfacing tissue injection molding technology can be applied to other medical imaging techniques that render 3D models of anatomy, demonstrating the potential to apply the current technique to engineering of many tissues and organs.

Cognitive Neuroscience of Attention Deficit Hyperactivity Disorder (ADHD) and Its Clinical Translation

PubMed Central

Rubia, Katya

2018-01-01

This review focuses on the cognitive neuroscience of Attention Deficit Hyperactivity Disorder (ADHD) based on functional magnetic resonance imaging (fMRI) studies and on recent clinically relevant applications such as fMRI-based diagnostic classification or neuromodulation therapies targeting fMRI deficits with neurofeedback (NF) or brain stimulation. Meta-analyses of fMRI studies of executive functions (EFs) show that ADHD patients have cognitive-domain dissociated complex multisystem impairments in several right and left hemispheric dorsal, ventral and medial fronto-cingulo-striato-thalamic and fronto-parieto-cerebellar networks that mediate cognitive control, attention, timing and working memory (WM). There is furthermore emerging evidence for abnormalities in orbital and ventromedial prefrontal and limbic areas that mediate motivation and emotion control. In addition, poor deactivation of the default mode network (DMN) suggests an abnormal interrelationship between hypo-engaged task-positive and poorly “switched off” hyper-engaged task-negative networks, both of which are related to impaired cognition. Translational cognitive neuroscience in ADHD is still in its infancy. Pattern recognition analyses have attempted to provide diagnostic classification of ADHD using fMRI data with respectable classification accuracies of over 80%. Necessary replication studies, however, are still outstanding. Brain stimulation has been tested in heterogeneously designed, small numbered proof of concept studies targeting key frontal functional impairments in ADHD. Transcranial direct current stimulation (tDCS) appears to be promising to improve ADHD symptoms and cognitive functions based on some studies, but larger clinical trials of repeated stimulation with and without cognitive training are needed to test clinical efficacy and potential costs on non-targeted functions. Only three studies have piloted NF of fMRI-based frontal dysfunctions in ADHD using fMRI or near-infrared spectroscopy, with the two larger ones finding some improvements in cognition and symptoms, which, however, were not superior to the active control conditions, suggesting potential placebo effects. Neurotherapeutics seems attractive for ADHD due to their safety and potential longer-term neuroplastic effects, which drugs cannot offer. However, they need to be thoroughly tested for short- and longer-term clinical and cognitive efficacy and their potential for individualized treatment. PMID:29651240

Cognitive Neuroscience of Attention Deficit Hyperactivity Disorder (ADHD) and Its Clinical Translation.

PubMed

Rubia, Katya

2018-01-01

This review focuses on the cognitive neuroscience of Attention Deficit Hyperactivity Disorder (ADHD) based on functional magnetic resonance imaging (fMRI) studies and on recent clinically relevant applications such as fMRI-based diagnostic classification or neuromodulation therapies targeting fMRI deficits with neurofeedback (NF) or brain stimulation. Meta-analyses of fMRI studies of executive functions (EFs) show that ADHD patients have cognitive-domain dissociated complex multisystem impairments in several right and left hemispheric dorsal, ventral and medial fronto-cingulo-striato-thalamic and fronto-parieto-cerebellar networks that mediate cognitive control, attention, timing and working memory (WM). There is furthermore emerging evidence for abnormalities in orbital and ventromedial prefrontal and limbic areas that mediate motivation and emotion control. In addition, poor deactivation of the default mode network (DMN) suggests an abnormal interrelationship between hypo-engaged task-positive and poorly "switched off" hyper-engaged task-negative networks, both of which are related to impaired cognition. Translational cognitive neuroscience in ADHD is still in its infancy. Pattern recognition analyses have attempted to provide diagnostic classification of ADHD using fMRI data with respectable classification accuracies of over 80%. Necessary replication studies, however, are still outstanding. Brain stimulation has been tested in heterogeneously designed, small numbered proof of concept studies targeting key frontal functional impairments in ADHD. Transcranial direct current stimulation (tDCS) appears to be promising to improve ADHD symptoms and cognitive functions based on some studies, but larger clinical trials of repeated stimulation with and without cognitive training are needed to test clinical efficacy and potential costs on non-targeted functions. Only three studies have piloted NF of fMRI-based frontal dysfunctions in ADHD using fMRI or near-infrared spectroscopy, with the two larger ones finding some improvements in cognition and symptoms, which, however, were not superior to the active control conditions, suggesting potential placebo effects. Neurotherapeutics seems attractive for ADHD due to their safety and potential longer-term neuroplastic effects, which drugs cannot offer. However, they need to be thoroughly tested for short- and longer-term clinical and cognitive efficacy and their potential for individualized treatment.

Discriminative analysis of early Alzheimer's disease based on two intrinsically anti-correlated networks with resting-state fMRI.

PubMed

Wang, Kun; Jiang, Tianzi; Liang, Meng; Wang, Liang; Tian, Lixia; Zhang, Xinqing; Li, Kuncheng; Liu, Zhening

2006-01-01

In this work, we proposed a discriminative model of Alzheimer's disease (AD) on the basis of multivariate pattern classification and functional magnetic resonance imaging (fMRI). This model used the correlation/anti-correlation coefficients of two intrinsically anti-correlated networks in resting brains, which have been suggested by two recent studies, as the feature of classification. Pseudo-Fisher Linear Discriminative Analysis (pFLDA) was then performed on the feature space and a linear classifier was generated. Using leave-one-out (LOO) cross validation, our results showed a correct classification rate of 83%. We also compared the proposed model with another one based on the whole brain functional connectivity. Our proposed model outperformed the other one significantly, and this implied that the two intrinsically anti-correlated networks may be a more susceptible part of the whole brain network in the early stage of AD.

Classification of High Intensity Zones of the Lumbar Spine and Their Association with Other Spinal MRI Phenotypes: The Wakayama Spine Study.

PubMed

Teraguchi, Masatoshi; Samartzis, Dino; Hashizume, Hiroshi; Yamada, Hiroshi; Muraki, Shigeyuki; Oka, Hiroyuki; Cheung, Jason Pui Yin; Kagotani, Ryohei; Iwahashi, Hiroki; Tanaka, Sakae; Kawaguchi, Hiroshi; Nakamura, Kozo; Akune, Toru; Cheung, Kenneth Man-Chee; Yoshimura, Noriko; Yoshida, Munehito

2016-01-01

High intensity zones (HIZ) of the lumbar spine are a phenotype of the intervertebral disc noted on MRI whose clinical relevance has been debated. Traditionally, T2-weighted (T2W) magnetic resonance imaging (MRI) has been utilized to identify HIZ of lumbar discs. However, controversy exists with regards to HIZ morphology, topography, and association with other MRI spinal phenotypes. Moreover, classification of HIZ has not been thoroughly defined in the past and the use of additional imaging parameters (e.g. T1W MRI) to assist in defining this phenotype has not been addressed. A cross-sectional study of 814 (69.8% females) subjects with mean age of 63.6 years from a homogenous Japanese population was performed. T2W and T1W sagittal 1.5T MRI was obtained on all subjects to assess HIZ from L1-S1. We created a morphological and topographical HIZ classification based on disc level, shape type (round, fissure, vertical, rim, and enlarged), location within the disc (posterior, anterior), and signal type on T1W MRI (low, high and iso intensity) in comparison to the typical high intensity on T2W MRI. HIZ was noted in 38.0% of subjects. Of these, the prevalence of posterior, anterior, and both posterior/anterior HIZ in the overall lumbar spine were 47.3%, 42.4%, and 10.4%, respectively. Posterior HIZ was most common, occurring at L4/5 (32.5%) and L5/S1 (47.0%), whereas anterior HIZ was most common at L3/4 (41.8%). T1W iso-intensity type of HIZ was most prevalent (71.8%), followed by T1W high-intensity (21.4%) and T1W low-intensity (6.8%). Of all discs, round types were most prevalent (anterior: 3.6%, posterior: 3.7%) followed by vertical type (posterior: 1.6%). At all affected levels, there was a significant association between HIZ and disc degeneration, disc bulge/protrusion and Modic type II (p<0.01). Posterior HIZ and T1W high-intensity type of HIZ were significantly associated with disc bulge/protrusion and disc degeneration (p<0.01). In addition, posterior HIZ was significantly associated with Modic type II and III. T1W low-intensity type of HIZ was significantly associated with Modic type II. This is the first large-scale study reporting a novel classification scheme of HIZ of the lumbar spine. This study is the first that has utilized T2W and T1W MRIs in differentiating HIZ sub-phenotypes. Specific HIZ sub-phenotypes were found to be more associated with specific MRI degenerative changes. With a more detailed description of the HIZ phenotype, this scheme can be standardized for future clinical and research initiatives.

Benign mural nodules within fluid collections at MRI after soft-tissue sarcoma resection.

PubMed

Lantos, Joshua E; Hwang, Sinchun; Panicek, David M

2014-06-01

The purpose of this study was to determine the prevalence and clinical significance of nodules within fluid collections on MRI after surgical resection of soft-tissue sarcoma. This retrospective study included 175 patients who underwent resection of primary soft-tissue sarcoma and whose postoperative MRI reports mentioned fluid. Images were reviewed to determine the presence of fluid collections of 1 cm or greater in diameter in the surgical bed and any nodule (measuring ≥ 0.7 cm) within the collection. Signal intensity and characteristics of each collection and rim and presence of septa or blood products were recorded. Size, signal intensity, and contrast enhancement of nodules were reviewed. Nodules were classified as benign or malignant on the basis of histologic results or clinical or MRI follow-up. Fluid collections were present in 75 patients. Of those, 45 collections (60%) showed homogeneous fluid signal intensity and 30 (40%) were heterogeneous; septa were present in 45 (60%) and blood products in 12 (16%). Most collections showed a thin rim (59%) and rim enhancement (88%). Nodules were present along the inner wall of six (8%) collections. Four (66%) nodules enhanced and two (33%) were T1 hyperintense. At follow-up MRI, two nodules were stable in size, one decreased, and three resolved. Nodules in three patients were biopsied; all were benign. Two other patients had no recurrence at follow-up, and another died at 3 months. A nodule within a postoperative fluid collection at MRI after soft-tissue sarcoma resection generally does not represent tumor recurrence; short-interval follow-up MRI is recommended rather than immediate biopsy.

Calibration standard of body tissue with magnetic nanocomposites for MRI and X-ray imaging

NASA Astrophysics Data System (ADS)

Rahn, Helene; Woodward, Robert; House, Michael; Engineer, Diana; Feindel, Kirk; Dutz, Silvio; Odenbach, Stefan; StPierre, Tim

2016-05-01

We present a first study of a long-term phantom for Magnetic Resonance Imaging (MRI) and X-ray imaging of biological tissues with magnetic nanocomposites (MNC) suitable for 3-dimensional and quantitative imaging of tissues after, e.g. magnetically assisted cancer treatments. We performed a cross-calibration of X-ray microcomputed tomography (XμCT) and MRI with a joint calibration standard for both imaging techniques. For this, we have designed a phantom for MRI and X-ray computed tomography which represents biological tissue enriched with MNC. The developed phantoms consist of an elastomer with different concentrations of multi-core MNC. The matrix material is a synthetic thermoplastic gel, PermaGel (PG). The developed phantoms have been analyzed with Nuclear Magnetic Resonance (NMR) Relaxometry (Bruker minispec mq 60) at 1.4 T to obtain R2 transverse relaxation rates, with SQUID (Superconducting QUantum Interference Device) magnetometry and Inductively Coupled Plasma Mass Spectrometry (ICP-MS) to verify the magnetite concentration, and with XμCT and 9.4 T MRI to visualize the phantoms 3-dimensionally and also to obtain T2 relaxation times. A specification of a sensitivity range is determined for standard imaging techniques X-ray computed tomography (XCT) and MRI as well as with NMR. These novel phantoms show a long-term stability over several months up to years. It was possible to suspend a particular MNC within the PG reaching a concentration range from 0 mg/ml to 6.914 mg/ml. The R2 relaxation rates from 1.4 T NMR-relaxometry show a clear connection (R2=0.994) with MNC concentrations between 0 mg/ml and 4.5 mg/ml. The MRI experiments have shown a linear correlation of R2 relaxation and MNC concentrations as well but in a range between MNC concentrations of 0 mg/ml and 1.435 mg/ml. It could be shown that XμCT displays best moderate and high MNC concentrations. The sensitivity range for this particular XμCT apparatus yields from 0.569 mg/ml to 6.914 mg/ml. The cross-calibration has defined a shared sensitivity range of XμCT, 1.4 T NMR relaxometer minispec, and 9.4 T MRI. The shared sensitivity range for the measuring method (NMR relaxometry) and the imaging modalities (XμCT and MRI) is from 0.569 mg/ml, limited by XμCT, and 1.435 mg/ml, limited by MRI. The presented phantoms have been found to be suitable to act as a body tissue substitute for XCT imaging as well as an acceptable T2 phantom of biological tissue enriched with magnetic nanoparticles for MRI.

Multimodal-3D imaging based on μMRI and μCT techniques bridges the gap with histology in visualization of the bone regeneration process.

PubMed

Sinibaldi, R; Conti, A; Sinjari, B; Spadone, S; Pecci, R; Palombo, M; Komlev, V S; Ortore, M G; Tromba, G; Capuani, S; Guidotti, R; De Luca, F; Caputi, S; Traini, T; Della Penna, S

2018-03-01

Bone repair/regeneration is usually investigated through X-ray computed microtomography (μCT) supported by histology of extracted samples, to analyse biomaterial structure and new bone formation processes. Magnetic resonance imaging (μMRI) shows a richer tissue contrast than μCT, despite at lower resolution, and could be combined with μCT in the perspective of conducting non-destructive 3D investigations of bone. A pipeline designed to combine μMRI and μCT images of bone samples is here described and applied on samples of extracted human jawbone core following bone graft. We optimized the coregistration procedure between μCT and μMRI images to avoid bias due to the different resolutions and contrasts. Furthermore, we used an Adaptive Multivariate Clustering, grouping homologous voxels in the coregistered images, to visualize different tissue types within a fused 3D metastructure. The tissue grouping matched the 2D histology applied only on 1 slice, thus extending the histology labelling in 3D. Specifically, in all samples, we could separate and map 2 types of regenerated bone, calcified tissue, soft tissues, and/or fat and marrow space. Remarkably, μMRI and μCT alone were not able to separate the 2 types of regenerated bone. Finally, we computed volumes of each tissue in the 3D metastructures, which might be exploited by quantitative simulation. The 3D metastructure obtained through our pipeline represents a first step to bridge the gap between the quality of information obtained from 2D optical microscopy and the 3D mapping of the bone tissue heterogeneity and could allow researchers and clinicians to non-destructively characterize and follow-up bone regeneration. Copyright © 2017 John Wiley & Sons, Ltd.

Evaluating Kurtosis-based Diffusion MRI Tissue Models for White Matter with Fiber Ball Imaging

PubMed Central

Jensen, Jens H.; McKinnon, Emilie T.; Glenn, G. Russell; Helpern, Joseph A.

2018-01-01

In order to quantify well-defined microstructural properties of brain tissue from diffusion MRI (dMRI) data, tissue models are typically employed that relate biological features, such as cell morphology and cell membrane permeability, to the diffusion dynamics. A variety of such models have been proposed for white matter, and their validation is a topic of active interest. In this paper, three different tissue models are tested by comparing their predictions for a specific microstructural parameter to the value measured independently with a recently proposed dMRI method known as fiber ball imaging (FBI). The three tissue models are all constructed with the diffusion and kurtosis tensors, and they are hence compatible with diffusional kurtosis imaging (DKI). Nevertheless, the models differ significantly in their details and predictions. For voxels with fractional anisotropies (FA) exceeding 0.5, all three are reasonably consistent with FBI. However, for lower FA values, one of these, called the white matter tract integrity (WMTI) model, is found to be in much better accord with FBI than the other two, suggesting that the WMTI model has a broader range of applicability. PMID:28085211

Correlation of MRI-derived adipose tissue measurements and anthropometric markers with prevalent hypertension in the community.

PubMed

Lorbeer, Roberto; Rospleszcz, Susanne; Schlett, Christopher L; Heber, Sophia D; Machann, Jürgen; Thorand, Barbara; Meisinger, Christa; Heier, Margit; Peters, Annette; Bamberg, Fabian; Lieb, Wolfgang

2018-07-01

To compare the correlations of MRI-derived adipose tissue measurements and anthropometric markers, respectively, with prevalent hypertension in a community-based sample, free of clinical cardiovascular disease. MRI-derived adipose tissue measurements were obtained in 345 participants (143 women; age 39-73 years) of the KORA FF4 survey from Southern Germany using a 3-Tesla machine and included total adipose tissue (TAT), visceral adipose tissue (VAT), subcutaneous adipose tissue (SCAT), hepatic fat fraction (HFF), pancreatic fat fraction (PFF) as well as pericardial adipose tissue (PAT). In addition, the anthropometric markers body mass index, waist circumference, hip circumference, waist-hip ratio (WHR) and waist-height ratio (WHtR) as well as blood pressure measurements were obtained. The prevalence of hypertension was 33.6% (women: 28%, men: 38%). VAT and PAT had the highest area under the curve (AUC) values for identifying individuals with prevalent hypertension (AUC: 0.75; 0.73, respectively), whereas WHtR and waist circumference were best performing anthropometric markers (AUC: 0.72; 0.70, respectively). A 1SD increment of TAT was associated with the highest odd for hypertension in the age-adjusted and sex-adjusted model (OR = 2.20, 95% CI 1.67-2.91, P < 0.001) and in the fully adjusted model (OR = 1.97, 95% CI 1.45-2.66, P < 0.001). TAT was the only MRI-derived adipose tissue measurement that was associated with hypertension independently of the best performing anthropometric marker waist circumference in the fully adjusted model (OR = 1.93, 95% CI 1.00-3.72, P = 0.049). MRI-derived adipose tissue measurements perform similarly in identifying prevalent hypertension compared with anthropometric markers. Especially, TAT, VAT and PAT as well as WHtR and waist circumference were highly correlated with prevalent hypertension.

Twelve-month prostate volume reduction after MRI-guided transurethral ultrasound ablation of the prostate.

PubMed

Bonekamp, David; Wolf, M B; Roethke, M C; Pahernik, S; Hadaschik, B A; Hatiboglu, G; Kuru, T H; Popeneciu, I V; Chin, J L; Billia, M; Relle, J; Hafron, J; Nandalur, K R; Staruch, R M; Burtnyk, M; Hohenfellner, M; Schlemmer, H-P

2018-06-25

To quantitatively assess 12-month prostate volume (PV) reduction based on T2-weighted MRI and immediate post-treatment contrast-enhanced MRI non-perfused volume (NPV), and to compare measurements with predictions of acute and delayed ablation volumes based on MR-thermometry (MR-t), in a central radiology review of the Phase I clinical trial of MRI-guided transurethral ultrasound ablation (TULSA) in patients with localized prostate cancer. Treatment day MRI and 12-month follow-up MRI and biopsy were available for central radiology review in 29 of 30 patients from the published institutional review board-approved, prospective, multi-centre, single-arm Phase I clinical trial of TULSA. Viable PV at 12 months was measured as the remaining PV on T2-weighted MRI, less 12-month NPV, scaled by the fraction of fibrosis in 12-month biopsy cores. Reduction of viable PV was compared to predictions based on the fraction of the prostate covered by the MR-t derived acute thermal ablation volume (ATAV, 55°C isotherm), delayed thermal ablation volume (DTAV, 240 cumulative equivalent minutes at 43°C thermal dose isocontour) and treatment-day NPV. We also report linear and volumetric comparisons between metrics. After TULSA, the median 12-month reduction in viable PV was 88%. DTAV predicted a reduction of 90%. Treatment day NPV predicted only 53% volume reduction, and underestimated ATAV and DTAV by 36% and 51%. Quantitative volumetry of the TULSA phase I MR and biopsy data identifies DTAV (240 CEM43 thermal dose boundary) as a useful predictor of viable prostate tissue reduction at 12 months. Immediate post-treatment NPV underestimates tissue ablation. • MRI-guided transurethral ultrasound ablation (TULSA) achieved an 88% reduction of viable prostate tissue volume at 12 months, in excellent agreement with expectation from thermal dose calculations. • Non-perfused volume on immediate post-treatment contrast-enhanced MRI represents only 64% of the acute thermal ablation volume (ATAV), and reports only 60% (53% instead of 88% achieved) of the reduction in viable prostate tissue volume at 12 months. • MR-thermometry-based predictions of 12-month prostate volume reduction based on 240 cumulative equivalent minute thermal dose volume are in excellent agreement with reduction in viable prostate tissue volume measured on pre- and 12-month post-treatment T2w-MRI.

What are the advantages and disadvantages of imaging modalities to diagnose wear-related corrosion problems?

PubMed

Nam, Denis; Barrack, Robert L; Potter, Hollis G

2014-12-01

Adverse tissue reactions are known to occur after total hip arthroplasty using both conventional and metal-on-metal (MoM) bearings and after MoM hip resurfacing arthroplasty (SRA). A variety of imaging tools, including ultrasound (US), CT, and MRI, have been used to diagnose problems associated with wear after MoM hip arthroplasty and corrosion at the head-trunnion junction; however, the relative advantages and disadvantages of each remain a source of controversy. The purposes of this review were to evaluate the advantages and disadvantages of (1) US; (2) CT; and (3) MRI as diagnostic tools in the assessment of wear-related corrosion problems after hip arthroplasty. A systematic literature review was performed through Medline, EMBASE, Scopus CINAHL, and the Cochrane Library without time restriction using search terms related to THA, SRA, US, CT, MRI, adverse tissue reactions, and corrosion. Inclusion criteria were Level I through IV studies in the English language, whereas expert opinions and case reports were excluded. The quality of included studies was judged by their level of evidence, method of intervention allocation, outcome assessments, and followup of patients. Four hundred ninety unique results were returned and 40 articles were reviewed. The prevalence of adverse local tissue reactions in both asymptomatic and symptomatic patients varies based on the method of evaluation (US, CT, MRI) and imaging protocols. US is accessible and relatively inexpensive, yet has not been used to report synovial thicknesses in the setting of wear-related corrosion. CT scans are highly sensitive and provide information regarding component positioning but are limited in providing enhanced soft tissue contrast and require ionizing radiation. MRI has shown promise in predicting both the presence and severity of adverse local tissue reactions but is more expensive. All three imaging modalities have a role in the assessment of adverse local tissue reactions and tribocorrosion after total hip arthroplasty. Although US may serve as a screening technique for the detection of larger periprosthetic collections, only MRI has been shown to predict the severity of tissue destruction found at revision and correlate to the degree of tissue necrosis at histologic evaluation.

Multi-atlas segmentation of subcortical brain structures via the AutoSeg software pipeline

PubMed Central

Wang, Jiahui; Vachet, Clement; Rumple, Ashley; Gouttard, Sylvain; Ouziel, Clémentine; Perrot, Emilie; Du, Guangwei; Huang, Xuemei; Gerig, Guido; Styner, Martin

2014-01-01

Automated segmenting and labeling of individual brain anatomical regions, in MRI are challenging, due to the issue of individual structural variability. Although atlas-based segmentation has shown its potential for both tissue and structure segmentation, due to the inherent natural variability as well as disease-related changes in MR appearance, a single atlas image is often inappropriate to represent the full population of datasets processed in a given neuroimaging study. As an alternative for the case of single atlas segmentation, the use of multiple atlases alongside label fusion techniques has been introduced using a set of individual “atlases” that encompasses the expected variability in the studied population. In our study, we proposed a multi-atlas segmentation scheme with a novel graph-based atlas selection technique. We first paired and co-registered all atlases and the subject MR scans. A directed graph with edge weights based on intensity and shape similarity between all MR scans is then computed. The set of neighboring templates is selected via clustering of the graph. Finally, weighted majority voting is employed to create the final segmentation over the selected atlases. This multi-atlas segmentation scheme is used to extend a single-atlas-based segmentation toolkit entitled AutoSeg, which is an open-source, extensible C++ based software pipeline employing BatchMake for its pipeline scripting, developed at the Neuro Image Research and Analysis Laboratories of the University of North Carolina at Chapel Hill. AutoSeg performs N4 intensity inhomogeneity correction, rigid registration to a common template space, automated brain tissue classification based skull-stripping, and the multi-atlas segmentation. The multi-atlas-based AutoSeg has been evaluated on subcortical structure segmentation with a testing dataset of 20 adult brain MRI scans and 15 atlas MRI scans. The AutoSeg achieved mean Dice coefficients of 81.73% for the subcortical structures. PMID:24567717

Quantifying the ultrastructure of carotid arteries using high-resolution micro-diffusion tensor imaging—comparison of intact versus open cut tissue

NASA Astrophysics Data System (ADS)

Salman Shahid, Syed; Gaul, Robert T.; Kerskens, Christian; Flamini, Vittoria; Lally, Caitríona

2017-12-01

Diffusion magnetic resonance imaging (dMRI) can provide insights into the microstructure of intact arterial tissue. The current study employed high magnetic field MRI to obtain ultra-high resolution dMRI at an isotropic voxel resolution of 117 µm3 in less than 2 h of scan time. A parameter selective single shell (128 directions) diffusion-encoding scheme based on Stejskel-Tanner sequence with echo-planar imaging (EPI) readout was used. EPI segmentation was used to reduce the echo time (TE) and to minimise the susceptibility-induced artefacts. The study utilised the dMRI analysis with diffusion tensor imaging (DTI) framework to investigate structural heterogeneity in intact arterial tissue and to quantify variations in tissue composition when the tissue is cut open and flattened. For intact arterial samples, the region of interest base comparison showed significant differences in fractional anisotropy and mean diffusivity across the media layer (p  <  0.05). For open cut flat samples, DTI based directionally invariant indices did not show significant differences across the media layer. For intact samples, fibre tractography based indices such as calculated helical angle and fibre dispersion showed near circumferential alignment and a high degree of fibre dispersion, respectively. This study demonstrates the feasibility of fast dMRI acquisition with ultra-high spatial and angular resolution at 7 T. Using the optimised sequence parameters, this study shows that DTI based markers are sensitive to local structural changes in intact arterial tissue samples and these markers may have clinical relevance in the diagnosis of atherosclerosis and aneurysm.

Evaluation of multimodality imaging using image fusion with ultrasound tissue elasticity imaging in an experimental animal model.

PubMed

Paprottka, P M; Zengel, P; Cyran, C C; Ingrisch, M; Nikolaou, K; Reiser, M F; Clevert, D A

2014-01-01

To evaluate the ultrasound tissue elasticity imaging by comparison to multimodality imaging using image fusion with Magnetic Resonance Imaging (MRI) and conventional grey scale imaging with additional elasticity-ultrasound in an experimental small-animal-squamous-cell carcinoma-model for the assessment of tissue morphology. Human hypopharynx carcinoma cells were subcutaneously injected into the left flank of 12 female athymic nude rats. After 10 days (SD ± 2) of subcutaneous tumor growth, sonographic grey scale including elasticity imaging and MRI measurements were performed using a high-end ultrasound system and a 3T MR. For image fusion the contrast-enhanced MRI DICOM data set was uploaded in the ultrasonic device which has a magnetic field generator, a linear array transducer (6-15 MHz) and a dedicated software package (GE Logic E9), that can detect transducers by means of a positioning system. Conventional grey scale and elasticity imaging were integrated in the image fusion examination. After successful registration and image fusion the registered MR-images were simultaneously shown with the respective ultrasound sectional plane. Data evaluation was performed using the digitally stored video sequence data sets by two experienced radiologist using a modified Tsukuba Elasticity score. The colors "red and green" are assigned for an area of soft tissue, "blue" indicates hard tissue. In all cases a successful image fusion and plan registration with MRI and ultrasound imaging including grey scale and elasticity imaging was possible. The mean tumor volume based on caliper measurements in 3 dimensions was ~323 mm3. 4/12 rats were evaluated with Score I, 5/12 rates were evaluated with Score II, 3/12 rates were evaluated with Score III. There was a close correlation in the fused MRI with existing small necrosis in the tumor. None of the scored II or III lesions was visible by conventional grey scale. The comparison of ultrasound tissue elasticity imaging enables a secure differentiation between different tumor tissue areas in comparison to image fusion with MRI in our small study group. Therefore ultrasound tissue elasticity imaging might be used for fast detection of tumor response in the future whereas conventional grey scale imaging alone could not provide the additional information. By using standard, contrast-enhanced MRI images for reliable and reproducible slice positioning, the strongly user-dependent limitation of ultrasound tissue elasticity imaging may be overcome, especially for a comparison between baseline and follow-up measurements.

Sparse Multivariate Autoregressive Modeling for Mild Cognitive Impairment Classification

PubMed Central

Li, Yang; Wee, Chong-Yaw; Jie, Biao; Peng, Ziwen

2014-01-01

Brain connectivity network derived from functional magnetic resonance imaging (fMRI) is becoming increasingly prevalent in the researches related to cognitive and perceptual processes. The capability to detect causal or effective connectivity is highly desirable for understanding the cooperative nature of brain network, particularly when the ultimate goal is to obtain good performance of control-patient classification with biological meaningful interpretations. Understanding directed functional interactions between brain regions via brain connectivity network is a challenging task. Since many genetic and biomedical networks are intrinsically sparse, incorporating sparsity property into connectivity modeling can make the derived models more biologically plausible. Accordingly, we propose an effective connectivity modeling of resting-state fMRI data based on the multivariate autoregressive (MAR) modeling technique, which is widely used to characterize temporal information of dynamic systems. This MAR modeling technique allows for the identification of effective connectivity using the Granger causality concept and reducing the spurious causality connectivity in assessment of directed functional interaction from fMRI data. A forward orthogonal least squares (OLS) regression algorithm is further used to construct a sparse MAR model. By applying the proposed modeling to mild cognitive impairment (MCI) classification, we identify several most discriminative regions, including middle cingulate gyrus, posterior cingulate gyrus, lingual gyrus and caudate regions, in line with results reported in previous findings. A relatively high classification accuracy of 91.89 % is also achieved, with an increment of 5.4 % compared to the fully-connected, non-directional Pearson-correlation-based functional connectivity approach. PMID:24595922

Recurrent neural networks for breast lesion classification based on DCE-MRIs

NASA Astrophysics Data System (ADS)

Antropova, Natasha; Huynh, Benjamin; Giger, Maryellen

2018-02-01

Dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) plays a significant role in breast cancer screening, cancer staging, and monitoring response to therapy. Recently, deep learning methods are being rapidly incorporated in image-based breast cancer diagnosis and prognosis. However, most of the current deep learning methods make clinical decisions based on 2-dimentional (2D) or 3D images and are not well suited for temporal image data. In this study, we develop a deep learning methodology that enables integration of clinically valuable temporal components of DCE-MRIs into deep learning-based lesion classification. Our work is performed on a database of 703 DCE-MRI cases for the task of distinguishing benign and malignant lesions, and uses the area under the ROC curve (AUC) as the performance metric in conducting that task. We train a recurrent neural network, specifically a long short-term memory network (LSTM), on sequences of image features extracted from the dynamic MRI sequences. These features are extracted with VGGNet, a convolutional neural network pre-trained on a large dataset of natural images ImageNet. The features are obtained from various levels of the network, to capture low-, mid-, and high-level information about the lesion. Compared to a classification method that takes as input only images at a single time-point (yielding an AUC = 0.81 (se = 0.04)), our LSTM method improves lesion classification with an AUC of 0.85 (se = 0.03).

Tissue classification using depth-dependent ultrasound time series analysis: in-vitro animal study

NASA Astrophysics Data System (ADS)

Imani, Farhad; Daoud, Mohammad; Moradi, Mehdi; Abolmaesumi, Purang; Mousavi, Parvin

2011-03-01

Time series analysis of ultrasound radio-frequency (RF) signals has been shown to be an effective tissue classification method. Previous studies of this method for tissue differentiation at high and clinical-frequencies have been reported. In this paper, analysis of RF time series is extended to improve tissue classification at the clinical frequencies by including novel features extracted from the time series spectrum. The primary feature examined is the Mean Central Frequency (MCF) computed for regions of interest (ROIs) in the tissue extending along the axial axis of the transducer. In addition, the intercept and slope of a line fitted to the MCF-values of the RF time series as a function of depth have been included. To evaluate the accuracy of the new features, an in vitro animal study is performed using three tissue types: bovine muscle, bovine liver, and chicken breast, where perfect two-way classification is achieved. The results show statistically significant improvements over the classification accuracies with previously reported features.

The role of T1 perfusion-based classification in magnetic resonance-guided high-intensity focused ultrasound ablation of uterine fibroids.

PubMed

Keserci, Bilgin; Duc, Nguyen Minh

2017-12-01

To comparatively evaluate the role of magnetic resonance (MR) T1 perfusion-based time-signal intensity (SI) curves of fibroid tissue and the myometrium in classification of fibroids for predicting treatment outcomes of high-intensity focused ultrasound (HIFU) treatment. The fibroids of 74 women who underwent MR-HIFU treatment were classified into group A (time-SI curve of fibroid lower than that of the myometrium) and group B (time-SI curve of fibroid equal to or higher than that of the myometrium). Non-perfused volume (NPV) ratios immediately after treatment and fibroid volume reduction ratios and symptom severity scores (SSS) at the 6-month follow-up were retrospectively assessed. The immediate NPV ratios in groups A and B were 95.3 ± 6.3% (n = 62) and 63.8 ± 11% (n = 12), respectively. At the 6-month follow-up, the fibroid volume reduction ratios in groups A and B were 0.52 ± 0.14 (n = 50) and 0.07 ± 0.14 (n = 11), with the corresponding improvement in mean transformed SSS being 0.86 ± 0.14 and 0.19 ± 0.3, respectively. No serious adverse effects were reported. Our novel classification method could play an important role in classifying fibroids for predicting the immediate outcomes of HIFU treatment. • MRI is an important modality for outcome prediction in HIFU treatment • Patient selection is a significant factor for achieving high NPV ratio • NPV ratio is very strongly correlated with T1 perfusion-based classification • T1 perfusion-based classification is a strong predictor of treatment outcome.

DCE-MRI: a review and applications in veterinary oncology.

PubMed

Boss, M Keara; Muradyan, N; Thrall, D E

2013-06-01

Dynamic contrast enhanced magnetic resonance imaging (DCE-MRI) is a functional imaging technique that assesses the physiology of tumour tissue by exploiting abnormal tumour microvasculature. Advances made through DCE-MRI include improvement in the diagnosis of cancer, optimization of treatment choices, assessment of treatment efficacy and non-invasive identification of prognostic information. DCE-MRI enables quantitative assessment of tissue vessel density, integrity, and permeability, and this information can be applied to study of angiogenesis, hypoxia and the evaluation of various biomarkers. Reproducibility of DCE-MRI results is important in determining the significance of observed changes in the parameters. As improvements are made towards the utility of DCE-MRI and interpreting biologic associations, the technique will be applied more frequently in the study of cancer in animals. Given the importance of tumour perfusion with respect to tumour oxygenation and drug delivery, the use of DCE-MRI is a convenient and powerful way to gain basic information about a tumour. © 2011 John Wiley & Sons Ltd.

PAIR Comparison between Two Within-Group Conditions of Resting-State fMRI Improves Classification Accuracy

PubMed Central

Zhou, Zhen; Wang, Jian-Bao; Zang, Yu-Feng; Pan, Gang

2018-01-01

Classification approaches have been increasingly applied to differentiate patients and normal controls using resting-state functional magnetic resonance imaging data (RS-fMRI). Although most previous classification studies have reported promising accuracy within individual datasets, achieving high levels of accuracy with multiple datasets remains challenging for two main reasons: high dimensionality, and high variability across subjects. We used two independent RS-fMRI datasets (n = 31, 46, respectively) both with eyes closed (EC) and eyes open (EO) conditions. For each dataset, we first reduced the number of features to a small number of brain regions with paired t-tests, using the amplitude of low frequency fluctuation (ALFF) as a metric. Second, we employed a new method for feature extraction, named the PAIR method, examining EC and EO as paired conditions rather than independent conditions. Specifically, for each dataset, we obtained EC minus EO (EC—EO) maps of ALFF from half of subjects (n = 15 for dataset-1, n = 23 for dataset-2) and obtained EO—EC maps from the other half (n = 16 for dataset-1, n = 23 for dataset-2). A support vector machine (SVM) method was used for classification of EC RS-fMRI mapping and EO mapping. The mean classification accuracy of the PAIR method was 91.40% for dataset-1, and 92.75% for dataset-2 in the conventional frequency band of 0.01–0.08 Hz. For cross-dataset validation, we applied the classifier from dataset-1 directly to dataset-2, and vice versa. The mean accuracy of cross-dataset validation was 94.93% for dataset-1 to dataset-2 and 90.32% for dataset-2 to dataset-1 in the 0.01–0.08 Hz range. For the UNPAIR method, classification accuracy was substantially lower (mean 69.89% for dataset-1 and 82.97% for dataset-2), and was much lower for cross-dataset validation (64.69% for dataset-1 to dataset-2 and 64.98% for dataset-2 to dataset-1) in the 0.01–0.08 Hz range. In conclusion, for within-group design studies (e.g., paired conditions or follow-up studies), we recommend the PAIR method for feature extraction. In addition, dimensionality reduction with strong prior knowledge of specific brain regions should also be considered for feature selection in neuroimaging studies. PMID:29375288

Analysis of dual tree M-band wavelet transform based features for brain image classification.

PubMed

Ayalapogu, Ratna Raju; Pabboju, Suresh; Ramisetty, Rajeswara Rao

2018-04-29

The most complex organ in the human body is the brain. The unrestrained growth of cells in the brain is called a brain tumor. The cause of a brain tumor is still unknown and the survival rate is lower than other types of cancers. Hence, early detection is very important for proper treatment. In this study, an efficient computer-aided diagnosis (CAD) system is presented for brain image classification by analyzing MRI of the brain. At first, the MRI brain images of normal and abnormal categories are modeled by using the statistical features of dual tree m-band wavelet transform (DTMBWT). A maximum margin classifier, support vector machine (SVM) is then used for the classification and validated with k-fold approach. Results show that the system provides promising results on a repository of molecular brain neoplasia data (REMBRANDT) with 97.5% accuracy using 4 th level statistical features of DTMBWT. Viewing the experimental results, we conclude that the system gives a satisfactory performance for the brain image classification. © 2018 International Society for Magnetic Resonance in Medicine.

Quantitative evaluation of ischemic myocardial scar tissue by unenhanced T1 mapping using 3.0 Tesla MR scanner

PubMed Central

Okur, Aylin; Kantarcı, Mecit; Kızrak, Yeşim; Yıldız, Sema; Pirimoğlu, Berhan; Karaca, Leyla; Oğul, Hayri; Sevimli, Serdar

2014-01-01

PURPOSE We aimed to use a noninvasive method for quantifying T1 values of chronic myocardial infarction scar by cardiac magnetic resonance imaging (MRI), and determine its diagnostic performance. MATERIALS AND METHODS We performed cardiac MRI on 29 consecutive patients with known coronary artery disease (CAD) on 3.0 Tesla MRI scanner. An unenhanced T1 mapping technique was used to calculate T1 relaxation time of myocardial scar tissue, and its diagnostic performance was evaluated. Chronic scar tissue was identified by delayed contrast-enhancement (DE) MRI and T2-weighted images. Sensitivity, specificity, and accuracy values were calculated for T1 mapping using DE images as the gold standard. RESULTS Four hundred and forty-two segments were analyzed in 26 patients. While myocardial chronic scar was demonstrated in 45 segments on DE images, T1 mapping MRI showed a chronic scar area in 54 segments. T1 relaxation time was higher in chronic scar tissue, compared with remote areas (1314±98 ms vs. 1099±90 ms, P < 0.001). Therefore, increased T1 values were shown in areas of myocardium colocalized with areas of DE and normal signal on T2-weighted images. There was a significant correlation between T1 mapping and DE images in evaluation of myocardial wall injury extent (P < 0.05). We calculated sensitivity, specificity, and accuracy as 95.5%, 97%, and 96%, respectively. CONCLUSION The results of the present study reveal that T1 mapping MRI combined with T2-weighted images might be a feasible imaging modality for detecting chronic myocardial infarction scar tissue. PMID:25010366

DCE-MRI as a predictor of clinical outcome in canine spontaneous soft-tissue sarcomas treated with thermoradiotherapy

PubMed Central

Viglianti, BL; Lora-Michiels, M; Poulson, JM; Lan, Lan; Yu, D; Sanders, L; Craciunescu, O; Vujaskovic, Z; Thrall, DE; MacFall, J; Charles, HC; Wong, T; Dewhirst, MW

2009-01-01

Purpose This study tests whether DCE-MRI parameters obtained from canine patients with soft tissue sarcomas, treated with hyperthermia and radiotherapy, are predictive of therapeutic outcome. Experimental Design 37 dogs with soft tissue sarcomas had DCE-MRI performed prior to and following the first hyperthermia. Signal enhancement for tumor and reference muscle were fitted empirically, yielding a washin/washout rate for the contrast agent, tumor AUC calculated from 0 to 60s, 90s, and the time of maximal enhancement in the reference muscle. These parameters were then compared to local tumor control, metastasis free survival, and overall survival. Results Pre-therapy rate of contrast agent washout was positively predictive of improved overall survival and metastasis free survival with hazard ratio of 0.67 (p = 0.015) and 0.68 (p = 0.012) respectively. After the first hyperthermia washin rate, AUC60, AUC90, and AUCt-max, were predictive of improved overall survivaloverall survival and metastasis free survival with hazard ratio ranging from 0.46 to 0.53 (p < 0.002) and 0.44 to 0.55 (p < 0.004), respectively. DCE-MRI parameters were compared with extracellular pH and 31-P-MR spectroscopy results (previously published) in the same patients demonstrating a correlation. This suggested that an increase in perfusion after therapy was effective in eliminating excess acid from the tumor. Conclusions This study demonstrates that DCE-MRI has utility predicting overall survivaloverall survival and metastasis free survival in canine patients with soft tissue sarcomas. To our knowledge, this is the first time that DCE-MRI parameters have been shown to be predictive of clinical outcome for soft tissue sarcomas. PMID:19622579

Cervical soft tissue imaging using a mobile CBCT scanner with a flat panel detector in comparison with corresponding CT and MRI data sets.

PubMed

Heiland, Max; Pohlenz, Philipp; Blessmann, Marco; Habermann, Christian R; Oesterhelweg, Lars; Begemann, Philipp C; Schmidgunst, Christian; Blake, Felix A S; Püschel, Klaus; Schmelzle, Rainer; Schulze, Dirk

2007-12-01

The aim of this study was to evaluate soft tissue image quality of a mobile cone-beam computed tomography (CBCT) scanner with an integrated flat-panel detector. Eight fresh human cadavers were used in this study. For evaluation of soft tissue visualization, CBCT data sets and corresponding computed tomography (CT) and magnetic resonance imaging (MRI) data sets were acquired. Evaluation was performed with the help of 10 defined cervical anatomical structures. The statistical analysis of the scoring results of 3 examiners revealed the CBCT images to be of inferior quality regarding the visualization of most of the predefined structures. Visualization without a significant difference was found regarding the demarcation of the vertebral bodies and the pyramidal cartilages, the arteriosclerosis of the carotids (compared with CT), and the laryngeal skeleton (compared with MRI). Regarding arteriosclerosis of the carotids compared with MRI, CBCT proved to be superior. The integration of a flat-panel detector improves soft tissue visualization using a mobile CBCT scanner.

Brain Tissue Compartment Density Estimated Using Diffusion-Weighted MRI Yields Tissue Parameters Consistent With Histology

PubMed Central

Sepehrband, Farshid; Clark, Kristi A.; Ullmann, Jeremy F.P.; Kurniawan, Nyoman D.; Leanage, Gayeshika; Reutens, David C.; Yang, Zhengyi

2015-01-01

We examined whether quantitative density measures of cerebral tissue consistent with histology can be obtained from diffusion magnetic resonance imaging (MRI). By incorporating prior knowledge of myelin and cell membrane densities, absolute tissue density values were estimated from relative intra-cellular and intra-neurite density values obtained from diffusion MRI. The NODDI (neurite orientation distribution and density imaging) technique, which can be applied clinically, was used. Myelin density estimates were compared with the results of electron and light microscopy in ex vivo mouse brain and with published density estimates in a healthy human brain. In ex vivo mouse brain, estimated myelin densities in different sub-regions of the mouse corpus callosum were almost identical to values obtained from electron microscopy (Diffusion MRI: 42±6%, 36±4% and 43±5%; electron microscopy: 41±10%, 36±8% and 44±12% in genu, body and splenium, respectively). In the human brain, good agreement was observed between estimated fiber density measurements and previously reported values based on electron microscopy. Estimated density values were unaffected by crossing fibers. PMID:26096639

Support vector machine for breast cancer classification using diffusion-weighted MRI histogram features: Preliminary study.

PubMed

Vidić, Igor; Egnell, Liv; Jerome, Neil P; Teruel, Jose R; Sjøbakk, Torill E; Østlie, Agnes; Fjøsne, Hans E; Bathen, Tone F; Goa, Pål Erik

2018-05-01

Diffusion-weighted MRI (DWI) is currently one of the fastest developing MRI-based techniques in oncology. Histogram properties from model fitting of DWI are useful features for differentiation of lesions, and classification can potentially be improved by machine learning. To evaluate classification of malignant and benign tumors and breast cancer subtypes using support vector machine (SVM). Prospective. Fifty-one patients with benign (n = 23) and malignant (n = 28) breast tumors (26 ER+, whereof six were HER2+). Patients were imaged with DW-MRI (3T) using twice refocused spin-echo echo-planar imaging with echo time / repetition time (TR/TE) = 9000/86 msec, 90 × 90 matrix size, 2 × 2 mm in-plane resolution, 2.5 mm slice thickness, and 13 b-values. Apparent diffusion coefficient (ADC), relative enhanced diffusivity (RED), and the intravoxel incoherent motion (IVIM) parameters diffusivity (D), pseudo-diffusivity (D*), and perfusion fraction (f) were calculated. The histogram properties (median, mean, standard deviation, skewness, kurtosis) were used as features in SVM (10-fold cross-validation) for differentiation of lesions and subtyping. Accuracies of the SVM classifications were calculated to find the combination of features with highest prediction accuracy. Mann-Whitney tests were performed for univariate comparisons. For benign versus malignant tumors, univariate analysis found 11 histogram properties to be significant differentiators. Using SVM, the highest accuracy (0.96) was achieved from a single feature (mean of RED), or from three feature combinations of IVIM or ADC. Combining features from all models gave perfect classification. No single feature predicted HER2 status of ER + tumors (univariate or SVM), although high accuracy (0.90) was achieved with SVM combining several features. Importantly, these features had to include higher-order statistics (kurtosis and skewness), indicating the importance to account for heterogeneity. Our findings suggest that SVM, using features from a combination of diffusion models, improves prediction accuracy for differentiation of benign versus malignant breast tumors, and may further assist in subtyping of breast cancer. 3 Technical Efficacy: Stage 3 J. Magn. Reson. Imaging 2018;47:1205-1216. © 2017 International Society for Magnetic Resonance in Medicine.

The molecular origin of a loading-induced black layer in the deep region of articular cartilage at the magic angle

PubMed Central

Wang, Nian; Kahn, David; Badar, Farid; Xia, Yang

2014-01-01

Purpose To investigate the molecular origin of an unusual low-intensity layer in the deep region of articular cartilage as seen in MRI when the tissue is imaged under compression and oriented at the magic angle. Materials and Methods Microscopic MRI (μMRI) T2 and T1ρ experiments were carried out for both native and degraded (treated with trypsin) 18 specimens. The glycosaminoglycan (GAG) concentrations in the specimens were quantified by both sodium ICP-OES and μMRI Gd(DTPA)2--contrast methods. The mechanical modulus of the specimens was also measured. Results Native tissue shows no load-induced layer, while the trypsin-degraded tissue shows clearly the low-intensity line at the deep part of tissue. The GAG reductions are confirmed by the sodium ICP-OES (from 81.7 ± 5.4 mg/ml to 9.2 ± 3.4 mg/ml), MRI GAG quantification (from 72.4 ± 6.7 mg/ml to 11.2 ± 2.9 mg/ml). The modulus reduction is confirmed by biomechanics (from 4.3 ± 0.7 MPa to 0.3 ± 0.1 MPa). Conclusion Both T2 and T1ρ profiles in native and degraded cartilage show strongly strain-, depth-, and angle-dependent using high resolution MRI. The GAG reduction is responsible for the visualization of a low-intensity layer in deep cartilage when it is loaded and orientated at 55°. PMID:24833266

REAL TIME MRI GUIDED RADIOFREQUENCY ATRIAL ABLATION AND VISUALIZATION OF LESION FORMATION AT 3-TESLA

PubMed Central

Vergara, Gaston R.; Vijayakumar, Sathya; Kholmovski, Eugene G.; Blauer, Joshua J.E.; Guttman, Mike A.; Gloschat, Christopher; Payne, Gene; Vij, Kamal; Akoum, Nazem W.; Daccarett, Marcos; McGann, Christopher J.; MacLeod, Rob S.; Marrouche, Nassir F.

2011-01-01

Background MRI allows visualization of location and extent of RF ablation lesion, myocardial scar formation, and real-time (RT) assessment of lesion formation. In this study, we report a novel 3-Tesla RT-MRI based porcine RF ablation model and visualization of lesion formation in the atrium during RF energy delivery. Objective To develop of a 3-Tesla RT-MRI based catheter ablation and lesion visualization system. Methods RF energy was delivered to six pigs under RT-MRI guidance. A novel MRI compatible mapping and ablation catheter was used. Under RT-MRI this catheter was safely guided and positioned within either the left or right atrium. Unipolar and bi-polar electrograms were recorded. The catheter tip-tissue interface was visualized with a T1-weighted gradient echo sequence. RF energy was then delivered in a power-controlled fashion. Myocardial changes and lesion formation were visualized with a T2-weighted (T2w) HASTE sequence during ablation. Results Real-time visualization of lesion formation was achieved in 30% of the ablations performed. In the other cases, either the lesion was formed outside the imaged region (25%) or lesion was not created (45%) presumably due to poor tissue-catheter tip contact. The presence of lesions was confirmed by late gadolinium enhancement (LGE) MRI and macroscopic tissue examination. Conclusion MRI compatible catheters can be navigated and RF energy safely delivered under 3-Tesla RT-MRI guidance. It is also feasible to record electrograms during RT imaging. Real-time visualization of lesion as it forms during delivery of RF energy is possible and was demonstrated using T2w HASTE imaging. PMID:21034854

Multimodal 18F-Fluciclovine PET/MRI and Ultrasound-Guided Neurosurgery of an Anaplastic Oligodendroglioma.

PubMed

Karlberg, Anna; Berntsen, Erik Magnus; Johansen, Håkon; Myrthue, Mariane; Skjulsvik, Anne Jarstein; Reinertsen, Ingerid; Esmaeili, Morteza; Dai, Hong Yan; Xiao, Yiming; Rivaz, Hassan; Borghammer, Per; Solheim, Ole; Eikenes, Live

2017-12-01

Structural magnetic resonance imaging (MRI) and histopathologic tissue sampling are routinely performed as part of the diagnostic workup for patients with glioma. Because of the heterogeneous nature of gliomas, there is a risk of undergrading caused by histopathologic sampling errors. MRI has limitations in identifying tumor grade and type, detecting diffuse invasive growth, and separating recurrences from treatment induced changes. Positron emission tomography (PET) can provide quantitative information of cellular activity and metabolism, and may therefore complement MRI. In this report, we present the first patient with brain glioma examined with simultaneous PET/MRI using the amino acid tracer 18 F-fluciclovine ( 18 F-FACBC) for intraoperative image-guided surgery. A previously healthy 60-year old woman was admitted to the emergency care with speech difficulties and a mild left-sided hemiparesis. MRI revealed a tumor that was suggestive of glioma. Before surgery, the patient underwent a simultaneous PET/MRI examination. Fused PET/MRI, T1, FLAIR, and intraoperative three-dimensional ultrasound images were used to guide histopathologic tissue sampling and surgical resection. Navigated, image-guided histopathologic samples were compared with PET/MRI image data to assess the additional value of the PET acquisition. Histopathologic analysis showed anaplastic oligodendroglioma in the most malignant parts of the tumor, while several regions were World Health Organization (WHO) grade II. 18 F-Fluciclovine uptake was found in parts of the tumor where regional WHO grade, cell proliferation, and cell densities were highest. This finding suggests that PET/MRI with this tracer could be used to improve accuracy in histopathologic tissue sampling and grading, and possibly for guiding treatments targeting the most malignant part of extensive and eloquent gliomas. Copyright © 2017 The Author(s). Published by Elsevier Inc. All rights reserved.

Non-invasive imaging of transplanted human neural stem cells and ECM scaffold remodeling in the stroke-damaged rat brain by (19)F- and diffusion-MRI.

PubMed

Bible, Ellen; Dell'Acqua, Flavio; Solanky, Bhavana; Balducci, Anthony; Crapo, Peter M; Badylak, Stephen F; Ahrens, Eric T; Modo, Michel

2012-04-01

Transplantation of human neural stem cells (hNSCs) is emerging as a viable treatment for stroke related brain injury. However, intraparenchymal grafts do not regenerate lost tissue, but rather integrate into the host parenchyma without significantly affecting the lesion cavity. Providing a structural support for the delivered cells appears important for cell based therapeutic approaches. The non-invasive monitoring of therapeutic methods would provide valuable information regarding therapeutic strategies but remains a challenge. Labeling transplanted cells with metal-based (1)H-magnetic resonance imaging (MRI) contrast agents affects the visualization of the lesion cavity. Herein, we demonstrate that a (19)F-MRI contrast agent can adequately monitor the distribution of transplanted cells, whilst allowing an evaluation of the lesion cavity and the formation of new tissue on (1)H-MRI scans. Twenty percent of cells labeled with the (19)F agent were of host origin, potentially reflecting the re-uptake of label from dead transplanted cells. Both T(2)- and diffusion-weighted MRI scans indicated that transplantation of hNSCs suspended in a gel form of a xenogeneic extracellular matrix (ECM) bioscaffold resulted in uniformly distributed cells throughout the lesion cavity. However, diffusion MRI indicated that the injected materials did not yet establish diffusion barriers (i.e. cellular network, fiber tracts) normally found within striatal tissue. The ECM bioscaffold therefore provides an important support to hNSCs for the creation of de novo tissue and multi-nuclei MRI represents an adept method for the visualization of some aspects of this process. However, significant developments of both the transplantation paradigm, as well as regenerative imaging, are required to successfully create new tissue in the lesion cavity and to monitor this process non-invasively. Copyright © 2011 Elsevier Ltd. All rights reserved.

Application of Quantitative MRI for Brain Tissue Segmentation at 1.5 T and 3.0 T Field Strengths

PubMed Central

West, Janne; Blystad, Ida; Engström, Maria; Warntjes, Jan B. M.; Lundberg, Peter

2013-01-01

Background Brain tissue segmentation of white matter (WM), grey matter (GM), and cerebrospinal fluid (CSF) are important in neuroradiological applications. Quantitative Mri (qMRI) allows segmentation based on physical tissue properties, and the dependencies on MR scanner settings are removed. Brain tissue groups into clusters in the three dimensional space formed by the qMRI parameters R1, R2 and PD, and partial volume voxels are intermediate in this space. The qMRI parameters, however, depend on the main magnetic field strength. Therefore, longitudinal studies can be seriously limited by system upgrades. The aim of this work was to apply one recently described brain tissue segmentation method, based on qMRI, at both 1.5 T and 3.0 T field strengths, and to investigate similarities and differences. Methods In vivo qMRI measurements were performed on 10 healthy subjects using both 1.5 T and 3.0 T MR scanners. The brain tissue segmentation method was applied for both 1.5 T and 3.0 T and volumes of WM, GM, CSF and brain parenchymal fraction (BPF) were calculated on both field strengths. Repeatability was calculated for each scanner and a General Linear Model was used to examine the effect of field strength. Voxel-wise t-tests were also performed to evaluate regional differences. Results Statistically significant differences were found between 1.5 T and 3.0 T for WM, GM, CSF and BPF (p<0.001). Analyses of main effects showed that WM was underestimated, while GM and CSF were overestimated on 1.5 T compared to 3.0 T. The mean differences between 1.5 T and 3.0 T were -66 mL WM, 40 mL GM, 29 mL CSF and -1.99% BPF. Voxel-wise t-tests revealed regional differences of WM and GM in deep brain structures, cerebellum and brain stem. Conclusions Most of the brain was identically classified at the two field strengths, although some regional differences were observed. PMID:24066153

Magnetic resonance imaging (MRI) of hormone-induced breast changes in young premenopausal women.

PubMed

Clendenen, Tess V; Kim, Sungheon; Moy, Linda; Wan, Livia; Rusinek, Henry; Stanczyk, Frank Z; Pike, Malcolm C; Zeleniuch-Jacquotte, Anne

2013-01-01

We conducted a pilot study to identify whether MRI parameters are sensitive to hormone-induced changes in the breast during the natural menstrual cycle and whether changes could also be observed during an oral contraceptive (OC) cycle. The New York University Langone Medical Center Institutional Review Board approved this HIPAA-compliant prospective study. All participants provided written informed consent. Participants were aged 24-31 years.We measured several non-contrast breast MRI parameters during each week of a single menstrual cycle (among 9 women) and OC cycle (among 8 women). Hormones were measured to confirm ovulation and classify menstrual cycle phase among naturally cycling women and to monitor OC compliance among OC users. We investigated how the non-contrast MRI parameters of breast fibroglandular tissue (FGT), apparent diffusion coefficient (ADC), magnetization transfer ratio (MTR), and transverse relaxation time (T2) varied over the natural and the OC cycles. We observed significant increases in MRI FGT% and ADC in FGT, and longer T2 in FGT in the luteal vs. follicular phase of the menstrual cycle. We did not observe any consistent pattern of change for any of the MRI parameters among women using OCs. MRI is sensitive to hormone-induced breast tissue changes during the menstrual cycle. Larger studies are needed to assess whether MRI is also sensitive to the effects of exogenous hormones, such as various OC formulations, on the breast tissue of young premenopausal women. Copyright © 2013 Elsevier Inc. All rights reserved.

Surgical Accuracy of 3-Tesla Versus 7-Tesla Magnetic Resonance Imaging in Deep Brain Stimulation for Parkinson Disease.

PubMed

van Laar, Peter Jan; Oterdoom, D L Marinus; Ter Horst, Gert J; van Hulzen, Arjen L J; de Graaf, Eva K L; Hoogduin, Hans; Meiners, Linda C; van Dijk, J Marc C

2016-09-01

In deep brain stimulation (DBS), accurate placement of the lead is critical. Target definition is highly dependent on visual recognition on magnetic resonance imaging (MRI). We prospectively investigated whether the 7-T MRI enabled better visualization of targets and led to better placement of leads compared with the 1.5-T and the 3-T MRI. Three patients with PD (mean, 55 years) were scanned on 1.5-, 3-, and 7-T MRI before surgery. Tissue contrast and signal-to-noise ratio were measured. Target coordinates were noted on MRI and during surgery. Differences were analyzed with post-hoc analysis of variance. The 7-T MRI demonstrated a significant improvement in tissue visualization (P < 0.005) and signal-to-noise ratio (P < 0.005). However, no difference in the target coordinates was found between the 7-T and the 3-T MRI. Although the 7-T MRI enables a significant better visualization of the DBS target in patients with PD, we found no clinical benefit for the placement of the DBS leads. Copyright © 2016 Elsevier Inc. All rights reserved.

Three-dimensional MRI-linac intra-fraction guidance using multiple orthogonal cine-MRI planes

NASA Astrophysics Data System (ADS)

Bjerre, Troels; Crijns, Sjoerd; Rosenschöld, Per Munck af; Aznar, Marianne; Specht, Lena; Larsen, Rasmus; Keall, Paul

2013-07-01

The introduction of integrated MRI-radiation therapy systems will offer live intra-fraction imaging. We propose a feasible low-latency multi-plane MRI-linac guidance strategy. In this work we demonstrate how interleaved acquired, orthogonal cine-MRI planes can be used for low-latency tracking of the 3D trajectory of a soft-tissue target structure. The proposed strategy relies on acquiring a pre-treatment 3D breath-hold scan, extracting a 3D target template and performing template matching between this 3D template and pairs of orthogonal 2D cine-MRI planes intersecting the target motion path. For a 60 s free-breathing series of orthogonal cine-MRI planes, we demonstrate that the method was capable of accurately tracking the respiration related 3D motion of the left kidney. Quantitative evaluation of the method using a dataset designed for this purpose revealed a translational error of 1.15 mm for a translation of 39.9 mm. We have demonstrated how interleaved acquired, orthogonal cine-MRI planes can be used for online tracking of soft-tissue target volumes.

WE-DE-206-01: MRI Signal in Biological Tissues - Proton, Spin, T1, T2, T2*

DOE Office of Scientific and Technical Information (OSTI.GOV)

Gorny, K.

Magnetic resonance imaging (MRI) has become an essential part of clinical imaging due to its ability to render high soft tissue contrast. Instead of ionizing radiation, MRI use strong magnetic field, radio frequency waves and field gradients to create diagnostic useful images. It can be used to image the anatomy and also functional and physiological activities within the human body. Knowledge of the basic physical principles underlying MRI acquisition is vitally important to successful image production and proper image interpretation. This lecture will give an overview of the spin physics, imaging principle of MRI, the hardware of the MRI scanner,more » and various pulse sequences and their applications. It aims to provide a conceptual foundation to understand the image formation process of a clinical MRI scanner. Learning Objectives: Understand the origin of the MR signal and contrast from the spin physics level. Understand the main hardware components of a MRI scanner and their purposes Understand steps for MR image formation including spatial encoding and image reconstruction Understand the main kinds of MR pulse sequences and their characteristics.« less

Three-dimensional MRI-linac intra-fraction guidance using multiple orthogonal cine-MRI planes.

PubMed

Bjerre, Troels; Crijns, Sjoerd; af Rosenschöld, Per Munck; Aznar, Marianne; Specht, Lena; Larsen, Rasmus; Keall, Paul

2013-07-21

The introduction of integrated MRI-radiation therapy systems will offer live intra-fraction imaging. We propose a feasible low-latency multi-plane MRI-linac guidance strategy. In this work we demonstrate how interleaved acquired, orthogonal cine-MRI planes can be used for low-latency tracking of the 3D trajectory of a soft-tissue target structure. The proposed strategy relies on acquiring a pre-treatment 3D breath-hold scan, extracting a 3D target template and performing template matching between this 3D template and pairs of orthogonal 2D cine-MRI planes intersecting the target motion path. For a 60 s free-breathing series of orthogonal cine-MRI planes, we demonstrate that the method was capable of accurately tracking the respiration related 3D motion of the left kidney. Quantitative evaluation of the method using a dataset designed for this purpose revealed a translational error of 1.15 mm for a translation of 39.9 mm. We have demonstrated how interleaved acquired, orthogonal cine-MRI planes can be used for online tracking of soft-tissue target volumes.

Predictors of seizure freedom after surgery for malformations of cortical development.

PubMed

Chang, Edward F; Wang, Doris D; Barkovich, A James; Tihan, Tarik; Auguste, Kurtis I; Sullivan, Joseph E; Garcia, Paul A; Barbaro, Nicholas M

2011-07-01

Malformations of cortical development (MCDs) are a major cause of medically refractory epilepsy. Our aim was to examine a surgical series of patients with cortical malformations to determine the prognostic factors associated with long-term seizure control. We conducted a retrospective review of 143 patients with MCD who underwent resective surgery for medically refractory epilepsy. Demographic, imaging, histopathologic, and surgical variables were analyzed for potential association with seizure freedom. Preoperative magnetic resonance imaging (MRI) was evaluated in a blind fashion and classified according to a new imaging/embryologic MCD classification system. Gray-white blurring on MRI, smaller lesions, complete resection of structural lesions, complete resection of abnormal electrocorticographic areas, and locally confined electrocorticographic abnormalities are favorable prognosticators of seizure freedom on univariate analysis. Imaging features consistent with abnormal proliferation (Barkovich class I) were associated with better outcome compared to those related to abnormal neuronal migration (class II) or abnormal cortical organization (class III). Multivariate logistic regression revealed complete resection of tissue manifesting electrocorticographic and/or MRI anatomic abnormalities as the main independent predictor of seizure freedom. Other histopathologic or demographic factors were not associated with seizure control. Long-term follow-up of patients demonstrated sustained overall rates of seizure control (72% at 2 years, 65% at 5 years, and 67% at 10 years). Surgery for MCDs can result in high rates of seizure freedom. Complete resection of electrocorticographic and anatomic abnormalities appears to be most predictive of long-term seizure control. Copyright © 2011 American Neurological Association.

Comparison of breast tissue measurements using magnetic resonance imaging, digital mammography and a mathematical algorithm

NASA Astrophysics Data System (ADS)

Lu, Lee-Jane W.; Nishino, Thomas K.; Johnson, Raleigh F.; Nayeem, Fatima; Brunder, Donald G.; Ju, Hyunsu; Leonard, Morton H., Jr.; Grady, James J.; Khamapirad, Tuenchit

2012-11-01

Women with mostly mammographically dense fibroglandular tissue (breast density, BD) have a four- to six-fold increased risk for breast cancer compared to women with little BD. BD is most frequently estimated from two-dimensional (2D) views of mammograms by a histogram segmentation approach (HSM) and more recently by a mathematical algorithm consisting of mammographic imaging parameters (MATH). Two non-invasive clinical magnetic resonance imaging (MRI) protocols: 3D gradient-echo (3DGRE) and short tau inversion recovery (STIR) were modified for 3D volumetric reconstruction of the breast for measuring fatty and fibroglandular tissue volumes by a Gaussian-distribution curve-fitting algorithm. Replicate breast exams (N = 2 to 7 replicates in six women) by 3DGRE and STIR were highly reproducible for all tissue-volume estimates (coefficients of variation <5%). Reliability studies compared measurements from four methods, 3DGRE, STIR, HSM, and MATH (N = 95 women) by linear regression and intra-class correlation (ICC) analyses. Rsqr, regression slopes, and ICC, respectively, were (1) 0.76-0.86, 0.8-1.1, and 0.87-0.92 for %-gland tissue, (2) 0.72-0.82, 0.64-0.96, and 0.77-0.91, for glandular volume, (3) 0.87-0.98, 0.94-1.07, and 0.89-0.99, for fat volume, and (4) 0.89-0.98, 0.94-1.00, and 0.89-0.98, for total breast volume. For all values estimated, the correlation was stronger for comparisons between the two MRI than between each MRI versus mammography, and between each MRI versus MATH data than between each MRI versus HSM data. All ICC values were >0.75 indicating that all four methods were reliable for measuring BD and that the mathematical algorithm and the two complimentary non-invasive MRI protocols could objectively and reliably estimate different types of breast tissues.

Comparison of breast tissue measurements using magnetic resonance imaging, digital mammography and a mathematical algorithm

PubMed Central

Lu, Lee-Jane W.; Nishino, Thomas K.; Johnson, Raleigh F.; Nayeem, Fatima; Brunder, Donald G.; Ju, Hyunsu; Leonard, Morton H.; Grady, James J.; Khamapirad, Tuenchit

2012-01-01

Women with mostly mammographically dense fibroglandular tissue (breast density, BD) have a 4- to 6-fold increased risk for breast cancer compared to women with little BD. BD is most frequently estimated from 2-dimensional (2-D) views of mammograms by a histogram segmentation approach (HSM) and more recently by a mathematical algorithm consisting of mammographic imaging parameters (MATH). Two non-invasive clinical magnetic resonance imaging (MRI) protocols: 3-D gradient-echo (3DGRE) and short tau inversion recovery (STIR) were modified for 3-D volumetric reconstruction of the breast for measuring fatty and fibroglandular tissue volumes by a Gaussian-distribution curve-fitting algorithm. Replicate breast exams (N= 2 to 7 replicates in 6 women) by 3DGRE and STIR were highly reproducible for all tissue-volume estimates (coefficients of variation <5%). Reliability studies compared measurements from four methods, 3DGRE, STIR, HSM, and MATH (N=95 women) by linear regression and intra-class correlation (ICC) analyses. Rsqr, regression slopes, and ICC, respectively, were (I) 0.76–0.86, 0.8–1.1, and 0.87–0.92 for %-gland tissue, (II) 0.72–0.82, 0.64–0.96, and 0.77–0.91, for glandular volume, (III) 0.87–0.98, 0.94–1.07, and 0.89–0.99, for fat volume, and (IV) 0.89–0.98, 0.94–1.00, and 0.89–0.98, for total breast volume. For all values estimated, the correlation was stronger for comparisons between the two MRI than between each MRI vs. mammography, and between each MRI vs. MATH data than between each MRI vs. HSM data. All ICC values were >0.75 indicating that all four methods were reliable for measuring BD and that the mathematical algorithm and the two complimentary non-invasive MRI protocols could objectively and reliably estimate different types of breast tissues. PMID:23044556

TU-G-201-01: What Therapy Physicists Need to Know About CT and PET/CT: Terminology and Latest Developments

DOE Office of Scientific and Technical Information (OSTI.GOV)

Hua, C.

This session will update therapeutic physicists on technological advancements and radiation oncology features of commercial CT, MRI, and PET/CT imaging systems. Also described are physicists’ roles in every stage of equipment selection, purchasing, and operation, including defining specifications, evaluating vendors, making recommendations, and optimal and safe use of imaging equipment in radiation oncology environment. The first presentation defines important terminology of CT and PET/CT followed by a review of latest innovations, such as metal artifact reduction, statistical iterative reconstruction, radiation dose management, tissue classification by dual energy CT and spectral CT, improvement in spatial resolution and sensitivity in PET, andmore » potentials of PET/MR. We will also discuss important technical specifications and items in CT and PET/CT purchasing quotes and their impacts. The second presentation will focus on key components in the request for proposal for a MRI simulator and how to evaluate vendor proposals. MRI safety issues in radiation Oncology, including MRI scanner Zones (4-zone design), will be discussed. Basic MR terminologies, important functionalities, and advanced features, which are relevant to radiation therapy, will be discussed. In the third presentation, justification of imaging systems for radiation oncology, considerations in room design and construction in a RO department, shared use with diagnostic radiology, staffing needs and training, clinical/research use cases and implementation, will be discussed. The emphasis will be on understanding and bridging the differences between diagnostic and radiation oncology installations, building consensus amongst stakeholders for purchase and use, and integrating imaging technologies into the radiation oncology environment. Learning Objectives: Learn the latest innovations of major imaging systems relevant to radiation therapy Be able to describe important technical specifications of CT, MRI, and PET/CT Understand the process of budget request, equipment justification, comparisons of technical specifications, site visits, vendor selection, and contract development.« less

TU-G-201-00: Imaging Equipment Specification and Selection in Radiation Oncology Departments

DOE Office of Scientific and Technical Information (OSTI.GOV)

NONE

This session will update therapeutic physicists on technological advancements and radiation oncology features of commercial CT, MRI, and PET/CT imaging systems. Also described are physicists’ roles in every stage of equipment selection, purchasing, and operation, including defining specifications, evaluating vendors, making recommendations, and optimal and safe use of imaging equipment in radiation oncology environment. The first presentation defines important terminology of CT and PET/CT followed by a review of latest innovations, such as metal artifact reduction, statistical iterative reconstruction, radiation dose management, tissue classification by dual energy CT and spectral CT, improvement in spatial resolution and sensitivity in PET, andmore » potentials of PET/MR. We will also discuss important technical specifications and items in CT and PET/CT purchasing quotes and their impacts. The second presentation will focus on key components in the request for proposal for a MRI simulator and how to evaluate vendor proposals. MRI safety issues in radiation Oncology, including MRI scanner Zones (4-zone design), will be discussed. Basic MR terminologies, important functionalities, and advanced features, which are relevant to radiation therapy, will be discussed. In the third presentation, justification of imaging systems for radiation oncology, considerations in room design and construction in a RO department, shared use with diagnostic radiology, staffing needs and training, clinical/research use cases and implementation, will be discussed. The emphasis will be on understanding and bridging the differences between diagnostic and radiation oncology installations, building consensus amongst stakeholders for purchase and use, and integrating imaging technologies into the radiation oncology environment. Learning Objectives: Learn the latest innovations of major imaging systems relevant to radiation therapy Be able to describe important technical specifications of CT, MRI, and PET/CT Understand the process of budget request, equipment justification, comparisons of technical specifications, site visits, vendor selection, and contract development.« less

Study of the intra-arterial distribution of Fe₃O₄ nanoparticles in a model of colorectal neoplasm induced in rat liver by MRI and spectrometry.

PubMed

Echevarria-Uraga, José J; García-Alonso, Ignacio; Plazaola, Fernando; Insausti, Maite; Etxebarria, Néstor; Saiz-López, Alberto; Fernández-Ruanova, Begoña

2012-01-01

To evaluate, in an experimental model, the reliability of MRI for determining whether a higher iron concentration was obtained in tumor tissue than in normal liver parenchyma after intra-arterial administration of Fe₃O₄ lipophilic nanoparticles. WAG/RijCrl rats were inoculated in the left hepatic lobe with 25,000 syngeneic CC-531 colon adenocarcinoma cells, after which they were randomized into two groups: control (CG) and infused (IG). After confirming tumor induction, the IG rats received intra-arterial suspensions of Fe₃O₄ nanoparticles (2.6 mg) in Lipiodol® (0.15 mL). To calculate the iron concentration, [Fe], in the tumor and liver tissues of both groups of rats, measurements of signal intensity from the tumors, healthy liver tissue, and paravertebral muscles were made on a 1.5T MRI system in gradient-echo DP* and T2*-weighted sequences. In addition, samples were collected to quantify the [Fe] by inductively coupled plasma-mass spectrometry (ICP-MS), as well as for histological analysis. Statistical analysis was performed with non-parametric tests, and Bland-Altman plots were produced; P values <0.05 were considered significant. In the CG rats (n = 23), the mean [Fe] values estimated by MRI and ICP-MS were 13.2 μmol·g⁻¹ and 5.9 μmol·g⁻¹, respectively, in the tumors, and 19.0 μmol ·g⁻¹ and 11.7 μmol·g⁻¹, respectively, in the hepatic tissue. In the IG rats (n = 19), the values obtained by MRI and ICP-MS were 148.9 μmol·g⁻¹ and 9.4 μmol · g⁻¹, respectively, in the tumors, and 115.3 μmol·g⁻¹ and 11.6 μmol·g⁻¹, respectively, in the healthy liver tissue. The IG results revealed a clear disagreement between MRI and ICP-MS. In the comparative analysis between the groups regarding the [Fe] values obtained by ICP-MS, significant differences were found for the tumor samples (P < 0.001), but not for the hepatic tissue (P = 0.92). Under microscopy, scattered intravascular deposits of nanoparticles were observed, especially in the tumors. ICP-MS demonstrated significant uptake of exogenous iron in tumor tissue. MRI was useful for quantifying the [Fe] in the different tissues in the CG animals, but not in the IG animals. Although the irregular distribution of nanoparticles caused an important bias in the measurements obtained by MRI, the relative increase in iron content inside the tumor was suggested.

Study of the intra-arterial distribution of Fe3O4 nanoparticles in a model of colorectal neoplasm induced in rat liver by MRI and spectrometry

PubMed Central

Echevarria-Uraga, José J; García-Alonso, Ignacio; Plazaola, Fernando; Insausti, Maite; Etxebarria, Néstor; Saiz-López, Alberto; Fernández-Ruanova, Begoña

2012-01-01

Purpose To evaluate, in an experimental model, the reliability of MRI for determining whether a higher iron concentration was obtained in tumor tissue than in normal liver parenchyma after intra-arterial administration of Fe3O4 lipophilic nanoparticles. Materials and methods WAG/RijCrl rats were inoculated in the left hepatic lobe with 25,000 syngeneic CC-531 colon adenocarcinoma cells, after which they were randomized into two groups: control (CG) and infused (IG). After confirming tumor induction, the IG rats received intra-arterial suspensions of Fe3O4 nanoparticles (2.6 mg) in Lipiodol® (0.15 mL). To calculate the iron concentration, [Fe], in the tumor and liver tissues of both groups of rats, measurements of signal intensity from the tumors, healthy liver tissue, and paravertebral muscles were made on a 1.5T MRI system in gradient-echo DP* and T2*-weighted sequences. In addition, samples were collected to quantify the [Fe] by inductively coupled plasma-mass spectrometry (ICP-MS), as well as for histological analysis. Statistical analysis was performed with non-parametric tests, and Bland–Altman plots were produced; P values <0.05 were considered significant. Results In the CG rats (n = 23), the mean [Fe] values estimated by MRI and ICP-MS were 13.2 μmol·g−1 and 5.9 μmol·g−1, respectively, in the tumors, and 19.0μmol ·g−1 and 11.7 μmol·g−1, respectively, in the hepatic tissue. In the IG rats (n = 19), the values obtained by MRI and ICP-MS were 148.9 μmol·g−1 and 9.4 μmol · g−1, respectively, in the tumors, and 115.3 μmol·g−1 and 11.6 μmol·g−1, respectively, in the healthy liver tissue. The IG results revealed a clear disagreement between MRI and ICP-MS. In the comparative analysis between the groups regarding the [Fe] values obtained by ICP-MS, significant differences were found for the tumor samples (P < 0.001), but not for the hepatic tissue (P = 0.92). Under microscopy, scattered intravascular deposits of nanoparticles were observed, especially in the tumors. Conclusion ICP-MS demonstrated significant uptake of exogenous iron in tumor tissue. MRI was useful for quantifying the [Fe] in the different tissues in the CG animals, but not in the IG animals. Although the irregular distribution of nanoparticles caused an important bias in the measurements obtained by MRI, the relative increase in iron content inside the tumor was suggested. PMID:22661893

DOE Office of Scientific and Technical Information (OSTI.GOV)

Korhonen, Juha, E-mail: juha.p.korhonen@hus.fi; Kapanen, Mika; Department of Oncology, Helsinki University Central Hospital, POB-180, 00029 HUS

Purpose: The lack of electron density information in magnetic resonance images (MRI) poses a major challenge for MRI-based radiotherapy treatment planning (RTP). In this study the authors convert MRI intensity values into Hounsfield units (HUs) in the male pelvis and thus enable accurate MRI-based RTP for prostate cancer patients with varying tissue anatomy and body fat contents. Methods: T{sub 1}/T{sub 2}*-weighted MRI intensity values and standard computed tomography (CT) image HUs in the male pelvis were analyzed using image data of 10 prostate cancer patients. The collected data were utilized to generate a dual model HU conversion technique from MRImore » intensity values of the single image set separately within and outside of contoured pelvic bones. Within the bone segment local MRI intensity values were converted to HUs by applying a second-order polynomial model. This model was tuned for each patient by two patient-specific adjustments: MR signal normalization to correct shifts in absolute intensity level and application of a cutoff value to accurately represent low density bony tissue HUs. For soft tissues, such as fat and muscle, located outside of the bone contours, a threshold-based segmentation method without requirements for any patient-specific adjustments was introduced to convert MRI intensity values into HUs. The dual model HU conversion technique was implemented by constructing pseudo-CT images for 10 other prostate cancer patients. The feasibility of these images for RTP was evaluated by comparing HUs in the generated pseudo-CT images with those in standard CT images, and by determining deviations in MRI-based dose distributions compared to those in CT images with 7-field intensity modulated radiation therapy (IMRT) with the anisotropic analytical algorithm and 360° volumetric-modulated arc therapy (VMAT) with the Voxel Monte Carlo algorithm. Results: The average HU differences between the constructed pseudo-CT images and standard CT images of each test patient ranged from −2 to 5 HUs and from 22 to 78 HUs in soft and bony tissues, respectively. The average local absolute value differences were 11 HUs in soft tissues and 99 HUs in bones. The planning target volume doses (volumes 95%, 50%, 5%) in the pseudo-CT images were within 0.8% compared to those in CT images in all of the 20 treatment plans. The average deviation was 0.3%. With all the test patients over 94% (IMRT) and 92% (VMAT) of dose points within body (lower than 10% of maximum dose suppressed) passed the 1 mm and 1% 2D gamma index criterion. The statistical tests (t- and F-tests) showed significantly improved (p ≤ 0.05) HU and dose calculation accuracies with the soft tissue conversion method instead of homogeneous representation of these tissues in MRI-based RTP images. Conclusions: This study indicates that it is possible to construct high quality pseudo-CT images by converting the intensity values of a single MRI series into HUs in the male pelvis, and to use these images for accurate MRI-based prostate RTP dose calculations.« less

Encoding the local connectivity patterns of fMRI for cognitive task and state classification.

PubMed

Onal Ertugrul, Itir; Ozay, Mete; Yarman Vural, Fatos T

2018-06-15

In this work, we propose a novel framework to encode the local connectivity patterns of brain, using Fisher vectors (FV), vector of locally aggregated descriptors (VLAD) and bag-of-words (BoW) methods. We first obtain local descriptors, called mesh arc descriptors (MADs) from fMRI data, by forming local meshes around anatomical regions, and estimating their relationship within a neighborhood. Then, we extract a dictionary of relationships, called brain connectivity dictionary by fitting a generative Gaussian mixture model (GMM) to a set of MADs, and selecting codewords at the mean of each component of the mixture. Codewords represent connectivity patterns among anatomical regions. We also encode MADs by VLAD and BoW methods using k-Means clustering. We classify cognitive tasks using the Human Connectome Project (HCP) task fMRI dataset and cognitive states using the Emotional Memory Retrieval (EMR). We train support vector machines (SVMs) using the encoded MADs. Results demonstrate that, FV encoding of MADs can be successfully employed for classification of cognitive tasks, and outperform VLAD and BoW representations. Moreover, we identify the significant Gaussians in mixture models by computing energy of their corresponding FV parts, and analyze their effect on classification accuracy. Finally, we suggest a new method to visualize the codewords of the learned brain connectivity dictionary.

Iatrogenic Bone and Soft Tissue Trauma in Robotic-Arm Assisted Total Knee Arthroplasty Compared With Conventional Jig-Based Total Knee Arthroplasty: A Prospective Cohort Study and Validation of a New Classification System.

PubMed

Kayani, Babar; Konan, Sujith; Pietrzak, Jurek R T; Haddad, Fares S

2018-03-27

The objective of this study was to compare macroscopic bone and soft tissue injury between robotic-arm assisted total knee arthroplasty (RA-TKA) and conventional jig-based total knee arthroplasty (CJ-TKA) and create a validated classification system for reporting iatrogenic bone and periarticular soft tissue injury after TKA. This study included 30 consecutive CJ-TKAs followed by 30 consecutive RA-TKAs performed by a single surgeon. Intraoperative photographs of the femur, tibia, and periarticular soft tissues were taken before implantation of prostheses. Using these outcomes, the macroscopic soft tissue injury (MASTI) classification system was developed to grade iatrogenic bone and soft tissue injuries. Interobserver and Intraobserver validity of the proposed classification system was assessed. Patients undergoing RA-TKA had reduced medial soft tissue injury in both passively correctible (P < .05) and noncorrectible varus deformities (P < .05); more pristine femoral (P < .05) and tibial (P < .05) bone resection cuts; and improved MASTI scores compared to CJ-TKA (P < .05). There was high interobserver (intraclass correlation coefficient 0.92 [95% confidence interval: 0.88-0.96], P < .05) and intraobserver agreement (intraclass correlation coefficient 0.94 [95% confidence interval: 0.92-0.97], P < .05) of the proposed MASTI classification system. There is reduced bone and periarticular soft tissue injury in patients undergoing RA-TKA compared to CJ-TKA. The proposed MASTI classification system is a reproducible grading scheme for describing iatrogenic bone and soft tissue injury in TKA. RA-TKA is associated with reduced bone and soft tissue injury compared with conventional jig-based TKA. The proposed MASTI classification may facilitate further research correlating macroscopic soft tissue injury during TKA to long-term clinical and functional outcomes. Copyright © 2018 Elsevier Inc. All rights reserved.

Assistance to neurosurgical planning: using a fuzzy spatial graph model of the brain for locating anatomical targets in MRI

NASA Astrophysics Data System (ADS)

Villéger, Alice; Ouchchane, Lemlih; Lemaire, Jean-Jacques; Boire, Jean-Yves

2007-03-01

Symptoms of neurodegenerative pathologies such as Parkinson's disease can be relieved through Deep Brain Stimulation. This neurosurgical technique relies on high precision positioning of electrodes in specific areas of the basal ganglia and the thalamus. These subcortical anatomical targets must be located at pre-operative stage, from a set of MRI acquired under stereotactic conditions. In order to assist surgical planning, we designed a semi-automated image analysis process for extracting anatomical areas of interest. Complementary information, provided by both patient's data and expert knowledge, is represented as fuzzy membership maps, which are then fused by means of suitable possibilistic operators in order to achieve the segmentation of targets. More specifically, theoretical prior knowledge on brain anatomy is modelled within a 'virtual atlas' organised as a spatial graph: a list of vertices linked by edges, where each vertex represents an anatomical structure of interest and contains relevant information such as tissue composition, whereas each edge represents a spatial relationship between two structures, such as their relative directions. The model is built using heterogeneous sources of information such as qualitative descriptions from the expert, or quantitative information from prelabelled images. For each patient, tissue membership maps are extracted from MR data through a classification step. Prior model and patient's data are then matched by using a research algorithm (or 'strategy') which simultaneously computes an estimation of the location of every structures. The method was tested on 10 clinical images, with promising results. Location and segmentation results were statistically assessed, opening perspectives for enhancements.

New Findings, Classification and Long-Term Follow-Up Study Based on MRI Characterization of Brainstem Encephalitis Induced by Enterovirus 71

PubMed Central

Wen, Feiqiu; Huang, Wenxian; Gan, Yungen; Zeng, Weibin; Chen, Ranran; He, Yanxia; Wang, Yonker; Liu, Zaiyi; Liang, Changhong; Wong, Kelvin K. L.

2016-01-01

Background To report the diversity of MRI features of brainstem encephalitis (BE) induced by Enterovirus 71. This is supported by implementation and testing of our new classification scheme in order to improve the diagnostic level on this specific disease. Methods Neuroimaging of 91 pediatric patients who got EV71 related BE were hospitalized between March, 2010 to October, 2012, were analyzed retrospectively. All patients underwent pre- and post-contrast MRI scan. Thereafter, 31 patients were randomly called back for follow-up MRI study during December 2013 to August 2014. The MRI signal patterns of BE primary lesion were analyzed and classified according to MR signal alteration at various disease stages. Findings in fatal and non-fatal cases were compared, and according to the MRI scan time point during the course of this disease, the patients’ conditions were classified as 1) acute stage, 2) convalescence stage, 3) post mortem stage, and 4) long term follow-up study. Results 103 patients were identified. 11 patients did not undergo MRI, as they died within 48 hours. One patient died on 14th day without MR imaging. 2 patients had postmortem MRI. Medical records and imaging were reviewed in the 91 patients, aged 4 months to 12 years, and two cadavers who have had MRI scan. At acute stage: the most frequent pattern (40 patients) was foci of prolonged T1 and T2 signal, with (15) or without (25) contrast enhancement. We observed a novel pattern in 4 patients having foci of low signal intensity on T2WI, with contrast enhancement. Another pattern in 10 patients having foci of contrast enhancement without abnormalities in T1WI or T2WI weighted images. Based on 2 cases, the entire medulla and pons had prolonged T1 and T2 signal, and 2 of our postmortem cases demonstrated the same pattern. At convalescence stage, the pattern observed in 4 patients was foci of prolonged T1 and T2 signal without contrast enhancement. Follow-up MR study of 31 cases showed normal in 26 cases, and demonstrated foci of prolonged T1 and T2 signal with hyper-intensity on FLAIR in 3 cases, or of prolonged T1 and T2 signal with hypo-intensity on FLAIR in 2 cases. Most importantly, MR findings of each case were thoroughly investigated and classified according to phases and MRI signal alteration. Conclusions This study has provided enhanced and useful information for the MRI features of BE induced by EV71, apart from common practice established by previous reports. In addition, a classification scheme that summarizes all types of features based on the MRI signal at the four different stages of the disease would be helpful to improve the diagnostic level. PMID:27798639

New Findings, Classification and Long-Term Follow-Up Study Based on MRI Characterization of Brainstem Encephalitis Induced by Enterovirus 71.

PubMed

Zeng, Hongwu; Wen, Feiqiu; Huang, Wenxian; Gan, Yungen; Zeng, Weibin; Chen, Ranran; He, Yanxia; Wang, Yonker; Liu, Zaiyi; Liang, Changhong; Wong, Kelvin K L

2016-01-01

To report the diversity of MRI features of brainstem encephalitis (BE) induced by Enterovirus 71. This is supported by implementation and testing of our new classification scheme in order to improve the diagnostic level on this specific disease. Neuroimaging of 91 pediatric patients who got EV71 related BE were hospitalized between March, 2010 to October, 2012, were analyzed retrospectively. All patients underwent pre- and post-contrast MRI scan. Thereafter, 31 patients were randomly called back for follow-up MRI study during December 2013 to August 2014. The MRI signal patterns of BE primary lesion were analyzed and classified according to MR signal alteration at various disease stages. Findings in fatal and non-fatal cases were compared, and according to the MRI scan time point during the course of this disease, the patients' conditions were classified as 1) acute stage, 2) convalescence stage, 3) post mortem stage, and 4) long term follow-up study. 103 patients were identified. 11 patients did not undergo MRI, as they died within 48 hours. One patient died on 14th day without MR imaging. 2 patients had postmortem MRI. Medical records and imaging were reviewed in the 91 patients, aged 4 months to 12 years, and two cadavers who have had MRI scan. At acute stage: the most frequent pattern (40 patients) was foci of prolonged T1 and T2 signal, with (15) or without (25) contrast enhancement. We observed a novel pattern in 4 patients having foci of low signal intensity on T2WI, with contrast enhancement. Another pattern in 10 patients having foci of contrast enhancement without abnormalities in T1WI or T2WI weighted images. Based on 2 cases, the entire medulla and pons had prolonged T1 and T2 signal, and 2 of our postmortem cases demonstrated the same pattern. At convalescence stage, the pattern observed in 4 patients was foci of prolonged T1 and T2 signal without contrast enhancement. Follow-up MR study of 31 cases showed normal in 26 cases, and demonstrated foci of prolonged T1 and T2 signal with hyper-intensity on FLAIR in 3 cases, or of prolonged T1 and T2 signal with hypo-intensity on FLAIR in 2 cases. Most importantly, MR findings of each case were thoroughly investigated and classified according to phases and MRI signal alteration. This study has provided enhanced and useful information for the MRI features of BE induced by EV71, apart from common practice established by previous reports. In addition, a classification scheme that summarizes all types of features based on the MRI signal at the four different stages of the disease would be helpful to improve the diagnostic level.

SU-F-J-17: Patient Localization Using MRI-Guided Soft Tissue for Head-And-Neck Radiotherapy: Indication for Margin Reduction and Its Feasibility

DOE Office of Scientific and Technical Information (OSTI.GOV)

Qi, X; Yang, Y; Jack, N

Purpose: On-board MRI provides superior soft-tissue contrast, allowing patient alignment using tumor or nearby critical structures. This study aims to study H&N MRI-guided IGRT to analyze inter-fraction patient setup variations using soft-tissue targets and design appropriate CTV-to-PTV margin and clinical implication. Methods: 282 MR images for 10 H&N IMRT patients treated on a ViewRay system were retrospectively analyzed. Patients were immobilized using a thermoplastic mask on a customized headrest fitted in a radiofrequency coil and positioned to soft-tissue targets. The inter-fraction patient displacements were recorded to compute the PTV margins using the recipe: 2.5∑+0.7σ. New IMRT plans optimized on themore » revised PTVs were generated to evaluate the delivered dose distributions. An in-house dose deformation registration tool was used to assess the resulting dosimetric consequences when margin adaption is performed based on weekly MR images. The cumulative doses were compared to the reduced margin plans for targets and critical structures. Results: The inter-fraction displacements (and standard deviations), ∑ and σ were tabulated for MRI and compared to kVCBCT. The computed CTV-to-PTV margin was 3.5mm for soft-tissue based registration. There were minimal differences between the planned and delivered doses when comparing clinical and the PTV reduced margin plans: the paired t-tests yielded p=0.38 and 0.66 between the planned and delivered doses for the adapted margin plans for the maximum cord and mean parotid dose, respectively. Target V95 received comparable doses as planned for the reduced margin plans. Conclusion: The 0.35T MRI offers acceptable soft-tissue contrast and good spatial resolution for patient alignment and target visualization. Better tumor conspicuity from MRI allows soft-tissue based alignments with potentially improved accuracy, suggesting a benefit of margin reduction for H&N radiotherapy. The reduced margin plans (i.e., 2 mm) resulted in improved normal structure sparing and accurate dose delivery to achieve intended treatment goal under MR guidance.« less

Detection of infarct lesions from single MRI modality using inconsistency between voxel intensity and spatial location--a 3-D automatic approach.

PubMed

Shen, Shan; Szameitat, André J; Sterr, Annette

2008-07-01

Detection of infarct lesions using traditional segmentation methods is always problematic due to intensity similarity between lesions and normal tissues, so that multispectral MRI modalities were often employed for this purpose. However, the high costs of MRI scan and the severity of patient conditions restrict the collection of multiple images. Therefore, in this paper, a new 3-D automatic lesion detection approach was proposed, which required only a single type of anatomical MRI scan. It was developed on a theory that, when lesions were present, the voxel-intensity-based segmentation and the spatial-location-based tissue distribution should be inconsistent in the regions of lesions. The degree of this inconsistency was calculated, which indicated the likelihood of tissue abnormality. Lesions were identified when the inconsistency exceeded a defined threshold. In this approach, the intensity-based segmentation was implemented by the conventional fuzzy c-mean (FCM) algorithm, while the spatial location of tissues was provided by prior tissue probability maps. The use of simulated MRI lesions allowed us to quantitatively evaluate the performance of the proposed method, as the size and location of lesions were prespecified. The results showed that our method effectively detected lesions with 40-80% signal reduction compared to normal tissues (similarity index > 0.7). The capability of the proposed method in practice was also demonstrated on real infarct lesions from 15 stroke patients, where the lesions detected were in broad agreement with true lesions. Furthermore, a comparison to a statistical segmentation approach presented in the literature suggested that our 3-D lesion detection approach was more reliable. Future work will focus on adapting the current method to multiple sclerosis lesion detection.

Design and fabrication of a realistic anthropomorphic heterogeneous head phantom for MR purposes

PubMed Central

Wood, Sossena; Krishnamurthy, Narayanan; Santini, Tales; Raval, Shailesh; Farhat, Nadim; Holmes, John Andy; Ibrahim, Tamer S.

2017-01-01

Objective The purpose of this study is to design an anthropomorphic heterogeneous head phantom that can be used for MRI and other electromagnetic applications. Materials and methods An eight compartment, physical anthropomorphic head phantom was developed from a 3T MRI dataset of a healthy male. The designed phantom was successfully built and preliminarily evaluated through an application that involves electromagnetic-tissue interactions: MRI (due to it being an available resource). The developed phantom was filled with media possessing electromagnetic constitutive parameters that correspond to biological tissues at ~297 MHz. A preliminary comparison between an in-vivo human volunteer (based on whom the anthropomorphic head phantom was created) and various phantoms types, one being the anthropomorphic heterogeneous head phantom, were performed using a 7 Tesla human MRI scanner. Results Echo planar imaging was performed and minimal ghosting and fluctuations were observed using the proposed anthropomorphic phantom. The magnetic field distributions (during MRI experiments at 7 Tesla) and the scattering parameter (measured using a network analyzer) were most comparable between the anthropomorphic heterogeneous head phantom and an in-vivo human volunteer. Conclusion The developed anthropomorphic heterogeneous head phantom can be used as a resource to various researchers in applications that involve electromagnetic-biological tissue interactions such as MRI. PMID:28806768

Detection of FUS induced lesions by MR-elastography

NASA Astrophysics Data System (ADS)

Jenne, Jürgen W.; Divkovic, Gabriela; Siegler, Peter

2005-03-01

MRI (Magnetic Resonance Imaging) has proven to be an exact and safe method to guide FUS (Focused ultrasound surgery) therapy. Besides its excellent soft tissue contrast, important for a precise treatment planning, MRI allows fast and reliable measurement of temperature changes caused by FUS application. In this study we compare standard MR-imaging parameters (relaxation times, spin density) with MR measured tissue elasticity in order to differentiate between FUS induced thermal lesions and normal tissue in vitro. In addition we tried to observe FUS induced shear waves by dynamic MRE. FUS was performed with an MRI compatible 1.7 MHz fixed focus transducer (NA 0.44; f'= 68 mm). With increasing acoustic power (30-70 W) the difference in relaxation times T1, T2 and spin density between normal and lesioned tissue also increased. We measured values in the range 5% to 24%. The difference in tissue strain had a value of 23% at 30 W and was nearly constant (52-61%) at higher FUS power. Compared with standard MRI parameters MRE showed a clearly higher sensitivity to detect FUS induced lesions. With our experimental setup it was possible to image FUS induced shear waves. The measured wave length at 400Hz repetition rate was 7 mm. However, further experiments are necessary to utilize the potential of MRE in practice.

Practical use of imaging technique for management of bone and soft tissue tumors.

PubMed

Miwa, Shinji; Otsuka, Takanobu

2017-05-01

Imaging modalities including radiography, computed tomography (CT), and magnetic resonance imaging (MRI) are necessary for the diagnosis of bone and soft tissue tumors. The history of imaging began with the discovery of X-rays in the 19th century. The development of CT, MRI, ultrasonography, and positron emission tomography (PET) have improved the management of bone and soft tissue tumors. X-ray imaging and CT scans enable the evaluation of bone destruction, periosteal reaction, sclerotic changes in lesions, condition of cortical bone, and ossification. MRI enables the assessment of tissue characteristics, tumor extent, and the reactive areas. Functional imaging modalities including 201 thallium ( 201 Tl) scintigraphy can be used to differentiate benign lesions from malignant lesions and to assess chemotherapeutic effects. Real-time assessment of soft tissue tumors by ultrasonography enables accurate and safe performance of surgery and biopsy. This article describes useful imaging modalities and characteristic findings in the management of bone and soft tissue tumors. Copyright © 2017 The Japanese Orthopaedic Association. Published by Elsevier B.V. All rights reserved.

Design and Fabrication of an MRI-Compatible, Autonomous Incubation System.

PubMed

Khalilzad-Sharghi, Vahid; Xu, Huihui

2015-10-01

Tissue engineers have long sought access to an autonomous, imaging-compatible tissue incubation system that, with minimum operator handling, can provide real-time visualization and quantification of cells, tissue constructs, and organs. This type of screening system, capable of operating noninvasively to validate tissue, can overcome current limitations like temperature shock, unsustainable cellular environments, sample contamination, and handling/stress. However, this type of system has been a major challenge, until now. Here, we describe the design, fabrication, and characterization of an innovative, autonomous incubation system that is compatible with a 9.4 T magnetic resonance imaging (MRI) scanner. Termed the e-incubator (patent pending; application number: 13/953,984), this microcontroller-based system is integrated into an MRI scanner and noninvasively screens cells and tissue cultures in an environment where temperature, pH, and media/gas handling are regulated. The 4-week study discussed herein details the continuous operation of the e-incubator for a tissue-engineered osteogenic construct, validated by LIVE/DEAD(®) cell assays and histology. The evolving MR quantitative parameters of the osteogenic construct were used as biomarkers for bone tissue engineering and to further validate the quality of the product noninvasively before harvesting. Importantly, the e-incubator reliably facilitates culturing cells and tissue constructs to create engineered tissues and/or investigate disease therapies.

Multi-Modality Cascaded Convolutional Neural Networks for Alzheimer's Disease Diagnosis.

PubMed

Liu, Manhua; Cheng, Danni; Wang, Kundong; Wang, Yaping

2018-03-23

Accurate and early diagnosis of Alzheimer's disease (AD) plays important role for patient care and development of future treatment. Structural and functional neuroimages, such as magnetic resonance images (MRI) and positron emission tomography (PET), are providing powerful imaging modalities to help understand the anatomical and functional neural changes related to AD. In recent years, machine learning methods have been widely studied on analysis of multi-modality neuroimages for quantitative evaluation and computer-aided-diagnosis (CAD) of AD. Most existing methods extract the hand-craft imaging features after image preprocessing such as registration and segmentation, and then train a classifier to distinguish AD subjects from other groups. This paper proposes to construct cascaded convolutional neural networks (CNNs) to learn the multi-level and multimodal features of MRI and PET brain images for AD classification. First, multiple deep 3D-CNNs are constructed on different local image patches to transform the local brain image into more compact high-level features. Then, an upper high-level 2D-CNN followed by softmax layer is cascaded to ensemble the high-level features learned from the multi-modality and generate the latent multimodal correlation features of the corresponding image patches for classification task. Finally, these learned features are combined by a fully connected layer followed by softmax layer for AD classification. The proposed method can automatically learn the generic multi-level and multimodal features from multiple imaging modalities for classification, which are robust to the scale and rotation variations to some extent. No image segmentation and rigid registration are required in pre-processing the brain images. Our method is evaluated on the baseline MRI and PET images of 397 subjects including 93 AD patients, 204 mild cognitive impairment (MCI, 76 pMCI +128 sMCI) and 100 normal controls (NC) from Alzheimer's Disease Neuroimaging Initiative (ADNI) database. Experimental results show that the proposed method achieves an accuracy of 93.26% for classification of AD vs. NC and 82.95% for classification pMCI vs. NC, demonstrating the promising classification performance.

Rapid ex vivo imaging of PAIII prostate to bone tumor with SWIFT-MRI.

PubMed

Luhach, Ihor; Idiyatullin, Djaudat; Lynch, Conor C; Corum, Curt; Martinez, Gary V; Garwood, Michael; Gillies, Robert J

2014-09-01

The limiting factor for MRI of skeletal/mineralized tissue is fast transverse relaxation. A recent advancement in MRI technology, SWIFT (Sweep Imaging with Fourier Transform), is emerging as a new approach to overcome this difficulty. Among other techniques like UTE, ZTE, and WASPI, the application of SWIFT technology has the strong potential to impact preclinical and clinical imaging, particularly in the context of primary or metastatic bone cancers because it has the added advantage of imaging water in mineralized tissues of bone allowing MRI images to be obtained of tissues previously visible only with modalities such as computed tomography (CT). The goal of the current study is to examine the feasibility of SWIFT for the assessment of the prostate cancer induced changes in bone formation (osteogenesis) and destruction (osteolysis) in ex vivo specimens. A luciferase expressing prostate cancer cell line (PAIII) or saline control was inoculated directly into the tibia of 6-week-old immunocompromised male mice. Tumor growth was assessed weekly for 3 weeks before euthanasia and dissection of the tumor bearing and sham tibias. The ex vivo mouse tibia specimens were imaged with a 9.4 Tesla (T) and 7T MRI systems. SWIFT images are compared with traditional gradient-echo and spin-echo MRI images as well as CT and histological sections. SWIFT images with nominal resolution of 78 μm are obtained with the tumor and different bone structures identified. Prostate cancer induced changes in the bone microstructure are visible in SWIFT images, which is supported by spin-echo, high resolution CT and histological analysis. SWIFT MRI is capable of high-quality high-resolution ex vivo imaging of bone tumor and surrounding bone and soft tissues. Furthermore, SWIFT MRI shows promise for in vivo bone tumor imaging, with the added benefits of nonexposure to ionizing radiation, quietness, and speed. Copyright © 2013 Wiley Periodicals, Inc.

WE-FG-206-07: Assessing the Lung Function of Patients with Non-Small Cell Lung Cancer Using Hyperpolarized Xenon-129 Dissolved-Phase MRI

DOE Office of Scientific and Technical Information (OSTI.GOV)

Qing, K; Mugler, J; Chen, Q

Purpose: Hyperpolarized xenon-129 dissolved-phase MRI is the first imaging technique that allows 3-dimensional regional mapping of ventilation and gas uptake by tissue and blood the in human lung. Multiple outcome measures can be produced from this method. Existing studies in subjects with major lung diseases compared to healthy controls demonstrated high sensitivities of this method to pulmonary physiological factors including ventilation, alveolar tissue density, surface-to-volume ratio, pulmonary perfusion and gas-blood barrier thickness. The purpose of this study is to evaluate the utility of this new imaging tool to assess the lung function in patients with non-small cell lung cancer (NSCLC).more » Methods: Ten healthy controls (age: 63±10) and five patients (age: 62±13) with NSCLC underwent the xenon-129 dissolved-phase MRI, pulmonary function test (PFT) and CT for clinical purpose. Three outcome measures were produced from xenon-129 dissolved-phase MRI, including ventilation defect fraction (Vdef%) reflecting the airflow obstruction, tissue-to-gas ratio reflecting lung tissue density, and RBC-to-tissue ratio reflecting pulmonary perfusion and gas exchange. Results: Compared to healthy controls, patients with NSCLC showed more ventilation defects (NSCLC: 22±6%; control: 40±18%; P=0.01), lower tissue-to-gas (NSCLC: 0.82±0.31%; control: 1.07±0.13%; P=0.05) and RBC-to-tissue ratios (NSCLC: 0.82±0.31%; control: 1.07±0.13%; P=0.01). Maps for ventilation and gas uptake by tissue and blood were highly heterogeneous in the lungs of patients. Vdef% and RBC-to-tissue ratios in all 15 subjects correlated with corresponding global lung functional measures from PFT: FEV1/FVC (R=−0.91, P<0.001) and DLCO % predicted (R=0.54, P=0.03), respectively. The tissue-to-gas ratios correlated with tissue density (HU) measured by CT (R=0.88, P<0.001). Conclusion: With the unique ability to provide detailed information about lung function including ventilation, tissue density, perfusion and gas exchange with 3D resolution, hyperpolarized xenon-129 dissolved-phase MRI has high potential to be used as an important reference for radiotherapy treatment planning and for evaluating the side effects of the treatment. Receive research support and funding from Siemens.« less

A computational framework for the detection of subcortical brain dysmaturation in neonatal MRI using 3D Convolutional Neural Networks.

PubMed

Ceschin, Rafael; Zahner, Alexandria; Reynolds, William; Gaesser, Jenna; Zuccoli, Giulio; Lo, Cecilia W; Gopalakrishnan, Vanathi; Panigrahy, Ashok

2018-05-21

Deep neural networks are increasingly being used in both supervised learning for classification tasks and unsupervised learning to derive complex patterns from the input data. However, the successful implementation of deep neural networks using neuroimaging datasets requires adequate sample size for training and well-defined signal intensity based structural differentiation. There is a lack of effective automated diagnostic tools for the reliable detection of brain dysmaturation in the neonatal period, related to small sample size and complex undifferentiated brain structures, despite both translational research and clinical importance. Volumetric information alone is insufficient for diagnosis. In this study, we developed a computational framework for the automated classification of brain dysmaturation from neonatal MRI, by combining a specific deep neural network implementation with neonatal structural brain segmentation as a method for both clinical pattern recognition and data-driven inference into the underlying structural morphology. We implemented three-dimensional convolution neural networks (3D-CNNs) to specifically classify dysplastic cerebelli, a subset of surface-based subcortical brain dysmaturation, in term infants born with congenital heart disease. We obtained a 0.985 ± 0. 0241-classification accuracy of subtle cerebellar dysplasia in CHD using 10-fold cross-validation. Furthermore, the hidden layer activations and class activation maps depicted regional vulnerability of the superior surface of the cerebellum, (composed of mostly the posterior lobe and the midline vermis), in regards to differentiating the dysplastic process from normal tissue. The posterior lobe and the midline vermis provide regional differentiation that is relevant to not only to the clinical diagnosis of cerebellar dysplasia, but also genetic mechanisms and neurodevelopmental outcome correlates. These findings not only contribute to the detection and classification of a subset of neonatal brain dysmaturation, but also provide insight to the pathogenesis of cerebellar dysplasia in CHD. In addition, this is one of the first examples of the application of deep learning to a neuroimaging dataset, in which the hidden layer activation revealed diagnostically and biologically relevant features about the clinical pathogenesis. The code developed for this project is open source, published under the BSD License, and designed to be generalizable to applications both within and beyond neonatal brain imaging. Copyright © 2018 Elsevier Inc. All rights reserved.

Real-Time MRI-Guided Cardiac Cryo-Ablation: A Feasibility Study.

PubMed

Kholmovski, Eugene G; Coulombe, Nicolas; Silvernagel, Joshua; Angel, Nathan; Parker, Dennis; Macleod, Rob; Marrouche, Nassir; Ranjan, Ravi

2016-05-01

MRI-based ablation provides an attractive capability of seeing ablation-related tissue changes in real time. Here we describe a real-time MRI-based cardiac cryo-ablation system. Studies were performed in canine model (n = 4) using MR-compatible cryo-ablation devices built for animal use: focal cryo-catheter with 8 mm tip and 28 mm diameter cryo-balloon. The main steps of MRI-guided cardiac cryo-ablation procedure (real-time navigation, confirmation of tip-tissue contact, confirmation of vessel occlusion, real-time monitoring of a freeze zone formation, and intra-procedural assessment of lesions) were validated in a 3 Tesla clinical MRI scanner. The MRI compatible cryo-devices were advanced to the right atrium (RA) and right ventricle (RV) and their position was confirmed by real-time MRI. Specifically, contact between catheter tip and myocardium and occlusion of superior vena cava (SVC) by the balloon was visually validated. Focal cryo-lesions were created in the RV septum. Circumferential ablation of SVC-RA junction with no gaps was achieved using the cryo-balloon. Real-time visualization of freeze zone formation was achieved in all studies when lesions were successfully created. The ablations and presence of collateral damage were confirmed by T1-weighted and late gadolinium enhancement MRI and gross pathological examination. This study confirms the feasibility of a MRI-based cryo-ablation system in performing cardiac ablation procedures. The system allows real-time catheter navigation, confirmation of catheter tip-tissue contact, validation of vessel occlusion by cryo-balloon, real-time monitoring of a freeze zone formation, and intra-procedural assessment of ablations including collateral damage. © 2016 Wiley Periodicals, Inc.

An in vivo MRI Template Set for Morphometry, Tissue Segmentation, and fMRI Localization in Rats

PubMed Central

Valdés-Hernández, Pedro Antonio; Sumiyoshi, Akira; Nonaka, Hiroi; Haga, Risa; Aubert-Vásquez, Eduardo; Ogawa, Takeshi; Iturria-Medina, Yasser; Riera, Jorge J.; Kawashima, Ryuta

2011-01-01

Over the last decade, several papers have focused on the construction of highly detailed mouse high field magnetic resonance image (MRI) templates via non-linear registration to unbiased reference spaces, allowing for a variety of neuroimaging applications such as robust morphometric analyses. However, work in rats has only provided medium field MRI averages based on linear registration to biased spaces with the sole purpose of approximate functional MRI (fMRI) localization. This precludes any morphometric analysis in spite of the need of exploring in detail the neuroanatomical substrates of diseases in a recent advent of rat models. In this paper we present a new in vivo rat T2 MRI template set, comprising average images of both intensity and shape, obtained via non-linear registration. Also, unlike previous rat template sets, we include white and gray matter probabilistic segmentations, expanding its use to those applications demanding prior-based tissue segmentation, e.g., statistical parametric mapping (SPM) voxel-based morphometry. We also provide a preliminary digitalization of latest Paxinos and Watson atlas for anatomical and functional interpretations within the cerebral cortex. We confirmed that, like with previous templates, forepaw and hindpaw fMRI activations can be correctly localized in the expected atlas structure. To exemplify the use of our new MRI template set, were reported the volumes of brain tissues and cortical structures and probed their relationships with ontogenetic development. Other in vivo applications in the near future can be tensor-, deformation-, or voxel-based morphometry, morphological connectivity, and diffusion tensor-based anatomical connectivity. Our template set, freely available through the SPM extension website, could be an important tool for future longitudinal and/or functional extensive preclinical studies. PMID:22275894

Oxidative stress measured in vivo without an exogenous contrast agent using QUEST MRI

NASA Astrophysics Data System (ADS)

Berkowitz, Bruce A.

2018-06-01

Decades of experimental studies have implicated excessive generation of reactive oxygen species (ROS) in the decline of tissue function during normal aging, and as a pathogenic factor in a vast array of fatal or debilitating morbidities. This massive body of work has important clinical implications since many antioxidants are FDA approved, readily cross blood-tissue barriers, and are effective at improving disease outcomes. Yet, the potential benefits of antioxidants have remained largely unrealized in patients because conventional methods cannot determine the dose, timing, and drug combinations to be used in clinical trials to localize and decrease oxidative stress. To address this major problem and improve translational success, new methods are urgently needed that non-invasively measure the same ROS biomarker both in animal models and patients with high spatial resolution. Here, we summarize a transformative solution based on a novel method: QUEnch-assiSTed MRI (QUEST MRI). The QUEST MRI index is a significant antioxidant-induced improvement in pathophysiology, or a reduction in 1/T1 (i.e., R1). The latter form of QUEST MRI provides a unique measure of uncontrolled production of endogenous, paramagnetic reactive oxygen species (ROS). QUEST MRI results to-date have been validated by gold standard oxidative stress assays. QUEST MRI has high translational potential because it does not use an exogenous contrast agent and requires only standard MRI equipment. Summarizing, QUEST MRI is a powerful non-invasive approach with unprecedented potential for (i) bridging antioxidant treatment in animal models and patients, (ii) identifying tissue subregions exhibiting oxidative stress, and (iii) coupling oxidative stress localization with behavioral dysfunction, disease pathology, and genetic vulnerabilities to serve as a marker of susceptibility.

DOE Office of Scientific and Technical Information (OSTI.GOV)

Emin, David, E-mail: emin@unm.edu; Akhtari, Massoud; Ellingson, B. M.

We analyze the transient-dc and frequency-dependent electrical conductivities between blocking electrodes. We extend this analysis to measurements of ions’ transport in freshly excised bulk samples of human brain tissue whose complex cellular structure produces blockages. The associated ionic charge-carrier density and diffusivity are consistent with local values for sodium cations determined non-invasively in brain tissue by MRI (NMR) and diffusion-MRI (spin-echo NMR). The characteristic separation between blockages, about 450 microns, is very much shorter than that found for sodium-doped gel proxies for brain tissue, >1 cm.

Spatial and temporal MRI profile of ischemic tissue after the acute stages of a permanent mouse model of stroke.

PubMed

Bogaert-Buchmann, A; Poittevin, M; Po, C; Dupont, D; Sebrié, C; Tomita, Y; Trandinh, A; Seylaz, J; Pinard, E; Méric, P; Kubis, N; Gillet, B

2013-01-01

To characterize the progression of injured tissue resulting from a permanent focal cerebral ischemia after the acute phase, Magnetic Resonance Imaging (MRI) monitoring was performed on adult male C57BL/6J mice in the subacute stages, and correlated to histological analyses. Lesions were induced by electrocoagulation of the middle cerebral artery. Serial MRI measurements and weighted-images (T2, T1, T2* and Diffusion Tensor Imaging) were performed on a 9.4T scanner. Histological data (Cresyl-Violet staining and laminin-, Iba1- and GFAP-immunostainings) were obtained 1 and 2 weeks after the stroke. Two days after stroke, tissues assumed to correspond to the infarct core, were detected as a hyperintensity signal area in T2-weighted images. One week later, low-intensity signal areas appeared. Longitudinal MRI study showed that these areas remained present over the following week, and was mainly linked to a drop of the T2 relaxation time value in the corresponding tissues. Correlation with histological data and immuno-histochemistry showed that these areas corresponded to microglial cells. The present data provide, for the first time detailed MRI parameters of microglial cells dynamics, allowing its non-invasive monitoring during the chronic stages of a stroke. This could be particularly interesting in regards to emerging anti-inflammatory stroke therapies.

Spatial and Temporal MRI Profile of Ischemic Tissue after the Acute Stages of a Permanent Mouse Model of Stroke

PubMed Central

Bogaert-Buchmann, A; Poittevin, M; Po, C; Dupont, D; Sebrié, C; Tomita, Y; TranDinh, A; Seylaz, J; Pinard, E; Méric, P; Kubis, N; Gillet, B

2013-01-01

Object: To characterize the progression of injured tissue resulting from a permanent focal cerebral ischemia after the acute phase, Magnetic Resonance Imaging (MRI) monitoring was performed on adult male C57BL/6J mice in the subacute stages, and correlated to histological analyses. Material and methods: Lesions were induced by electrocoagulation of the middle cerebral artery. Serial MRI measurements and weighted-images (T2, T1, T2* and Diffusion Tensor Imaging) were performed on a 9.4T scanner. Histological data (Cresyl-Violet staining and laminin-, Iba1- and GFAP-immunostainings) were obtained 1 and 2 weeks after the stroke. Results: Two days after stroke, tissues assumed to correspond to the infarct core, were detected as a hyperintensity signal area in T2-weighted images. One week later, low-intensity signal areas appeared. Longitudinal MRI study showed that these areas remained present over the following week, and was mainly linked to a drop of the T2 relaxation time value in the corresponding tissues. Correlation with histological data and immuno-histochemistry showed that these areas corresponded to microglial cells. Conclusion: The present data provide, for the first time detailed MRI parameters of microglial cells dynamics, allowing its non-invasive monitoring during the chronic stages of a stroke. This could be particularly interesting in regards to emerging anti-inflammatory stroke therapies. PMID:23459141

Quantum Cascade Laser-Based Infrared Microscopy for Label-Free and Automated Cancer Classification in Tissue Sections.

PubMed

Kuepper, Claus; Kallenbach-Thieltges, Angela; Juette, Hendrik; Tannapfel, Andrea; Großerueschkamp, Frederik; Gerwert, Klaus

2018-05-16

A feasibility study using a quantum cascade laser-based infrared microscope for the rapid and label-free classification of colorectal cancer tissues is presented. Infrared imaging is a reliable, robust, automated, and operator-independent tissue classification method that has been used for differential classification of tissue thin sections identifying tumorous regions. However, long acquisition time by the so far used FT-IR-based microscopes hampered the clinical translation of this technique. Here, the used quantum cascade laser-based microscope provides now infrared images for precise tissue classification within few minutes. We analyzed 110 patients with UICC-Stage II and III colorectal cancer, showing 96% sensitivity and 100% specificity of this label-free method as compared to histopathology, the gold standard in routine clinical diagnostics. The main hurdle for the clinical translation of IR-Imaging is overcome now by the short acquisition time for high quality diagnostic images, which is in the same time range as frozen sections by pathologists.

A minimum spanning forest based classification method for dedicated breast CT images

DOE Office of Scientific and Technical Information (OSTI.GOV)

Pike, Robert; Sechopoulos, Ioannis; Fei, Baowei, E-mail: bfei@emory.edu

Purpose: To develop and test an automated algorithm to classify different types of tissue in dedicated breast CT images. Methods: Images of a single breast of five different patients were acquired with a dedicated breast CT clinical prototype. The breast CT images were processed by a multiscale bilateral filter to reduce noise while keeping edge information and were corrected to overcome cupping artifacts. As skin and glandular tissue have similar CT values on breast CT images, morphologic processing is used to identify the skin based on its position information. A support vector machine (SVM) is trained and the resulting modelmore » used to create a pixelwise classification map of fat and glandular tissue. By combining the results of the skin mask with the SVM results, the breast tissue is classified as skin, fat, and glandular tissue. This map is then used to identify markers for a minimum spanning forest that is grown to segment the image using spatial and intensity information. To evaluate the authors’ classification method, they use DICE overlap ratios to compare the results of the automated classification to those obtained by manual segmentation on five patient images. Results: Comparison between the automatic and the manual segmentation shows that the minimum spanning forest based classification method was able to successfully classify dedicated breast CT image with average DICE ratios of 96.9%, 89.8%, and 89.5% for fat, glandular, and skin tissue, respectively. Conclusions: A 2D minimum spanning forest based classification method was proposed and evaluated for classifying the fat, skin, and glandular tissue in dedicated breast CT images. The classification method can be used for dense breast tissue quantification, radiation dose assessment, and other applications in breast imaging.« less

Automated classification of optical coherence tomography images of human atrial tissue

NASA Astrophysics Data System (ADS)

Gan, Yu; Tsay, David; Amir, Syed B.; Marboe, Charles C.; Hendon, Christine P.

2016-10-01

Tissue composition of the atria plays a critical role in the pathology of cardiovascular disease, tissue remodeling, and arrhythmogenic substrates. Optical coherence tomography (OCT) has the ability to capture the tissue composition information of the human atria. In this study, we developed a region-based automated method to classify tissue compositions within human atria samples within OCT images. We segmented regional information without prior information about the tissue architecture and subsequently extracted features within each segmented region. A relevance vector machine model was used to perform automated classification. Segmentation of human atrial ex vivo datasets was correlated with trichrome histology and our classification algorithm had an average accuracy of 80.41% for identifying adipose, myocardium, fibrotic myocardium, and collagen tissue compositions.

MRI histogram analysis enables objective and continuous classification of intervertebral disc degeneration.

PubMed

Waldenberg, Christian; Hebelka, Hanna; Brisby, Helena; Lagerstrand, Kerstin Magdalena

2018-05-01

Magnetic resonance imaging (MRI) is the best diagnostic imaging method for low back pain. However, the technique is currently not utilized in its full capacity, often failing to depict painful intervertebral discs (IVDs), potentially due to the rough degeneration classification system used clinically today. MR image histograms, which reflect the IVD heterogeneity, may offer sensitive imaging biomarkers for IVD degeneration classification. This study investigates the feasibility of using histogram analysis as means of objective and continuous grading of IVD degeneration. Forty-nine IVDs in ten low back pain patients (six males, 25-69 years) were examined with MRI (T2-weighted images and T2-maps). Each IVD was semi-automatically segmented on three mid-sagittal slices. Histogram features of the IVD were extracted from the defined regions of interest and correlated to Pfirrmann grade. Both T2-weighted images and T2-maps displayed similar histogram features. Histograms of well-hydrated IVDs displayed two separate peaks, representing annulus fibrosus and nucleus pulposus. Degenerated IVDs displayed decreased peak separation, where the separation was shown to correlate strongly with Pfirrmann grade (P < 0.05). In addition, some degenerated IVDs within the same Pfirrmann grade displayed diametrically different histogram appearances. Histogram features correlated well with IVD degeneration, suggesting that IVD histogram analysis is a suitable tool for objective and continuous IVD degeneration classification. As histogram analysis revealed IVD heterogeneity, it may be a clinical tool for characterization of regional IVD degeneration effects. To elucidate the usefulness of histogram analysis in patient management, IVD histogram features between asymptomatic and symptomatic individuals needs to be compared.

Amyloid positron emission tomography with (18)F-flutemetamol and structural magnetic resonance imaging in the classification of mild cognitive impairment and Alzheimer's disease.

PubMed

Duara, Ranjan; Loewenstein, David A; Shen, Qian; Barker, Warren; Potter, Elizabeth; Varon, Daniel; Heurlin, Kristen; Vandenberghe, Rik; Buckley, Christopher

2013-05-01

To evaluate the contributions of amyloid-positive (Am+) and medial temporal atrophy-positive (MTA+) scans to the diagnostic classification of prodromal and probable Alzheimer's disease (AD). (18)F-flutemetamol-labeled amyloid positron emission tomography (PET) and magnetic resonance imaging (MRI) were used to classify 10 young normal, 15 elderly normal, 20 amnestic mild cognitive impairment (aMCI), and 27 AD subjects. MTA+ status was determined using a cut point derived from a previous study, and Am+ status was determined using a conservative and liberal cut point. The rates of MRI scans with positive results among young normal, elderly normal, aMCI, and AD subjects were 0%, 20%, 75%, and 82%, respectively. Using conservative cut points, the rates of Am+ scans for these same groups of subjects were 0%, 7%, 50%, and 93%, respectively, with the aMCI group showing the largest discrepancy between Am+ and MTA+ scans. Among aMCI cases, 80% of Am+ subjects were also MTA+, and 70% of amyloid-negative (Am-) subjects were MTA+. The combination of amyloid PET and MTA data was additive, with an overall correct classification rate for aMCI of 86%, when a liberal cut point (standard uptake value ratio = 1.4) was used for amyloid positivity. (18)F-flutemetamol PET and structural MRI provided additive information in the diagnostic classification of aMCI subjects, suggesting an amyloid-independent neurodegenerative component among aMCI subjects in this sample. Copyright © 2013 The Alzheimer's Association. Published by Elsevier Inc. All rights reserved.

Reliability of a novel, semi-quantitative scale for classification of structural brain magnetic resonance imaging in children with cerebral palsy.

PubMed

Fiori, Simona; Cioni, Giovanni; Klingels, Katrjin; Ortibus, Els; Van Gestel, Leen; Rose, Stephen; Boyd, Roslyn N; Feys, Hilde; Guzzetta, Andrea

2014-09-01

To describe the development of a novel rating scale for classification of brain structural magnetic resonance imaging (MRI) in children with cerebral palsy (CP) and to assess its interrater and intrarater reliability. The scale consists of three sections. Section 1 contains descriptive information about the patient and MRI. Section 2 contains the graphical template of brain hemispheres onto which the lesion is transposed. Section 3 contains the scoring system for the quantitative analysis of the lesion characteristics, grouped into different global scores and subscores that assess separately side, regions, and depth. A larger interrater and intrarater reliability study was performed in 34 children with CP (22 males, 12 females; mean age at scan of 9 y 5 mo [SD 3 y 3 mo], range 4 y-16 y 11 mo; Gross Motor Function Classification System level I, [n=22], II [n=10], and level III [n=2]). Very high interrater and intrarater reliability of the total score was found with indices above 0.87. Reliability coefficients of the lobar and hemispheric subscores ranged between 0.53 and 0.95. Global scores for hemispheres, basal ganglia, brain stem, and corpus callosum showed reliability coefficients above 0.65. This study presents the first visual, semi-quantitative scale for classification of brain structural MRI in children with CP. The high degree of reliability of the scale supports its potential application for investigating the relationship between brain structure and function and examining treatment response according to brain lesion severity in children with CP. © 2014 Mac Keith Press.

Multivariate pattern analysis of fMRI data reveals deficits in distributed representations in schizophrenia

PubMed Central

Yoon, Jong H.; Tamir, Diana; Minzenberg, Michael J.; Ragland, J. Daniel; Ursu, Stefan; Carter, Cameron S.

2009-01-01

Background Multivariate pattern analysis is an alternative method of analyzing fMRI data, which is capable of decoding distributed neural representations. We applied this method to test the hypothesis of the impairment in distributed representations in schizophrenia. We also compared the results of this method with traditional GLM-based univariate analysis. Methods 19 schizophrenia and 15 control subjects viewed two runs of stimuli--exemplars of faces, scenes, objects, and scrambled images. To verify engagement with stimuli, subjects completed a 1-back matching task. A multi-voxel pattern classifier was trained to identify category-specific activity patterns on one run of fMRI data. Classification testing was conducted on the remaining run. Correlation of voxel-wise activity across runs evaluated variance over time in activity patterns. Results Patients performed the task less accurately. This group difference was reflected in the pattern analysis results with diminished classification accuracy in patients compared to controls, 59% and 72% respectively. In contrast, there was no group difference in GLM-based univariate measures. In both groups, classification accuracy was significantly correlated with behavioral measures. Both groups showed highly significant correlation between inter-run correlations and classification accuracy. Conclusions Distributed representations of visual objects are impaired in schizophrenia. This impairment is correlated with diminished task performance, suggesting that decreased integrity of cortical activity patterns is reflected in impaired behavior. Comparisons with univariate results suggest greater sensitivity of pattern analysis in detecting group differences in neural activity and reduced likelihood of non-specific factors driving these results. PMID:18822407

3D Fast Spin Echo T2-weighted Contrast for Imaging the Female Cervix

NASA Astrophysics Data System (ADS)

Vargas Sanchez, Andrea Fernanda

Magnetic Resonance Imaging (MRI) with T2-weighted contrast is the preferred modality for treatment planning and monitoring of cervical cancer. Current clinical protocols image the volume of interest multiple times with two dimensional (2D) T2-weighted MRI techniques. It is of interest to replace these multiple 2D acquisitions with a single three dimensional (3D) MRI acquisition to save time. However, at present the image contrast of standard 3D MRI does not distinguish cervical healthy tissue from cancerous tissue. The purpose of this thesis is to better understand the underlying factors that govern the contrast of 3D MRI and exploit this understanding via sequence modifications to improve the contrast. Numerical simulations are developed to predict observed contrast alterations and to propose an improvement. Improvements of image contrast are shown in simulation and with healthy volunteers. Reported results are only preliminary but a promising start to establish definitively 3D MRI for cervical cancer applications.

T₁ρ MRI of human musculoskeletal system.

PubMed

Wang, Ligong; Regatte, Ravinder R

2015-03-01

Magnetic resonance imaging (MRI) offers the direct visualization of the human musculoskeletal (MSK) system, especially all diarthrodial tissues including cartilage, bone, menisci, ligaments, tendon, hip, synovium, etc. Conventional MRI techniques based on T1 - and T2 -weighted, proton density (PD) contrast are inconclusive in quantifying early biochemically degenerative changes in MSK system in general and articular cartilage in particular. In recent years, quantitative MR parameter mapping techniques have been used to quantify the biochemical changes in articular cartilage, with a special emphasis on evaluating joint injury, cartilage degeneration, and soft tissue repair. In this article we focus on cartilage biochemical composition, basic principles of T1ρ MRI, implementation of T1ρ pulse sequences, biochemical validation, and summarize the potential applications of the T1ρ MRI technique in MSK diseases including osteoarthritis (OA), anterior cruciate ligament (ACL) injury, and knee joint repair. Finally, we also review the potential advantages, challenges, and future prospects of T1ρ MRI for widespread clinical translation. © 2014 Wiley Periodicals, Inc.

[Redox Molecular Imaging Using ReMI].

PubMed

Hyodo, Fuminori; Ito, Shinji; Utsumi, Hideo

2015-01-01

Tissue redox status is one of the most important parameters to maintain homeostasis in the living body. Numerous redox reactions are involved in metabolic processes, such as energy production in the mitochondrial electron transfer system. A variety of intracellular molecules such as reactive oxygen species, glutathione, thioredoxins, NADPH, flavins, and ascorbic acid may contribute to the overall redox status in tissues. Breakdown of redox balance may lead to oxidative stress and can induce many pathological conditions such as cancer, neurological disorders, and aging. Therefore imaging of tissue redox status and monitoring antioxidant levels in living organisms can be useful in the diagnosis of disease states and assessment of treatment response. In vivo redox molecular imaging technology such as electron spin resonance imaging (ESRI), magnetic resonance imaging (MRI), and dynamic nuclear polarization (DNP)-MRI (redox molecular imaging; ReMI) is emerging as a viable redox status imaging modality. This review focuses on the application of magnetic resonance technologies using MRI or DNP-MRI and redox-sensitive contrast agents.

Usage of CT data in biomechanical research

NASA Astrophysics Data System (ADS)

Safonov, Roman A.; Golyadkina, Anastasiya A.; Kirillova, Irina V.; Kossovich, Leonid Y.

2017-02-01

Object of study: The investigation is focused on development of personalized medicine. The determination of mechanical properties of bone tissues based on in vivo data was considered. Methods: CT, MRI, natural experiments on versatile test machine Instron 5944, numerical experiments using Python programs. Results: The medical diagnostics methods, which allows determination of mechanical properties of bone tissues based on in vivo data. The series of experiments to define the values of mechanical parameters of bone tissues. For one and the same sample, computed tomography (CT), magnetic resonance imaging (MRI), ultrasonic investigations and mechanical experiments on single-column test machine Instron 5944 were carried out. The computer program for comparison of CT and MRI images was created. The grayscale values in the same points of the samples were determined on both CT and MRI images. The Haunsfield grayscale values were used to determine rigidity (Young module) and tensile strength of the samples. The obtained data was compared to natural experiments results for verification.

Augmenting intraoperative MRI with preoperative fMRI and DTI by biomechanical simulation of brain deformation

NASA Astrophysics Data System (ADS)

Warfield, Simon K.; Talos, Florin; Kemper, Corey; Cosman, Eric; Tei, Alida; Ferrant, Matthieu; Macq, Benoit M. M.; Wells, William M., III; Black, Peter M.; Jolesz, Ferenc A.; Kikinis, Ron

2003-05-01

The key challenge facing the neurosurgeon during neurosurgery is to be able to remove from the brain as much tumor tissue as possible while preserving healthy tissue and minimizing the disruption of critical anatomical structures. The purpose of this work was to demonstrate the use of biomechanical simulation of brain deformation to project preoperative fMRI and DTI data into the coordinate system of the patient brain deformed during neurosurgery. This projection enhances the visualization of relevant critical structures available to the neurosurgeon. Our approach to tracking brain changes during neurosurgery has been previously described. We applied this procedure to warp preoperative fMRI and DTI to match intraoperative MRI. We constructed visualizations of preoperative fMRI and DTI, and intraoperative MRI showing a close correspondence between the matched data. We have previously demonstrated our biomechanical simulation of brain deformation can be executed entirely during neurosurgery. We previously used a generic atlas as a substitute for patient specific data. Here we report the successful alignment of patient-specific DTI and fMRI preoperative data into the intraoperative configuration of the patient's brain. This can significantly enhance the information available to the neurosurgeon.

Fabrication of custom-shaped grafts for cartilage regeneration.

PubMed

Koo, Seungbum; Hargreaves, Brian A; Gold, Garry E; Dragoo, Jason L

2010-10-01

to create a custom-shaped graft through 3D tissue shape reconstruction and rapid-prototype molding methods using MRI data, and to test the accuracy of the custom-shaped graft against the original anatomical defect. An iatrogenic defect on the distal femur was identified with a 1.5 Tesla MRI and its shape was reconstructed into a three-dimensional (3D) computer model by processing the 3D MRI data. First, the accuracy of the MRI-derived 3D model was tested against a laser-scan based 3D model of the defect. A custom-shaped polyurethane graft was fabricated from the laser-scan based 3D model by creating custom molds through computer aided design and rapid-prototyping methods. The polyurethane tissue was laser-scanned again to calculate the accuracy of this process compared to the original defect. The volumes of the defect models from MRI and laser-scan were 537 mm3 and 405 mm3, respectively, implying that the MRI model was 33% larger than the laser-scan model. The average (±SD) distance deviation of the exterior surface of the MRI model from the laser-scan model was 0.4 ± 0.4 mm. The custom-shaped tissue created from the molds was qualitatively very similar to the original shape of the defect. The volume of the custom-shaped cartilage tissue was 463 mm3 which was 15% larger than the laser-scan model. The average (±SD) distance deviation between the two models was 0.04 ± 0.19 mm. This investigation proves the concept that custom-shaped engineered grafts can be fabricated from standard sequence 3-D MRI data with the use of CAD and rapid-prototyping technology. The accuracy of this technology may help solve the interfacial problem between native cartilage and graft, if the grafts are custom made for the specific defect. The major source of error in fabricating a 3D custom-shaped cartilage graft appears to be the accuracy of a MRI data itself; however, the precision of the model is expected to increase by the utilization of advanced MR sequences with higher magnet strengths.

A continuous tensor field approximation of discrete DT-MRI data for extracting microstructural and architectural features of tissue.

PubMed

Pajevic, Sinisa; Aldroubi, Akram; Basser, Peter J

2002-01-01

The effective diffusion tensor of water, D, measured by diffusion tensor MRI (DT-MRI), is inherently a discrete, noisy, voxel-averaged sample of an underlying macroscopic effective diffusion tensor field, D(x). Within fibrous tissues this field is presumed to be continuous and smooth at a gross anatomical length scale. Here a new, general mathematical framework is proposed that uses measured DT-MRI data to produce a continuous approximation to D(x). One essential finding is that the continuous tensor field representation can be constructed by repeatedly performing one-dimensional B-spline transforms of the DT-MRI data. The fidelity and noise-immunity of this approximation are tested using a set of synthetically generated tensor fields to which background noise is added via Monte Carlo methods. Generally, these tensor field templates are reproduced faithfully except at boundaries where diffusion properties change discontinuously or where the tensor field is not microscopically homogeneous. Away from such regions, the tensor field approximation does not introduce bias in useful DT-MRI parameters, such as Trace(D(x)). It also facilitates the calculation of several new parameters, particularly differential quantities obtained from the tensor of spatial gradients of D(x). As an example, we show that they can identify tissue boundaries across which diffusion properties change rapidly using in vivo human brain data. One important application of this methodology is to improve the reliability and robustness of DT-MRI fiber tractography.

Linewidth narrowing for 31Phosphorus MRI of cell membranes

NASA Astrophysics Data System (ADS)

Barrett, Sean; Frey, Merideth; Madri, Joseph; Michaud, Michael

2011-03-01

Most 31 P Magnetic Resonance Spectroscopy studies of tissues try to avoid contamination by a relatively large, but broad, spectral feature attributed to cell membrane phospholipids. MRI using this broad 31 P membrane spectrum is not even attempted, since the spatial resolution and signal-to-noise would be poor, relative to conventional MRI using the narrow 1 H water spectrum. This long-standing barrier has been overcome by a novel pulse sequence, recently discovered in fundamental quantum computation research, which narrows the broad 31 P spectrum by ~ 1000 × . Applying time-dependent gradients in synch with a repeating pulse block enables a new route to high spatial resolution, 3D 31 P MRI of the soft solid components of cells and tissues. So far, intact and sectioned samples of ex vivo fixed mouse organs have been imaged, with (sub-mm)3 voxels. Extending the reach of MRI to broad spectra in natural and artificial tissues opens a new window into cells, enabling progress in biomedical research. W.J. Thoma et al., J. MR 61, 141 (1985); E.J. Murphy et al., MR Med 12, 282 (1989); R. McNamara et al., NMR Biomed 7, 237 (1994).

Nuclear Magnetic Resonance Imaging in Endodontics: A Review.

PubMed

Di Nardo, Dario; Gambarini, Gianluca; Capuani, Silvia; Testarelli, Luca

2018-04-01

This review analyzes the increasing role of magnetic resonance imaging (MRI) in dentistry and its relevance in endodontics. Limits and new strategies to develop MRI protocols for endodontic purposes are reported and discussed. Eligible studies were identified by searching the PubMed databases. Only original articles on dental structures, anatomy, and endodontics investigated by in vitro and in vivo MRI were included in this review. Original articles on MRI in dentistry not concerning anatomy and endodontics were excluded. All the consulted studies showed well-defined images of pathological conditions such as caries and microcracks. The enhanced contrast of pulp provided a high-quality reproduction of the tooth shape and root canal in vitro and in vivo. Assessment of periapical lesions is possible even without the use of contrast medium. MRI is a nonionizing technique characterized by high tissue contrast and high image resolution of soft tissues; it could be considered a valid and safe diagnostic investigation in endodontics because of its potential to identify pulp tissues, define root canal shape, and locate periapical lesions. Copyright © 2018 American Association of Endodontists. Published by Elsevier Inc. All rights reserved.

Automated segmentation and reconstruction of patient-specific cardiac anatomy and pathology from in vivo MRI*

NASA Astrophysics Data System (ADS)

Ringenberg, Jordan; Deo, Makarand; Devabhaktuni, Vijay; Filgueiras-Rama, David; Pizarro, Gonzalo; Ibañez, Borja; Berenfeld, Omer; Boyers, Pamela; Gold, Jeffrey

2012-12-01

This paper presents an automated method to segment left ventricle (LV) tissues from functional and delayed-enhancement (DE) cardiac magnetic resonance imaging (MRI) scans using a sequential multi-step approach. First, a region of interest (ROI) is computed to create a subvolume around the LV using morphological operations and image arithmetic. From the subvolume, the myocardial contours are automatically delineated using difference of Gaussians (DoG) filters and GSV snakes. These contours are used as a mask to identify pathological tissues, such as fibrosis or scar, within the DE-MRI. The presented automated technique is able to accurately delineate the myocardium and identify the pathological tissue in patient sets. The results were validated by two expert cardiologists, and in one set the automated results are quantitatively and qualitatively compared with expert manual delineation. Furthermore, the method is patient-specific, performed on an entire patient MRI series. Thus, in addition to providing a quick analysis of individual MRI scans, the fully automated segmentation method is used for effectively tagging regions in order to reconstruct computerized patient-specific 3D cardiac models. These models can then be used in electrophysiological studies and surgical strategy planning.

Comparison of Dynamic Contrast Enhanced MRI and Quantitative SPECT in a Rat Glioma Model

PubMed Central

Skinner, Jack T.; Yankeelov, Thomas E.; Peterson, Todd E.; Does, Mark D.

2012-01-01

Pharmacokinetic modeling of dynamic contrast enhanced (DCE)-MRI data provides measures of the extracellular volume fraction (ve) and the volume transfer constant (Ktrans) in a given tissue. These parameter estimates may be biased, however, by confounding issues such as contrast agent and tissue water dynamics, or assumptions of vascularization and perfusion made by the commonly used model. In contrast to MRI, radiotracer imaging with SPECT is insensitive to water dynamics. A quantitative dual-isotope SPECT technique was developed to obtain an estimate of ve in a rat glioma model for comparison to the corresponding estimates obtained using DCE-MRI with a vascular input function (VIF) and reference region model (RR). Both DCE-MRI methods produced consistently larger estimates of ve in comparison to the SPECT estimates, and several experimental sources were postulated to contribute to these differences. PMID:22991315

Imaging of non-osteochondral tissues in osteoarthritis.

PubMed

Guermazi, A; Roemer, F W; Crema, M D; Englund, M; Hayashi, D

2014-10-01

The aim of this review is to describe imaging techniques for evaluation of non-osteochondral structures such as the synovium, menisci in the knee, labrum in the hip, ligaments and muscles and to review the literature from recent clinical and epidemiological studies of OA. This is a non-systematic narrative review of published literature on imaging of non-osteochondral tissues in OA. PubMed and MEDLINE search for articles published up to 2014, using the keywords osteoarthritis, synovitis, meniscus, labrum, ligaments, plica, muscles, magnetic resonance imaging (MRI), ultrasound, computed tomography (CT), scintigraphy, and positron emission tomography (PET). Published literature showed imaging of non-osteochondral tissues in OA relies primarily on MRI and ultrasound. The use of semiquantitative and quantitative imaging biomarkers of non-osteochondral tissues in clinical and epidemiological OA studies is reported. We highlight studies that have compared both imaging methodologies directly, and those that have established a relationship between imaging biomarkers and clinical outcomes. We provide recommendations as to which imaging protocols should be used to assess disease-specific changes regarding synovium, meniscus in the knee, labrum in the hip, and ligaments, and highlight potential pitfalls in their usage. MRI and ultrasound are currently the most useful imaging modalities for evaluation of non-osteochondral tissues in OA. MRI evaluation of any tissue needs to be performed using appropriate MR pulse sequences. Ultrasound may be particularly useful for evaluation of small joints of the hand. Nuclear medicine and CT play a limited role in imaging of non-osteochondral tissues in OA. Copyright © 2014 Osteoarthritis Research Society International. Published by Elsevier Ltd. All rights reserved.

Deep learning of joint myelin and T1w MRI features in normal-appearing brain tissue to distinguish between multiple sclerosis patients and healthy controls.

PubMed

Yoo, Youngjin; Tang, Lisa Y W; Brosch, Tom; Li, David K B; Kolind, Shannon; Vavasour, Irene; Rauscher, Alexander; MacKay, Alex L; Traboulsee, Anthony; Tam, Roger C

2018-01-01

Myelin imaging is a form of quantitative magnetic resonance imaging (MRI) that measures myelin content and can potentially allow demyelinating diseases such as multiple sclerosis (MS) to be detected earlier. Although focal lesions are the most visible signs of MS pathology on conventional MRI, it has been shown that even tissues that appear normal may exhibit decreased myelin content as revealed by myelin-specific images (i.e., myelin maps). Current methods for analyzing myelin maps typically use global or regional mean myelin measurements to detect abnormalities, but ignore finer spatial patterns that may be characteristic of MS. In this paper, we present a machine learning method to automatically learn, from multimodal MR images, latent spatial features that can potentially improve the detection of MS pathology at early stage. More specifically, 3D image patches are extracted from myelin maps and the corresponding T1-weighted (T1w) MRIs, and are used to learn a latent joint myelin-T1w feature representation via unsupervised deep learning. Using a data set of images from MS patients and healthy controls, a common set of patches are selected via a voxel-wise t -test performed between the two groups. In each MS image, any patches overlapping with focal lesions are excluded, and a feature imputation method is used to fill in the missing values. A feature selection process (LASSO) is then utilized to construct a sparse representation. The resulting normal-appearing features are used to train a random forest classifier. Using the myelin and T1w images of 55 relapse-remitting MS patients and 44 healthy controls in an 11-fold cross-validation experiment, the proposed method achieved an average classification accuracy of 87.9% (SD = 8.4%), which is higher and more consistent across folds than those attained by regional mean myelin (73.7%, SD = 13.7%) and T1w measurements (66.7%, SD = 10.6%), or deep-learned features in either the myelin (83.8%, SD = 11.0%) or T1w (70.1%, SD = 13.6%) images alone, suggesting that the proposed method has strong potential for identifying image features that are more sensitive and specific to MS pathology in normal-appearing brain tissues.

Fusion of multi-parametric MRI and temporal ultrasound for characterization of prostate cancer: in vivo feasibility study

NASA Astrophysics Data System (ADS)

Imani, Farhad; Ghavidel, Sahar; Abolmaesumi, Purang; Khallaghi, Siavash; Gibson, Eli; Khojaste, Amir; Gaed, Mena; Moussa, Madeleine; Gomez, Jose A.; Romagnoli, Cesare; Cool, Derek W.; Bastian-Jordan, Matthew; Kassam, Zahra; Siemens, D. Robert; Leveridge, Michael; Chang, Silvia; Fenster, Aaron; Ward, Aaron D.; Mousavi, Parvin

2016-03-01

Recently, multi-parametric Magnetic Resonance Imaging (mp-MRI) has been used to improve the sensitivity of detecting high-risk prostate cancer (PCa). Prior to biopsy, primary and secondary cancer lesions are identified on mp-MRI. The lesions are then targeted using TRUS guidance. In this paper, for the first time, we present a fused mp-MRI-temporal-ultrasound framework for characterization of PCa, in vivo. Cancer classification results obtained using temporal ultrasound are fused with those achieved using consolidated mp-MRI maps determined by multiple observers. We verify the outcome of our study using histopathology following deformable registration of ultrasound and histology images. Fusion of temporal ultrasound and mp-MRI for characterization of the PCa results in an area under the receiver operating characteristic curve (AUC) of 0.86 for cancerous regions with Gleason scores (GSs)>=3+3, and AUC of 0.89 for those with GSs>=3+4.

Towards automated spectroscopic tissue classification in thyroid and parathyroid surgery.

PubMed

Schols, Rutger M; Alic, Lejla; Wieringa, Fokko P; Bouvy, Nicole D; Stassen, Laurents P S

2017-03-01

In (para-)thyroid surgery iatrogenic parathyroid injury should be prevented. To aid the surgeons' eye, a camera system enabling parathyroid-specific image enhancement would be useful. Hyperspectral camera technology might work, provided that the spectral signature of parathyroid tissue offers enough specific features to be reliably and automatically distinguished from surrounding tissues. As a first step to investigate this, we examined the feasibility of wide band diffuse reflectance spectroscopy (DRS) for automated spectroscopic tissue classification, using silicon (Si) and indium-gallium-arsenide (InGaAs) sensors. DRS (350-1830 nm) was performed during (para-)thyroid resections. From the acquired spectra 36 features at predefined wavelengths were extracted. The best features for classification of parathyroid from adipose or thyroid were assessed by binary logistic regression for Si- and InGaAs-sensor ranges. Classification performance was evaluated by leave-one-out cross-validation. In 19 patients 299 spectra were recorded (62 tissue sites: thyroid = 23, parathyroid = 21, adipose = 18). Classification accuracy of parathyroid-adipose was, respectively, 79% (Si), 82% (InGaAs) and 97% (Si/InGaAs combined). Parathyroid-thyroid classification accuracies were 80% (Si), 75% (InGaAs), 82% (Si/InGaAs combined). Si and InGaAs sensors are fairly accurate for automated spectroscopic classification of parathyroid, adipose and thyroid tissues. Combination of both sensor technologies improves accuracy. Follow-up research, aimed towards hyperspectral imaging seems justified. Copyright © 2016 John Wiley & Sons, Ltd. Copyright © 2016 John Wiley & Sons, Ltd.

Perspectives on Porous Media MR in Clinical MRI

NASA Astrophysics Data System (ADS)

Sigmund, E. E.

2011-03-01

Many goals and challenges of research in natural or synthetic porous media are mirrored in quantitative medical MRI. This review will describe examples where MR techniques used in porous media (particularly diffusion-weighted imaging (DWI)) are applied to physiological pathologies. Tissue microstructure is one area with great overlap with porous media science. Diffusion-weighting (esp. in neurological tissue) has motivated models with explicit physical dimensions, statistical parameters, empirical descriptors, or hybrids thereof. Another clinically relevant microscopic process is active flow. Renal (kidney) tissue possesses significant active vascular / tubular transport that manifests as "pseudodiffusion." Cancerous lesions involve anomalies in both structure and flow. The tools of magnetic resonance and their interpretation in porous media has had great impact on clinical MRI, and continued cross-fertilization of ideas can only enhance the progress of both fields.

Soft tissue rapid prototyping in neurosurgery.

PubMed

Vloeberghs, M; Hatfield, F; Daemi, F; Dickens, P

1998-01-01

As part of our research into the fluid hydrodynamics of the human ventricular system, a fused deposition model of the human ventricular system was made using magnetic resonance imaging (MRI) data. This article describes the manufacturing of a positive cast of the ventricles as a first step in the construction of a hollow model. After decryption of the original MRI file (ACR-Nema format), the MRI slices were reassembled semiautomatically and a rapid prototyping station produced a resin model. Because of its ease and speed, this method harbors great potential for teaching purposes, research, and preoperative planning in complex three-dimensional soft tissue targets.

Deep learning for brain tumor classification

NASA Astrophysics Data System (ADS)

Paul, Justin S.; Plassard, Andrew J.; Landman, Bennett A.; Fabbri, Daniel

2017-03-01

Recent research has shown that deep learning methods have performed well on supervised machine learning, image classification tasks. The purpose of this study is to apply deep learning methods to classify brain images with different tumor types: meningioma, glioma, and pituitary. A dataset was publicly released containing 3,064 T1-weighted contrast enhanced MRI (CE-MRI) brain images from 233 patients with either meningioma, glioma, or pituitary tumors split across axial, coronal, or sagittal planes. This research focuses on the 989 axial images from 191 patients in order to avoid confusing the neural networks with three different planes containing the same diagnosis. Two types of neural networks were used in classification: fully connected and convolutional neural networks. Within these two categories, further tests were computed via the augmentation of the original 512×512 axial images. Training neural networks over the axial data has proven to be accurate in its classifications with an average five-fold cross validation of 91.43% on the best trained neural network. This result demonstrates that a more general method (i.e. deep learning) can outperform specialized methods that require image dilation and ring-forming subregions on tumors.

Fine-Granularity Functional Interaction Signatures for Characterization of Brain Conditions

PubMed Central

Hu, Xintao; Zhu, Dajiang; Lv, Peili; Li, Kaiming; Han, Junwei; Wang, Lihong; Shen, Dinggang; Guo, Lei; Liu, Tianming

2014-01-01

In the human brain, functional activity occurs at multiple spatial scales. Current studies on functional brain networks and their alterations in brain diseases via resting-state functional magnetic resonance imaging (rs-fMRI) are generally either at local scale (regionally confined analysis and inter-regional functional connectivity analysis) or at global scale (graph theoretic analysis). In contrast, inferring functional interaction at fine-granularity sub-network scale has not been adequately explored yet. Here our hypothesis is that functional interaction measured at fine-granularity subnetwork scale can provide new insight into the neural mechanisms of neurological and psychological conditions, thus offering complementary information for healthy and diseased population classification. In this paper, we derived fine-granularity functional interaction (FGFI) signatures in subjects with Mild Cognitive Impairment (MCI) and Schizophrenia by diffusion tensor imaging (DTI) and rsfMRI, and used patient-control classification experiments to evaluate the distinctiveness of the derived FGFI features. Our experimental results have shown that the FGFI features alone can achieve comparable classification performance compared with the commonly used inter-regional connectivity features. However, the classification performance can be substantially improved when FGFI features and inter-regional connectivity features are integrated, suggesting the complementary information achieved from the FGFI signatures. PMID:23319242

Clinical feasibility of using mean apparent propagator (MAP) MRI to characterize brain tissue microstructure.

PubMed

Avram, Alexandru V; Sarlls, Joelle E; Barnett, Alan S; Özarslan, Evren; Thomas, Cibu; Irfanoglu, M Okan; Hutchinson, Elizabeth; Pierpaoli, Carlo; Basser, Peter J

2016-02-15

Diffusion tensor imaging (DTI) is the most widely used method for characterizing noninvasively structural and architectural features of brain tissues. However, the assumption of a Gaussian spin displacement distribution intrinsic to DTI weakens its ability to describe intricate tissue microanatomy. Consequently, the biological interpretation of microstructural parameters, such as fractional anisotropy or mean diffusivity, is often equivocal. We evaluate the clinical feasibility of assessing brain tissue microstructure with mean apparent propagator (MAP) MRI, a powerful analytical framework that efficiently measures the probability density function (PDF) of spin displacements and quantifies useful metrics of this PDF indicative of diffusion in complex microstructure (e.g., restrictions, multiple compartments). Rotation invariant and scalar parameters computed from the MAP show consistent variation across neuroanatomical brain regions and increased ability to differentiate tissues with distinct structural and architectural features compared with DTI-derived parameters. The return-to-origin probability (RTOP) appears to reflect cellularity and restrictions better than MD, while the non-Gaussianity (NG) measures diffusion heterogeneity by comprehensively quantifying the deviation between the spin displacement PDF and its Gaussian approximation. Both RTOP and NG can be decomposed in the local anatomical frame for reference determined by the orientation of the diffusion tensor and reveal additional information complementary to DTI. The propagator anisotropy (PA) shows high tissue contrast even in deep brain nuclei and cortical gray matter and is more uniform in white matter than the FA, which drops significantly in regions containing crossing fibers. Orientational profiles of the propagator computed analytically from the MAP MRI series coefficients allow separation of different fiber populations in regions of crossing white matter pathways, which in turn improves our ability to perform whole-brain fiber tractography. Reconstructions from subsampled data sets suggest that MAP MRI parameters can be computed from a relatively small number of DWIs acquired with high b-value and good signal-to-noise ratio in clinically achievable scan durations of less than 10min. The neuroanatomical consistency across healthy subjects and reproducibility in test-retest experiments of MAP MRI microstructural parameters further substantiate the robustness and clinical feasibility of this technique. The MAP MRI metrics could potentially provide more sensitive clinical biomarkers with increased pathophysiological specificity compared to microstructural measures derived using conventional diffusion MRI techniques. Published by Elsevier Inc.

Efficacy of hidden markov model over support vector machine on multiclass classification of healthy and cancerous cervical tissues

NASA Astrophysics Data System (ADS)

Mukhopadhyay, Sabyasachi; Kurmi, Indrajit; Pratiher, Sawon; Mukherjee, Sukanya; Barman, Ritwik; Ghosh, Nirmalya; Panigrahi, Prasanta K.

2018-02-01

In this paper, a comparative study between SVM and HMM has been carried out for multiclass classification of cervical healthy and cancerous tissues. In our study, the HMM methodology is more promising to produce higher accuracy in classification.

Multivariate classification of infrared spectra of cell and tissue samples

DOEpatents

Haaland, David M.; Jones, Howland D. T.; Thomas, Edward V.

1997-01-01

Multivariate classification techniques are applied to spectra from cell and tissue samples irradiated with infrared radiation to determine if the samples are normal or abnormal (cancerous). Mid and near infrared radiation can be used for in vivo and in vitro classifications using at least different wavelengths.

TU-AB-201-11: A Novel Theoretical Framework for MRI-Only Image Guided LDR Prostate and Breast Brachytherapy Implant Dosimetry

DOE Office of Scientific and Technical Information (OSTI.GOV)

Soliman, A; Elzibak, A; Fatemi, A

Purpose: To propose a novel framework for accurate model-based dose calculations using only MR images for LDR prostate and breast seed implant brachytherapy. Methods: Model-based dose calculation methodologies recommended by TG-186 require further knowledge about specific tissue composition, which is challenging with MRI. However, relying on MRI-only for implant dosimetry would reduce the soft tissue delineation uncertainty, costs, and uncertainties associated with multi-modality registration and fusion processes. We propose a novel framework to address this problem using quantitative MRI acquisitions and reconstruction techniques. The framework includes three steps: (1) Identify the locations of seeds(2) Identify the presence (or absence) ofmore » calcification(s)(3) Quantify the water and fat content in the underlying tissueSteps (1) and (2) consider the sources that limit patient dosimetry, particularly the inter-seed attenuation and the calcified regions; while step (3) targets the quantification of the tissue composition to consider the heterogeneities in the medium. Our preliminary work has shown that the seeds and the calcifications can be identified with MRI using both the magnitude and the phase images. By employing susceptibility-weighted imaging with specific post-processing techniques, the phase images can be further explored to distinguish the seeds from the calcifications. Absolute quantification of tissue, water, and fat content is feasible and was previously demonstrated in phantoms and in-vivo applications, particularly for brain diseases. The approach relies on the proportionality of the MR signal to the number of protons in an image volume. By employing appropriate correction algorithms for T1 - and T2*-related biases, B1 transmit and receive field inhomogeneities, absolute water/fat content can be determined. Results: By considering calcification and interseed attenuation, and through the knowledge of water and fat mass density, accurate patient-specific implant dosimetry can be achieved with MRI-only. Conclusion: The proposed framework showed that model-based dose calculation is feasible using MRI-only state-of-the-art techniques.« less

Magnetic Resonance Imaging of Stroke in the Rat

PubMed Central

CHOPP, Michael; LI, Lian; ZHANG, Li; ZHANG, Zheng-gang; LI, Qing-jiang; JIANG, Quan

2014-01-01

Magnetic resonance imaging (MRI) is now a routine neuroimaging tool in the clinic. Throughout all phases of stroke from acute to chronic, MRI plays an important role to diagnose, evaluate and monitor the cerebral tissue undergoing stroke. This review provides a description of various MRI methods and an overview of selected MRI studies, with an embolic stroke model of rat, performed in the MRI laboratory of Department of Neurology, Henry Ford Hospital, Detroit, Michigan, US. PMID:24920874

Comparison of dual-energy X-ray absorptiometry and magnetic resonance imaging-measured adipose tissue depots in HIV-infected and control subjects.

PubMed

Scherzer, Rebecca; Shen, Wei; Bacchetti, Peter; Kotler, Donald; Lewis, Cora E; Shlipak, Michael G; Punyanitya, Mark; Heymsfield, Steven B; Grunfeld, Carl

2008-10-01

Studies in persons without HIV infection have compared adipose tissue measured by dual-energy X-ray absorptiometry (DXA) and magnetic resonance imaging (MRI), but no such study has been conducted in HIV-infected (HIV+) subjects, who have a high prevalence of regional fat loss. We compared DXA- with MRI-measured trunk, leg, arm, and total fat in HIV+ and control subjects. A cross-sectional analysis was conducted in 877 HIV+ subjects and 260 control subjects in FRAM (Study of Fat Redistribution and Metabolic Change in HIV Infection), stratified by sex and HIV status. Univariate associations of DXA with MRI were strongest for total and trunk fat (r > or = 0.92) and slightly weaker for leg (r > or = 0.87) and arm (r > or = 0.71) fat. The average estimated limb fat was substantially greater for DXA than for MRI for HIV+ and control men and women (all P < 0.0001). Less of a difference was observed in trunk fat measured by DXA and MRI, but the difference was still statistically significant (P < 0.0001). Bland-Altman plots showed increasing differences and variability. Greater average limb fat in control and HIV+ subjects (both P < 0.0001) was associated with greater differences between DXA and MRI measurements. Because the control subjects had more limb fat than did the HIV+ subjects, greater amounts of fat were measured by DXA than by MRI when control subjects were compared with HIV+ subjects. More HIV+ subjects had leg fat in the bottom decile of the control subjects by DXA than by MRI (P < 0.0001). Although DXA- and MRI-measured adipose tissue depots correlate strongly in HIV+ and control subjects, differences increase as average fat increases, particularly for limb fat. DXA may estimate a higher prevalence of peripheral lipoatrophy than does MRI in HIV+ subjects.

Examining multi-component DNA-templated nanostructures as imaging agents

NASA Astrophysics Data System (ADS)

Jaganathan, Hamsa

2011-12-01

Magnetic resonance imaging (MRI) is the leading non-invasive tool for disease imaging and diagnosis. Although MRI exhibits high spatial resolution for anatomical features, the contrast resolution is low. Imaging agents serve as an aid to distinguish different types of tissues within images. Gadolinium chelates, which are considered first generation designs, can be toxic to health, while ultra-small, superparamagnetic nanoparticles (NPs) have low tissue-targeting efficiency and rapid bio-distribution, resulting to an inadequate detection of the MRI signal and enhancement of image contrast. In order to improve the utility of MRI agents, the challenge in composition and structure needs to be addressed. One-dimensional (1D), superparamagnetic nanostructures have been reported to enhance magnetic and in vivo properties and therefore has a potential to improve contrast enhancement in MRI images. In this dissertation, the structure of 1D, multi-component NP chains, scaffolded on DNA, were pre-clinically examined as potential MRI agents. First, research was focused on characterizing and understanding the mechanism of proton relaxation for DNA-templated NP chains using nuclear magnetic resonance (NMR) spectrometry. Proton relaxation and transverse relaxivity were higher in multi-component NP chains compared to disperse NPs, indicating the arrangement of NPs on a 1D structure improved proton relaxation sensitivity. Second, in vitro evaluation for potential issues in toxicity and contrast efficiency in tissue environments using a 3 Tesla clinical MRI scanner was performed. Cell uptake of DNA-templated NP chains was enhanced after encapsulating the nanostructure with layers of polyelectrolytes and targeting ligands. Compared to dispersed NPs, DNA-templated NP chains improved MRI contrast in both the epithelial basement membrane and colon cancer tumors scaffolds. The last part of the project was focused on developing a novel MRI agent that detects changes in DNA methylation levels. The findings from this dissertation suggest that the structural arrangement of NPs on DNA significantly influenced their function and utility as MRI agents.

Magnetic Resonance Imaging Predicts Adverse Local Tissue Reaction Histologic Severity in Modular Neck Total Hip Arthroplasty.

PubMed

Barlow, Brian T; Ortiz, Philippe A; Fields, Kara G; Burge, Alissa J; Potter, Hollis G; Westrich, Geoffrey H

2016-10-01

The association between advanced imaging, serum metal ion levels, and histologic adverse local tissue reaction (ALTR) severity has not been previously reported for Rejuvenate modular neck femoral stems. A cohort of 90 patients with 98 Rejuvenate modular neck femoral stems was revised by a single surgeon from July 2011 to December 2014. Before revision, patients underwent multiacquisition variable resonance image combination sequence magnetic resonance imaging (MRI), and serum cobalt and chromium ion levels were measured. Histologic samples from the revision surgery were scored for synovial lining, inflammatory infiltrate, and tissue organization as proposed by Campbell. Regression based on the generalized estimating equations approach was used to assess the univariate association between each MRI, demographic, and metal ion measure and ALTR severity while accounting for the correlation between bilateral hips. Random forest analysis was then used to determine the relative importance of MRI characteristics, demographics, and metal ion levels in predicting ALTR severity. Synovial thickness as measured on MRI was found to be the strongest predictor of ALTR histologic severity in a recalled modular neck femoral stem. MRI can accurately describe ALTR in modular femoral neck total hip arthroplasty. MRI characteristics, particularly maximal synovial thickness and synovitis volume, predicted histologic severity. Serum metal ion levels do not correlate with histologic severity in Rejuvenate modular neck total hip arthroplasty. Copyright © 2016 Elsevier Inc. All rights reserved.

Quantitative rotating frame relaxometry methods in MRI.

PubMed

Gilani, Irtiza Ali; Sepponen, Raimo

2016-06-01

Macromolecular degeneration and biochemical changes in tissue can be quantified using rotating frame relaxometry in MRI. It has been shown in several studies that the rotating frame longitudinal relaxation rate constant (R1ρ ) and the rotating frame transverse relaxation rate constant (R2ρ ) are sensitive biomarkers of phenomena at the cellular level. In this comprehensive review, existing MRI methods for probing the biophysical mechanisms that affect the rotating frame relaxation rates of the tissue (i.e. R1ρ and R2ρ ) are presented. Long acquisition times and high radiofrequency (RF) energy deposition into tissue during the process of spin-locking in rotating frame relaxometry are the major barriers to the establishment of these relaxation contrasts at high magnetic fields. Therefore, clinical applications of R1ρ and R2ρ MRI using on- or off-resonance RF excitation methods remain challenging. Accordingly, this review describes the theoretical and experimental approaches to the design of hard RF pulse cluster- and adiabatic RF pulse-based excitation schemes for accurate and precise measurements of R1ρ and R2ρ . The merits and drawbacks of different MRI acquisition strategies for quantitative relaxation rate measurement in the rotating frame regime are reviewed. In addition, this review summarizes current clinical applications of rotating frame MRI sequences. Copyright © 2016 John Wiley & Sons, Ltd. Copyright © 2016 John Wiley & Sons, Ltd.

Quantitative breast MRI radiomics for cancer risk assessment and the monitoring of high-risk populations

NASA Astrophysics Data System (ADS)

Mendel, Kayla R.; Li, Hui; Giger, Maryellen L.

2016-03-01

Breast density is routinely assessed qualitatively in screening mammography. However, it is challenging to quantitatively determine a 3D density from a 2D image such as a mammogram. Furthermore, dynamic contrast enhanced magnetic resonance imaging (DCE-MRI) is used more frequently in the screening of high-risk populations. The purpose of our study is to segment parenchyma and to quantitatively determine volumetric breast density on pre-contrast axial DCE-MRI images (i.e., non-contrast) using a semi-automated quantitative approach. In this study, we retroactively examined 3D DCE-MRI images taken for breast cancer screening of a high-risk population. We analyzed 66 cases with ages between 28 and 76 (mean 48.8, standard deviation 10.8). DCE-MRIs were obtained on a Philips 3.0 T scanner. Our semi-automated DCE-MRI algorithm includes: (a) segmentation of breast tissue from non-breast tissue using fuzzy cmeans clustering (b) separation of dense and fatty tissues using Otsu's method, and (c) calculation of volumetric density as the ratio of dense voxels to total breast voxels. We examined the relationship between pre-contrast DCE-MRI density and clinical BI-RADS density obtained from radiology reports, and obtained a statistically significant correlation [Spearman ρ-value of 0.66 (p < 0.0001)]. Our method within precision medicine may be useful for monitoring high-risk populations.

Adipose tissue MRI for quantitative measurement of central obesity.

PubMed

Poonawalla, Aziz H; Sjoberg, Brett P; Rehm, Jennifer L; Hernando, Diego; Hines, Catherine D; Irarrazaval, Pablo; Reeder, Scott B

2013-03-01

To validate adipose tissue magnetic resonance imaging (atMRI) for rapid, quantitative volumetry of visceral adipose tissue (VAT) and total adipose tissue (TAT). Data were acquired on normal adults and clinically overweight girls with Institutional Review Board (IRB) approval/parental consent using sagittal 6-echo 3D-spoiled gradient-echo (SPGR) (26-sec single-breath-hold) at 3T. Fat-fraction images were reconstructed with quantitative corrections, permitting measurement of a physiologically based fat-fraction threshold in normals to identify adipose tissue, for automated measurement of TAT, and semiautomated measurement of VAT. TAT accuracy was validated using oil phantoms and in vivo TAT/VAT measurements validated with manual segmentation. Group comparisons were performed between normals and overweight girls using TAT, VAT, VAT-TAT-ratio (VTR), body-mass-index (BMI), waist circumference, and waist-hip-ratio (WHR). Oil phantom measurements were highly accurate (<3% error). The measured adipose fat-fraction threshold was 96% ± 2%. VAT and TAT correlated strongly with manual segmentation (normals r(2) ≥ 0.96, overweight girls r(2) ≥ 0.99). VAT segmentation required 30 ± 11 minutes/subject (14 ± 5 sec/slice) using atMRI, versus 216 ± 73 minutes/subject (99 ± 31 sec/slice) manually. Group discrimination was significant using WHR (P < 0.001) and VTR (P = 0.004). The atMRI technique permits rapid, accurate measurements of TAT, VAT, and VTR. Copyright © 2012 Wiley Periodicals, Inc.

Monitoring Cartilage Tissue Engineering Using Magnetic Resonance Spectroscopy, Imaging, and Elastography

PubMed Central

Klatt, Dieter; Magin, Richard L.

2013-01-01

A key technical challenge in cartilage tissue engineering is the development of a noninvasive method for monitoring the composition, structure, and function of the tissue at different growth stages. Due to its noninvasive, three-dimensional imaging capabilities and the breadth of available contrast mechanisms, magnetic resonance imaging (MRI) techniques can be expected to play a leading role in assessing engineered cartilage. In this review, we describe the new MR-based tools (spectroscopy, imaging, and elastography) that can provide quantitative biomarkers for cartilage tissue development both in vitro and in vivo. Magnetic resonance spectroscopy can identify the changing molecular structure and alternations in the conformation of major macromolecules (collagen and proteoglycans) using parameters such as chemical shift, relaxation rates, and magnetic spin couplings. MRI provides high-resolution images whose contrast reflects developing tissue microstructure and porosity through changes in local relaxation times and the apparent diffusion coefficient. Magnetic resonance elastography uses low-frequency mechanical vibrations in conjunction with MRI to measure soft tissue mechanical properties (shear modulus and viscosity). When combined, these three techniques provide a noninvasive, multiscale window for characterizing cartilage tissue growth at all stages of tissue development, from the initial cell seeding of scaffolds to the development of the extracellular matrix during construct incubation, and finally, to the postimplantation assessment of tissue integration in animals and patients. PMID:23574498

Technical Note: MRI only prostate radiotherapy planning using the statistical decomposition algorithm

DOE Office of Scientific and Technical Information (OSTI.GOV)

Siversson, Carl, E-mail: carl.siversson@med.lu.se; Nordström, Fredrik; Department of Radiation Physics, Skåne University Hospital, Lund 214 28

2015-10-15

Purpose: In order to enable a magnetic resonance imaging (MRI) only workflow in radiotherapy treatment planning, methods are required for generating Hounsfield unit (HU) maps (i.e., synthetic computed tomography, sCT) for dose calculations, directly from MRI. The Statistical Decomposition Algorithm (SDA) is a method for automatically generating sCT images from a single MR image volume, based on automatic tissue classification in combination with a model trained using a multimodal template material. This study compares dose calculations between sCT generated by the SDA and conventional CT in the male pelvic region. Methods: The study comprised ten prostate cancer patients, for whommore » a 3D T2 weighted MRI and a conventional planning CT were acquired. For each patient, sCT images were generated from the acquired MRI using the SDA. In order to decouple the effect of variations in patient geometry between imaging modalities from the effect of uncertainties in the SDA, the conventional CT was nonrigidly registered to the MRI to assure that their geometries were well aligned. For each patient, a volumetric modulated arc therapy plan was created for the registered CT (rCT) and recalculated for both the sCT and the conventional CT. The results were evaluated using several methods, including mean average error (MAE), a set of dose-volume histogram parameters, and a restrictive gamma criterion (2% local dose/1 mm). Results: The MAE within the body contour was 36.5 ± 4.1 (1 s.d.) HU between sCT and rCT. Average mean absorbed dose difference to target was 0.0% ± 0.2% (1 s.d.) between sCT and rCT, whereas it was −0.3% ± 0.3% (1 s.d.) between CT and rCT. The average gamma pass rate was 99.9% for sCT vs rCT, whereas it was 90.3% for CT vs rCT. Conclusions: The SDA enables a highly accurate MRI only workflow in prostate radiotherapy planning. The dosimetric uncertainties originating from the SDA appear negligible and are notably lower than the uncertainties introduced by variations in patient geometry between imaging sessions.« less

Characterization of groups using composite kernels and multi-source fMRI analysis data: application to schizophrenia

PubMed Central

Castro, Eduardo; Martínez-Ramón, Manel; Pearlson, Godfrey; Sui, Jing; Calhoun, Vince D.

2011-01-01

Pattern classification of brain imaging data can enable the automatic detection of differences in cognitive processes of specific groups of interest. Furthermore, it can also give neuroanatomical information related to the regions of the brain that are most relevant to detect these differences by means of feature selection procedures, which are also well-suited to deal with the high dimensionality of brain imaging data. This work proposes the application of recursive feature elimination using a machine learning algorithm based on composite kernels to the classification of healthy controls and patients with schizophrenia. This framework, which evaluates nonlinear relationships between voxels, analyzes whole-brain fMRI data from an auditory task experiment that is segmented into anatomical regions and recursively eliminates the uninformative ones based on their relevance estimates, thus yielding the set of most discriminative brain areas for group classification. The collected data was processed using two analysis methods: the general linear model (GLM) and independent component analysis (ICA). GLM spatial maps as well as ICA temporal lobe and default mode component maps were then input to the classifier. A mean classification accuracy of up to 95% estimated with a leave-two-out cross-validation procedure was achieved by doing multi-source data classification. In addition, it is shown that the classification accuracy rate obtained by using multi-source data surpasses that reached by using single-source data, hence showing that this algorithm takes advantage of the complimentary nature of GLM and ICA. PMID:21723948

Noninvasive Classification of Hepatic Fibrosis Based on Texture Parameters From Double Contrast-Enhanced Magnetic Resonance Images

PubMed Central

Bahl, Gautam; Cruite, Irene; Wolfson, Tanya; Gamst, Anthony C.; Collins, Julie M.; Chavez, Alyssa D.; Barakat, Fatma; Hassanein, Tarek; Sirlin, Claude B.

2016-01-01

Purpose To demonstrate a proof of concept that quantitative texture feature analysis of double contrast-enhanced magnetic resonance imaging (MRI) can classify fibrosis noninvasively, using histology as a reference standard. Materials and Methods A Health Insurance Portability and Accountability Act (HIPAA)-compliant Institutional Review Board (IRB)-approved retrospective study of 68 patients with diffuse liver disease was performed at a tertiary liver center. All patients underwent double contrast-enhanced MRI, with histopathology-based staging of fibrosis obtained within 12 months of imaging. The MaZda software program was used to compute 279 texture parameters for each image. A statistical regularization technique, generalized linear model (GLM)-path, was used to develop a model based on texture features for dichotomous classification of fibrosis category (F ≤2 vs. F ≥3) of the 68 patients, with histology as the reference standard. The model's performance was assessed and cross-validated. There was no additional validation performed on an independent cohort. Results Cross-validated sensitivity, specificity, and total accuracy of the texture feature model in classifying fibrosis were 91.9%, 83.9%, and 88.2%, respectively. Conclusion This study shows proof of concept that accurate, noninvasive classification of liver fibrosis is possible by applying quantitative texture analysis to double contrast-enhanced MRI. Further studies are needed in independent cohorts of subjects. PMID:22851409

Measuring the volume of brain tumour and determining its location in T2-weighted MRI images using hidden Markov random field: expectation maximization algorithm

NASA Astrophysics Data System (ADS)

Mat Jafri, Mohd. Zubir; Abdulbaqi, Hayder Saad; Mutter, Kussay N.; Mustapha, Iskandar Shahrim; Omar, Ahmad Fairuz

2017-06-01

A brain tumour is an abnormal growth of tissue in the brain. Most tumour volume measurement processes are carried out manually by the radiographer and radiologist without relying on any auto program. This manual method is a timeconsuming task and may give inaccurate results. Treatment, diagnosis, signs and symptoms of the brain tumours mainly depend on the tumour volume and its location. In this paper, an approach is proposed to improve volume measurement of brain tumors as well as using a new method to determine the brain tumour location. The current study presents a hybrid method that includes two methods. One method is hidden Markov random field - expectation maximization (HMRFEM), which employs a positive initial classification of the image. The other method employs the threshold, which enables the final segmentation. In this method, the tumour volume is calculated using voxel dimension measurements. The brain tumour location was determined accurately in T2- weighted MRI image using a new algorithm. According to the results, this process was proven to be more useful compared to the manual method. Thus, it provides the possibility of calculating the volume and determining location of a brain tumour.

Distinguishing medication-free subjects with unipolar disorder from subjects with bipolar disorder: state matters.

PubMed

Rive, Maria M; Redlich, Ronny; Schmaal, Lianne; Marquand, André F; Dannlowski, Udo; Grotegerd, Dominik; Veltman, Dick J; Schene, Aart H; Ruhé, Henricus G

2016-11-01

Recent studies have indicated that pattern recognition techniques of functional magnetic resonance imaging (fMRI) data for individual classification may be valuable for distinguishing between major depressive disorder (MDD) and bipolar disorder (BD). Importantly, medication may have affected previous classification results as subjects with MDD and BD use different classes of medication. Furthermore, almost all studies have investigated only depressed subjects. Therefore, we focused on medication-free subjects. We additionally investigated whether classification would be mood state independent by including depressed and remitted subjects alike. We applied Gaussian process classifiers to investigate the discriminatory power of structural MRI (gray matter volumes of emotion regulation areas) and resting-state fMRI (resting-state networks implicated in mood disorders: default mode network [DMN], salience network [SN], and lateralized frontoparietal networks [FPNs]) in depressed (n=42) and remitted (n=49) medication-free subjects with MDD and BD. Depressed subjects with MDD and BD could be classified based on the gray matter volumes of emotion regulation areas as well as DMN functional connectivity with 69.1% prediction accuracy. Prediction accuracy using the FPNs and SN did not exceed chance level. It was not possible to discriminate between remitted subjects with MDD and BD. For the first time, we showed that medication-free subjects with MDD and BD can be differentiated based on structural MRI as well as resting-state functional connectivity. Importantly, the results indicated that research concerning diagnostic neuroimaging tools distinguishing between MDD and BD should consider mood state as only depressed subjects with MDD and BD could be correctly classified. Future studies, in larger samples are needed to investigate whether the results can be generalized to medication-naïve or first-episode subjects. © 2016 John Wiley & Sons A/S. Published by John Wiley & Sons Ltd.

Application of advanced machine learning methods on resting-state fMRI network for identification of mild cognitive impairment and Alzheimer's disease.

PubMed

Khazaee, Ali; Ebrahimzadeh, Ata; Babajani-Feremi, Abbas

2016-09-01

The study of brain networks by resting-state functional magnetic resonance imaging (rs-fMRI) is a promising method for identifying patients with dementia from healthy controls (HC). Using graph theory, different aspects of the brain network can be efficiently characterized by calculating measures of integration and segregation. In this study, we combined a graph theoretical approach with advanced machine learning methods to study the brain network in 89 patients with mild cognitive impairment (MCI), 34 patients with Alzheimer's disease (AD), and 45 age-matched HC. The rs-fMRI connectivity matrix was constructed using a brain parcellation based on a 264 putative functional areas. Using the optimal features extracted from the graph measures, we were able to accurately classify three groups (i.e., HC, MCI, and AD) with accuracy of 88.4 %. We also investigated performance of our proposed method for a binary classification of a group (e.g., MCI) from two other groups (e.g., HC and AD). The classification accuracies for identifying HC from AD and MCI, AD from HC and MCI, and MCI from HC and AD, were 87.3, 97.5, and 72.0 %, respectively. In addition, results based on the parcellation of 264 regions were compared to that of the automated anatomical labeling atlas (AAL), consisted of 90 regions. The accuracy of classification of three groups using AAL was degraded to 83.2 %. Our results show that combining the graph measures with the machine learning approach, on the basis of the rs-fMRI connectivity analysis, may assist in diagnosis of AD and MCI.

Magnetic resonance imaging of live freshwater mussels (Unionidae)

USGS Publications Warehouse

Michael, Holliman F.; Davis, Denise; Bogan, Arthur E.; Kwak, Thomas J.; Cope, W. Gregory; Levine, Jay F.

2008-01-01

We examined the soft tissues of live freshwater mussels, Eastern elliptio Elliptio complanata, via magnetic resonance imaging (MRI), acquiring data with a widely available human whole-body MRI system. Anatomical features depicted in the profile images included the foot, stomach, intestine, anterior and posterior adductor muscles, and pericardial cavity. Noteworthy observations on soft tissue morphology included a concentration of lipids at the most posterior aspect of the foot, the presence of hemolymph-filled fissures in the posterior adductor muscle, the presence of a relatively large hemolymph-filled sinus adjacent to the posterior adductor muscle (at the ventral-anterior aspect), and segmentation of the intestine (a diagnostic description not reported previously in Unionidae). Relatively little is known about the basic biology and ecological physiology of freshwater mussels. Traditional approaches for studying anatomy and tissue processes, and for measuring sub-lethal physiological stress, are destructive or invasive. Our study, the first to evaluate freshwater mussel soft tissues by MRI, clarifies the body plan of unionid mussels and demonstrates the efficacy of this technology for in vivoevaluation of the structure, function, and integrity of mussel soft tissues.

Automatic brain tissue segmentation based on graph filter.

PubMed

Kong, Youyong; Chen, Xiaopeng; Wu, Jiasong; Zhang, Pinzheng; Chen, Yang; Shu, Huazhong

2018-05-09

Accurate segmentation of brain tissues from magnetic resonance imaging (MRI) is of significant importance in clinical applications and neuroscience research. Accurate segmentation is challenging due to the tissue heterogeneity, which is caused by noise, bias filed and partial volume effects. To overcome this limitation, this paper presents a novel algorithm for brain tissue segmentation based on supervoxel and graph filter. Firstly, an effective supervoxel method is employed to generate effective supervoxels for the 3D MRI image. Secondly, the supervoxels are classified into different types of tissues based on filtering of graph signals. The performance is evaluated on the BrainWeb 18 dataset and the Internet Brain Segmentation Repository (IBSR) 18 dataset. The proposed method achieves mean dice similarity coefficient (DSC) of 0.94, 0.92 and 0.90 for the segmentation of white matter (WM), grey matter (GM) and cerebrospinal fluid (CSF) for BrainWeb 18 dataset, and mean DSC of 0.85, 0.87 and 0.57 for the segmentation of WM, GM and CSF for IBSR18 dataset. The proposed approach can well discriminate different types of brain tissues from the brain MRI image, which has high potential to be applied for clinical applications.

Clinically Practical Magnetic Resonance Protocol for Improved Specifically in Breast Cancer Diagnosis

DTIC Science & Technology

2006-06-01

MRI, MRS, DCE, Choline , Perfusion, Breast Cancer, Diagnosis, Specificity 16. SECURITY CLASSIFICATION OF: 17. LIMITATION OF ABSTRACT 18...data analysis, patient recruitment and consent, and can now perform these tasks independently. 3. Through interactions with the DOD representative (Dr...out at 4 cc/sec during perfusion MRI acquisition. The detection of an apparent choline compounds (Cho) peak (S/N > 2) at 3.23 ppm was defined as

Machine learning algorithm accurately detects fMRI signature of vulnerability to major depression.

PubMed

Sato, João R; Moll, Jorge; Green, Sophie; Deakin, John F W; Thomaz, Carlos E; Zahn, Roland

2015-08-30

Standard functional magnetic resonance imaging (fMRI) analyses cannot assess the potential of a neuroimaging signature as a biomarker to predict individual vulnerability to major depression (MD). Here, we use machine learning for the first time to address this question. Using a recently identified neural signature of guilt-selective functional disconnection, the classification algorithm was able to distinguish remitted MD from control participants with 78.3% accuracy. This demonstrates the high potential of our fMRI signature as a biomarker of MD vulnerability. Crown Copyright © 2015. Published by Elsevier Ireland Ltd. All rights reserved.

A Non-Parametric Approach for the Activation Detection of Block Design fMRI Simulated Data Using Self-Organizing Maps and Support Vector Machine.

PubMed

Bahrami, Sheyda; Shamsi, Mousa

2017-01-01

Functional magnetic resonance imaging (fMRI) is a popular method to probe the functional organization of the brain using hemodynamic responses. In this method, volume images of the entire brain are obtained with a very good spatial resolution and low temporal resolution. However, they always suffer from high dimensionality in the face of classification algorithms. In this work, we combine a support vector machine (SVM) with a self-organizing map (SOM) for having a feature-based classification by using SVM. Then, a linear kernel SVM is used for detecting the active areas. Here, we use SOM for feature extracting and labeling the datasets. SOM has two major advances: (i) it reduces dimension of data sets for having less computational complexity and (ii) it is useful for identifying brain regions with small onset differences in hemodynamic responses. Our non-parametric model is compared with parametric and non-parametric methods. We use simulated fMRI data sets and block design inputs in this paper and consider the contrast to noise ratio (CNR) value equal to 0.6 for simulated datasets. fMRI simulated dataset has contrast 1-4% in active areas. The accuracy of our proposed method is 93.63% and the error rate is 6.37%.

Real-time magnetic resonance imaging-guided radiofrequency atrial ablation and visualization of lesion formation at 3 Tesla.

PubMed

Vergara, Gaston R; Vijayakumar, Sathya; Kholmovski, Eugene G; Blauer, Joshua J E; Guttman, Mike A; Gloschat, Christopher; Payne, Gene; Vij, Kamal; Akoum, Nazem W; Daccarett, Marcos; McGann, Christopher J; Macleod, Rob S; Marrouche, Nassir F

2011-02-01

Magnetic resonance imaging (MRI) allows visualization of location and extent of radiofrequency (RF) ablation lesion, myocardial scar formation, and real-time (RT) assessment of lesion formation. In this study, we report a novel 3-Tesla RT -RI based porcine RF ablation model and visualization of lesion formation in the atrium during RF energy delivery. The purpose of this study was to develop a 3-Tesla RT MRI-based catheter ablation and lesion visualization system. RF energy was delivered to six pigs under RT MRI guidance. A novel MRI-compatible mapping and ablation catheter was used. Under RT MRI, this catheter was safely guided and positioned within either the left or right atrium. Unipolar and bipolar electrograms were recorded. The catheter tip-tissue interface was visualized with a T1-weighted gradient echo sequence. RF energy was then delivered in a power-controlled fashion. Myocardial changes and lesion formation were visualized with a T2-weighted (T2W) half Fourier acquisition with single-shot turbo spin echo (HASTE) sequence during ablation. RT visualization of lesion formation was achieved in 30% of the ablations performed. In the other cases, either the lesion was formed outside the imaged region (25%) or the lesion was not created (45%) presumably due to poor tissue-catheter tip contact. The presence of lesions was confirmed by late gadolinium enhancement MRI and macroscopic tissue examination. MRI-compatible catheters can be navigated and RF energy safely delivered under 3-Tesla RT MRI guidance. Recording electrograms during RT imaging also is feasible. RT visualization of lesion as it forms during RF energy delivery is possible and was demonstrated using T2W HASTE imaging. Copyright © 2011 Heart Rhythm Society. Published by Elsevier Inc. All rights reserved.

MRI-based biomechanical parameters for carotid artery plaque vulnerability assessment.

PubMed

Speelman, Lambert; Teng, Zhongzhao; Nederveen, Aart J; van der Lugt, Aad; Gillard, Jonathan H

2016-03-01

Carotid atherosclerotic plaques are a major cause of ischaemic stroke. The biomechanical environment to which the arterial wall and plaque is subjected to plays an important role in the initiation, progression and rupture of carotid plaques. MRI is frequently used to characterize the morphology of a carotid plaque, but new developments in MRI enable more functional assessment of carotid plaques. In this review, MRI based biomechanical parameters are evaluated on their current status, clinical applicability, and future developments. Blood flow related biomechanical parameters, including endothelial wall shear stress and oscillatory shear index, have been shown to be related to plaque formation. Deriving these parameters directly from MRI flow measurements is feasible and has great potential for future carotid plaque development prediction. Blood pressure induced stresses in a plaque may exceed the tissue strength, potentially leading to plaque rupture. Multi-contrast MRI based stress calculations in combination with tissue strength assessment based on MRI inflammation imaging may provide a plaque stress-strength balance that can be used to assess the plaque rupture risk potential. Direct plaque strain analysis based on dynamic MRI is already able to identify local plaque displacement during the cardiac cycle. However, clinical evidence linking MRI strain to plaque vulnerability is still lacking. MRI based biomechanical parameters may lead to improved assessment of carotid plaque development and rupture risk. However, better MRI systems and faster sequences are required to improve the spatial and temporal resolution, as well as increase the image contrast and signal-to-noise ratio.

Follow-up frequency and compliance in women with probably benign findings on breast magnetic resonance imaging.

PubMed

Marshall, Ariela L; Domchek, Susan M; Weinstein, Susan P

2012-04-01

Six-month short-interval follow-up is recommended for probably benign findings on breast magnetic resonance imaging (MRI). We wanted to examine patient adherence to follow-up recommendation for Breast Imaging-Reporting and Data System (BI-RADS) category 3 lesions at a tertiary care medical center. We performed a retrospective review of frequency and adherence rates to follow-up recommendation for women with an initial BI-RADS 3 breast MRI between 2005 and 2007. A total of 132 women with BI-RADS 3 breast MRI recommendations were included. Ninety-six of 132 (72.7%) women adhered to the first follow-up recommendation or elected to have tissue diagnosis; 78/132 (59.1%) had follow-up MRI and 18/132 (13.6%) had tissue diagnosis. Thirty-six of 132 (27.3%) women did not return for follow-up. Nine of nine (100%) of BRCA carriers returned for follow-up or had tissue diagnosis, compared to 87/123 (70.7%) of non-BRCA carriers. A total of 35/41 (85.4%) of patients with a prior history of breast cancer returned for follow-up or had tissue diagnosis, compared to 61/91 (67%) of patients without a history of breast cancer. Only 5/15 (33%) of patients undergoing MRI for symptom alone adhered to follow-up recommendations. Adherence to BI-RADS category 3 follow-up recommendation is often low. Women with a history of breast cancer or who were BRCA carriers were significantly more likely to adhere to follow-up recommendation than women without a history of breast cancer or women undergoing MRI for symptoms alone. Strategies to improve adherence should be developed. Copyright © 2012 AUR. Published by Elsevier Inc. All rights reserved.

Automated diagnosis of prostate cancer in multi-parametric MRI based on multimodal convolutional neural networks

NASA Astrophysics Data System (ADS)

Le, Minh Hung; Chen, Jingyu; Wang, Liang; Wang, Zhiwei; Liu, Wenyu; (Tim Cheng, Kwang-Ting; Yang, Xin

2017-08-01

Automated methods for prostate cancer (PCa) diagnosis in multi-parametric magnetic resonance imaging (MP-MRIs) are critical for alleviating requirements for interpretation of radiographs while helping to improve diagnostic accuracy (Artan et al 2010 IEEE Trans. Image Process. 19 2444-55, Litjens et al 2014 IEEE Trans. Med. Imaging 33 1083-92, Liu et al 2013 SPIE Medical Imaging (International Society for Optics and Photonics) p 86701G, Moradi et al 2012 J. Magn. Reson. Imaging 35 1403-13, Niaf et al 2014 IEEE Trans. Image Process. 23 979-91, Niaf et al 2012 Phys. Med. Biol. 57 3833, Peng et al 2013a SPIE Medical Imaging (International Society for Optics and Photonics) p 86701H, Peng et al 2013b Radiology 267 787-96, Wang et al 2014 BioMed. Res. Int. 2014). This paper presents an automated method based on multimodal convolutional neural networks (CNNs) for two PCa diagnostic tasks: (1) distinguishing between cancerous and noncancerous tissues and (2) distinguishing between clinically significant (CS) and indolent PCa. Specifically, our multimodal CNNs effectively fuse apparent diffusion coefficients (ADCs) and T2-weighted MP-MRI images (T2WIs). To effectively fuse ADCs and T2WIs we design a new similarity loss function to enforce consistent features being extracted from both ADCs and T2WIs. The similarity loss is combined with the conventional classification loss functions and integrated into the back-propagation procedure of CNN training. The similarity loss enables better fusion results than existing methods as the feature learning processes of both modalities are mutually guided, jointly facilitating CNN to ‘see’ the true visual patterns of PCa. The classification results of multimodal CNNs are further combined with the results based on handcrafted features using a support vector machine classifier. To achieve a satisfactory accuracy for clinical use, we comprehensively investigate three critical factors which could greatly affect the performance of our multimodal CNNs but have not been carefully studied previously. (1) Given limited training data, how can these be augmented in sufficient numbers and variety for fine-tuning deep CNN networks for PCa diagnosis? (2) How can multimodal MP-MRI information be effectively combined in CNNs? (3) What is the impact of different CNN architectures on the accuracy of PCa diagnosis? Experimental results on extensive clinical data from 364 patients with a total of 463 PCa lesions and 450 identified noncancerous image patches demonstrate that our system can achieve a sensitivity of 89.85% and a specificity of 95.83% for distinguishing cancer from noncancerous tissues and a sensitivity of 100% and a specificity of 76.92% for distinguishing indolent PCa from CS PCa. This result is significantly superior to the state-of-the-art method relying on handcrafted features.

Quantification of human body fat tissue percentage by MRI.

PubMed

Müller, Hans-Peter; Raudies, Florian; Unrath, Alexander; Neumann, Heiko; Ludolph, Albert C; Kassubek, Jan

2011-01-01

The MRI-based evaluation of the quantity and regional distribution of adipose tissue is one objective measure in the investigation of obesity. The aim of this article was to report a comprehensive and automatic analytical method for the determination of the volumes of subcutaneous fat tissue (SFT) and visceral fat tissue (VFT) in either the whole human body or selected slices or regions of interest. Using an MRI protocol in an examination position that was convenient for volunteers and patients with severe diseases, 22 healthy subjects were examined. The software platform was able to merge MRI scans of several body regions acquired in separate acquisitions. Through a cascade of image processing steps, SFT and VFT volumes were calculated. Whole-body SFT and VFT distributions, as well as fat distributions of defined body slices, were analysed in detail. Complete three-dimensional datasets were analysed in a reproducible manner with as few operator-dependent interventions as possible. In order to determine the SFT volume, the ARTIS (Adapted Rendering for Tissue Intensity Segmentation) algorithm was introduced. The advantage of the ARTIS algorithm was the delineation of SFT volumes in regions in which standard region grow techniques fail. Using the ARTIS algorithm, an automatic SFT volume detection was feasible. MRI data analysis was able to determine SFT and VFT volume percentages using new analytical strategies. With the techniques described, it was possible to detect changes in SFT and VFT percentages of the whole body and selected regions. The techniques presented in this study are likely to be of use in obesity-related investigations, as well as in the examination of longitudinal changes in weight during various medical conditions. Copyright © 2010 John Wiley & Sons, Ltd.

Preliminary experience using dynamic MRI at 3.0 Tesla for evaluation of soft tissue tumors.

PubMed

Park, Michael Yong; Jee, Won-Hee; Kim, Sun Ki; Lee, So-Yeon; Jung, Joon-Yong

2013-01-01

We aimed to evaluate the use of dynamic contrast enhanced magnetic resonance imaging (DCE-MRI) at 3.0 T for differentiating the benign from malignant soft tissue tumors. Also we aimed to assess whether the shorter length of DCE-MRI protocols are adequate, and to evaluate the effect of temporal resolution. Dynamic contrast-enhanced magnetic resonance imaging, at 3.0 T with a 1 second temporal resolution in 13 patients with pathologically confirmed soft tissue tumors, was analyzed. Visual assessment of time-signal curves, subtraction images, maximal relative enhancement at the first (maximal peak enhancement [Emax]/1) and second (Emax/2) minutes, Emax, steepest slope calculated by using various time intervals (5, 30, 60 seconds), and the start of dynamic enhancement were analyzed. The 13 tumors were comprised of seven benign and six malignant soft tissue neoplasms. Washout on time-signal curves was seen on three (50%) malignant tumors and one (14%) benign one. The most discriminating DCE-MRI parameter was the steepest slope calculated, by using at 5-second intervals, followed by Emax/1 and Emax/2. All of the steepest slope values occurred within 2 minutes of the dynamic study. Start of dynamic enhancement did not show a significant difference, but no malignant tumor rendered a value greater than 14 seconds. The steepest slope and early relative enhancement have the potential for differentiating benign from malignant soft tissue tumors. Short-length rather than long-length DCE-MRI protocol may be adequate for our purpose. The steepest slope parameters require a short temporal resolution, while maximal peak enhancement parameter may be more optimal for a longer temporal resolution.

Direct estimation of 17 O MR images (DIESIS) for quantification of oxygen metabolism in the human brain with partial volume correction.

PubMed

Kurzhunov, Dmitry; Borowiak, Robert; Reisert, Marco; Özen, Ali Caglar; Bock, Michael

2018-05-16

To provide a data post-processing method that corrects for partial volume effects (PVE) and fast T2* decay in dynamic 17 O MRI for the mapping of cerebral metabolic rates of oxygen consumption (CMRO 2 ). CMRO 2 is altered in neurodegenerative diseases and tumors and can be measured after 17 O gas inhalation using dynamic 17 O MRI. CMRO 2 quantification is difficult because of PVE. To correct for PVE, a direct estimation of the MR images (DIESIS) method is proposed and used in 4 dynamic 17 O MRI data sets of a healthy volunteer acquired on a 3T MRI system. With DIESIS, 17 O MR signal time curves in selected regions were directly estimated based on parcellation of a coregistered 1 H MPRAGE image. Profile likelihood analysis of the DIESIS method showed identifiability of CMRO 2 . In white matter (WM), DIESES reduced CMRO 2 from 0.97 ± 0.25 µmol/g tissue /min with Kaiser-Bessel gridding reconstruction to 0.85 ± 0.21 µmol/g tissue /min, whereas in gray matter (GM) it increases from 1.3 ± 0.31 µmol/g tissue /min to 1.86 ± 0.36 µmol/g tissue /min; both values are closer to the literature values from the 15 O-PET studies. DIESIS provided an increased separation of CMRO 2 values in GM and WM brain regions and corrected for partial volume effects in 17 O-MRI inhalation experiments. DIESIS could also be applied to more heterogeneous tissues such as glioblastomas if subregions of the tumor can be represented as additional parcels. © 2018 International Society for Magnetic Resonance in Medicine.

Use of trimetasphere metallofullerene MRI contrast agent for the non-invasive longitudinal tracking of stem cells in the lung

PubMed Central

Murphy, Sean V.; Hale, Austin; Reid, Tanya; Olson, John; Kidiyoor, Amritha; Tan, Josh; Zhou, Zhiguo; Jackson, John; Atala, Anthony

2016-01-01

Magnetic Resonance Imaging (MRI) is a commonly used, non-invasive imaging technique that provides visualization of soft tissues with high spatial resolution. In both a research and clinical setting, the major challenge has been identifying a non-invasive and safe method for longitudinal tracking of delivered cells in vivo. The labeling and tracking of contrast agent labeled cells using MRI has the potential to fulfill this need. Contrast agents are often used to enhance the image contrast between the tissue of interest and surrounding tissues with MRI. The most commonly used MRI contrast agents contain Gd(III) ions. However, Gd(III) ions are highly toxic in their ionic form, as they tend to accumulate in the liver, spleen, kidney and bones and block calcium channels. Endohedral metallofullerenes such as trimetallic nitride endohedral metallofullerenes (Trimetasphere®) are one unique class of fullerene molecules where a Gd3N cluster is encapsulated inside a C80 carbon cage referred to as Gd3N@C80. These endohedral metallofullerenes have several advantages over small chelated Gd(III) complexes such as increased stability of the Gd(III) ion, minimal toxic effects, high solubility in water and high proton relativity. In this study, we describe the evaluation of gadolinium-based Trimetasphere® positive contrast agent for the in vitro labeling and in vivo tracking of human amniotic fluid-derived stem cells within lung tissue. In addition, we conducted a ‘proof-of-concept’ experiment demonstrating that this methodology can be used to track the homing of stem cells to injured lung tissue and provide longitudinal analysis of cell localization over an extended time course. PMID:26546729

Use of trimetasphere metallofullerene MRI contrast agent for the non-invasive longitudinal tracking of stem cells in the lung.

PubMed

Murphy, Sean V; Hale, Austin; Reid, Tanya; Olson, John; Kidiyoor, Amritha; Tan, Josh; Zhou, Zhiguo; Jackson, John; Atala, Anthony

2016-04-15

Magnetic Resonance Imaging (MRI) is a commonly used, non-invasive imaging technique that provides visualization of soft tissues with high spatial resolution. In both a research and clinical setting, the major challenge has been identifying a non-invasive and safe method for longitudinal tracking of delivered cells in vivo. The labeling and tracking of contrast agent labeled cells using MRI has the potential to fulfill this need. Contrast agents are often used to enhance the image contrast between the tissue of interest and surrounding tissues with MRI. The most commonly used MRI contrast agents contain Gd(III) ions. However, Gd(III) ions are highly toxic in their ionic form, as they tend to accumulate in the liver, spleen, kidney and bones and block calcium channels. Endohedral metallofullerenes such as trimetallic nitride endohedral metallofullerenes (Trimetasphere®) are one unique class of fullerene molecules where a Gd3N cluster is encapsulated inside a C80 carbon cage referred to as Gd3N@C80. These endohedral metallofullerenes have several advantages over small chelated Gd(III) complexes such as increased stability of the Gd(III) ion, minimal toxic effects, high solubility in water and high proton relativity. In this study, we describe the evaluation of gadolinium-based Trimetasphere® positive contrast agent for the ​in vitro labeling and in vivo tracking of human amniotic fluid-derived stem cells within lung tissue. In addition, we conducted a 'proof-of-concept' experiment demonstrating that this methodology can be used to track the homing of stem cells to injured lung tissue and provide longitudinal analysis of cell localization over an extended time course. Copyright © 2015 Elsevier Inc. All rights reserved.

Optimized magnetic resonance diffusion protocol for ex-vivo whole human brain imaging with a clinical scanner

NASA Astrophysics Data System (ADS)

Scherrer, Benoit; Afacan, Onur; Stamm, Aymeric; Singh, Jolene; Warfield, Simon K.

2015-03-01

Diffusion-weighted magnetic resonance imaging (DW-MRI) provides a novel insight into the brain to facilitate our understanding of the brain connectivity and microstructure. While in-vivo DW-MRI enables imaging of living patients and longitudinal studies of brain changes, post-mortem ex-vivo DW-MRI has numerous advantages. Ex-vivo imaging benefits from greater resolution and sensitivity due to the lack of imaging time constraints; the use of tighter fitting coils; and the lack of movement artifacts. This allows characterization of normal and abnormal tissues with unprecedented resolution and sensitivity, facilitating our ability to investigate anatomical structures that are inaccessible in-vivo. This also offers the opportunity to develop today novel imaging biomarkers that will, with tomorrow's MR technology, enable improved in-vivo assessment of the risk of disease in an individual. Post-mortem studies, however, generally rely on the fixation of specimen to inhibit tissue decay which starts as soon as tissue is deprived from its blood supply. Unfortunately, fixation of tissues substantially alters tissue diffusivity profiles. In addition, ex-vivo DW-MRI requires particular care when packaging the specimen because the presence of microscopic air bubbles gives rise to geometric and intensity image distortion. In this work, we considered the specific requirements of post-mortem imaging and designed an optimized protocol for ex-vivo whole brain DW-MRI using a human clinical 3T scanner. Human clinical 3T scanners are available to a large number of researchers and, unlike most animal scanners, have a bore diameter large enough to image a whole human brain. Our optimized protocol will facilitate widespread ex-vivo investigations of large specimen.

Unsupervised nonlinear dimensionality reduction machine learning methods applied to multiparametric MRI in cerebral ischemia: preliminary results

NASA Astrophysics Data System (ADS)

Parekh, Vishwa S.; Jacobs, Jeremy R.; Jacobs, Michael A.

2014-03-01

The evaluation and treatment of acute cerebral ischemia requires a technique that can determine the total area of tissue at risk for infarction using diagnostic magnetic resonance imaging (MRI) sequences. Typical MRI data sets consist of T1- and T2-weighted imaging (T1WI, T2WI) along with advanced MRI parameters of diffusion-weighted imaging (DWI) and perfusion weighted imaging (PWI) methods. Each of these parameters has distinct radiological-pathological meaning. For example, DWI interrogates the movement of water in the tissue and PWI gives an estimate of the blood flow, both are critical measures during the evolution of stroke. In order to integrate these data and give an estimate of the tissue at risk or damaged; we have developed advanced machine learning methods based on unsupervised non-linear dimensionality reduction (NLDR) techniques. NLDR methods are a class of algorithms that uses mathematically defined manifolds for statistical sampling of multidimensional classes to generate a discrimination rule of guaranteed statistical accuracy and they can generate a two- or three-dimensional map, which represents the prominent structures of the data and provides an embedded image of meaningful low-dimensional structures hidden in their high-dimensional observations. In this manuscript, we develop NLDR methods on high dimensional MRI data sets of preclinical animals and clinical patients with stroke. On analyzing the performance of these methods, we observed that there was a high of similarity between multiparametric embedded images from NLDR methods and the ADC map and perfusion map. It was also observed that embedded scattergram of abnormal (infarcted or at risk) tissue can be visualized and provides a mechanism for automatic methods to delineate potential stroke volumes and early tissue at risk.

Prediction of activation patterns preceding hallucinations in patients with schizophrenia using machine learning with structured sparsity.

PubMed

de Pierrefeu, Amicie; Fovet, Thomas; Hadj-Selem, Fouad; Löfstedt, Tommy; Ciuciu, Philippe; Lefebvre, Stephanie; Thomas, Pierre; Lopes, Renaud; Jardri, Renaud; Duchesnay, Edouard

2018-04-01

Despite significant progress in the field, the detection of fMRI signal changes during hallucinatory events remains difficult and time-consuming. This article first proposes a machine-learning algorithm to automatically identify resting-state fMRI periods that precede hallucinations versus periods that do not. When applied to whole-brain fMRI data, state-of-the-art classification methods, such as support vector machines (SVM), yield dense solutions that are difficult to interpret. We proposed to extend the existing sparse classification methods by taking the spatial structure of brain images into account with structured sparsity using the total variation penalty. Based on this approach, we obtained reliable classifying performances associated with interpretable predictive patterns, composed of two clearly identifiable clusters in speech-related brain regions. The variation in transition-to-hallucination functional patterns not only from one patient to another but also from one occurrence to the next (e.g., also depending on the sensory modalities involved) appeared to be the major difficulty when developing effective classifiers. Consequently, second, this article aimed to characterize the variability within the prehallucination patterns using an extension of principal component analysis with spatial constraints. The principal components (PCs) and the associated basis patterns shed light on the intrinsic structures of the variability present in the dataset. Such results are promising in the scope of innovative fMRI-guided therapy for drug-resistant hallucinations, such as fMRI-based neurofeedback. © 2018 Wiley Periodicals, Inc.

Magnetic Resonance Imaging Findings Predict the Recurrence of Chronic Subdural Hematoma

PubMed Central

GOTO, Haruo; ISHIKAWA, Osamu; NOMURA, Masashi; TANAKA, Kentaro; NOMURA, Seiji; MAEDA, Keiichiro

2015-01-01

The exact predictive factors for postoperative recurrence of chronic subdural hematoma (CSDH) are still unknown. Based on the preoperative magnetic resonance imaging (MRI), low recurrence rate of T1-hyperintensity hematoma was previously reported. We investigated the other types of radiological findings which are related to the recurrence rate of CSDH in large number of patients analyzed by multivariate logistic regression model. Preoperative MRI and postoperative computed tomography (CT) were performed and the influence of the preoperative use of antiplatelet or anticoagulant drugs was also studied. The overall recurrence rate was 9.3% (47 of 505 hematomas). The MRI T1-iso/hypointensity group showed a significantly higher recurrence rate (18.2%, 29 of 159) compared to the other groups (5.2%, 18 of 346; p < 0.001). Multivariate logistic regression analysis showed T1 classification was the solo significant prognostic predictor among various factors such as bilateral hematoma, antiplatelet or anticoagulant drug usage, residual hematoma on postoperative CT, and MRI classification (p < 0.001): adjusted odds ratio for the recurrence in T1-iso/hypointensity group relative to the T1-hyperintensity group was 5.58 [95% confidence interval (CI), 2.09–14.86] (p = 0.001). Postoperative residual hematoma and antiplatelet or anticoagulant drug usage did not increase the recurrence risk. The preoperative MRI findings, especially T1WI findings, have predictive value for postoperative recurrence of CSDH and the T1-iso/hypointensity group can be assumed to be a high recurrence risk group. PMID:25746312

Textural kinetics: a novel dynamic contrast-enhanced (DCE)-MRI feature for breast lesion classification.

PubMed

Agner, Shannon C; Soman, Salil; Libfeld, Edward; McDonald, Margie; Thomas, Kathleen; Englander, Sarah; Rosen, Mark A; Chin, Deanna; Nosher, John; Madabhushi, Anant

2011-06-01

Dynamic contrast-enhanced (DCE)-magnetic resonance imaging (MRI) of the breast has emerged as an adjunct imaging tool to conventional X-ray mammography due to its high detection sensitivity. Despite the increasing use of breast DCE-MRI, specificity in distinguishing malignant from benign breast lesions is low, and interobserver variability in lesion classification is high. The novel contribution of this paper is in the definition of a new DCE-MRI descriptor that we call textural kinetics, which attempts to capture spatiotemporal changes in breast lesion texture in order to distinguish malignant from benign lesions. We qualitatively and quantitatively demonstrated on 41 breast DCE-MRI studies that textural kinetic features outperform signal intensity kinetics and lesion morphology features in distinguishing benign from malignant lesions. A probabilistic boosting tree (PBT) classifier in conjunction with textural kinetic descriptors yielded an accuracy of 90%, sensitivity of 95%, specificity of 82%, and an area under the curve (AUC) of 0.92. Graph embedding, used for qualitative visualization of a low-dimensional representation of the data, showed the best separation between benign and malignant lesions when using textural kinetic features. The PBT classifier results and trends were also corroborated via a support vector machine classifier which showed that textural kinetic features outperformed the morphological, static texture, and signal intensity kinetics descriptors. When textural kinetic attributes were combined with morphologic descriptors, the resulting PBT classifier yielded 89% accuracy, 99% sensitivity, 76% specificity, and an AUC of 0.91.

An Automated and Intelligent Medical Decision Support System for Brain MRI Scans Classification.

PubMed

Siddiqui, Muhammad Faisal; Reza, Ahmed Wasif; Kanesan, Jeevan

2015-01-01

A wide interest has been observed in the medical health care applications that interpret neuroimaging scans by machine learning systems. This research proposes an intelligent, automatic, accurate, and robust classification technique to classify the human brain magnetic resonance image (MRI) as normal or abnormal, to cater down the human error during identifying the diseases in brain MRIs. In this study, fast discrete wavelet transform (DWT), principal component analysis (PCA), and least squares support vector machine (LS-SVM) are used as basic components. Firstly, fast DWT is employed to extract the salient features of brain MRI, followed by PCA, which reduces the dimensions of the features. These reduced feature vectors also shrink the memory storage consumption by 99.5%. At last, an advanced classification technique based on LS-SVM is applied to brain MR image classification using reduced features. For improving the efficiency, LS-SVM is used with non-linear radial basis function (RBF) kernel. The proposed algorithm intelligently determines the optimized values of the hyper-parameters of the RBF kernel and also applied k-fold stratified cross validation to enhance the generalization of the system. The method was tested by 340 patients' benchmark datasets of T1-weighted and T2-weighted scans. From the analysis of experimental results and performance comparisons, it is observed that the proposed medical decision support system outperformed all other modern classifiers and achieves 100% accuracy rate (specificity/sensitivity 100%/100%). Furthermore, in terms of computation time, the proposed technique is significantly faster than the recent well-known methods, and it improves the efficiency by 71%, 3%, and 4% on feature extraction stage, feature reduction stage, and classification stage, respectively. These results indicate that the proposed well-trained machine learning system has the potential to make accurate predictions about brain abnormalities from the individual subjects, therefore, it can be used as a significant tool in clinical practice.

Decoding Multiple Sound Categories in the Human Temporal Cortex Using High Resolution fMRI

PubMed Central

Zhang, Fengqing; Wang, Ji-Ping; Kim, Jieun; Parrish, Todd; Wong, Patrick C. M.

2015-01-01

Perception of sound categories is an important aspect of auditory perception. The extent to which the brain’s representation of sound categories is encoded in specialized subregions or distributed across the auditory cortex remains unclear. Recent studies using multivariate pattern analysis (MVPA) of brain activations have provided important insights into how the brain decodes perceptual information. In the large existing literature on brain decoding using MVPA methods, relatively few studies have been conducted on multi-class categorization in the auditory domain. Here, we investigated the representation and processing of auditory categories within the human temporal cortex using high resolution fMRI and MVPA methods. More importantly, we considered decoding multiple sound categories simultaneously through multi-class support vector machine-recursive feature elimination (MSVM-RFE) as our MVPA tool. Results show that for all classifications the model MSVM-RFE was able to learn the functional relation between the multiple sound categories and the corresponding evoked spatial patterns and classify the unlabeled sound-evoked patterns significantly above chance. This indicates the feasibility of decoding multiple sound categories not only within but across subjects. However, the across-subject variation affects classification performance more than the within-subject variation, as the across-subject analysis has significantly lower classification accuracies. Sound category-selective brain maps were identified based on multi-class classification and revealed distributed patterns of brain activity in the superior temporal gyrus and the middle temporal gyrus. This is in accordance with previous studies, indicating that information in the spatially distributed patterns may reflect a more abstract perceptual level of representation of sound categories. Further, we show that the across-subject classification performance can be significantly improved by averaging the fMRI images over items, because the irrelevant variations between different items of the same sound category are reduced and in turn the proportion of signals relevant to sound categorization increases. PMID:25692885

Decoding multiple sound categories in the human temporal cortex using high resolution fMRI.

PubMed

Zhang, Fengqing; Wang, Ji-Ping; Kim, Jieun; Parrish, Todd; Wong, Patrick C M

2015-01-01

Perception of sound categories is an important aspect of auditory perception. The extent to which the brain's representation of sound categories is encoded in specialized subregions or distributed across the auditory cortex remains unclear. Recent studies using multivariate pattern analysis (MVPA) of brain activations have provided important insights into how the brain decodes perceptual information. In the large existing literature on brain decoding using MVPA methods, relatively few studies have been conducted on multi-class categorization in the auditory domain. Here, we investigated the representation and processing of auditory categories within the human temporal cortex using high resolution fMRI and MVPA methods. More importantly, we considered decoding multiple sound categories simultaneously through multi-class support vector machine-recursive feature elimination (MSVM-RFE) as our MVPA tool. Results show that for all classifications the model MSVM-RFE was able to learn the functional relation between the multiple sound categories and the corresponding evoked spatial patterns and classify the unlabeled sound-evoked patterns significantly above chance. This indicates the feasibility of decoding multiple sound categories not only within but across subjects. However, the across-subject variation affects classification performance more than the within-subject variation, as the across-subject analysis has significantly lower classification accuracies. Sound category-selective brain maps were identified based on multi-class classification and revealed distributed patterns of brain activity in the superior temporal gyrus and the middle temporal gyrus. This is in accordance with previous studies, indicating that information in the spatially distributed patterns may reflect a more abstract perceptual level of representation of sound categories. Further, we show that the across-subject classification performance can be significantly improved by averaging the fMRI images over items, because the irrelevant variations between different items of the same sound category are reduced and in turn the proportion of signals relevant to sound categorization increases.

Variability of non-Gaussian diffusion MRI and intravoxel incoherent motion (IVIM) measurements in the breast.

PubMed

Iima, Mami; Kataoka, Masako; Kanao, Shotaro; Kawai, Makiko; Onishi, Natsuko; Koyasu, Sho; Murata, Katsutoshi; Ohashi, Akane; Sakaguchi, Rena; Togashi, Kaori

2018-01-01

We prospectively examined the variability of non-Gaussian diffusion magnetic resonance imaging (MRI) and intravoxel incoherent motion (IVIM) measurements with different numbers of b-values and excitations in normal breast tissue and breast lesions. Thirteen volunteers and fourteen patients with breast lesions (seven malignant, eight benign; one patient had bilateral lesions) were recruited in this prospective study (approved by the Internal Review Board). Diffusion-weighted MRI was performed with 16 b-values (0-2500 s/mm2 with one number of excitations [NEX]) and five b-values (0-2500 s/mm2, 3 NEX), using a 3T breast MRI. Intravoxel incoherent motion (flowing blood volume fraction [fIVIM] and pseudodiffusion coefficient [D*]) and non-Gaussian diffusion (theoretical apparent diffusion coefficient [ADC] at b value of 0 sec/mm2 [ADC0] and kurtosis [K]) parameters were estimated from IVIM and Kurtosis models using 16 b-values, and synthetic apparent diffusion coefficient (sADC) values were obtained from two key b-values. The variabilities between and within subjects and between different diffusion acquisition methods were estimated. There were no statistical differences in ADC0, K, or sADC values between the different b-values or NEX. A good agreement of diffusion parameters was observed between 16 b-values (one NEX), five b-values (one NEX), and five b-values (three NEX) in normal breast tissue or breast lesions. Insufficient agreement was observed for IVIM parameters. There were no statistical differences in the non-Gaussian diffusion MRI estimated values obtained from a different number of b-values or excitations in normal breast tissue or breast lesions. These data suggest that a limited MRI protocol using a few b-values might be relevant in a clinical setting for the estimation of non-Gaussian diffusion MRI parameters in normal breast tissue and breast lesions.

Variability of non-Gaussian diffusion MRI and intravoxel incoherent motion (IVIM) measurements in the breast

PubMed Central

Kataoka, Masako; Kanao, Shotaro; Kawai, Makiko; Onishi, Natsuko; Koyasu, Sho; Murata, Katsutoshi; Ohashi, Akane; Sakaguchi, Rena; Togashi, Kaori

2018-01-01

We prospectively examined the variability of non-Gaussian diffusion magnetic resonance imaging (MRI) and intravoxel incoherent motion (IVIM) measurements with different numbers of b-values and excitations in normal breast tissue and breast lesions. Thirteen volunteers and fourteen patients with breast lesions (seven malignant, eight benign; one patient had bilateral lesions) were recruited in this prospective study (approved by the Internal Review Board). Diffusion-weighted MRI was performed with 16 b-values (0–2500 s/mm2 with one number of excitations [NEX]) and five b-values (0–2500 s/mm2, 3 NEX), using a 3T breast MRI. Intravoxel incoherent motion (flowing blood volume fraction [fIVIM] and pseudodiffusion coefficient [D*]) and non-Gaussian diffusion (theoretical apparent diffusion coefficient [ADC] at b value of 0 sec/mm2 [ADC0] and kurtosis [K]) parameters were estimated from IVIM and Kurtosis models using 16 b-values, and synthetic apparent diffusion coefficient (sADC) values were obtained from two key b-values. The variabilities between and within subjects and between different diffusion acquisition methods were estimated. There were no statistical differences in ADC0, K, or sADC values between the different b-values or NEX. A good agreement of diffusion parameters was observed between 16 b-values (one NEX), five b-values (one NEX), and five b-values (three NEX) in normal breast tissue or breast lesions. Insufficient agreement was observed for IVIM parameters. There were no statistical differences in the non-Gaussian diffusion MRI estimated values obtained from a different number of b-values or excitations in normal breast tissue or breast lesions. These data suggest that a limited MRI protocol using a few b-values might be relevant in a clinical setting for the estimation of non-Gaussian diffusion MRI parameters in normal breast tissue and breast lesions. PMID:29494639

DOE Office of Scientific and Technical Information (OSTI.GOV)

Swanson, K; Corwin, D; Rockne, R

Purpose: To demonstrate a method of generating patient-specific, biologically-guided radiation therapy (RT) plans and to quantify and predict response to RT in glioblastoma. We investigate the biological correlates and imaging physics driving T2-MRI based response to radiation therapy using an MRI simulator. Methods: We have integrated a patient-specific biomathematical model of glioblastoma proliferation, invasion and radiotherapy with a multiobjective evolutionary algorithm for intensity-modulated RT optimization to construct individualized, biologically-guided plans. Patient-individualized simulations of the standard-of-care and optimized plans are compared in terms of several biological metrics quantified on MRI. An extension of the PI model is used to investigate themore » role of angiogenesis and its correlates in glioma response to therapy with the Proliferation-Invasion-Hypoxia- Necrosis-Angiogenesis model (PIHNA). The PIHNA model is used with a brain tissue phantom to predict tumor-induced vasogenic edema, tumor and tissue density that is used in a multi-compartmental MRI signal equation for generation of simulated T2- weighted MRIs. Results: Applying a novel metric of treatment response (Days Gained) to the patient-individualized simulation results predicted that the optimized RT plans would have a significant impact on delaying tumor progression, with Days Gained increases from 21% to 105%. For the T2- MRI simulations, initial validation tests compared average simulated T2 values for white matter, tumor, and peripheral edema to values cited in the literature. Simulated results closely match the characteristic T2 value for each tissue. Conclusion: Patient-individualized simulations using the combination of a biomathematical model with an optimization algorithm for RT generated biologically-guided doses that decreased normal tissue dose and increased therapeutic ratio with the potential to improve survival outcomes for treatment of glioblastoma. Simulated T2-MRI is shown to be consistent with known physics of MRI and can be used to further investigate biological drivers of imaging-based response to RT.« less

GLISTRboost: Combining Multimodal MRI Segmentation, Registration, and Biophysical Tumor Growth Modeling with Gradient Boosting Machines for Glioma Segmentation.

PubMed

Bakas, Spyridon; Zeng, Ke; Sotiras, Aristeidis; Rathore, Saima; Akbari, Hamed; Gaonkar, Bilwaj; Rozycki, Martin; Pati, Sarthak; Davatzikos, Christos

2016-01-01

We present an approach for segmenting low- and high-grade gliomas in multimodal magnetic resonance imaging volumes. The proposed approach is based on a hybrid generative-discriminative model. Firstly, a generative approach based on an Expectation-Maximization framework that incorporates a glioma growth model is used to segment the brain scans into tumor, as well as healthy tissue labels. Secondly, a gradient boosting multi-class classification scheme is used to refine tumor labels based on information from multiple patients. Lastly, a probabilistic Bayesian strategy is employed to further refine and finalize the tumor segmentation based on patient-specific intensity statistics from the multiple modalities. We evaluated our approach in 186 cases during the training phase of the BRAin Tumor Segmentation (BRATS) 2015 challenge and report promising results. During the testing phase, the algorithm was additionally evaluated in 53 unseen cases, achieving the best performance among the competing methods.

Magnetic Resonance Imaging of Chondrocytes Labeled with Superparamagnetic Iron Oxide Nanoparticles in Tissue-Engineered Cartilage

PubMed Central

Ramaswamy, Sharan; Greco, Jane B.; Uluer, Mehmet C.; Zhang, Zijun; Zhang, Zhuoli; Fishbein, Kenneth W.

2009-01-01

The distribution of cells within tissue-engineered constructs is difficult to study through nondestructive means, such as would be required after implantation. However, cell labeling with iron-containing particles may prove to be a useful approach to this problem, because regions containing such labeled cells have been shown to be readily detectable using magnetic resonance imaging (MRI). In this study, we used the Food and Drug Administration–approved superparamagnetic iron oxide (SPIO) contrast agent Feridex in combination with transfection agents to label chondrocytes and visualize them with MRI in two different tissue-engineered cartilage constructs. Correspondence between labeled cell spatial location as determined using MRI and histology was established. The SPIO-labeling process was found not to affect the phenotype or viability of the chondrocytes or the production of major cartilage matrix constituents. We believe that this method of visualizing and tracking chondrocytes may be useful in the further development of tissue engineered cartilage therapeutics. PMID:19788362

Abbreviated MRI Protocols: Wave of the Future for Breast Cancer Screening.

PubMed

Chhor, Chloe M; Mercado, Cecilia L

2017-02-01

The purpose of this article is to describe the use of abbreviated breast MRI protocols for improving access to screening for women at intermediate risk. Breast MRI is not a cost-effective modality for screening women at intermediate risk, including those with dense breast tissue as the only risk. Abbreviated breast MRI protocols have been proposed as a way of achieving efficiency and rapid throughput. Use of these abbreviated protocols may increase availability and provide women with greater access to breast MRI.

Boosting Classification Accuracy of Diffusion MRI Derived Brain Networks for the Subtypes of Mild Cognitive Impairment Using Higher Order Singular Value Decomposition

PubMed Central

Zhan, L.; Liu, Y.; Zhou, J.; Ye, J.; Thompson, P.M.

2015-01-01

Mild cognitive impairment (MCI) is an intermediate stage between normal aging and Alzheimer's disease (AD), and around 10-15% of people with MCI develop AD each year. More recently, MCI has been further subdivided into early and late stages, and there is interest in identifying sensitive brain imaging biomarkers that help to differentiate stages of MCI. Here, we focused on anatomical brain networks computed from diffusion MRI and proposed a new feature extraction and classification framework based on higher order singular value decomposition and sparse logistic regression. In tests on publicly available data from the Alzheimer's Disease Neuroimaging Initiative, our proposed framework showed promise in detecting brain network differences that help in classifying early versus late MCI. PMID:26413202

Monitoring of tissue ablation using time series of ultrasound RF data.

PubMed

Imani, Farhad; Wu, Mark Z; Lasso, Andras; Burdette, Everett C; Daoud, Mohammad; Fitchinger, Gabor; Abolmaesumi, Purang; Mousavi, Parvin

2011-01-01

This paper is the first report on the monitoring of tissue ablation using ultrasound RF echo time series. We calcuate frequency and time domain features of time series of RF echoes from stationary tissue and transducer, and correlate them with ablated and non-ablated tissue properties. We combine these features in a nonlinear classification framework and demonstrate up to 99% classification accuracy in distinguishing ablated and non-ablated regions of tissue, in areas as small as 12mm2 in size. We also demonstrate significant improvement of ablated tissue classification using RF time series compared to the conventional approach of using single RF scan lines. The results of this study suggest RF echo time series as a promising approach for monitoring ablation, and capturing the changes in the tissue microstructure as a result of heat-induced necrosis.

Passive Ventricular Mechanics Modelling Using MRI of Structure and Function

PubMed Central

Wang, V.Y.; Lam, H.I.; Ennis, D.B.; Young, A.A.; Nash, M.P.

2009-01-01

Patients suffering from dilated cardiomyopathy or myocardial infarction can develop left ventricular (LV) diastolic impairment. The LV remodels its structure and function to adapt to pathophysiological changes in geometry and loading conditions and this remodeling process can alter the passive ventricular mechanics. In order to better understand passive ventricular mechanics, a LV finite element model was developed to incorporate physiological and mechanical information derived from in vivo magnetic resonance imaging (MRI) tissue tagging, in vivo LV cavity pressure recording and ex vivo diffusion tensor MRI (DTMRI) of a canine heart. MRI tissue tagging enables quantitative evaluation of cardiac mechanical function with high spatial and temporal resolution, whilst the direction of maximum water diffusion (the primary eigenvector) in each voxel of a DTMRI directly correlates with the myocardial fibre orientation. This model was customized to the geometry of the canine LV during diastasis by fitting the segmented epicardial and endocardial surface data from tagged MRI using nonlinear finite element fitting techniques. Myofibre orientations, extracted from DTMRI of the same heart, were incorporated into this geometric model using a free form deformation methodology. Pressure recordings, temporally synchronized to the tissue tagging MRI data, were used to simulate the LV deformation during diastole. Simulation of the diastolic LV mechanics allowed us to estimate the stiffness of the passive LV myocardium based on kinematic data obtained from tagged MRI. This integrated physiological model will allow more insight into the regional passive diastolic mechanics of the LV on an individualized basis, thereby improving our understanding of the underlying structural basis of mechanical dysfunction in pathological conditions. PMID:18982680

Evaluation of Visceral Adipose Tissue Oxygenation by Blood Oxygen Level-Dependent MRI in Zucker Diabetic Fatty Rats.

PubMed

Shi, Hong-Jian; Li, Yan-Feng; Ji, Wen-Jie; Lin, Zhi-Chun; Cai, Wei; Chen, Tao; Yuan, Bin; Niu, Xiu-Long; Li, Han-Ying; Shu, Wen; Li, Yu-Ming; Yuan, Fei; Zhou, Xin; Zhang, Zhuoli

2018-06-01

This study aimed to investigate the feasibility of blood oxygen level-dependent magnetic resonance imaging (BOLD-MRI) to evaluate visceral adipose tissue (VAT) oxygenation in Zucker diabetic fatty (ZDF) rats and its associations with systemic metaflammation. Five-week-old ZDF rats and Zucker lean (ZL) rats were fed a high-fat diet (HFD) for 18 weeks. A baseline BOLD-MRI scan of perirenal adipose tissue was performed after 8 weeks of HFD feeding, and then the rats were randomized to receive pioglitazone or a vehicle for the following 10 weeks. At sacrifice, BOLD-MRI scan, Hypoxyprobe-1 injection, and circulating T helper 17 (Th17), regulatory T (Treg) cells, and monocyte subtype flow cytometry analysis were performed. HFD feeding led to a significant increase in VAT BOLD-MRI R2* signals (20.14 ± 0.23 per second vs. 21.53 ± 0.20 per second; P = 0.012), an indicator for decreased oxygenation. R2* signal was significantly correlated with VAT pimonidazole adduct-positive area, insulin resistance, Th17 and Treg cells, CD43 + and CD43+ + monocyte subtypes, and VAT macrophage infiltration. Pioglitazone treatment improved the insulin resistance and was associated with a delayed progression of VAT oxygenation. This work demonstrated the feasibility of BOLD-MRI for detecting the VAT oxygenation status in ZDF rats, and the BOLD-MRI signals were associated with insulin resistance and systemic metaflammation in ZDF rats during the development of obesity. © 2018 The Obesity Society.

Passive ventricular mechanics modelling using MRI of structure and function.

PubMed

Wang, V Y; Lam, H I; Ennis, D B; Young, A A; Nash, M P

2008-01-01

Patients suffering from dilated cardiomyopathy or myocardial infarction can develop left ventricular (LV) diastolic impairment. The LV remodels its structure and function to adapt to pathophysiological changes in geometry and loading conditions and this remodeling process can alter the passive ventricular mechanics. In order to better understand passive ventricular mechanics, a LV finite element model was developed to incorporate physiological and mechanical information derived from in vivo magnetic resonance imaging (MRI) tissue tagging, in vivo LV cavity pressure recording and ex vivo diffusion tensor MRI (DTMRI) of a canine heart. MRI tissue tagging enables quantitative evaluation of cardiac mechanical function with high spatial and temporal resolution, whilst the direction of maximum water diffusion (the primary eigenvector) in each voxel of a DTMRI directly correlates with the myocardial fibre orientation. This model was customized to the geometry of the canine LV during diastasis by fitting the segmented epicardial and endocardial surface data from tagged MRI using nonlinear finite element fitting techniques. Myofibre orientations, extracted from DTMRI of the same heart, were incorporated into this geometric model using a free form deformation methodology. Pressure recordings, temporally synchronized to the tissue tagging MRI data, were used to simulate the LV deformation during diastole. Simulation of the diastolic LV mechanics allowed us to estimate the stiffness of the passive LV myocardium based on kinematic data obtained from tagged MRI. This integrated physiological model will allow more insight into the regional passive diastolic mechanics of the LV on an individualized basis, thereby improving our understanding of the underlying structural basis of mechanical dysfunction in pathological conditions.

Suggestions for Lymph Node Classification of UICC/AJCC Staging System: A Retrospective Study Based on 1197 Nasopharyngeal Carcinoma Patients Treated With Intensity-Modulated Radiation Therapy

PubMed Central

Guo, Qiaojuan; Pan, Jianji; Zong, Jingfeng; Zheng, Wei; Zhang, Chun; Tang, Linbo; Chen, Bijuan; Cui, Xiaofei; Xiao, Youping; Chen, Yunbin; Lin, Shaojun

2015-01-01

Abstract This article provides suggestions for N classification of Union for International Cancer Control/American Joint Committee on Cancer (UICC/AJCC) staging system of nasopharyngeal carcinoma (NPC), purely based on magnetic resonance imaging (MRI) in intensity-modulated radiation therapy (IMRT) era. A total of 1197 nonmetastatic NPC patients treated with IMRT were enrolled, and all were scanned by MRI at nasopharynx and neck before treatment. MRI-based nodal variables including level, laterality, maximal axial diameter (MAD), extracapsular spread (ECS), and necrosis were analyzed as potential prognostic factors. Modifications of N classification were then proposed and verified. Only nodal level and laterality were considered to be significant variables affecting the treatment outcome. N classification was thus proposed accordingly: N0, no regional lymph node (LN) metastasis; N1, retropharyngeal LNs involvement (regardless of laterality), and/or unilateral levels I, II, III, and/or Va involvement; N2, bilateral levels I, II, III, and/or Va involvement; and N3, levels IV, Vb, and Vc involvement. This proposal showed significant predicting value in multivariate analysis. N3 patients indicated relatively inferior overall survival (OS) and distant metastasis-free survival (DMFS) than N2 patients; however, the difference showed no statistical significance (P = 0.673 and 0.265 for OS and DMFS, respectively), and this was considered to be correlated with the small sample sizes of N3 patients (79 patients, 6.6%). Nodal level and laterality, but not MAD, ECS, and necrosis, were considered to be significant predicting factors for NPC. The proposed N classification was proved to be powerfully predictive in our cohort; however, treatment outcome of the proposed N2 and N3 patients could not differ significantly from each other. This insignificance may be because of the small sample sizes of N3 patients. Our results are based on a single-center data, to develop a new N classification that is universally acceptable; further verification by data from multicenter is warranted. PMID:25997052

Diffusion MRI and its role in neuropsychology

PubMed Central

Mueller, Bryon A; Lim, Kelvin O; Hemmy, Laura; Camchong, Jazmin

2015-01-01

Diffusion Magnetic Resonance Imaging (dMRI) is a popular method used by neuroscientists to uncover unique information about the structural connections within the brain. dMRI is a non-invasive imaging methodology in which image contrast is based on the diffusion of water molecules in tissue. While applicable to many tissues in the body, this review focuses exclusively on the use of dMRI to examine white matter in the brain. In this review, we begin with a definition of diffusion and how diffusion is measured with MRI. Next we introduce the diffusion tensor model, the predominant model used in dMRI. We then describe acquisition issues related to acquisition parameters and scanner hardware and software. Sources of artifacts are then discussed, followed by a brief review of analysis approaches. We provide an overview of the limitations of the traditional diffusion tensor model, and highlight several more sophisticated non-tensor models that better describe the complex architecture of the brain’s white matter. We then touch on reliability and validity issues of diffusion measurements. Finally, we describe examples of ways in which dMRI has been applied to studies of brain disorders and how identified alterations relate to symptomatology and cognition. PMID:26255305

Efficacy of magnetic resonance imaging in diagnosing diabetic foot osteomyelitis in the presence of ischemia.

PubMed

Fujii, Miki; Armstrong, David G; Armsrong, David G; Terashi, Hiroto

2013-01-01

Magnetic resonance imaging (MRI) has been recognized as the most accurate imaging modality for the detection of diabetic foot osteomyelitis. However, how accurately MRI displays the extent of diabetic foot osteomyelitis in the presence of ischemia is still unclear. We retrospectively compared the preoperative MRI findings with the results of histopathologic examinations of resected bones and studied the efficacy of MRI in the diagnosis of diabetic foot osteomyelitis of different etiologies. A total 104 bones from 18 foot ulcers in 16 diabetic patients (10 men and 6 women; age range 42 to 84 years) treated by surgical intervention from 2008 to 2012 was examined. In 8 neuropathic ulcers, 29 bones were accurately diagnosed in detail using MRI, even those with severe soft tissue infection. Of 75 bones in 10 ischemic ulcers, only 7 bones evaluated by MRI after revascularization were diagnosed accurately; the other 68 could not be diagnosed because of unclear or equivocal MRI findings. On histopathologic examination, all the bones were found to be infected through the bone cortex by the surrounding infected soft tissue, not directly by articulation. Overall, preoperative MRI is effective in the diagnosis of neuropathic ulcers, but less so of ischemic ones. Copyright © 2013 American College of Foot and Ankle Surgeons. Published by Elsevier Inc. All rights reserved.

Identifying metastatic breast tumors using textural kinetic features of a contrast based habitat in DCE-MRI

NASA Astrophysics Data System (ADS)

Chaudhury, Baishali; Zhou, Mu; Goldgof, Dmitry B.; Hall, Lawrence O.; Gatenby, Robert A.; Gillies, Robert J.; Drukteinis, Jennifer S.

2015-03-01

The ability to identify aggressive tumors from indolent tumors using quantitative analysis on dynamic contrast enhanced magnetic resonance imaging (DCE-MRI) would dramatically change the breast cancer treatment paradigm. With this prognostic information, patients with aggressive tumors that have the ability to spread to distant sites outside of the breast could be selected for more aggressive treatment and surveillance regimens. Conversely, patients with tumors that do not have the propensity to metastasize could be treated less aggressively, avoiding some of the morbidity associated with surgery, radiation and chemotherapy. We propose a computer aided detection framework to determine which breast cancers will metastasize to the loco-regional lymph nodes as well as which tumors will eventually go on to develop distant metastses using quantitative image analysis and radiomics. We defined a new contrast based tumor habitat and analyzed textural kinetic features from this habitat for classification purposes. The proposed tumor habitat, which we call combined-habitat, is derived from the intersection of two individual tumor sub-regions: one that exhibits rapid initial contrast uptake and the other that exhibits rapid delayed contrast washout. Hence the combined-habitat represents the tumor sub-region within which the pixels undergo both rapid initial uptake and rapid delayed washout. We analyzed a dataset of twenty-seven representative two dimensional (2D) images from volumetric DCE-MRI of breast tumors, for classification of tumors with no lymph nodes from tumors with positive number of axillary lymph nodes. For this classification an accuracy of 88.9% was achieved. Twenty of the twenty-seven patients were analyzed for classification of distant metastatic tumors from indolent cancers (tumors with no lymph nodes), for which the accuracy was 84.3%.

Application of machine learning classification for structural brain MRI in mood disorders: Critical review from a clinical perspective.

PubMed

Kim, Yong-Ku; Na, Kyoung-Sae

2018-01-03

Mood disorders are a highly prevalent group of mental disorders causing substantial socioeconomic burden. There are various methodological approaches for identifying the underlying mechanisms of the etiology, symptomatology, and therapeutics of mood disorders; however, neuroimaging studies have provided the most direct evidence for mood disorder neural substrates by visualizing the brains of living individuals. The prefrontal cortex, hippocampus, amygdala, thalamus, ventral striatum, and corpus callosum are associated with depression and bipolar disorder. Identifying the distinct and common contributions of these anatomical regions to depression and bipolar disorder have broadened and deepened our understanding of mood disorders. However, the extent to which neuroimaging research findings contribute to clinical practice in the real-world setting is unclear. As traditional or non-machine learning MRI studies have analyzed group-level differences, it is not possible to directly translate findings from research to clinical practice; the knowledge gained pertains to the disorder, but not to individuals. On the other hand, a machine learning approach makes it possible to provide individual-level classifications. For the past two decades, many studies have reported on the classification accuracy of machine learning-based neuroimaging studies from the perspective of diagnosis and treatment response. However, for the application of a machine learning-based brain MRI approach in real world clinical settings, several major issues should be considered. Secondary changes due to illness duration and medication, clinical subtypes and heterogeneity, comorbidities, and cost-effectiveness restrict the generalization of the current machine learning findings. Sophisticated classification of clinical and diagnostic subtypes is needed. Additionally, as the approach is inevitably limited by sample size, multi-site participation and data-sharing are needed in the future. Copyright © 2017 Elsevier Inc. All rights reserved.

Development of a brain MRI-based hidden Markov model for dementia recognition.

PubMed

Chen, Ying; Pham, Tuan D

2013-01-01

Dementia is an age-related cognitive decline which is indicated by an early degeneration of cortical and sub-cortical structures. Characterizing those morphological changes can help to understand the disease development and contribute to disease early prediction and prevention. But modeling that can best capture brain structural variability and can be valid in both disease classification and interpretation is extremely challenging. The current study aimed to establish a computational approach for modeling the magnetic resonance imaging (MRI)-based structural complexity of the brain using the framework of hidden Markov models (HMMs) for dementia recognition. Regularity dimension and semi-variogram were used to extract structural features of the brains, and vector quantization method was applied to convert extracted feature vectors to prototype vectors. The output VQ indices were then utilized to estimate parameters for HMMs. To validate its accuracy and robustness, experiments were carried out on individuals who were characterized as non-demented and mild Alzheimer's diseased. Four HMMs were constructed based on the cohort of non-demented young, middle-aged, elder and demented elder subjects separately. Classification was carried out using a data set including both non-demented and demented individuals with a wide age range. The proposed HMMs have succeeded in recognition of individual who has mild Alzheimer's disease and achieved a better classification accuracy compared to other related works using different classifiers. Results have shown the ability of the proposed modeling for recognition of early dementia. The findings from this research will allow individual classification to support the early diagnosis and prediction of dementia. By using the brain MRI-based HMMs developed in our proposed research, it will be more efficient, robust and can be easily used by clinicians as a computer-aid tool for validating imaging bio-markers for early prediction of dementia.

Dynamic Contrast-enhanced Magnetic Resonance Imaging for Differentiating Between Primary Tumor, Metastatic Node and Normal Tissue in Head and Neck Cancer.

PubMed

Chen, Liangliang; Ye, Yufeng; Chen, Hanwei; Chen, Shihui; Jiang, Jinzhao; Dan, Guo; Huang, Bingsheng

2018-06-01

To study the difference of the Dynamic Contrast-Enhanced Magnetic Resonance Imaging (DCE-MRI) parameters among the primary tumor, metastatic node and peripheral normal tissue of head and neck cancer. Consecutive newly-diagnosed head and neck cancer patients with nodal metastasis between December 2010 and July 2013 were recruited, and 25 patients (8 females; 24~63,mean 43±11 years old) were enrolled. DCE-MRI was performed in the primary tumor region including the regional lymph nodes on a 3.0-T MRI system. Three quantitative parameters: Ktrans (volume transfer constant), ve (volume fraction of extravascular extracellular space) and kep (the rate constant of contrast transfer) were calculated for the largest node. A repeated-measure ANOVA with a Greenhouse-Geisser correction and post hoc tests using the Bonferroni correction were used to evaluate the differences in Ktrans, ve and kep among primary tumors, metastatic nodes and normal tissue. The values of both Ktrans and ve of normal tissue differed significantly from those of nodes (both P < 0.001) and primary tumors (both P < 0.001) respectively, while no significant differences of Ktrans and ve were observed between nodes and primary tumors (P = 0.075 and 0.365 respectively). The kep values of primary tumors were significantly different from those of nodes (P = 0.001) and normal tissue (P = 0.002), while no significant differences between nodes and normal tissue (P > 0.999). The DCE-MRI parameters were different in the tumors, metastatic nodes and normal tissue in head and neck cancer. These findings may be useful in the characterization of head and neck cancer.

Polarimetry based partial least square classification of ex vivo healthy and basal cell carcinoma human skin tissues.

PubMed

Ahmad, Iftikhar; Ahmad, Manzoor; Khan, Karim; Ikram, Masroor

2016-06-01

Optical polarimetry was employed for assessment of ex vivo healthy and basal cell carcinoma (BCC) tissue samples from human skin. Polarimetric analyses revealed that depolarization and retardance for healthy tissue group were significantly higher (p<0.001) compared to BCC tissue group. Histopathology indicated that these differences partially arise from BCC-related characteristic changes in tissue morphology. Wilks lambda statistics demonstrated the potential of all investigated polarimetric properties for computer assisted classification of the two tissue groups. Based on differences in polarimetric properties, partial least square (PLS) regression classified the samples with 100% accuracy, sensitivity and specificity. These findings indicate that optical polarimetry together with PLS statistics hold promise for automated pathology classification. Copyright © 2016 Elsevier B.V. All rights reserved.

Phase 0 Trial of Itraconazole for Early-Stage Non-Small Cell Lung Cancer

DTIC Science & Technology

2016-10-01

tissue and blood sampling in addition to magnetic resonance imaging ( MRI ) scans for biomarker analysis. At the time of surgery, resected tissue will...original proposal, these subjects underwent study-related MRI scans, skin biopsies, blood tests, treatment with itraconazole, and surgical resection...not complete serial MRIs scans. Task 2: Determine anti-angiogenic effects of itraconazole Subtask 2a: Blood-based PD studies As described in the

Quantification of carotid atherosclerotic plaque components using feature space analysis and magnetic resonance imaging.

PubMed

Karmonik, Christof; Basto, Pamela; Morrisett, Joel D

2006-01-01

Atherosclerosis is one of the main causes of cardiovascular disease, accounting for more than one third of all deaths in the United States, there is a growing need to develop non-invasive techniques to assess the severity of atherosclerotic plaque burden. Recent research has suggested that not the size of the atherosclerotic plaque but rather its composition is indicative for plaque rupture as the underlying event of stroke and acute coronary syndrome. With its excellent soft-tissue contrast, magnetic resonance imaging (MRI) is a favored modality for examining plaque composition. In an ex-vivo study, aimed to show the feasibility of quantifying the components of carotid atherosclerotic plaques in-vivo, we acquired multi-contrast MRI images of 13 freshly excised endarterectomy tissues with commercially available MRI sequences and a human surface coil. Feature space analysis (FSA) was utilized in four representative tissues to determine the total relative abundance of calcific, lipidic, fibrotic, thrombotic and normal components as well as in consecutive 2 mm sections across the carotid bifurcation in each tissue. Excellent qualitative agreement between the FSA results and the results obtained from histological methods was observed. This study demonstrates the feasibility of combining MRI with FSA to quantify carotid atherosclerotic plaques in-vivo.

New concept on an integrated interior magnetic resonance imaging and medical linear accelerator system for radiation therapy.

PubMed

Jia, Xun; Tian, Zhen; Xi, Yan; Jiang, Steve B; Wang, Ge

2017-01-01

Image guidance plays a critical role in radiotherapy. Currently, cone-beam computed tomography (CBCT) is routinely used in clinics for this purpose. While this modality can provide an attenuation image for therapeutic planning, low soft-tissue contrast affects the delineation of anatomical and pathological features. Efforts have recently been devoted to several MRI linear accelerator (LINAC) projects that lead to the successful combination of a full diagnostic MRI scanner with a radiotherapy machine. We present a new concept for the development of the MRI-LINAC system. Instead of combining a full MRI scanner with the LINAC platform, we propose using an interior MRI (iMRI) approach to image a specific region of interest (RoI) containing the radiation treatment target. While the conventional CBCT component still delivers a global image of the patient's anatomy, the iMRI offers local imaging of high soft-tissue contrast for tumor delineation. We describe a top-level system design for the integration of an iMRI component into an existing LINAC platform. We performed numerical analyses of the magnetic field for the iMRI to show potentially acceptable field properties in a spherical RoI with a diameter of 15 cm. This field could be shielded to a sufficiently low level around the LINAC region to avoid electromagnetic interference. Furthermore, we investigate the dosimetric impacts of this integration on the radiotherapy beam.

An Integrated MRI and MRS Approach to Evaluation of Multiple Sclerosis with Cognitive Impairment

NASA Astrophysics Data System (ADS)

Liang, Zhengrong; Li, Lihong; Lu, Hongbing; Huang, Wei; Tudorica, Alina; Krupp, Lauren

Magnetic resonance imaging and spectroscopy (MRI/MRS) plays a unique role in multiple sclerosis (MS) evaluation, because of its ability to provide both high image contrast and significant chemical change among brain tissues. The image contrast renders the possibility of quantifying the tissue volumetric and texture variations, e.g., cerebral atrophy and progressing speed, reflecting the ongoing destructive pathologic processes. Any chemical change reflects an early sign of pathological alteration, e.g., decreased N-acetyl aspartate (NAA) in lesions and normal appearing white matter, related to axonal damage or dysfunction. Both MRI and MRS encounter partial volume (PV) effect, which compromises the quantitative capability, especially for MRS. This work aims to develop a statistical framework to segment the tissue mixtures inside each image element, eliminating theoretically the PV effect, and apply the framework to the evaluation of MS with cognitive impairment. The quantitative measures from MRI/MRS neuroimaging are strongly correlated with the qualitative neuropsychological scores of Brief Repeatable Battery (BRB) test on cognitive impairment, demonstrating the usefulness of the PV image segmentation framework in this clinically significant problem.

Measurement of liver iron overload: noninvasive calibration of MRI-R2* by magnetic iron detector susceptometer.

PubMed

Gianesin, B; Zefiro, D; Musso, M; Rosa, A; Bruzzone, C; Balocco, M; Carrara, P; Bacigalupo, L; Banderali, S; Rollandi, G A; Gambaro, M; Marinelli, M; Forni, G L

2012-06-01

An accurate assessment of body iron accumulation is essential for the diagnosis and therapy of iron overload in diseases such as thalassemia or hemochromatosis. Magnetic iron detector susceptometry and MRI are noninvasive techniques capable of detecting iron overload in the liver. Although the transverse relaxation rate measured by MRI can be correlated with the presence of iron, a calibration step is needed to obtain the liver iron concentration. Magnetic iron detector provides an evaluation of the iron overload in the whole liver. In this article, we describe a retrospective observational study comparing magnetic iron detector and MRI examinations performed on the same group of 97 patients with transfusional or congenital iron overload. A biopsy-free linear calibration to convert the average transverse relaxation rate in iron overload (R(2) = 0.72), or in liver iron concentration evaluated in wet tissue (R(2) = 0.68), is presented. This article also compares liver iron concentrations calculated in dry tissue using MRI and the existing biopsy calibration with liver iron concentrations evaluated in wet tissue by magnetic iron detector to obtain an estimate of the wet-to-dry conversion factor of 6.7 ± 0.8 (95% confidence level). Copyright © 2011 Wiley-Liss, Inc.

Cartilage Repair Surgery: Outcome Evaluation by Using Noninvasive Cartilage Biomarkers Based on Quantitative MRI Techniques?

PubMed Central

Jungmann, Pia M.; Baum, Thomas; Bauer, Jan S.; Karampinos, Dimitrios C.; Link, Thomas M.; Li, Xiaojuan; Trattnig, Siegfried; Rummeny, Ernst J.; Woertler, Klaus; Welsch, Goetz H.

2014-01-01

Background. New quantitative magnetic resonance imaging (MRI) techniques are increasingly applied as outcome measures after cartilage repair. Objective. To review the current literature on the use of quantitative MRI biomarkers for evaluation of cartilage repair at the knee and ankle. Methods. Using PubMed literature research, studies on biochemical, quantitative MR imaging of cartilage repair were identified and reviewed. Results. Quantitative MR biomarkers detect early degeneration of articular cartilage, mainly represented by an increasing water content, collagen disruption, and proteoglycan loss. Recently, feasibility of biochemical MR imaging of cartilage repair tissue and surrounding cartilage was demonstrated. Ultrastructural properties of the tissue after different repair procedures resulted in differences in imaging characteristics. T2 mapping, T1rho mapping, delayed gadolinium-enhanced MRI of cartilage (dGEMRIC), and diffusion weighted imaging (DWI) are applicable on most clinical 1.5 T and 3 T MR scanners. Currently, a standard of reference is difficult to define and knowledge is limited concerning correlation of clinical and MR findings. The lack of histological correlations complicates the identification of the exact tissue composition. Conclusions. A multimodal approach combining several quantitative MRI techniques in addition to morphological and clinical evaluation might be promising. Further investigations are required to demonstrate the potential for outcome evaluation after cartilage repair. PMID:24877139

Non-rigid registration for fusion of carotid vascular ultrasound and MRI volumetric datasets

NASA Astrophysics Data System (ADS)

Chan, R. C.; Sokka, S.; Hinton, D.; Houser, S.; Manzke, R.; Hanekamp, A.; Reddy, V. Y.; Kaazempur-Mofrad, M. R.; Rasche, V.

2006-03-01

In carotid plaque imaging, MRI provides exquisite soft-tissue characterization, but lacks the temporal resolution for tissue strain imaging that real-time 3D ultrasound (3DUS) can provide. On the other hand, real-time 3DUS currently lacks the spatial resolution of carotid MRI. Non-rigid alignment of ultrasound and MRI data is essential for integrating complementary morphology and biomechanical information for carotid vascular assessment. We assessed non-rigid registration for fusion of 3DUS and MRI carotid data based on deformable models which are warped to maximize voxel similarity. We performed validation in vitro using isolated carotid artery imaging. These samples were subjected to soft-tissue deformations during 3DUS and were imaged in a static configuration with standard MR carotid pulse sequences. Registration of the source ultrasound sequences to the target MR volume was performed and the mean absolute distance between fiducials within the ultrasound and MR datasets was measured to determine inter-modality alignment quality. Our results indicate that registration errors on the order of 1mm are possible in vitro despite the low-resolution of current generation 3DUS transducers. Registration performance should be further improved with the use of higher frequency 3DUS prototypes and efforts are underway to test those probes for in vivo 3DUS carotid imaging.

Diagnostic accuracy for macroscopic classification of nodular hepatocellular carcinoma: comparison of gadolinium ethoxybenzyl diethylenetriamine pentaacetic acid-enhanced magnetic resonance imaging and angiography-assisted computed tomography.

PubMed

Tada, Toshifumi; Kumada, Takashi; Toyoda, Hidenori; Ito, Takanori; Sone, Yasuhiro; Okuda, Seiji; Ogawa, Sadanobu; Igura, Takumi; Imai, Yasuharu

2015-01-01

The macroscopic type of hepatocellular carcinoma (HCC) is a predictor of prognosis. We clarified the diagnostic value of gadolinium ethoxybenzyl diethylenetriamine pentaacetic acid (Gd-EOB-DTPA)-enhanced magnetic resonance imaging (MRI) in the macroscopic classification of nodular hepatocellular carcinoma (HCC) as compared to angiography-assisted computed tomography (CT). A total of 71 surgically resected nodular HCCs with a maximum diameter of ≤5 cm were investigated. HCCs were evaluated preoperatively using Gd-EOB-DTPA-enhanced MRI and angiography-assisted CT. HCCs were pathologically classified as simple nodular (SN), SN with extranodular growth (SN-EG), or confluent multinodular (CMN). SN-EG and CMN were grouped as non-SN. Five readers independently reviewed the images using a five-point scale. We examined the accuracy of both imaging modalities in differentiating between SN and non-SN HCC. Overall, the area under the receiver operating characteristic curve (A z ) for the diagnosis of non-SN did not differ between Gd-EOB-DTPA-enhanced MRI and angiography-assisted CT [0.879 (95% confidence interval (CI), 0.779-0.937) and 0.845 (95% CI, 0.723-0.919), respectively]. For HCCs >2 cm, the A z for Gd-EOB-DTPA-enhanced MRI was greater than 0.9. The sensitivity, specificity, and accuracy of Gd-EOB-DTPA-enhanced MRI for identifying non-SN were equal to or higher than values with angiography-assisted CT in all three categories (all tumors, ≤2 cm, and >2 cm), but the differences were not statistically significant. Using Gd-EOB-DTPA-enhanced MRI to assess the macroscopic findings in nodular HCC was equal or superior to using angiography-assisted CT.

Patient identification using a near-infrared laser scanner

NASA Astrophysics Data System (ADS)

Manit, Jirapong; Bremer, Christina; Schweikard, Achim; Ernst, Floris

2017-03-01

We propose a new biometric approach where the tissue thickness of a person's forehead is used as a biometric feature. Given that the spatial registration of two 3D laser scans of the same human face usually produces a low error value, the principle of point cloud registration and its error metric can be applied to human classification techniques. However, by only considering the spatial error, it is not possible to reliably verify a person's identity. We propose to use a novel near-infrared laser-based head tracking system to determine an additional feature, the tissue thickness, and include this in the error metric. Using MRI as a ground truth, data from the foreheads of 30 subjects was collected from which a 4D reference point cloud was created for each subject. The measurements from the near-infrared system were registered with all reference point clouds using the ICP algorithm. Afterwards, the spatial and tissue thickness errors were extracted, forming a 2D feature space. For all subjects, the lowest feature distance resulted from the registration of a measurement and the reference point cloud of the same person. The combined registration error features yielded two clusters in the feature space, one from the same subject and another from the other subjects. When only the tissue thickness error was considered, these clusters were less distinct but still present. These findings could help to raise safety standards for head and neck cancer patients and lays the foundation for a future human identification technique.

Quantitative Volumetric K-Means Cluster Segmentation of Fibroglandular Tissue and Skin in Breast MRI.

PubMed

Niukkanen, Anton; Arponen, Otso; Nykänen, Aki; Masarwah, Amro; Sutela, Anna; Liimatainen, Timo; Vanninen, Ritva; Sudah, Mazen

2017-10-18

Mammographic breast density (MBD) is the most commonly used method to assess the volume of fibroglandular tissue (FGT). However, MRI could provide a clinically feasible and more accurate alternative. There were three aims in this study: (1) to evaluate a clinically feasible method to quantify FGT with MRI, (2) to assess the inter-rater agreement of MRI-based volumetric measurements and (3) to compare them to measurements acquired using digital mammography and 3D tomosynthesis. This retrospective study examined 72 women (mean age 52.4 ± 12.3 years) with 105 disease-free breasts undergoing diagnostic 3.0-T breast MRI and either digital mammography or tomosynthesis. Two observers analyzed MRI images for breast and FGT volumes and FGT-% from T1-weighted images (0.7-, 2.0-, and 4.0-mm-thick slices) using K-means clustering, data from histogram, and active contour algorithms. Reference values were obtained with Quantra software. Inter-rater agreement for MRI measurements made with 2-mm-thick slices was excellent: for FGT-%, r = 0.994 (95% CI 0.990-0.997); for breast volume, r = 0.985 (95% CI 0.934-0.994); and for FGT volume, r = 0.979 (95% CI 0.958-0.989). MRI-based FGT-% correlated strongly with MBD in mammography (r = 0.819-0.904, P < 0.001) and moderately to high with MBD in tomosynthesis (r = 0.630-0.738, P < 0.001). K-means clustering-based assessments of the proportion of the fibroglandular tissue in the breast at MRI are highly reproducible. In the future, quantitative assessment of FGT-% to complement visual estimation of FGT should be performed on a more regular basis as it provides a component which can be incorporated into the individual's breast cancer risk stratification.

Multi-class biological tissue classification based on a multi-classifier: Preliminary study of an automatic output power control for ultrasonic surgical units.

PubMed

Youn, Su Hyun; Sim, Taeyong; Choi, Ahnryul; Song, Jinsung; Shin, Ki Young; Lee, Il Kwon; Heo, Hyun Mu; Lee, Daeweon; Mun, Joung Hwan

2015-06-01

Ultrasonic surgical units (USUs) have the advantage of minimizing tissue damage during surgeries that require tissue dissection by reducing problems such as coagulation and unwanted carbonization, but the disadvantage of requiring manual adjustment of power output according to the target tissue. In order to overcome this limitation, it is necessary to determine the properties of in vivo tissues automatically. We propose a multi-classifier that can accurately classify tissues based on the unique impedance of each tissue. For this purpose, a multi-classifier was built based on single classifiers with high classification rates, and the classification accuracy of the proposed model was compared with that of single classifiers for various electrode types (Type-I: 6 mm invasive; Type-II: 3 mm invasive; Type-III: surface). The sensitivity and positive predictive value (PPV) of the multi-classifier by cross checks were determined. According to the 10-fold cross validation results, the classification accuracy of the proposed model was significantly higher (p<0.05 or <0.01) than that of existing single classifiers for all electrode types. In particular, the classification accuracy of the proposed model was highest when the 3mm invasive electrode (Type-II) was used (sensitivity=97.33-100.00%; PPV=96.71-100.00%). The results of this study are an important contribution to achieving automatic optimal output power adjustment of USUs according to the properties of individual tissues. Copyright © 2015 Elsevier Ltd. All rights reserved.

Evaluation of Multimodal Imaging Biomarkers of Prostate Cancer

DTIC Science & Technology

2015-09-01

and PET images. Figure 2 highlights the dynamic uptake of TSPO as compared to muscle. Across 60 minutes the %ID/cc continues to increase which is...p53 double null mutant mouse model. Towards that end, we have successfully acquired anatomic MRI and PET data in orthotopic tumors within the Pten...castration resistant prostate cancer, MRI, PET , FDHT, image optimization 16. SECURITY CLASSIFICATION OF: 17. LIMITATION OF ABSTRACT 18. NUMBER OF PAGES

Characterizing and differentiating task-based and resting state fMRI signals via two-stage sparse representations.

PubMed

Zhang, Shu; Li, Xiang; Lv, Jinglei; Jiang, Xi; Guo, Lei; Liu, Tianming

2016-03-01

A relatively underexplored question in fMRI is whether there are intrinsic differences in terms of signal composition patterns that can effectively characterize and differentiate task-based or resting state fMRI (tfMRI or rsfMRI) signals. In this paper, we propose a novel two-stage sparse representation framework to examine the fundamental difference between tfMRI and rsfMRI signals. Specifically, in the first stage, the whole-brain tfMRI or rsfMRI signals of each subject were composed into a big data matrix, which was then factorized into a subject-specific dictionary matrix and a weight coefficient matrix for sparse representation. In the second stage, all of the dictionary matrices from both tfMRI/rsfMRI data across multiple subjects were composed into another big data-matrix, which was further sparsely represented by a cross-subjects common dictionary and a weight matrix. This framework has been applied on the recently publicly released Human Connectome Project (HCP) fMRI data and experimental results revealed that there are distinctive and descriptive atoms in the cross-subjects common dictionary that can effectively characterize and differentiate tfMRI and rsfMRI signals, achieving 100% classification accuracy. Moreover, our methods and results can be meaningfully interpreted, e.g., the well-known default mode network (DMN) activities can be recovered from the very noisy and heterogeneous aggregated big-data of tfMRI and rsfMRI signals across all subjects in HCP Q1 release.

Automated Tissue Classification Framework for Reproducible Chronic Wound Assessment

PubMed Central

Mukherjee, Rashmi; Manohar, Dhiraj Dhane; Das, Dev Kumar; Achar, Arun; Mitra, Analava; Chakraborty, Chandan

2014-01-01

The aim of this paper was to develop a computer assisted tissue classification (granulation, necrotic, and slough) scheme for chronic wound (CW) evaluation using medical image processing and statistical machine learning techniques. The red-green-blue (RGB) wound images grabbed by normal digital camera were first transformed into HSI (hue, saturation, and intensity) color space and subsequently the “S” component of HSI color channels was selected as it provided higher contrast. Wound areas from 6 different types of CW were segmented from whole images using fuzzy divergence based thresholding by minimizing edge ambiguity. A set of color and textural features describing granulation, necrotic, and slough tissues in the segmented wound area were extracted using various mathematical techniques. Finally, statistical learning algorithms, namely, Bayesian classification and support vector machine (SVM), were trained and tested for wound tissue classification in different CW images. The performance of the wound area segmentation protocol was further validated by ground truth images labeled by clinical experts. It was observed that SVM with 3rd order polynomial kernel provided the highest accuracies, that is, 86.94%, 90.47%, and 75.53%, for classifying granulation, slough, and necrotic tissues, respectively. The proposed automated tissue classification technique achieved the highest overall accuracy, that is, 87.61%, with highest kappa statistic value (0.793). PMID:25114925

[Classification and MR imaging of triangular fibrocartilage complex lesions].

PubMed

Zhan, H L; Liu, Y; Bai, R J; Qian, Z H; Ye, W; Li, Y X; Wu, B D

2016-06-07

To explore the MRI characteristics of injuries of triangular fibrocartilage complex (TFCC), and provide imaging basis for the early diagnosis and treatment of the injuries. A total of 10 healthy volunteers without wrist injuries and 200 patients from Beijing Jishuitan Hospital who complained ulnar-sided wrist pain and were highly suspected as the injury of TFCC underwent the wrist magnetic resonance examination. All subjects were in a prone position and underwent examination on coronal T1WI scan and PD-FS on 3 planes respectively. Then the MRI characteristics of 3 healthy volunteers and 67 patients with TFCC injuries that confirmed by operation were analyzed. According to the comparative analysis of normal anatomy and Palmer classification, the injuries were classified and MRI features of different types of injuries were analyzed. At last, imaging findings were compared with surgical results. Three healthy volunteers without injuries showed mainly in low signal intensity on T1WI and PD-FS images. According to Palmer classification, there were 52 traumatic injuries (ⅠA 9, ⅠB 25, ⅠC 3, ⅠD 13, In addition, 1 has central perforation and ulnar avulsion and 1 has ulnar and radial injuries simultaneously) and 15 degenerative injuries (ⅡA 5, ⅡB 1, ⅡC 2 , ⅡD 1 , ⅡE 6) among 67 patients. The central perforation mainly demonstrated as linear high signal perpendicular to the disk, and run in a sagittal line. The ulnar, distal, and radial avulsion mainly showed the injuries were irregular, the structures were ambiguous, and there was high signal intensity in the injured structures on PD-FS. Degenerative injuries demonstrated the irregularity of TFC and heterogeneous signals on PD-FS. There were mixed intermediate-high signals and changes in the articular cartilage of lunate and ulna, high signal in the lunotriquetral ligament and ulnocarpal or radioulnar arthritis. MRI can demonstrate the anatomy of TFCC accurately, evaluate and make the general classification of injuries. It is of significance for the early diagnosis and treatment protocols of the TFCC injuries.

Alterations of functional connectivities from early to middle adulthood: Clues from multivariate pattern analysis of resting-state fMRI data.

PubMed

Tian, Lixia; Ma, Lin; Wang, Linlin

2016-04-01

In contrast to extended research interests in the maturation and aging of human brain, alterations of brain structure and function from early to middle adulthood have been much less studied. The aim of the present study was to investigate the extent and pattern of the alterations of functional interactions between brain regions from early to middle adulthood. We carried out the study by multivariate pattern analysis of resting-state fMRI (RS-fMRI) data of 63 adults aged 18 to 45 years. Specifically, using elastic net, we performed brain age estimation and age-group classification (young adults aged 18-28 years vs. middle-aged adults aged 35-45 years) based on the resting-state functional connectivities (RSFCs) between 160 regions of interest (ROIs) evaluated on the RS-fMRI data of each subject. The results indicate that the estimated brain ages were significantly correlated with the chronological age (R=0.78, MAE=4.81), and a classification rate of 94.44% and area under the receiver operating characteristic curve (AUC) of 0.99 were obtained when classifying the young and middle-aged adults. These results provide strong evidence that functional interactions between brain regions undergo notable alterations from early to middle adulthood. By analyzing the RSFCs that contribute to brain age estimation/age-group classification, we found that a majority of the RSFCs were inter-network, and we speculate that inter-network RSFCs might mature late but age early as compared to intra-network ones. In addition, the strengthening/weakening of the RSFCs associated with the left/right hemispheric ROIs, the weakening of cortico-cerebellar RSFCs and the strengthening of the RSFCs between the default mode network and other networks contributed much to both brain age estimation and age-group classification. All these alterations might reflect that aging of brain function is already in progress in middle adulthood. Overall, the present study indicated that the RSFCs undergo notable alterations from early to middle adulthood and highlighted the necessity of careful considerations of possible influences of these alterations in related studies. Copyright © 2016 Elsevier Inc. All rights reserved.

Potential of PET-MRI for imaging of non-oncologic musculoskeletal disease.

PubMed

Kogan, Feliks; Fan, Audrey P; Gold, Garry E

2016-12-01

Early detection of musculoskeletal disease leads to improved therapies and patient outcomes, and would benefit greatly from imaging at the cellular and molecular level. As it becomes clear that assessment of multiple tissues and functional processes are often necessary to study the complex pathogenesis of musculoskeletal disorders, the role of multi-modality molecular imaging becomes increasingly important. New positron emission tomography-magnetic resonance imaging (PET-MRI) systems offer to combine high-resolution MRI with simultaneous molecular information from PET to study the multifaceted processes involved in numerous musculoskeletal disorders. In this article, we aim to outline the potential clinical utility of hybrid PET-MRI to these non-oncologic musculoskeletal diseases. We summarize current applications of PET molecular imaging in osteoarthritis (OA), rheumatoid arthritis (RA), metabolic bone diseases and neuropathic peripheral pain. Advanced MRI approaches that reveal biochemical and functional information offer complementary assessment in soft tissues. Additionally, we discuss technical considerations for hybrid PET-MR imaging including MR attenuation correction, workflow, radiation dose, and quantification.

Ex vivo diffusion MRI of the human brain: Technical challenges and recent advances.

PubMed

Roebroeck, Alard; Miller, Karla L; Aggarwal, Manisha

2018-06-04

This review discusses ex vivo diffusion magnetic resonance imaging (dMRI) as an important research tool for neuroanatomical investigations and the validation of in vivo dMRI techniques, with a focus on the human brain. We review the challenges posed by the properties of post-mortem tissue, and discuss state-of-the-art tissue preparation methods and recent advances in pulse sequences and acquisition techniques to tackle these. We then review recent ex vivo dMRI studies of the human brain, highlighting the validation of white matter orientation estimates and the atlasing and mapping of large subcortical structures. We also give particular emphasis to the delineation of layered gray matter structure with ex vivo dMRI, as this application illustrates the strength of its mesoscale resolution over large fields of view. We end with a discussion and outlook on future and potential directions of the field. © 2018 The Authors. NMR in Biomedicine published by John Wiley & Sons Ltd.

[Imaging in rheumatoid arthritis of the elbow].

PubMed

Lerch, K; Herold, T; Borisch, N; Grifka, J

2003-08-01

Early specific radiologic changes of rheumatoid arthritis can usually be detected in the hands and feet. Later stages of the disease process show a typical centripetal spread of the affected joints, i.e., shoulder, elbow, and knee. For prognostic assessment of cubital rheumatoid arthritis, conventional radiography still remains the gold standard. X-rays allow objective scoring and thus classification into standardized stages. A concentric destruction of the rheumatic joint as compared to deformity in the degenerative joint is the typical radiologic symptom to look for. For soft tissue assessment, ultrasound (US) should be the diagnostic tool of choice. Due to the thin surrounding soft tissue layer, as well as the advanced high-resolution technology, bony structures can also be well demonstrated in any plane. In the early arthritic stages, particularly the small changes, e.g., minimal erosions of the cortical area, are very well detectable by US. The use of "color" allows good evaluation of the synovial inflammatory status. Modern imaging methods such as computer- assisted tomography (CAT) scan and magnetic resonance imaging (MRI) are restricted to a few set indications and should not be chosen for routine examination. More invasive methods such as arthrography are no longer indicated for assessment of cubital rheumatoid arthritis.

Diagnosis and management of transfusion iron overload: The role of imaging

PubMed Central

Wood, John C.

2010-01-01

The characterization of iron stores is important to prevent and treat iron overload. Serum markers such as ferritin, serum iron, iron binding capacity, transferrin saturation, and nontransferrin-bound iron can be used to follow trends in iron status; however, variability in these markers limits predictive power for any given individual. Liver iron represents the best single marker of total iron balance. Measures of liver iron include biopsy, superconducting quantum interference device, computer tomography, and magnetic resonance imaging (MRI). MRI is the most accurate and widely available noninvasive tool to assess liver iron. The main advantages of MRI include a low-rate of variability between measurements and the ability to assess iron loading in endocrine tissues, the heart and the liver. This manuscript describes the principles, validation, and clinical utility of MRI for tissue iron estimation. PMID:17963249

Translational MR Neuroimaging of Stroke and Recovery

PubMed Central

Mandeville, Emiri T.; Ayata, Cenk; Zheng, Yi; Mandeville, Joseph B.

2016-01-01

Multiparametric magnetic resonance imaging (MRI) has become a critical clinical tool for diagnosing focal ischemic stroke severity, staging treatment, and predicting outcome. Imaging during the acute phase focuses on tissue viability in the stroke vicinity, while imaging during recovery requires the evaluation of distributed structural and functional connectivity. Preclinical MRI of experimental stroke models provides validation of non-invasive biomarkers in terms of cellular and molecular mechanisms, while also providing a translational platform for evaluation of prospective therapies. This brief review of translational stroke imaging discusses the acute to chronic imaging transition, the principles underlying common MRI methods employed in stroke research, and experimental results obtained by clinical and preclinical imaging to determine tissue viability, vascular remodeling, structural connectivity of major white matter tracts, and functional connectivity using task-based and resting-state fMRI during the stroke recovery process. PMID:27578048

Magnetic resonance imaging of the rat Harderian gland

PubMed Central

Sbarbati, Andrea; Calderan, Laura; Nicolato, Elena; Marzola, Pasquina; Lunati, Ernesto; Donatella, Benati; Bernardi, Paolo; Osculati, Francesco

2002-01-01

The intra-orbital lachrymal gland (Harderian gland, or HG) of the female rat was studied by magnetic resonance imaging (MRI) to evaluate whether MRI can be used to visualize the gland in vivo and localized-1H-spectroscopy detect its lipid content. The results were correlated with post-mortem anatomical sections, and with light and electron microscopy. On MRI, HG presented as a mass located between the ocular bulb and the orbit. In strongly T2W sequences the secretory structures had a reduced signal while intraparenchymal connective tissue was visible. T2-quantitative maps values of HG (60.12 ± 8.15 ms, mean ± SD) were different from other tissues (i.e. muscular tissue, T2 = 44.79 ± 3.43 ms and olfactory bulb, T2 = 79.26 ± 4.25 ms). In contrast-enhanced-MRI, HG had a signal-intensity-drop of 0.074 ± 0.072 (mean ± SD), after injection of AMI-25, significantly different from the muscle (0.17 ± 0.10). Localized MRI spectra gave a large part of the signal originating from fat protons, but with a significant percentage from water protons. At light and electron microscopy the lipid deposition appeared to be composed of low-density material filling a large part of the cytoplasm, and the porphyrin aggregates were easily recognizable. The data demonstrate that an in vivo study of the HG was feasible and that high-field MRI allowed analysis of the gross anatomy detecting the lipid content of the gland. PMID:12363274

Bone marrow lesions in hip osteoarthritis are characterized by increased bone turnover and enhanced angiogenesis.

PubMed

Shabestari, M; Vik, J; Reseland, J E; Eriksen, E F

2016-10-01

Bone marrow lesions (BML), previously denoted bone marrow edema, are detected as water signals by magnetic resonance imaging (MRI). Previous histologic studies were unable to demonstrate any edematous changes at the tissue level. Therefore, our aim was to investigate the underlying biological mechanisms of the water signal in MRI scans of bone affected by BML. Tetracycline labeling in addition to water sensitive MRI scans of 30 patients planned for total hip replacement surgery was undertaken. Twenty-one femoral heads revealed BML on MRI, while nine were negative and used as controls (CON). Guided by the MRI images cylindrical biopsies were extracted from areas with BML in the femoral heads. Tissue sections from the biopsies were subjected to histomorphometric image analyses of the cancellous bone envelope. Patients with BML exhibited an average 40- and 18-fold increase of bone formation rate and mineralizing surface, respectively. Additionally, samples with BML demonstrated 2-fold reduction of marrow fat and 28-fold increase of woven bone. Immunohistochemical analysis showed a 4-fold increase of angiogenesis markers CD31 and von Willebrand Factor (vWF) in the BML-group compared to CON. This study indicates that BML are characterized by increased bone turnover, vascularity and angiogenesis in keeping with it being a reparatory process. Thus, the water signal, which is the hallmark of BML on MRI, is most probably reflecting increased tissue vascularity accompanying increased remodeling activity. Copyright © 2016 Osteoarthritis Research Society International. Published by Elsevier Ltd. All rights reserved.

Lung parenchymal analysis on dynamic MRI in thoracic insufficiency syndrome to assess changes following surgical intervention

NASA Astrophysics Data System (ADS)

Jagadale, Basavaraj N.; Udupa, Jayaram K.; Tong, Yubing; Wu, Caiyun; McDonough, Joseph; Torigian, Drew A.; Campbell, Robert M.

2018-02-01

General surgeons, orthopedists, and pulmonologists individually treat patients with thoracic insufficiency syndrome (TIS). The benefits of growth-sparing procedures such as Vertical Expandable Prosthetic Titanium Rib (VEPTR)insertionfor treating patients with TIS have been demonstrated. However, at present there is no objective assessment metricto examine different thoracic structural components individually as to their roles in the syndrome, in contributing to dynamics and function, and in influencing treatment outcome. Using thoracic dynamic MRI (dMRI), we have been developing a methodology to overcome this problem. In this paper, we extend this methodology from our previous structural analysis approaches to examining lung tissue properties. We process the T2-weighted dMRI images through a series of steps involving 4D image construction of the acquired dMRI images, intensity non-uniformity correction and standardization of the 4D image, lung segmentation, and estimation of the parameters describing lung tissue intensity distributions in the 4D image. Based on pre- and post-operative dMRI data sets from 25 TIS patients (predominantly neuromuscular and congenital conditions), we demonstrate how lung tissue can be characterized by the estimated distribution parameters. Our results show that standardized T2-weighted image intensity values decrease from the pre- to post-operative condition, likely reflecting improved lung aeration post-operatively. In both pre- and post-operative conditions, the intensity values decrease also from end-expiration to end-inspiration, supporting the basic premise of our results.

Quantitative assessment of the equine hoof using digital radiography and magnetic resonance imaging.

PubMed

Grundmann, I N M; Drost, W T; Zekas, L J; Belknap, J K; Garabed, R B; Weisbrode, S E; Parks, A H; Knopp, M V; Maierl, J

2015-09-01

Evaluation of laminitis cases relies on radiographic measurements of the equine foot. Reference values have not been established for all layers of the foot. To establish normal hoof wall and sole measurements using digital radiography (DR) and magnetic resonance imaging (MRI) and to document tissue components present in the dorsal hoof wall and solar layers seen on DR. Prospective observational case-control study. Digital radiography and MRI were performed on 50 cadaver front feet from 25 horses subjected to euthanasia for nonlameness-related reasons. Four observers measured hoof wall (dorsal, lateral and medial) and sole thickness (sagittal, lateral and medial) using DR and magnetic resonance images. One observer repeated the measurements 3 times. Inter- and intraobserver correlation was assessed. Digital radiography and MRI measurements for the normal hoof wall and sole were established. Inter- and intraobserver pairwise Pearson's correlation for DR (r>0.98) and MRI measurements (r>0.99) was excellent. Based on MRI, the less radiopaque layer on DR is comprised of the stratum lamellatum and stratum reticulare. Normal DR and MRI measurements for the hoof wall and sole were established. On DR images, the less radiopaque layer of the foot observed corresponds to the critical tissues injured in laminitis, the strata lamellatum and reticulare. These reference measurements may be used by the clinician to detect soft-tissue changes in the laminitic equine foot and provide a foundation for future research determining changes in these measurements in horses with laminitis. © 2014 EVJ Ltd.

Streamlined Hyperacute Magnetic Resonance Imaging Protocol Identifies Tissue-Type Plasminogen Activator-Eligible Stroke Patients When Clinical Impression Is Stroke Mimic.

PubMed

Goyal, Manu S; Hoff, Brian G; Williams, Jennifer; Khoury, Naim; Wiesehan, Rebecca; Heitsch, Laura; Panagos, Peter; Vo, Katie D; Benzinger, Tammie; Derdeyn, Colin P; Lee, Jin-Moo; Ford, Andria L

2016-04-01

Stroke mimics (SM) challenge the initial assessment of patients presenting with possible acute ischemic stroke (AIS). When SM is considered likely, intravenous tissue-type plasminogen activator (tPA) may be withheld, risking an opportunity to treat AIS. Although computed tomography is routinely used for tPA decision making, magnetic resonance imaging (MRI) may diagnose AIS when SM is favored but not certain. We hypothesized that a hyperacute MRI (hMRI) protocol would identify tPA-eligible AIS patients among those initially favored to have SM. A streamlined hMRI protocol was designed based on barriers to rapid patient transport, MRI acquisition, and post-MRI tPA delivery. Neurologists were trained to order hMRI when SM was favored and tPA was being withheld. The use of hMRI for tPA decision making, door-to-needle times, and outcomes were compared before hMRI implementation (pre-hMRI: August 1, 2011 to July 31, 2013) and after (post-hMRI, August 1, 2013, to January 15, 2015). Post hMRI, 57 patients with suspected SM underwent hMRI (median MRI-order-to-start time, 29 minutes), of whom, 11 (19%) were diagnosed with AIS and 7 (12%) received tPA. Pre-hMRI, no tPA-treated patients were screened with hMRI. Post hMRI, 7 of 106 (6.6%) tPA-treated patients underwent hMRI to aid in decision making because of suspected SM (0% versus 6.6%; P=0.001). To ensure standard care was maintained after implementing the hMRI protocol, pre- versus post-hMRI tPA-treated cohorts were compared and did not differ: door-to-needle time (39 versus 37 minutes; P=0.63), symptomatic hemorrhage rate (4.5% versus 1.9%; P=0.32), and favorable discharge location (85% versus 89%; P=0.37). A streamlined hMRI protocol permitted tPA administration to a small, but significant, subset of AIS patients initially considered to have SM. © 2016 American Heart Association, Inc.

Objective breast tissue image classification using Quantitative Transmission ultrasound tomography

NASA Astrophysics Data System (ADS)

Malik, Bilal; Klock, John; Wiskin, James; Lenox, Mark

2016-12-01

Quantitative Transmission Ultrasound (QT) is a powerful and emerging imaging paradigm which has the potential to perform true three-dimensional image reconstruction of biological tissue. Breast imaging is an important application of QT and allows non-invasive, non-ionizing imaging of whole breasts in vivo. Here, we report the first demonstration of breast tissue image classification in QT imaging. We systematically assess the ability of the QT images’ features to differentiate between normal breast tissue types. The three QT features were used in Support Vector Machines (SVM) classifiers, and classification of breast tissue as either skin, fat, glands, ducts or connective tissue was demonstrated with an overall accuracy of greater than 90%. Finally, the classifier was validated on whole breast image volumes to provide a color-coded breast tissue volume. This study serves as a first step towards a computer-aided detection/diagnosis platform for QT.

Investigation of Factors Affecting Body Temperature Changes During Routine Clinical Head Magnetic Resonance Imaging

PubMed Central

Kim, Myeong Seong

2016-01-01

Background Pulsed radiofrequency (RF) magnetic fields, required to produce magnetic resonance imaging (MRI) signals from tissue during the MRI procedure have been shown to heat tissues. Objectives To investigate the relationship between body temperature rise and the RF power deposited during routine clinical MRI procedures, and to determine the correlation between this effect and the body’s physiological response. Patients and Methods We investigated 69 patients from the Korean national cancer center to identify the main factors that contribute to an increase in body temperature (external factors and the body’s response) during a clinical brain MRI. A routine protocol sequence of MRI scans (1.5 T and 3.0 T) was performed. The patient’s tympanic temperature was recorded before and immediately after the MRI procedure and compared with changes in variables related to the body’s physiological response to heat. Results Our investigation of the physiological response to RF heating indicated a link between increasing age and body temperature. A higher increase in body temperature was observed in older patients after a 3.0-T MRI (r = 0.07, P = 0.29 for 1.5-T MRI; r = 0.45, P = 0.002 for 3.0-T MRI). The relationship between age and body heat was related to the heart rate (HR) and changes in HR during the MRI procedure; a higher RF power combined with a reduction in HR resulted in an increase in body temperature. Conclusion A higher magnetic field strength and a decrease in the HR resulted in an increase in body temperature during the MRI procedure. PMID:27895872

The pathology of lumbosacral lipomas: macroscopic and microscopic disparity have implications for embryogenesis and mode of clinical deterioration.

PubMed

Jones, Victoria; Wykes, Victoria; Cohen, Nicki; Thompson, Dominic; Jacques, Tom S

2018-06-01

Lumbosacral lipomas (LSL) are congenital disorders of the terminal spinal cord region that have the potential to cause significant spinal cord dysfunction in children. They are of unknown embryogenesis with variable clinical presentation and natural history. It is unclear whether the spinal cord dysfunction reflects a primary developmental dysplasia or whether it occurs secondarily to mechanical traction (spinal cord tethering) with growth. While different anatomical subtypes are recognised and classified according to radiological criteria, these subtypes correlate poorly with clinical prognosis. We have undertaken an analysis of surgical specimens in order to describe the spectrum of histological changes that occur and have correlated the histology with the anatomical type of LSL to determine if there are distinct histological subtypes. The histopathology was reviewed of 64 patients who had undergone surgical resection of LSL. The presence of additional tissues and cell types were recorded. LSLs were classified from pre-operative magnetic resonance imaging (MRI) scans according to Chapman classification. Ninety-five per cent of the specimens consisted predominantly of mature adipocytes with all containing thickened bands of connective tissue and peripheral nerve fibres, 91% of samples contained ectatic blood vessels with thickened walls, while 22% contained central nervous system (CNS) glial tissue. Additional tissue was identified of both mesodermal and neuroectodermal origin. Our analysis highlights the heterogeneity of tissue types within all samples, not reflected in the nomenclature. The diversity of tissue types, consistent across all subtypes, challenges currently held notions regarding the embryogenesis of LSLs and the assumption that clinical deterioration is due simply to tethering. © 2018 The Authors. Histopathology Published by John Wiley & Sons Ltd.

Low back pain: an assessment using positional MRI and MDT.

PubMed

Hedberg, Karen; Alexander, Lyndsay A; Cooper, Kay; Hancock, Elizabeth; Ross, Jenny; Smith, Francis W

2013-04-01

Current guidelines advise against the use of routine imaging for low back pain. Positional MRI can provide enhanced assessment of the lumbar spine in functionally loaded positions which are often relevant to the presenting clinical symptoms. The purpose of this case report is to highlight the use of positional MRI in the assessment and classification of a subject with low back pain. A low back pain subject underwent a Mechanical Diagnosis and Therapy (MDT) assessment and positional MRI scan of the lumbar spine. The MDT assessment classified the subject as "other" since the subjective history indicated a possible posterior derangement whilst the objective assessment indicated a possible anterior derangement. Positional MRI scanning in flexed, upright and extended sitting postures confirmed the MDT assessment findings to reveal a dynamic spinal stenosis which reduced in flexion and increased in extension. Copyright © 2012 Elsevier Ltd. All rights reserved.

Classification of kidney and liver tissue using ultrasound backscatter data

NASA Astrophysics Data System (ADS)

Aalamifar, Fereshteh; Rivaz, Hassan; Cerrolaza, Juan J.; Jago, James; Safdar, Nabile; Boctor, Emad M.; Linguraru, Marius G.

2015-03-01

Ultrasound (US) tissue characterization provides valuable information for the initialization of automatic segmentation algorithms, and can further provide complementary information for diagnosis of pathologies. US tissue characterization is challenging due to the presence of various types of image artifacts and dependence on the sonographer's skills. One way of overcoming this challenge is by characterizing images based on the distribution of the backscatter data derived from the interaction between US waves and tissue. The goal of this work is to classify liver versus kidney tissue in 3D volumetric US data using the distribution of backscatter US data recovered from end-user displayed Bmode image available in clinical systems. To this end, we first propose the computation of a large set of features based on the homodyned-K distribution of the speckle as well as the correlation coefficients between small patches in 3D images. We then utilize the random forests framework to select the most important features for classification. Experiments on in-vivo 3D US data from nine pediatric patients with hydronephrosis showed an average accuracy of 94% for the classification of liver and kidney tissues showing a good potential of this work to assist in the classification and segmentation of abdominal soft tissue.

Therapeutic Vascular Targeting and Irradiation: Correlation of MRI Tissue Changes at Cellular and Molecular Levels to Optimizing Outcome

DTIC Science & Technology

2008-06-01

cascade of tumor cell death in experimental tumors (4-6). However, survived tissues in a thin viable rim of tumor usually re-grow in spite of...changes monitored by MRI, optimum scheme of the combined radiation and CA4P will be designed and experimental treatment will be performed on the...CD31 Overlap Figure 4 CD 10 Task 2. Experimental tumor therapy

Removal of BCG artifacts using a non-Kirchhoffian overcomplete representation.

PubMed

Dyrholm, Mads; Goldman, Robin; Sajda, Paul; Brown, Truman R

2009-02-01

We present a nonlinear unmixing approach for extracting the ballistocardiogram (BCG) from EEG recorded in an MR scanner during simultaneous acquisition of functional MRI (fMRI). First, an overcomplete basis is identified in the EEG based on a custom multipath EEG electrode cap. Next, the overcomplete basis is used to infer non-Kirchhoffian latent variables that are not consistent with a conservative electric field. Neural activity is strictly Kirchhoffian while the BCG artifact is not, and the representation can hence be used to remove the artifacts from the data in a way that does not attenuate the neural signals needed for optimal single-trial classification performance. We compare our method to more standard methods for BCG removal, namely independent component analysis and optimal basis sets, by looking at single-trial classification performance for an auditory oddball experiment. We show that our overcomplete representation method for removing BCG artifacts results in better single-trial classification performance compared to the conventional approaches, indicating that the derived neural activity in this representation retains the complex information in the trial-to-trial variability.

Assessing paedophilia based on the haemodynamic brain response to face images.

PubMed

Ponseti, Jorge; Granert, Oliver; Van Eimeren, Thilo; Jansen, Olav; Wolff, Stephan; Beier, Klaus; Deuschl, Günther; Huchzermeier, Christian; Stirn, Aglaja; Bosinski, Hartmut; Roman Siebner, Hartwig

2016-01-01

Objective assessment of sexual preferences may be of relevance in the treatment and prognosis of child sexual offenders. Previous research has indicated that this can be achieved by pattern classification of brain responses to sexual child and adult images. Our recent research showed that human face processing is tuned to sexual age preferences. This observation prompted us to test whether paedophilia can be inferred based on the haemodynamic brain responses to adult and child faces. Twenty-four men sexually attracted to prepubescent boys or girls (paedophiles) and 32 men sexually attracted to men or women (teleiophiles) were exposed to images of child and adult, male and female faces during a functional magnetic resonance imaging (fMRI) session. A cross-validated, automatic pattern classification algorithm of brain responses to facial stimuli yielded four misclassified participants (three false positives), corresponding to a specificity of 91% and a sensitivity of 95%. These results indicate that the functional response to facial stimuli can be reliably used for fMRI-based classification of paedophilia, bypassing the problem of showing child sexual stimuli to paedophiles.

Localised drug release using MRI-controlled focused ultrasound hyperthermia.

PubMed

Staruch, Robert; Chopra, Rajiv; Hynynen, Kullervo

2011-01-01

Thermosensitive liposomes provide a mechanism for triggering the local release of anticancer drugs, but this technology requires precise temperature control in targeted regions with minimal heating of surrounding tissue. The objective of this study was to evaluate the feasibility of using MRI-controlled focused ultrasound (FUS) and thermosensitive liposomes to achieve thermally mediated localised drug delivery in vivo. Results are reported from ten rabbits, where a FUS beam was scanned in a circular trajectory to heat 10-15 mm diameter regions in normal thigh to 43°C for 20-30 min. MRI thermometry was used for closed-loop feedback control to achieve temporally and spatially uniform heating. Lyso-thermosensitive liposomal doxorubicin was infused intravenously during hyperthermia. Unabsorbed liposomes were flushed from the vasculature by saline perfusion 2 h later, and tissue samples were harvested from heated and unheated thigh regions. The fluorescence intensity of the homogenised samples was used to calculate the concentration of doxorubicin in tissue. Closed-loop control of FUS heating using MRI thermometry achieved temperature distributions with mean, T90 and T10 of 42.9°C, 41.0°C and 44.8°C, respectively, over a period of 20 min. Doxorubicin concentrations were significantly higher in tissues sampled from heated than unheated regions of normal thigh muscle (8.3 versus 0.5 ng/mg, mean per-animal difference = 7.8 ng/mg, P < 0.05, Wilcoxon matched pairs signed rank test). The results show the potential of MRI-controlled focused ultrasound hyperthermia for enhanced local drug delivery with temperature-sensitive drug carriers.

Local contrast-enhanced MR images via high dynamic range processing.

PubMed

Chandra, Shekhar S; Engstrom, Craig; Fripp, Jurgen; Neubert, Ales; Jin, Jin; Walker, Duncan; Salvado, Olivier; Ho, Charles; Crozier, Stuart

2018-09-01

To develop a local contrast-enhancing and feature-preserving high dynamic range (HDR) image processing algorithm for multichannel and multisequence MR images of multiple body regions and tissues, and to evaluate its performance for structure visualization, bias field (correction) mitigation, and automated tissue segmentation. A multiscale-shape and detail-enhancement HDR-MRI algorithm is applied to data sets of multichannel and multisequence MR images of the brain, knee, breast, and hip. In multisequence 3T hip images, agreement between automatic cartilage segmentations and corresponding synthesized HDR-MRI series were computed for mean voxel overlap established from manual segmentations for a series of cases. Qualitative comparisons between the developed HDR-MRI and standard synthesis methods were performed on multichannel 7T brain and knee data, and multisequence 3T breast and knee data. The synthesized HDR-MRI series provided excellent enhancement of fine-scale structure from multiple scales and contrasts, while substantially reducing bias field effects in 7T brain gradient echo, T 1 and T 2 breast images and 7T knee multichannel images. Evaluation of the HDR-MRI approach on 3T hip multisequence images showed superior outcomes for automatic cartilage segmentations with respect to manual segmentation, particularly around regions with hyperintense synovial fluid, across a set of 3D sequences. The successful combination of multichannel/sequence MR images into a single-fused HDR-MR image format provided consolidated visualization of tissues within 1 omnibus image, enhanced definition of thin, complex anatomical structures in the presence of variable or hyperintense signals, and improved tissue (cartilage) segmentation outcomes. © 2018 International Society for Magnetic Resonance in Medicine.

Multi-Site Diagnostic Classification of Schizophrenia Using Discriminant Deep Learning with Functional Connectivity MRI.

PubMed

Zeng, Ling-Li; Wang, Huaning; Hu, Panpan; Yang, Bo; Pu, Weidan; Shen, Hui; Chen, Xingui; Liu, Zhening; Yin, Hong; Tan, Qingrong; Wang, Kai; Hu, Dewen

2018-04-01

A lack of a sufficiently large sample at single sites causes poor generalizability in automatic diagnosis classification of heterogeneous psychiatric disorders such as schizophrenia based on brain imaging scans. Advanced deep learning methods may be capable of learning subtle hidden patterns from high dimensional imaging data, overcome potential site-related variation, and achieve reproducible cross-site classification. However, deep learning-based cross-site transfer classification, despite less imaging site-specificity and more generalizability of diagnostic models, has not been investigated in schizophrenia. A large multi-site functional MRI sample (n = 734, including 357 schizophrenic patients from seven imaging resources) was collected, and a deep discriminant autoencoder network, aimed at learning imaging site-shared functional connectivity features, was developed to discriminate schizophrenic individuals from healthy controls. Accuracies of approximately 85·0% and 81·0% were obtained in multi-site pooling classification and leave-site-out transfer classification, respectively. The learned functional connectivity features revealed dysregulation of the cortical-striatal-cerebellar circuit in schizophrenia, and the most discriminating functional connections were primarily located within and across the default, salience, and control networks. The findings imply that dysfunctional integration of the cortical-striatal-cerebellar circuit across the default, salience, and control networks may play an important role in the "disconnectivity" model underlying the pathophysiology of schizophrenia. The proposed discriminant deep learning method may be capable of learning reliable connectome patterns and help in understanding the pathophysiology and achieving accurate prediction of schizophrenia across multiple independent imaging sites. Copyright © 2018 German Center for Neurodegenerative Diseases (DZNE). Published by Elsevier B.V. All rights reserved.

Functional Communication Profiles in Children with Cerebral Palsy in Relation to Gross Motor Function and Manual and Intellectual Ability.

PubMed

Choi, Ja Young; Park, Jieun; Choi, Yoon Seong; Goh, Yu Ra; Park, Eun Sook

2018-07-01

The aim of the present study was to investigate communication function using classification systems and its association with other functional profiles, including gross motor function, manual ability, intellectual functioning, and brain magnetic resonance imaging (MRI) characteristics in children with cerebral palsy (CP). This study recruited 117 individuals with CP aged from 4 to 16 years. The Communication Function Classification System (CFCS), Viking Speech Scale (VSS), Speech Language Profile Groups (SLPG), Gross Motor Function Classification System (GMFCS), Manual Ability Classification System (MACS), and intellectual functioning were assessed in the children along with brain MRI categorization. Very strong relationships were noted among the VSS, CFCS, and SLPG, although these three communication systems provide complementary information, especially for children with mid-range communication impairment. These three communication classification systems were strongly related with the MACS, but moderately related with the GMFCS. Multiple logistic regression analysis indicated that manual ability and intellectual functioning were significantly related with VSS and CFCS function, whereas only intellectual functioning was significantly related with SLPG functioning in children with CP. Communication function in children with a periventricular white matter lesion (PVWL) varied widely. In the cases with a PVWL, poor functioning was more common on the SLPG, compared to the VSS and CFCS. Very strong relationships were noted among three communication classification systems that are closely related with intellectual ability. Compared to gross motor function, manual ability seemed more closely related with communication function in these children. © Copyright: Yonsei University College of Medicine 2018.

MRI-guided fluorescence tomography of the breast: a phantom study

NASA Astrophysics Data System (ADS)

Davis, Scott C.; Pogue, Brian W.; Dehghani, Hamid; Paulsen, Keith D.

2009-02-01

Tissue phantoms simulating the human breast were used to demonstrate the imaging capabilities of an MRI-coupled fluorescence molecular tomography (FMT) imaging system. Specifically, phantoms with low tumor-to-normal drug contrast and complex internal structure were imaged with the MR-coupled FMT system. Images of indocyanine green (ICG) fluorescence yield were recovered using a diffusion model-based approach capable of estimating the distribution of fluorescence activity in a tissue volume from tissue-boundary measurements of transmitted light. Tissue structural information, which can be determined from standard T1 and T2 MR images, was used to guide the recovery of fluorescence activity. The study revealed that this spatial guidance is critical for recovering images of fluorescence yield in tissue with low tumor-to-normal drug contrast.

A human visual based binarization technique for histological images

NASA Astrophysics Data System (ADS)

Shreyas, Kamath K. M.; Rajendran, Rahul; Panetta, Karen; Agaian, Sos

2017-05-01

In the field of vision-based systems for object detection and classification, thresholding is a key pre-processing step. Thresholding is a well-known technique for image segmentation. Segmentation of medical images, such as Computed Axial Tomography (CAT), Magnetic Resonance Imaging (MRI), X-Ray, Phase Contrast Microscopy, and Histological images, present problems like high variability in terms of the human anatomy and variation in modalities. Recent advances made in computer-aided diagnosis of histological images help facilitate detection and classification of diseases. Since most pathology diagnosis depends on the expertise and ability of the pathologist, there is clearly a need for an automated assessment system. Histological images are stained to a specific color to differentiate each component in the tissue. Segmentation and analysis of such images is problematic, as they present high variability in terms of color and cell clusters. This paper presents an adaptive thresholding technique that aims at segmenting cell structures from Haematoxylin and Eosin stained images. The thresholded result can further be used by pathologists to perform effective diagnosis. The effectiveness of the proposed method is analyzed by visually comparing the results to the state of art thresholding methods such as Otsu, Niblack, Sauvola, Bernsen, and Wolf. Computer simulations demonstrate the efficiency of the proposed method in segmenting critical information.

A theoretical framework for determining cerebral vascular function and heterogeneity from dynamic susceptibility contrast MRI.

PubMed

Digernes, Ingrid; Bjørnerud, Atle; Vatnehol, Svein Are S; Løvland, Grete; Courivaud, Frédéric; Vik-Mo, Einar; Meling, Torstein R; Emblem, Kyrre E

2017-06-01

Mapping the complex heterogeneity of vascular tissue in the brain is important for understanding cerebrovascular disease. In this translational study, we build on previous work using vessel architectural imaging (VAI) and present a theoretical framework for determining cerebral vascular function and heterogeneity from dynamic susceptibility contrast magnetic resonance imaging (MRI). Our tissue model covers realistic structural architectures for vessel branching and orientations, as well as a range of hemodynamic scenarios for blood flow, capillary transit times and oxygenation. In a typical image voxel, our findings show that the apparent MRI relaxation rates are independent of the mean vessel orientation and that the vortex area, a VAI-based parameter, is determined by the relative oxygen saturation level and the vessel branching of the tissue. Finally, in both simulated and patient data, we show that the relative distributions of the vortex area parameter as a function of capillary transit times show unique characteristics in normal-appearing white and gray matter tissue, whereas tumour-voxels in comparison display a heterogeneous distribution. Collectively, our study presents a comprehensive framework that may serve as a roadmap for in vivo and per-voxel determination of vascular status and heterogeneity in cerebral tissue.