Automatic recognition of holistic functional brain networks using iteratively optimized convolutional neural networks (IO-CNN) with weak label initialization.

PubMed

Zhao, Yu; Ge, Fangfei; Liu, Tianming

2018-07-01

fMRI data decomposition techniques have advanced significantly from shallow models such as Independent Component Analysis (ICA) and Sparse Coding and Dictionary Learning (SCDL) to deep learning models such Deep Belief Networks (DBN) and Convolutional Autoencoder (DCAE). However, interpretations of those decomposed networks are still open questions due to the lack of functional brain atlases, no correspondence across decomposed or reconstructed networks across different subjects, and significant individual variabilities. Recent studies showed that deep learning, especially deep convolutional neural networks (CNN), has extraordinary ability of accommodating spatial object patterns, e.g., our recent works using 3D CNN for fMRI-derived network classifications achieved high accuracy with a remarkable tolerance for mistakenly labelled training brain networks. However, the training data preparation is one of the biggest obstacles in these supervised deep learning models for functional brain network map recognitions, since manual labelling requires tedious and time-consuming labours which will sometimes even introduce label mistakes. Especially for mapping functional networks in large scale datasets such as hundreds of thousands of brain networks used in this paper, the manual labelling method will become almost infeasible. In response, in this work, we tackled both the network recognition and training data labelling tasks by proposing a new iteratively optimized deep learning CNN (IO-CNN) framework with an automatic weak label initialization, which enables the functional brain networks recognition task to a fully automatic large-scale classification procedure. Our extensive experiments based on ABIDE-II 1099 brains' fMRI data showed the great promise of our IO-CNN framework. Copyright © 2018 Elsevier B.V. All rights reserved.

Label-indicator morpheme growth on LSTM for Chinese healthcare question department classification.

PubMed

Hu, Yang; Wen, Guihua; Ma, Jiajiong; Li, Danyang; Wang, Changjun; Li, Huihui; Huan, Eryang

2018-04-26

Current Chinese medicine has an urgent demand for convenient medical services. When facing a large number of patients, understanding patients' questions automatically and precisely is useful. Different from the high professional medical text, patients' questions contain only a small amount of descriptions regarding the symptoms, and the questions are slightly professional and colloquial. The aim of this paper is to implement a department classification system for patient questions. Patients' questions will be classified into 11 departments, such as surgery and others. This paper presents a morpheme growth model that enhances the memories of key elements in questions, and later extracts the "label-indicators" and germinates the expansion vectors around them. Finally, the model inputs the expansion vectors into a neural network to assign department labels for patients' questions. All compared methods are validated by experiments on three datasets that are composed of real patient questions. The proposed method has some ability to improve the performance of the classification. The proposed method is effective for the departments classification of patients questions and serves as a useful system for the automatic understanding of patient questions. Copyright © 2018. Published by Elsevier Inc.

Novel image processing method study for a label-free optical biosensor

NASA Astrophysics Data System (ADS)

Yang, Chenhao; Wei, Li'an; Yang, Rusong; Feng, Ying

2015-10-01

Optical biosensor is generally divided into labeled type and label-free type, the former mainly contains fluorescence labeled method and radioactive-labeled method, while fluorescence-labeled method is more mature in the application. The mainly image processing methods of fluorescent-labeled biosensor includes smooth filtering, artificial gridding and constant thresholding. Since some fluorescent molecules may influence the biological reaction, label-free methods have been the main developing direction of optical biosensors nowadays. The using of wider field of view and larger angle of incidence light path which could effectively improve the sensitivity of the label-free biosensor also brought more difficulties in image processing, comparing with the fluorescent-labeled biosensor. Otsu's method is widely applied in machine vision, etc, which choose the threshold to minimize the intraclass variance of the thresholded black and white pixels. It's capacity-constrained with the asymmetrical distribution of images as a global threshold segmentation. In order to solve the irregularity of light intensity on the transducer, we improved the algorithm. In this paper, we present a new image processing algorithm based on a reflectance modulation biosensor platform, which mainly comprises the design of sliding normalization algorithm for image rectification and utilizing the improved otsu's method for image segmentation, in order to implement automatic recognition of target areas. Finally we used adaptive gridding method extracting the target parameters for analysis. Those methods could improve the efficiency of image processing, reduce human intervention, enhance the reliability of experiments and laid the foundation for the realization of high throughput of label-free optical biosensors.

Interactive lung segmentation in abnormal human and animal chest CT scans

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

Kockelkorn, Thessa T. J. P., E-mail: thessa@isi.uu.nl; Viergever, Max A.; Schaefer-Prokop, Cornelia M.

2014-08-15

Purpose: Many medical image analysis systems require segmentation of the structures of interest as a first step. For scans with gross pathology, automatic segmentation methods may fail. The authors’ aim is to develop a versatile, fast, and reliable interactive system to segment anatomical structures. In this study, this system was used for segmenting lungs in challenging thoracic computed tomography (CT) scans. Methods: In volumetric thoracic CT scans, the chest is segmented and divided into 3D volumes of interest (VOIs), containing voxels with similar densities. These VOIs are automatically labeled as either lung tissue or nonlung tissue. The automatic labeling resultsmore » can be corrected using an interactive or a supervised interactive approach. When using the supervised interactive system, the user is shown the classification results per slice, whereupon he/she can adjust incorrect labels. The system is retrained continuously, taking the corrections and approvals of the user into account. In this way, the system learns to make a better distinction between lung tissue and nonlung tissue. When using the interactive framework without supervised learning, the user corrects all incorrectly labeled VOIs manually. Both interactive segmentation tools were tested on 32 volumetric CT scans of pigs, mice and humans, containing pulmonary abnormalities. Results: On average, supervised interactive lung segmentation took under 9 min of user interaction. Algorithm computing time was 2 min on average, but can easily be reduced. On average, 2.0% of all VOIs in a scan had to be relabeled. Lung segmentation using the interactive segmentation method took on average 13 min and involved relabeling 3.0% of all VOIs on average. The resulting segmentations correspond well to manual delineations of eight axial slices per scan, with an average Dice similarity coefficient of 0.933. Conclusions: The authors have developed two fast and reliable methods for interactive lung segmentation in challenging chest CT images. Both systems do not require prior knowledge of the scans under consideration and work on a variety of scans.« less

volBrain: An Online MRI Brain Volumetry System

PubMed Central

Manjón, José V.; Coupé, Pierrick

2016-01-01

The amount of medical image data produced in clinical and research settings is rapidly growing resulting in vast amount of data to analyze. Automatic and reliable quantitative analysis tools, including segmentation, allow to analyze brain development and to understand specific patterns of many neurological diseases. This field has recently experienced many advances with successful techniques based on non-linear warping and label fusion. In this work we present a novel and fully automatic pipeline for volumetric brain analysis based on multi-atlas label fusion technology that is able to provide accurate volumetric information at different levels of detail in a short time. This method is available through the volBrain online web interface (http://volbrain.upv.es), which is publically and freely accessible to the scientific community. Our new framework has been compared with current state-of-the-art methods showing very competitive results. PMID:27512372

volBrain: An Online MRI Brain Volumetry System.

PubMed

Manjón, José V; Coupé, Pierrick

2016-01-01

The amount of medical image data produced in clinical and research settings is rapidly growing resulting in vast amount of data to analyze. Automatic and reliable quantitative analysis tools, including segmentation, allow to analyze brain development and to understand specific patterns of many neurological diseases. This field has recently experienced many advances with successful techniques based on non-linear warping and label fusion. In this work we present a novel and fully automatic pipeline for volumetric brain analysis based on multi-atlas label fusion technology that is able to provide accurate volumetric information at different levels of detail in a short time. This method is available through the volBrain online web interface (http://volbrain.upv.es), which is publically and freely accessible to the scientific community. Our new framework has been compared with current state-of-the-art methods showing very competitive results.

A coloured oil level indicator detection method based on simple linear iterative clustering

NASA Astrophysics Data System (ADS)

Liu, Tianli; Li, Dongsong; Jiao, Zhiming; Liang, Tao; Zhou, Hao; Yang, Guoqing

2017-12-01

A detection method of coloured oil level indicator is put forward. The method is applied to inspection robot in substation, which realized the automatic inspection and recognition of oil level indicator. Firstly, the detected image of the oil level indicator is collected, and the detected image is clustered and segmented to obtain the label matrix of the image. Secondly, the detection image is processed by colour space transformation, and the feature matrix of the image is obtained. Finally, the label matrix and feature matrix are used to locate and segment the detected image, and the upper edge of the recognized region is obtained. If the upper limb line exceeds the preset oil level threshold, the alarm will alert the station staff. Through the above-mentioned image processing, the inspection robot can independently recognize the oil level of the oil level indicator, and instead of manual inspection. It embodies the automatic and intelligent level of unattended operation.

Automated Volumetry and Regional Thickness Analysis of Hippocampal Subfields and Medial Temporal Cortical Structures in Mild Cognitive Impairment

PubMed Central

Yushkevich, Paul A.; Pluta, John B.; Wang, Hongzhi; Xie, Long; Ding, Song-Lin; Gertje, E. C.; Mancuso, Lauren; Kliot, Daria; Das, Sandhitsu R.; Wolk, David A.

2014-01-01

We evaluate a fully automatic technique for labeling hippocampal subfields and cortical subregions in the medial temporal lobe (MTL) in in vivo 3 Tesla MRI. The method performs segmentation on a T2-weighted MRI scan with 0.4 × 0.4 × 2.0 mm3 resolution, partial brain coverage, and oblique orientation. Hippocampal subfields, entorhinal cortex, and perirhinal cortex are labeled using a pipeline that combines multi-atlas label fusion and learning-based error correction. In contrast to earlier work on automatic subfield segmentation in T2-weighted MRI (Yushkevich et al., 2010), our approach requires no manual initialization, labels hippocampal subfields over a greater anterior-posterior extent, and labels the perirhinal cortex, which is further subdivided into Brodmann areas 35 and 36. The accuracy of the automatic segmentation relative to manual segmentation is measured using cross-validation in 29 subjects from a study of amnestic Mild Cognitive Impairment (aMCI), and is highest for the dentate gyrus (Dice coefficient is 0.823), CA1 (0.803), perirhinal cortex (0.797) and entorhinal cortex (0.786) labels. A larger cohort of 83 subjects is used to examine the effects of aMCI in the hippocampal region using both subfield volume and regional subfield thickness maps. Most significant differences between aMCI and healthy aging are observed bilaterally in the CA1 subfield and in the left Brodmann area 35. Thickness analysis results are consistent with volumetry, but provide additional regional specificity and suggest non-uniformity in the effects of aMCI on hippocampal subfields and MTL cortical subregions. PMID:25181316

A multi-label learning based kernel automatic recommendation method for support vector machine.

PubMed

Zhang, Xueying; Song, Qinbao

2015-01-01

Choosing an appropriate kernel is very important and critical when classifying a new problem with Support Vector Machine. So far, more attention has been paid on constructing new kernels and choosing suitable parameter values for a specific kernel function, but less on kernel selection. Furthermore, most of current kernel selection methods focus on seeking a best kernel with the highest classification accuracy via cross-validation, they are time consuming and ignore the differences among the number of support vectors and the CPU time of SVM with different kernels. Considering the tradeoff between classification success ratio and CPU time, there may be multiple kernel functions performing equally well on the same classification problem. Aiming to automatically select those appropriate kernel functions for a given data set, we propose a multi-label learning based kernel recommendation method built on the data characteristics. For each data set, the meta-knowledge data base is first created by extracting the feature vector of data characteristics and identifying the corresponding applicable kernel set. Then the kernel recommendation model is constructed on the generated meta-knowledge data base with the multi-label classification method. Finally, the appropriate kernel functions are recommended to a new data set by the recommendation model according to the characteristics of the new data set. Extensive experiments over 132 UCI benchmark data sets, with five different types of data set characteristics, eleven typical kernels (Linear, Polynomial, Radial Basis Function, Sigmoidal function, Laplace, Multiquadric, Rational Quadratic, Spherical, Spline, Wave and Circular), and five multi-label classification methods demonstrate that, compared with the existing kernel selection methods and the most widely used RBF kernel function, SVM with the kernel function recommended by our proposed method achieved the highest classification performance.

A Multi-Label Learning Based Kernel Automatic Recommendation Method for Support Vector Machine

PubMed Central

Zhang, Xueying; Song, Qinbao

2015-01-01

Choosing an appropriate kernel is very important and critical when classifying a new problem with Support Vector Machine. So far, more attention has been paid on constructing new kernels and choosing suitable parameter values for a specific kernel function, but less on kernel selection. Furthermore, most of current kernel selection methods focus on seeking a best kernel with the highest classification accuracy via cross-validation, they are time consuming and ignore the differences among the number of support vectors and the CPU time of SVM with different kernels. Considering the tradeoff between classification success ratio and CPU time, there may be multiple kernel functions performing equally well on the same classification problem. Aiming to automatically select those appropriate kernel functions for a given data set, we propose a multi-label learning based kernel recommendation method built on the data characteristics. For each data set, the meta-knowledge data base is first created by extracting the feature vector of data characteristics and identifying the corresponding applicable kernel set. Then the kernel recommendation model is constructed on the generated meta-knowledge data base with the multi-label classification method. Finally, the appropriate kernel functions are recommended to a new data set by the recommendation model according to the characteristics of the new data set. Extensive experiments over 132 UCI benchmark data sets, with five different types of data set characteristics, eleven typical kernels (Linear, Polynomial, Radial Basis Function, Sigmoidal function, Laplace, Multiquadric, Rational Quadratic, Spherical, Spline, Wave and Circular), and five multi-label classification methods demonstrate that, compared with the existing kernel selection methods and the most widely used RBF kernel function, SVM with the kernel function recommended by our proposed method achieved the highest classification performance. PMID:25893896

Automated Bone Segmentation and Surface Evaluation of a Small Animal Model of Post-Traumatic Osteoarthritis.

PubMed

Ramme, Austin J; Voss, Kevin; Lesporis, Jurinus; Lendhey, Matin S; Coughlin, Thomas R; Strauss, Eric J; Kennedy, Oran D

2017-05-01

MicroCT imaging allows for noninvasive microstructural evaluation of mineralized bone tissue, and is essential in studies of small animal models of bone and joint diseases. Automatic segmentation and evaluation of articular surfaces is challenging. Here, we present a novel method to create knee joint surface models, for the evaluation of PTOA-related joint changes in the rat using an atlas-based diffeomorphic registration to automatically isolate bone from surrounding tissues. As validation, two independent raters manually segment datasets and the resulting segmentations were compared to our novel automatic segmentation process. Data were evaluated using label map volumes, overlap metrics, Euclidean distance mapping, and a time trial. Intraclass correlation coefficients were calculated to compare methods, and were greater than 0.90. Total overlap, union overlap, and mean overlap were calculated to compare the automatic and manual methods and ranged from 0.85 to 0.99. A Euclidean distance comparison was also performed and showed no measurable difference between manual and automatic segmentations. Furthermore, our new method was 18 times faster than manual segmentation. Overall, this study describes a reliable, accurate, and automatic segmentation method for mineralized knee structures from microCT images, and will allow for efficient assessment of bony changes in small animal models of PTOA.

Peptide and protein quantitation by acid-catalyzed 18O-labeling of carboxyl groups.

PubMed

Haaf, Erik; Schlosser, Andreas

2012-01-03

We have developed a new method that applies acidic catalysis with hydrochloric acid for (18)O-labeling of peptides at their carboxyl groups. With this method, peptides get labeled at their C-terminus, at Asp and Glu residues, and at carboxymethylated cysteine residues. Oxygen atoms at phosphate groups of phosphopeptide are not exchanged. Our elaborated labeling protocol is easy to perform, fast (5 h and 30 min), and results in 95-97 atom % incorporation of (18)O at carboxyl groups. Undesired side reactions, such as deamidation or peptide hydrolysis, occur only at a very low level under the conditions applied. In addition, data analysis can be performed automatically using common software tools, such as Mascot Distiller. We have demonstrated the capability of this method for the quantitation of peptides as well as for phosphopeptides. © 2011 American Chemical Society

Learning classification models with soft-label information.

PubMed

Nguyen, Quang; Valizadegan, Hamed; Hauskrecht, Milos

2014-01-01

Learning of classification models in medicine often relies on data labeled by a human expert. Since labeling of clinical data may be time-consuming, finding ways of alleviating the labeling costs is critical for our ability to automatically learn such models. In this paper we propose a new machine learning approach that is able to learn improved binary classification models more efficiently by refining the binary class information in the training phase with soft labels that reflect how strongly the human expert feels about the original class labels. Two types of methods that can learn improved binary classification models from soft labels are proposed. The first relies on probabilistic/numeric labels, the other on ordinal categorical labels. We study and demonstrate the benefits of these methods for learning an alerting model for heparin induced thrombocytopenia. The experiments are conducted on the data of 377 patient instances labeled by three different human experts. The methods are compared using the area under the receiver operating characteristic curve (AUC) score. Our AUC results show that the new approach is capable of learning classification models more efficiently compared to traditional learning methods. The improvement in AUC is most remarkable when the number of examples we learn from is small. A new classification learning framework that lets us learn from auxiliary soft-label information provided by a human expert is a promising new direction for learning classification models from expert labels, reducing the time and cost needed to label data.

Multi-Residential Activity Labelling in Smart Homes with Wearable Tags Using BLE Technology

PubMed Central

Mokhtari, Ghassem; Zhang, Qing; Karunanithi, Mohanraj

2018-01-01

Smart home platforms show promising outcomes to provide a better quality of life for residents in their homes. One of the main challenges that exists with these platforms in multi-residential houses is activity labeling. As most of the activity sensors do not provide any information regarding the identity of the person who triggers them, it is difficult to label the sensor events in multi-residential smart homes. To deal with this challenge, individual localization in different areas can be a promising solution. The localization information can be used to automatically label the activity sensor data to individuals. Bluetooth low energy (BLE) is a promising technology for this application due to how easy it is to implement and its low energy footprint. In this approach, individuals wear a tag that broadcasts its unique identity (ID) in certain time intervals, while fixed scanners listen to the broadcasting packet to localize the tag and the individual. However, the localization accuracy of this method depends greatly on different settings of broadcasting signal strength, and the time interval of BLE tags. To achieve the best localization accuracy, this paper studies the impacts of different advertising time intervals and power levels, and proposes an efficient and applicable algorithm to select optimal value settings of BLE sensors. Moreover, it proposes an automatic activity labeling method, through integrating BLE localization information and ambient sensor data. The applicability and effectiveness of the proposed structure is also demonstrated in a real multi-resident smart home scenario. PMID:29562666

Multi-Residential Activity Labelling in Smart Homes with Wearable Tags Using BLE Technology.

PubMed

Mokhtari, Ghassem; Anvari-Moghaddam, Amjad; Zhang, Qing; Karunanithi, Mohanraj

2018-03-19

Smart home platforms show promising outcomes to provide a better quality of life for residents in their homes. One of the main challenges that exists with these platforms in multi-residential houses is activity labeling. As most of the activity sensors do not provide any information regarding the identity of the person who triggers them, it is difficult to label the sensor events in multi-residential smart homes. To deal with this challenge, individual localization in different areas can be a promising solution. The localization information can be used to automatically label the activity sensor data to individuals. Bluetooth low energy (BLE) is a promising technology for this application due to how easy it is to implement and its low energy footprint. In this approach, individuals wear a tag that broadcasts its unique identity (ID) in certain time intervals, while fixed scanners listen to the broadcasting packet to localize the tag and the individual. However, the localization accuracy of this method depends greatly on different settings of broadcasting signal strength, and the time interval of BLE tags. To achieve the best localization accuracy, this paper studies the impacts of different advertising time intervals and power levels, and proposes an efficient and applicable algorithm to select optimal value settings of BLE sensors. Moreover, it proposes an automatic activity labeling method, through integrating BLE localization information and ambient sensor data. The applicability and effectiveness of the proposed structure is also demonstrated in a real multi-resident smart home scenario.

Tooth labeling in cone-beam CT using deep convolutional neural network for forensic identification

NASA Astrophysics Data System (ADS)

Miki, Yuma; Muramatsu, Chisako; Hayashi, Tatsuro; Zhou, Xiangrong; Hara, Takeshi; Katsumata, Akitoshi; Fujita, Hiroshi

2017-03-01

In large disasters, dental record plays an important role in forensic identification. However, filing dental charts for corpses is not an easy task for general dentists. Moreover, it is laborious and time-consuming work in cases of large scale disasters. We have been investigating a tooth labeling method on dental cone-beam CT images for the purpose of automatic filing of dental charts. In our method, individual tooth in CT images are detected and classified into seven tooth types using deep convolutional neural network. We employed the fully convolutional network using AlexNet architecture for detecting each tooth and applied our previous method using regular AlexNet for classifying the detected teeth into 7 tooth types. From 52 CT volumes obtained by two imaging systems, five images each were randomly selected as test data, and the remaining 42 cases were used as training data. The result showed the tooth detection accuracy of 77.4% with the average false detection of 5.8 per image. The result indicates the potential utility of the proposed method for automatic recording of dental information.

Label-free optical lymphangiography: development of an automatic segmentation method applied to optical coherence tomography to visualize lymphatic vessels using Hessian filters

PubMed Central

Yousefi, Siavash; Qin, Jia; Zhi, Zhongwei

2013-01-01

Abstract. Lymphatic vessels are a part of the circulatory system that collect plasma and other substances that have leaked from the capillaries into interstitial fluid (lymph) and transport lymph back to the circulatory system. Since lymph is transparent, lymphatic vessels appear as dark hallow vessel-like regions in optical coherence tomography (OCT) cross sectional images. We propose an automatic method to segment lymphatic vessel lumen from OCT structural cross sections using eigenvalues of Hessian filters. Compared to the existing method based on intensity threshold, Hessian filters are more selective on vessel shape and less sensitive to intensity variations and noise. Using this segmentation technique along with optical micro-angiography allows label-free noninvasive simultaneous visualization of blood and lymphatic vessels in vivo. Lymphatic vessels play an important role in cancer, immune system response, inflammatory disease, wound healing and tissue regeneration. Development of imaging techniques and visualization tools for lymphatic vessels is valuable in understanding the mechanisms and studying therapeutic methods in related disease and tissue response. PMID:23922124

Automatic detection of spiculation of pulmonary nodules in computed tomography images

NASA Astrophysics Data System (ADS)

Ciompi, F.; Jacobs, C.; Scholten, E. T.; van Riel, S. J.; W. Wille, M. M.; Prokop, M.; van Ginneken, B.

2015-03-01

We present a fully automatic method for the assessment of spiculation of pulmonary nodules in low-dose Computed Tomography (CT) images. Spiculation is considered as one of the indicators of nodule malignancy and an important feature to assess in order to decide on a patient-tailored follow-up procedure. For this reason, lung cancer screening scenario would benefit from the presence of a fully automatic system for the assessment of spiculation. The presented framework relies on the fact that spiculated nodules mainly differ from non-spiculated ones in their morphology. In order to discriminate the two categories, information on morphology is captured by sampling intensity profiles along circular patterns on spherical surfaces centered on the nodule, in a multi-scale fashion. Each intensity profile is interpreted as a periodic signal, where the Fourier transform is applied, obtaining a spectrum. A library of spectra is created by clustering data via unsupervised learning. The centroids of the clusters are used to label back each spectrum in the sampling pattern. A compact descriptor encoding the nodule morphology is obtained as the histogram of labels along all the spherical surfaces and used to classify spiculated nodules via supervised learning. We tested our approach on a set of nodules from the Danish Lung Cancer Screening Trial (DLCST) dataset. Our results show that the proposed method outperforms other 3-D descriptors of morphology in the automatic assessment of spiculation.

Automatic textual annotation of video news based on semantic visual object extraction

NASA Astrophysics Data System (ADS)

Boujemaa, Nozha; Fleuret, Francois; Gouet, Valerie; Sahbi, Hichem

2003-12-01

In this paper, we present our work for automatic generation of textual metadata based on visual content analysis of video news. We present two methods for semantic object detection and recognition from a cross modal image-text thesaurus. These thesaurus represent a supervised association between models and semantic labels. This paper is concerned with two semantic objects: faces and Tv logos. In the first part, we present our work for efficient face detection and recogniton with automatic name generation. This method allows us also to suggest the textual annotation of shots close-up estimation. On the other hand, we were interested to automatically detect and recognize different Tv logos present on incoming different news from different Tv Channels. This work was done jointly with the French Tv Channel TF1 within the "MediaWorks" project that consists on an hybrid text-image indexing and retrieval plateform for video news.

A Patch-Based Approach for the Segmentation of Pathologies: Application to Glioma Labelling.

PubMed

Cordier, Nicolas; Delingette, Herve; Ayache, Nicholas

2016-04-01

In this paper, we describe a novel and generic approach to address fully-automatic segmentation of brain tumors by using multi-atlas patch-based voting techniques. In addition to avoiding the local search window assumption, the conventional patch-based framework is enhanced through several simple procedures: an improvement of the training dataset in terms of both label purity and intensity statistics, augmented features to implicitly guide the nearest-neighbor-search, multi-scale patches, invariance to cube isometries, stratification of the votes with respect to cases and labels. A probabilistic model automatically delineates regions of interest enclosing high-probability tumor volumes, which allows the algorithm to achieve highly competitive running time despite minimal processing power and resources. This method was evaluated on Multimodal Brain Tumor Image Segmentation challenge datasets. State-of-the-art results are achieved, with a limited learning stage thus restricting the risk of overfit. Moreover, segmentation smoothness does not involve any post-processing.

Development and evaluation of an automatic labeling technique for spring small grains

NASA Technical Reports Server (NTRS)

Crist, E. P.; Malila, W. A. (Principal Investigator)

1981-01-01

A labeling technique is described which seeks to associate a sampling entity with a particular crop or crop group based on similarity of growing season and temporal-spectral patterns of development. Human analyst provide contextual information, after which labeling decisions are made automatically. Results of a test of the technique on a large, multi-year data set are reported. Grain labeling accuracies are similar to those achieved by human analysis techniques, while non-grain accuracies are lower. Recommendations for improvments and implications of the test results are discussed.

A Probabilistic Framework for Peptide and Protein Quantification from Data-Dependent and Data-Independent LC-MS Proteomics Experiments

PubMed Central

Richardson, Keith; Denny, Richard; Hughes, Chris; Skilling, John; Sikora, Jacek; Dadlez, Michał; Manteca, Angel; Jung, Hye Ryung; Jensen, Ole Nørregaard; Redeker, Virginie; Melki, Ronald; Langridge, James I.; Vissers, Johannes P.C.

2013-01-01

A probability-based quantification framework is presented for the calculation of relative peptide and protein abundance in label-free and label-dependent LC-MS proteomics data. The results are accompanied by credible intervals and regulation probabilities. The algorithm takes into account data uncertainties via Poisson statistics modified by a noise contribution that is determined automatically during an initial normalization stage. Protein quantification relies on assignments of component peptides to the acquired data. These assignments are generally of variable reliability and may not be present across all of the experiments comprising an analysis. It is also possible for a peptide to be identified to more than one protein in a given mixture. For these reasons the algorithm accepts a prior probability of peptide assignment for each intensity measurement. The model is constructed in such a way that outliers of any type can be automatically reweighted. Two discrete normalization methods can be employed. The first method is based on a user-defined subset of peptides, while the second method relies on the presence of a dominant background of endogenous peptides for which the concentration is assumed to be unaffected. Normalization is performed using the same computational and statistical procedures employed by the main quantification algorithm. The performance of the algorithm will be illustrated on example data sets, and its utility demonstrated for typical proteomics applications. The quantification algorithm supports relative protein quantification based on precursor and product ion intensities acquired by means of data-dependent methods, originating from all common isotopically-labeled approaches, as well as label-free ion intensity-based data-independent methods. PMID:22871168

A direct morphometric comparison of five labeling protocols for multi-atlas driven automatic segmentation of the hippocampus in Alzheimer's disease.

PubMed

Nestor, Sean M; Gibson, Erin; Gao, Fu-Qiang; Kiss, Alex; Black, Sandra E

2013-02-01

Hippocampal volumetry derived from structural MRI is increasingly used to delineate regions of interest for functional measurements, assess efficacy in therapeutic trials of Alzheimer's disease (AD) and has been endorsed by the new AD diagnostic guidelines as a radiological marker of disease progression. Unfortunately, morphological heterogeneity in AD can prevent accurate demarcation of the hippocampus. Recent developments in automated volumetry commonly use multi-template fusion driven by expert manual labels, enabling highly accurate and reproducible segmentation in disease and healthy subjects. However, there are several protocols to define the hippocampus anatomically in vivo, and the method used to generate atlases may impact automatic accuracy and sensitivity - particularly in pathologically heterogeneous samples. Here we report a fully automated segmentation technique that provides a robust platform to directly evaluate both technical and biomarker performance in AD among anatomically unique labeling protocols. For the first time we test head-to-head the performance of five common hippocampal labeling protocols for multi-atlas based segmentation, using both the Sunnybrook Longitudinal Dementia Study and the entire Alzheimer's Disease Neuroimaging Initiative 1 (ADNI-1) baseline and 24-month dataset. We based these atlas libraries on the protocols of (Haller et al., 1997; Killiany et al., 1993; Malykhin et al., 2007; Pantel et al., 2000; Pruessner et al., 2000), and a single operator performed all manual tracings to generate de facto "ground truth" labels. All methods distinguished between normal elders, mild cognitive impairment (MCI), and AD in the expected directions, and showed comparable correlations with measures of episodic memory performance. Only more inclusive protocols distinguished between stable MCI and MCI-to-AD converters, and had slightly better associations with episodic memory. Moreover, we demonstrate that protocols including more posterior anatomy and dorsal white matter compartments furnish the best voxel-overlap accuracies (Dice Similarity Coefficient=0.87-0.89), compared to expert manual tracings, and achieve the smallest sample sizes required to power clinical trials in MCI and AD. The greatest distribution of errors was localized to the caudal hippocampus and the alveus-fimbria compartment when these regions were excluded. The definition of the medial body did not significantly alter accuracy among more comprehensive protocols. Voxel-overlap accuracies between automatic and manual labels were lower for the more pathologically heterogeneous Sunnybrook study in comparison to the ADNI-1 sample. Finally, accuracy among protocols appears to significantly differ the most in AD subjects compared to MCI and normal elders. Together, these results suggest that selection of a candidate protocol for fully automatic multi-template based segmentation in AD can influence both segmentation accuracy when compared to expert manual labels and performance as a biomarker in MCI and AD. Copyright © 2012 Elsevier Inc. All rights reserved.

A Direct Morphometric Comparison of Five Labeling Protocols for Multi-Atlas Driven Automatic Segmentation of the Hippocampus in Alzheimer’s Disease

PubMed Central

Nestor, Sean M.; Gibson, Erin; Gao, Fu-Qiang; Kiss, Alex; Black, Sandra E.

2012-01-01

Hippocampal volumetry derived from structural MRI is increasingly used to delineate regions of interest for functional measurements, assess efficacy in therapeutic trials of Alzheimer’s disease (AD) and has been endorsed by the new AD diagnostic guidelines as a radiological marker of disease progression. Unfortunately, morphological heterogeneity in AD can prevent accurate demarcation of the hippocampus. Recent developments in automated volumetry commonly use multitemplate fusion driven by expert manual labels, enabling highly accurate and reproducible segmentation in disease and healthy subjects. However, there are several protocols to define the hippocampus anatomically in vivo, and the method used to generate atlases may impact automatic accuracy and sensitivity – particularly in pathologically heterogeneous samples. Here we report a fully automated segmentation technique that provides a robust platform to directly evaluate both technical and biomarker performance in AD among anatomically unique labeling protocols. For the first time we test head-to-head the performance of five common hippocampal labeling protocols for multi-atlas based segmentation, using both the Sunnybrook Longitudinal Dementia Study and the entire Alzheimer’s Disease Neuroimaging Initiative 1 (ADNI-1) baseline and 24-month dataset. We based these atlas libraries on the protocols of (Haller et al., 1997; Killiany et al., 1993; Malykhin et al., 2007; Pantel et al., 2000; Pruessner et al., 2000), and a single operator performed all manual tracings to generate de facto “ground truth” labels. All methods distinguished between normal elders, mild cognitive impairment (MCI), and AD in the expected directions, and showed comparable correlations with measures of episodic memory performance. Only more inclusive protocols distinguished between stable MCI and MCI-to-AD converters, and had slightly better associations with episodic memory. Moreover, we demonstrate that protocols including more posterior anatomy and dorsal white matter compartments furnish the best voxel-overlap accuracies (Dice Similarity Coefficient = 0.87–0.89), compared to expert manual tracings, and achieve the smallest sample sizes required to power clinical trials in MCI and AD. The greatest distribution of errors was localized to the caudal hippocampus and alveus-fimbria compartment when these regions were excluded. The definition of the medial body did not significantly alter accuracy among more comprehensive protocols. Voxel-overlap accuracies between automatic and manual labels were lower for the more pathologically heterogeneous Sunnybrook study in comparison to the ADNI-1 sample. Finally, accuracy among protocols appears to significantly differ the most in AD subjects compared to MCI and normal elders. Together, these results suggest that selection of a candidate protocol for fully automatic multi-template based segmentation in AD can influence both segmentation accuracy when compared to expert manual labels and performance as a biomarker in MCI and AD. PMID:23142652

Automatic measurement of voice onset time using discriminative structured prediction.

PubMed

Sonderegger, Morgan; Keshet, Joseph

2012-12-01

A discriminative large-margin algorithm for automatic measurement of voice onset time (VOT) is described, considered as a case of predicting structured output from speech. Manually labeled data are used to train a function that takes as input a speech segment of an arbitrary length containing a voiceless stop, and outputs its VOT. The function is explicitly trained to minimize the difference between predicted and manually measured VOT; it operates on a set of acoustic feature functions designed based on spectral and temporal cues used by human VOT annotators. The algorithm is applied to initial voiceless stops from four corpora, representing different types of speech. Using several evaluation methods, the algorithm's performance is near human intertranscriber reliability, and compares favorably with previous work. Furthermore, the algorithm's performance is minimally affected by training and testing on different corpora, and remains essentially constant as the amount of training data is reduced to 50-250 manually labeled examples, demonstrating the method's practical applicability to new datasets.

Image annotation based on positive-negative instances learning

NASA Astrophysics Data System (ADS)

Zhang, Kai; Hu, Jiwei; Liu, Quan; Lou, Ping

2017-07-01

Automatic image annotation is now a tough task in computer vision, the main sense of this tech is to deal with managing the massive image on the Internet and assisting intelligent retrieval. This paper designs a new image annotation model based on visual bag of words, using the low level features like color and texture information as well as mid-level feature as SIFT, and mixture the pic2pic, label2pic and label2label correlation to measure the correlation degree of labels and images. We aim to prune the specific features for each single label and formalize the annotation task as a learning process base on Positive-Negative Instances Learning. Experiments are performed using the Corel5K Dataset, and provide a quite promising result when comparing with other existing methods.

Automated annotation of functional imaging experiments via multi-label classification

PubMed Central

Turner, Matthew D.; Chakrabarti, Chayan; Jones, Thomas B.; Xu, Jiawei F.; Fox, Peter T.; Luger, George F.; Laird, Angela R.; Turner, Jessica A.

2013-01-01

Identifying the experimental methods in human neuroimaging papers is important for grouping meaningfully similar experiments for meta-analyses. Currently, this can only be done by human readers. We present the performance of common machine learning (text mining) methods applied to the problem of automatically classifying or labeling this literature. Labeling terms are from the Cognitive Paradigm Ontology (CogPO), the text corpora are abstracts of published functional neuroimaging papers, and the methods use the performance of a human expert as training data. We aim to replicate the expert's annotation of multiple labels per abstract identifying the experimental stimuli, cognitive paradigms, response types, and other relevant dimensions of the experiments. We use several standard machine learning methods: naive Bayes (NB), k-nearest neighbor, and support vector machines (specifically SMO or sequential minimal optimization). Exact match performance ranged from only 15% in the worst cases to 78% in the best cases. NB methods combined with binary relevance transformations performed strongly and were robust to overfitting. This collection of results demonstrates what can be achieved with off-the-shelf software components and little to no pre-processing of raw text. PMID:24409112

Joint learning of labels and distance metric.

PubMed

Liu, Bo; Wang, Meng; Hong, Richang; Zha, Zhengjun; Hua, Xian-Sheng

2010-06-01

Machine learning algorithms frequently suffer from the insufficiency of training data and the usage of inappropriate distance metric. In this paper, we propose a joint learning of labels and distance metric (JLLDM) approach, which is able to simultaneously address the two difficulties. In comparison with the existing semi-supervised learning and distance metric learning methods that focus only on label prediction or distance metric construction, the JLLDM algorithm optimizes the labels of unlabeled samples and a Mahalanobis distance metric in a unified scheme. The advantage of JLLDM is multifold: 1) the problem of training data insufficiency can be tackled; 2) a good distance metric can be constructed with only very few training samples; and 3) no radius parameter is needed since the algorithm automatically determines the scale of the metric. Extensive experiments are conducted to compare the JLLDM approach with different semi-supervised learning and distance metric learning methods, and empirical results demonstrate its effectiveness.

Automatic segmentation of the choroid in enhanced depth imaging optical coherence tomography images.

PubMed

Tian, Jing; Marziliano, Pina; Baskaran, Mani; Tun, Tin Aung; Aung, Tin

2013-03-01

Enhanced Depth Imaging (EDI) optical coherence tomography (OCT) provides high-definition cross-sectional images of the choroid in vivo, and hence is used in many clinical studies. However, the quantification of the choroid depends on the manual labelings of two boundaries, Bruch's membrane and the choroidal-scleral interface. This labeling process is tedious and subjective of inter-observer differences, hence, automatic segmentation of the choroid layer is highly desirable. In this paper, we present a fast and accurate algorithm that could segment the choroid automatically. Bruch's membrane is detected by searching the pixel with the biggest gradient value above the retinal pigment epithelium (RPE) and the choroidal-scleral interface is delineated by finding the shortest path of the graph formed by valley pixels using Dijkstra's algorithm. The experiments comparing automatic segmentation results with the manual labelings are conducted on 45 EDI-OCT images and the average of Dice's Coefficient is 90.5%, which shows good consistency of the algorithm with the manual labelings. The processing time for each image is about 1.25 seconds.

Automatic testing and assessment of neuroanatomy using a digital brain atlas: method and development of computer- and mobile-based applications.

PubMed

Nowinski, Wieslaw L; Thirunavuukarasuu, Arumugam; Ananthasubramaniam, Anand; Chua, Beng Choon; Qian, Guoyu; Nowinska, Natalia G; Marchenko, Yevgen; Volkau, Ihar

2009-10-01

Preparation of tests and student's assessment by the instructor are time consuming. We address these two tasks in neuroanatomy education by employing a digital media application with a three-dimensional (3D), interactive, fully segmented, and labeled brain atlas. The anatomical and vascular models in the atlas are linked to Terminologia Anatomica. Because the cerebral models are fully segmented and labeled, our approach enables automatic and random atlas-derived generation of questions to test location and naming of cerebral structures. This is done in four steps: test individualization by the instructor, test taking by the students at their convenience, automatic student assessment by the application, and communication of the individual assessment to the instructor. A computer-based application with an interactive 3D atlas and a preliminary mobile-based application were developed to realize this approach. The application works in two test modes: instructor and student. In the instructor mode, the instructor customizes the test by setting the scope of testing and student performance criteria, which takes a few seconds. In the student mode, the student is tested and automatically assessed. Self-testing is also feasible at any time and pace. Our approach is automatic both with respect to test generation and student assessment. It is also objective, rapid, and customizable. We believe that this approach is novel from computer-based, mobile-based, and atlas-assisted standpoints.

Multiatlas whole heart segmentation of CT data using conditional entropy for atlas ranking and selection

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

Zhuang, Xiahai, E-mail: zhuangxiahai@sjtu.edu.cn; Qian, Xiaohua; Bai, Wenjia

Purpose: Cardiac computed tomography (CT) is widely used in clinical diagnosis of cardiovascular diseases. Whole heart segmentation (WHS) plays a vital role in developing new clinical applications of cardiac CT. However, the shape and appearance of the heart can vary greatly across different scans, making the automatic segmentation particularly challenging. The objective of this work is to develop and evaluate a multiatlas segmentation (MAS) scheme using a new atlas ranking and selection algorithm for automatic WHS of CT data. Research on different MAS strategies and their influence on WHS performance are limited. This work provides a detailed comparison study evaluatingmore » the impacts of label fusion, atlas ranking, and sizes of the atlas database on the segmentation performance. Methods: Atlases in a database were registered to the target image using a hierarchical registration scheme specifically designed for cardiac images. A subset of the atlases were selected for label fusion, according to the authors’ proposed atlas ranking criterion which evaluated the performance of each atlas by computing the conditional entropy of the target image given the propagated atlas labeling. Joint label fusion was used to combine multiple label estimates to obtain the final segmentation. The authors used 30 clinical cardiac CT angiography (CTA) images to evaluate the proposed MAS scheme and to investigate different segmentation strategies. Results: The mean WHS Dice score of the proposed MAS method was 0.918 ± 0.021, and the mean runtime for one case was 13.2 min on a workstation. This MAS scheme using joint label fusion generated significantly better Dice scores than the other label fusion strategies, including majority voting (0.901 ± 0.276, p < 0.01), locally weighted voting (0.905 ± 0.0247, p < 0.01), and probabilistic patch-based fusion (0.909 ± 0.0249, p < 0.01). In the atlas ranking study, the proposed criterion based on conditional entropy yielded a performance curve with higher WHS Dice scores compared to the conventional schemes (p < 0.03). In the atlas database study, the authors showed that the MAS using larger atlas databases generated better performance curves than the MAS using smaller ones, indicating larger atlas databases could produce more accurate segmentation. Conclusions: The authors have developed a new MAS framework for automatic WHS of CTA and investigated alternative implementations of MAS. With the proposed atlas ranking algorithm and joint label fusion, the MAS scheme is able to generate accurate segmentation within practically acceptable computation time. This method can be useful for the development of new clinical applications of cardiac CT.« less

The QUASAR reproducibility study, Part II: Results from a multi-center Arterial Spin Labeling test-retest study.

PubMed

Petersen, Esben Thade; Mouridsen, Kim; Golay, Xavier

2010-01-01

Arterial Spin Labeling (ASL) is a method to measure perfusion using magnetically labeled blood water as an endogenous tracer. Being fully non-invasive, this technique is attractive for longitudinal studies of cerebral blood flow in healthy and diseased individuals, or as a surrogate marker of metabolism. So far, ASL has been restricted mostly to specialist centers due to a generally low SNR of the method and potential issues with user-dependent analysis needed to obtain quantitative measurement of cerebral blood flow (CBF). Here, we evaluated a particular implementation of ASL (called Quantitative STAR labeling of Arterial Regions or QUASAR), a method providing user independent quantification of CBF in a large test-retest study across sites from around the world, dubbed "The QUASAR reproducibility study". Altogether, 28 sites located in Asia, Europe and North America participated and a total of 284 healthy volunteers were scanned. Minimal operator dependence was assured by using an automatic planning tool and its accuracy and potential usefulness in multi-center trials was evaluated as well. Accurate repositioning between sessions was achieved with the automatic planning tool showing mean displacements of 1.87+/-0.95 mm and rotations of 1.56+/-0.66 degrees . Mean gray matter CBF was 47.4+/-7.5 [ml/100 g/min] with a between-subject standard variation SD(b)=5.5 [ml/100 g/min] and a within-subject standard deviation SD(w)=4.7 [ml/100 g/min]. The corresponding repeatability was 13.0 [ml/100 g/min] and was found to be within the range of previous studies.

Prioritization of brain MRI volumes using medical image perception model and tumor region segmentation.

PubMed

Mehmood, Irfan; Ejaz, Naveed; Sajjad, Muhammad; Baik, Sung Wook

2013-10-01

The objective of the present study is to explore prioritization methods in diagnostic imaging modalities to automatically determine the contents of medical images. In this paper, we propose an efficient prioritization of brain MRI. First, the visual perception of the radiologists is adapted to identify salient regions. Then this saliency information is used as an automatic label for accurate segmentation of brain lesion to determine the scientific value of that image. The qualitative and quantitative results prove that the rankings generated by the proposed method are closer to the rankings created by radiologists. Copyright © 2013 Elsevier Ltd. All rights reserved.

Multiatlas whole heart segmentation of CT data using conditional entropy for atlas ranking and selection.

PubMed

Zhuang, Xiahai; Bai, Wenjia; Song, Jingjing; Zhan, Songhua; Qian, Xiaohua; Shi, Wenzhe; Lian, Yanyun; Rueckert, Daniel

2015-07-01

Cardiac computed tomography (CT) is widely used in clinical diagnosis of cardiovascular diseases. Whole heart segmentation (WHS) plays a vital role in developing new clinical applications of cardiac CT. However, the shape and appearance of the heart can vary greatly across different scans, making the automatic segmentation particularly challenging. The objective of this work is to develop and evaluate a multiatlas segmentation (MAS) scheme using a new atlas ranking and selection algorithm for automatic WHS of CT data. Research on different MAS strategies and their influence on WHS performance are limited. This work provides a detailed comparison study evaluating the impacts of label fusion, atlas ranking, and sizes of the atlas database on the segmentation performance. Atlases in a database were registered to the target image using a hierarchical registration scheme specifically designed for cardiac images. A subset of the atlases were selected for label fusion, according to the authors' proposed atlas ranking criterion which evaluated the performance of each atlas by computing the conditional entropy of the target image given the propagated atlas labeling. Joint label fusion was used to combine multiple label estimates to obtain the final segmentation. The authors used 30 clinical cardiac CT angiography (CTA) images to evaluate the proposed MAS scheme and to investigate different segmentation strategies. The mean WHS Dice score of the proposed MAS method was 0.918 ± 0.021, and the mean runtime for one case was 13.2 min on a workstation. This MAS scheme using joint label fusion generated significantly better Dice scores than the other label fusion strategies, including majority voting (0.901 ± 0.276, p < 0.01), locally weighted voting (0.905 ± 0.0247, p < 0.01), and probabilistic patch-based fusion (0.909 ± 0.0249, p < 0.01). In the atlas ranking study, the proposed criterion based on conditional entropy yielded a performance curve with higher WHS Dice scores compared to the conventional schemes (p < 0.03). In the atlas database study, the authors showed that the MAS using larger atlas databases generated better performance curves than the MAS using smaller ones, indicating larger atlas databases could produce more accurate segmentation. The authors have developed a new MAS framework for automatic WHS of CTA and investigated alternative implementations of MAS. With the proposed atlas ranking algorithm and joint label fusion, the MAS scheme is able to generate accurate segmentation within practically acceptable computation time. This method can be useful for the development of new clinical applications of cardiac CT.

Automatic lumbar spine measurement in CT images

NASA Astrophysics Data System (ADS)

Mao, Yunxiang; Zheng, Dong; Liao, Shu; Peng, Zhigang; Yan, Ruyi; Liu, Junhua; Dong, Zhongxing; Gong, Liyan; Zhou, Xiang Sean; Zhan, Yiqiang; Fei, Jun

2017-03-01

Accurate lumbar spine measurement in CT images provides an essential way for quantitative spinal diseases analysis such as spondylolisthesis and scoliosis. In today's clinical workflow, the measurements are manually performed by radiologists and surgeons, which is time consuming and irreproducible. Therefore, automatic and accurate lumbar spine measurement algorithm becomes highly desirable. In this study, we propose a method to automatically calculate five different lumbar spine measurements in CT images. There are three main stages of the proposed method: First, a learning based spine labeling method, which integrates both the image appearance and spine geometry information, is used to detect lumbar and sacrum vertebrae in CT images. Then, a multiatlases based image segmentation method is used to segment each lumbar vertebra and the sacrum based on the detection result. Finally, measurements are derived from the segmentation result of each vertebra. Our method has been evaluated on 138 spinal CT scans to automatically calculate five widely used clinical spine measurements. Experimental results show that our method can achieve more than 90% success rates across all the measurements. Our method also significantly improves the measurement efficiency compared to manual measurements. Besides benefiting the routine clinical diagnosis of spinal diseases, our method also enables the large scale data analytics for scientific and clinical researches.

Analysis of Technique to Extract Data from the Web for Improved Performance

NASA Astrophysics Data System (ADS)

Gupta, Neena; Singh, Manish

2010-11-01

The World Wide Web rapidly guides the world into a newly amazing electronic world, where everyone can publish anything in electronic form and extract almost all the information. Extraction of information from semi structured or unstructured documents, such as web pages, is a useful yet complex task. Data extraction, which is important for many applications, extracts the records from the HTML files automatically. Ontologies can achieve a high degree of accuracy in data extraction. We analyze method for data extraction OBDE (Ontology-Based Data Extraction), which automatically extracts the query result records from the web with the help of agents. OBDE first constructs an ontology for a domain according to information matching between the query interfaces and query result pages from different web sites within the same domain. Then, the constructed domain ontology is used during data extraction to identify the query result section in a query result page and to align and label the data values in the extracted records. The ontology-assisted data extraction method is fully automatic and overcomes many of the deficiencies of current automatic data extraction methods.

Adaptive and automatic red blood cell counting method based on microscopic hyperspectral imaging technology

NASA Astrophysics Data System (ADS)

Liu, Xi; Zhou, Mei; Qiu, Song; Sun, Li; Liu, Hongying; Li, Qingli; Wang, Yiting

2017-12-01

Red blood cell counting, as a routine examination, plays an important role in medical diagnoses. Although automated hematology analyzers are widely used, manual microscopic examination by a hematologist or pathologist is still unavoidable, which is time-consuming and error-prone. This paper proposes a full-automatic red blood cell counting method which is based on microscopic hyperspectral imaging of blood smears and combines spatial and spectral information to achieve high precision. The acquired hyperspectral image data of the blood smear in the visible and near-infrared spectral range are firstly preprocessed, and then a quadratic blind linear unmixing algorithm is used to get endmember abundance images. Based on mathematical morphological operation and an adaptive Otsu’s method, a binaryzation process is performed on the abundance images. Finally, the connected component labeling algorithm with magnification-based parameter setting is applied to automatically select the binary images of red blood cell cytoplasm. Experimental results show that the proposed method can perform well and has potential for clinical applications.

Eye-tracking for clinical decision support: A method to capture automatically what physicians are viewing in the EMR.

PubMed

King, Andrew J; Hochheiser, Harry; Visweswaran, Shyam; Clermont, Gilles; Cooper, Gregory F

2017-01-01

Eye-tracking is a valuable research tool that is used in laboratory and limited field environments. We take steps toward developing methods that enable widespread adoption of eye-tracking and its real-time application in clinical decision support. Eye-tracking will enhance awareness and enable intelligent views, more precise alerts, and other forms of decision support in the Electronic Medical Record (EMR). We evaluated a low-cost eye-tracking device and found the device's accuracy to be non-inferior to a more expensive device. We also developed and evaluated an automatic method for mapping eye-tracking data to interface elements in the EMR (e.g., a displayed laboratory test value). Mapping was 88% accurate across the six participants in our experiment. Finally, we piloted the use of the low-cost device and the automatic mapping method to label training data for a Learning EMR (LEMR) which is a system that highlights the EMR elements a physician is predicted to use.

Eye-tracking for clinical decision support: A method to capture automatically what physicians are viewing in the EMR

PubMed Central

King, Andrew J.; Hochheiser, Harry; Visweswaran, Shyam; Clermont, Gilles; Cooper, Gregory F.

2017-01-01

Eye-tracking is a valuable research tool that is used in laboratory and limited field environments. We take steps toward developing methods that enable widespread adoption of eye-tracking and its real-time application in clinical decision support. Eye-tracking will enhance awareness and enable intelligent views, more precise alerts, and other forms of decision support in the Electronic Medical Record (EMR). We evaluated a low-cost eye-tracking device and found the device’s accuracy to be non-inferior to a more expensive device. We also developed and evaluated an automatic method for mapping eye-tracking data to interface elements in the EMR (e.g., a displayed laboratory test value). Mapping was 88% accurate across the six participants in our experiment. Finally, we piloted the use of the low-cost device and the automatic mapping method to label training data for a Learning EMR (LEMR) which is a system that highlights the EMR elements a physician is predicted to use. PMID:28815151

An automatic multi-atlas prostate segmentation in MRI using a multiscale representation and a label fusion strategy

NASA Astrophysics Data System (ADS)

Álvarez, Charlens; Martínez, Fabio; Romero, Eduardo

2015-01-01

The pelvic magnetic Resonance images (MRI) are used in Prostate cancer radiotherapy (RT), a process which is part of the radiation planning. Modern protocols require a manual delineation, a tedious and variable activity that may take about 20 minutes per patient, even for trained experts. That considerable time is an important work ow burden in most radiological services. Automatic or semi-automatic methods might improve the efficiency by decreasing the measure times while conserving the required accuracy. This work presents a fully automatic atlas- based segmentation strategy that selects the more similar templates for a new MRI using a robust multi-scale SURF analysis. Then a new segmentation is achieved by a linear combination of the selected templates, which are previously non-rigidly registered towards the new image. The proposed method shows reliable segmentations, obtaining an average DICE Coefficient of 79%, when comparing with the expert manual segmentation, under a leave-one-out scheme with the training database.

Porosity estimation by semi-supervised learning with sparsely available labeled samples

NASA Astrophysics Data System (ADS)

Lima, Luiz Alberto; Görnitz, Nico; Varella, Luiz Eduardo; Vellasco, Marley; Müller, Klaus-Robert; Nakajima, Shinichi

2017-09-01

This paper addresses the porosity estimation problem from seismic impedance volumes and porosity samples located in a small group of exploratory wells. Regression methods, trained on the impedance as inputs and the porosity as output labels, generally suffer from extremely expensive (and hence sparsely available) porosity samples. To optimally make use of the valuable porosity data, a semi-supervised machine learning method was proposed, Transductive Conditional Random Field Regression (TCRFR), showing good performance (Görnitz et al., 2017). TCRFR, however, still requires more labeled data than those usually available, which creates a gap when applying the method to the porosity estimation problem in realistic situations. In this paper, we aim to fill this gap by introducing two graph-based preprocessing techniques, which adapt the original TCRFR for extremely weakly supervised scenarios. Our new method outperforms the previous automatic estimation methods on synthetic data and provides a comparable result to the manual labored, time-consuming geostatistics approach on real data, proving its potential as a practical industrial tool.

Deep Learning Methods for Quantifying Invasive Benthic Species in the Great Lakes

NASA Astrophysics Data System (ADS)

Billings, G.; Skinner, K.; Johnson-Roberson, M.

2017-12-01

In recent decades, invasive species such as the round goby and dreissenid mussels have greatly impacted the Great Lakes ecosystem. It is critical to monitor these species, model their distribution, and quantify the impacts on the native fisheries and surrounding ecosystem in order to develop an effective management response. However, data collection in underwater environments is challenging and expensive. Furthermore, the round goby is typically found in rocky habitats, which are inaccessible to standard survey techniques such as bottom trawling. In this work we propose a robotic system for visual data collection to automatically detect and quantify invasive round gobies and mussels in the Great Lakes. Robotic platforms equipped with cameras can perform efficient, cost-effective, low-bias benthic surveys. This data collection can be further optimized through automatic detection and annotation of the target species. Deep learning methods have shown success in image recognition tasks. However, these methods often rely on a labelled training dataset, with up to millions of labelled images. Hand labeling large numbers of images is expensive and often impracticable. Furthermore, data collected in the field may be sparse when only considering images that contain the objects of interest. It is easier to collect dense, clean data in controlled lab settings, but this data is not a realistic representation of real field environments. In this work, we propose a deep learning approach to generate a large set of labelled training data realistic of underwater environments in the field. To generate these images, first we draw random sample images of individual fish and mussels from a library of images captured in a controlled lab environment. Next, these randomly drawn samples will be automatically merged into natural background images. Finally, we will use a generative adversarial network (GAN) that incorporates constraints of the physical model of underwater light propagation to simulate the process of underwater image formation in various water conditions. The output of the GAN will be realistic looking annotated underwater images. This generated dataset of images will be used to train a classifier to identify round gobies and mussels in order to measure the biomass and abundance of these invasive species in the Great Lakes.

Automatic recognition of 3D GGO CT imaging signs through the fusion of hybrid resampling and layer-wise fine-tuning CNNs.

PubMed

Han, Guanghui; Liu, Xiabi; Zheng, Guangyuan; Wang, Murong; Huang, Shan

2018-06-06

Ground-glass opacity (GGO) is a common CT imaging sign on high-resolution CT, which means the lesion is more likely to be malignant compared to common solid lung nodules. The automatic recognition of GGO CT imaging signs is of great importance for early diagnosis and possible cure of lung cancers. The present GGO recognition methods employ traditional low-level features and system performance improves slowly. Considering the high-performance of CNN model in computer vision field, we proposed an automatic recognition method of 3D GGO CT imaging signs through the fusion of hybrid resampling and layer-wise fine-tuning CNN models in this paper. Our hybrid resampling is performed on multi-views and multi-receptive fields, which reduces the risk of missing small or large GGOs by adopting representative sampling panels and processing GGOs with multiple scales simultaneously. The layer-wise fine-tuning strategy has the ability to obtain the optimal fine-tuning model. Multi-CNN models fusion strategy obtains better performance than any single trained model. We evaluated our method on the GGO nodule samples in publicly available LIDC-IDRI dataset of chest CT scans. The experimental results show that our method yields excellent results with 96.64% sensitivity, 71.43% specificity, and 0.83 F1 score. Our method is a promising approach to apply deep learning method to computer-aided analysis of specific CT imaging signs with insufficient labeled images. Graphical abstract We proposed an automatic recognition method of 3D GGO CT imaging signs through the fusion of hybrid resampling and layer-wise fine-tuning CNN models in this paper. Our hybrid resampling reduces the risk of missing small or large GGOs by adopting representative sampling panels and processing GGOs with multiple scales simultaneously. The layer-wise fine-tuning strategy has ability to obtain the optimal fine-tuning model. Our method is a promising approach to apply deep learning method to computer-aided analysis of specific CT imaging signs with insufficient labeled images.

A Learning-Based Wrapper Method to Correct Systematic Errors in Automatic Image Segmentation: Consistently Improved Performance in Hippocampus, Cortex and Brain Segmentation

PubMed Central

Wang, Hongzhi; Das, Sandhitsu R.; Suh, Jung Wook; Altinay, Murat; Pluta, John; Craige, Caryne; Avants, Brian; Yushkevich, Paul A.

2011-01-01

We propose a simple but generally applicable approach to improving the accuracy of automatic image segmentation algorithms relative to manual segmentations. The approach is based on the hypothesis that a large fraction of the errors produced by automatic segmentation are systematic, i.e., occur consistently from subject to subject, and serves as a wrapper method around a given host segmentation method. The wrapper method attempts to learn the intensity, spatial and contextual patterns associated with systematic segmentation errors produced by the host method on training data for which manual segmentations are available. The method then attempts to correct such errors in segmentations produced by the host method on new images. One practical use of the proposed wrapper method is to adapt existing segmentation tools, without explicit modification, to imaging data and segmentation protocols that are different from those on which the tools were trained and tuned. An open-source implementation of the proposed wrapper method is provided, and can be applied to a wide range of image segmentation problems. The wrapper method is evaluated with four host brain MRI segmentation methods: hippocampus segmentation using FreeSurfer (Fischl et al., 2002); hippocampus segmentation using multi-atlas label fusion (Artaechevarria et al., 2009); brain extraction using BET (Smith, 2002); and brain tissue segmentation using FAST (Zhang et al., 2001). The wrapper method generates 72%, 14%, 29% and 21% fewer erroneously segmented voxels than the respective host segmentation methods. In the hippocampus segmentation experiment with multi-atlas label fusion as the host method, the average Dice overlap between reference segmentations and segmentations produced by the wrapper method is 0.908 for normal controls and 0.893 for patients with mild cognitive impairment. Average Dice overlaps of 0.964, 0.905 and 0.951 are obtained for brain extraction, white matter segmentation and gray matter segmentation, respectively. PMID:21237273

Automatic Lumbar Spondylolisthesis Measurement in CT Images.

PubMed

Liao, Shu; Zhan, Yiqiang; Dong, Zhongxing; Yan, Ruyi; Gong, Liyan; Zhou, Xiang Sean; Salganicoff, Marcos; Fei, Jun

2016-07-01

Lumbar spondylolisthesis is one of the most common spinal diseases. It is caused by the anterior shift of a lumbar vertebrae relative to subjacent vertebrae. In current clinical practices, staging of spondylolisthesis is often conducted in a qualitative way. Although meyerding grading opens the door to stage spondylolisthesis in a more quantitative way, it relies on the manual measurement, which is time consuming and irreproducible. Thus, an automatic measurement algorithm becomes desirable for spondylolisthesis diagnosis and staging. However, there are two challenges. 1) Accurate detection of the most anterior and posterior points on the superior and inferior surfaces of each lumbar vertebrae. Due to the small size of the vertebrae, slight errors of detection may lead to significant measurement errors, hence, wrong disease stages. 2) Automatic localize and label each lumbar vertebrae is required to provide the semantic meaning of the measurement. It is difficult since different lumbar vertebraes have high similarity of both shape and image appearance. To resolve these challenges, a new auto measurement framework is proposed with two major contributions: First, a learning based spine labeling method that integrates both the image appearance and spine geometry information is designed to detect lumbar vertebrae. Second, a hierarchical method using both the population information from atlases and domain-specific information in the target image is proposed for most anterior and posterior points positioning. Validated on 258 CT spondylolisthesis patients, our method shows very similar results to manual measurements by radiologists and significantly increases the measurement efficiency.

Kit for the rapid preparation of .sup.99m Tc red blood cells

DOEpatents

Richards, Powell; Smith, Terry D.

1976-01-01

A method and sample kit for the preparation of .sup.99m Tc-labeled red blood cells in a closed, sterile system. A partially evacuated tube, containing a freeze-dried stannous citrate formulation with heparin as an anticoagulant, allows whole blood to be automatically drawn from the patient. The radioisotope is added at the end of the labeling sequence to minimize operator exposure. Consistent 97% yields in 20 minutes are obtained with small blood samples. Freeze-dried kits have remained stable after five months.

Vessel segmentation in 4D arterial spin labeling magnetic resonance angiography images of the brain

NASA Astrophysics Data System (ADS)

Phellan, Renzo; Lindner, Thomas; Falcão, Alexandre X.; Forkert, Nils D.

2017-03-01

4D arterial spin labeling magnetic resonance angiography (4D ASL MRA) is a non-invasive and safe modality for cerebrovascular imaging procedures. It uses the patient's magnetically labeled blood as intrinsic contrast agent, so that no external contrast media is required. It provides important 3D structure and blood flow information but a sufficient cerebrovascular segmentation is important since it can help clinicians to analyze and diagnose vascular diseases faster, and with higher confidence as compared to simple visual rating of raw ASL MRA images. This work presents a new method for automatic cerebrovascular segmentation in 4D ASL MRA images of the brain. In this process images are denoised, corresponding image label/control image pairs of the 4D ASL MRA sequences are subtracted, and temporal intensity averaging is used to generate a static representation of the vascular system. After that, sets of vessel and background seeds are extracted and provided as input for the image foresting transform algorithm to segment the vascular system. Four 4D ASL MRA datasets of the brain arteries of healthy subjects and corresponding time-of-flight (TOF) MRA images were available for this preliminary study. For evaluation of the segmentation results of the proposed method, the cerebrovascular system was automatically segmented in the high-resolution TOF MRA images using a validated algorithm and the segmentation results were registered to the 4D ASL datasets. Corresponding segmentation pairs were compared using the Dice similarity coefficient (DSC). On average, a DSC of 0.9025 was achieved, indicating that vessels can be extracted successfully from 4D ASL MRA datasets by the proposed segmentation method.

The QUASAR reproducibility study, Part II: Results from a multi center Arterial Spin Labeling test-retest Study

PubMed Central

Petersen, Esben Thade; Mouridsen, Kim; Golay, Xavier

2009-01-01

Arterial Spin Labeling (ASL) is a method to measure perfusion using magnetically labeled blood water as an endogenous tracer. Being fully non-invasive, this technique is attractive for longitudinal studies of cerebral blood flow in healthy and diseased individuals, or as a surrogate marker of metabolism. So far, ASL has been restricted mostly to specialist centers due to a generally low SNR of the method and potential issues with user-dependent analysis needed to obtain quantitative measurement of cerebral blood flow (CBF). Here, we evaluated a particular implementation of ASL (called Quantitative STAR labeling of Arterial Regions or QUASAR), a method providing user independent quantification of CBF in a large test-retest study across sites from around the world, dubbed “The QUASAR reproducibility study”. Altogether, 28 sites located in Asia, Europe and North America participated and a total of 284 healthy volunteers were scanned. Minimal operator dependence was assured by using an automatic planning tool and its accuracy and potential usefulness in multi-center trials was evaluated as well. Accurate repositioning between sessions was achieved with the automatic planning tool showing mean displacements of 1.87±0.95mm and rotations of 1.56±0.66°. Mean gray matter CBF was 47.4±7.5 [ml/100g/min] with a between subject standard variation SDb = 5.5 [ml/100g/min] and a within subject standard deviation SDw = 4.7 [ml/100g/min]. The corresponding repeatability was 13.0 [ml/100g/min] and was found to be within the range of previous studies. PMID:19660557

Multiple layer identification label using stacked identification symbols

NASA Technical Reports Server (NTRS)

Schramm, Harry F. (Inventor)

2005-01-01

An automatic identification system and method are provided which employ a machine readable multiple layer label. The label has a plurality of machine readable marking layers stacked one upon another. Each of the marking layers encodes an identification symbol detectable using one or more sensing technologies. The various marking layers may comprise the same marking material or each marking layer may comprise a different medium having characteristics detectable by a different sensing technology. These sensing technologies include x-ray, radar, capacitance, thermal, magnetic and ultrasonic. A complete symbol may be encoded within each marking layer or a symbol may be segmented into fragments which are then divided within a single marking layer or encoded across multiple marking layers.

Refining Automatically Extracted Knowledge Bases Using Crowdsourcing.

PubMed

Li, Chunhua; Zhao, Pengpeng; Sheng, Victor S; Xian, Xuefeng; Wu, Jian; Cui, Zhiming

2017-01-01

Machine-constructed knowledge bases often contain noisy and inaccurate facts. There exists significant work in developing automated algorithms for knowledge base refinement. Automated approaches improve the quality of knowledge bases but are far from perfect. In this paper, we leverage crowdsourcing to improve the quality of automatically extracted knowledge bases. As human labelling is costly, an important research challenge is how we can use limited human resources to maximize the quality improvement for a knowledge base. To address this problem, we first introduce a concept of semantic constraints that can be used to detect potential errors and do inference among candidate facts. Then, based on semantic constraints, we propose rank-based and graph-based algorithms for crowdsourced knowledge refining, which judiciously select the most beneficial candidate facts to conduct crowdsourcing and prune unnecessary questions. Our experiments show that our method improves the quality of knowledge bases significantly and outperforms state-of-the-art automatic methods under a reasonable crowdsourcing cost.

Automated structure determination of proteins with the SAIL-FLYA NMR method.

PubMed

Takeda, Mitsuhiro; Ikeya, Teppei; Güntert, Peter; Kainosho, Masatsune

2007-01-01

The labeling of proteins with stable isotopes enhances the NMR method for the determination of 3D protein structures in solution. Stereo-array isotope labeling (SAIL) provides an optimal stereospecific and regiospecific pattern of stable isotopes that yields sharpened lines, spectral simplification without loss of information, and the ability to collect rapidly and evaluate fully automatically the structural restraints required to solve a high-quality solution structure for proteins up to twice as large as those that can be analyzed using conventional methods. Here, we describe a protocol for the preparation of SAIL proteins by cell-free methods, including the preparation of S30 extract and their automated structure analysis using the FLYA algorithm and the program CYANA. Once efficient cell-free expression of the unlabeled or uniformly labeled target protein has been achieved, the NMR sample preparation of a SAIL protein can be accomplished in 3 d. A fully automated FLYA structure calculation can be completed in 1 d on a powerful computer system.

Tomographic brain imaging with nucleolar detail and automatic cell counting

NASA Astrophysics Data System (ADS)

Hieber, Simone E.; Bikis, Christos; Khimchenko, Anna; Schweighauser, Gabriel; Hench, Jürgen; Chicherova, Natalia; Schulz, Georg; Müller, Bert

2016-09-01

Brain tissue evaluation is essential for gaining in-depth insight into its diseases and disorders. Imaging the human brain in three dimensions has always been a challenge on the cell level. In vivo methods lack spatial resolution, and optical microscopy has a limited penetration depth. Herein, we show that hard X-ray phase tomography can visualise a volume of up to 43 mm3 of human post mortem or biopsy brain samples, by demonstrating the method on the cerebellum. We automatically identified 5,000 Purkinje cells with an error of less than 5% at their layer and determined the local surface density to 165 cells per mm2 on average. Moreover, we highlight that three-dimensional data allows for the segmentation of sub-cellular structures, including dendritic tree and Purkinje cell nucleoli, without dedicated staining. The method suggests that automatic cell feature quantification of human tissues is feasible in phase tomograms obtained with isotropic resolution in a label-free manner.

Multi-spectral brain tissue segmentation using automatically trained k-Nearest-Neighbor classification.

PubMed

Vrooman, Henri A; Cocosco, Chris A; van der Lijn, Fedde; Stokking, Rik; Ikram, M Arfan; Vernooij, Meike W; Breteler, Monique M B; Niessen, Wiro J

2007-08-01

Conventional k-Nearest-Neighbor (kNN) classification, which has been successfully applied to classify brain tissue in MR data, requires training on manually labeled subjects. This manual labeling is a laborious and time-consuming procedure. In this work, a new fully automated brain tissue classification procedure is presented, in which kNN training is automated. This is achieved by non-rigidly registering the MR data with a tissue probability atlas to automatically select training samples, followed by a post-processing step to keep the most reliable samples. The accuracy of the new method was compared to rigid registration-based training and to conventional kNN-based segmentation using training on manually labeled subjects for segmenting gray matter (GM), white matter (WM) and cerebrospinal fluid (CSF) in 12 data sets. Furthermore, for all classification methods, the performance was assessed when varying the free parameters. Finally, the robustness of the fully automated procedure was evaluated on 59 subjects. The automated training method using non-rigid registration with a tissue probability atlas was significantly more accurate than rigid registration. For both automated training using non-rigid registration and for the manually trained kNN classifier, the difference with the manual labeling by observers was not significantly larger than inter-observer variability for all tissue types. From the robustness study, it was clear that, given an appropriate brain atlas and optimal parameters, our new fully automated, non-rigid registration-based method gives accurate and robust segmentation results. A similarity index was used for comparison with manually trained kNN. The similarity indices were 0.93, 0.92 and 0.92, for CSF, GM and WM, respectively. It can be concluded that our fully automated method using non-rigid registration may replace manual segmentation, and thus that automated brain tissue segmentation without laborious manual training is feasible.

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

Mackenzie, Cristóbal; Pichara, Karim; Protopapas, Pavlos

The success of automatic classification of variable stars depends strongly on the lightcurve representation. Usually, lightcurves are represented as a vector of many descriptors designed by astronomers called features. These descriptors are expensive in terms of computing, require substantial research effort to develop, and do not guarantee a good classification. Today, lightcurve representation is not entirely automatic; algorithms must be designed and manually tuned up for every survey. The amounts of data that will be generated in the future mean astronomers must develop scalable and automated analysis pipelines. In this work we present a feature learning algorithm designed for variablemore » objects. Our method works by extracting a large number of lightcurve subsequences from a given set, which are then clustered to find common local patterns in the time series. Representatives of these common patterns are then used to transform lightcurves of a labeled set into a new representation that can be used to train a classifier. The proposed algorithm learns the features from both labeled and unlabeled lightcurves, overcoming the bias using only labeled data. We test our method on data sets from the Massive Compact Halo Object survey and the Optical Gravitational Lensing Experiment; the results show that our classification performance is as good as and in some cases better than the performance achieved using traditional statistical features, while the computational cost is significantly lower. With these promising results, we believe that our method constitutes a significant step toward the automation of the lightcurve classification pipeline.« less

Clustering-based Feature Learning on Variable Stars

NASA Astrophysics Data System (ADS)

Mackenzie, Cristóbal; Pichara, Karim; Protopapas, Pavlos

2016-04-01

The success of automatic classification of variable stars depends strongly on the lightcurve representation. Usually, lightcurves are represented as a vector of many descriptors designed by astronomers called features. These descriptors are expensive in terms of computing, require substantial research effort to develop, and do not guarantee a good classification. Today, lightcurve representation is not entirely automatic; algorithms must be designed and manually tuned up for every survey. The amounts of data that will be generated in the future mean astronomers must develop scalable and automated analysis pipelines. In this work we present a feature learning algorithm designed for variable objects. Our method works by extracting a large number of lightcurve subsequences from a given set, which are then clustered to find common local patterns in the time series. Representatives of these common patterns are then used to transform lightcurves of a labeled set into a new representation that can be used to train a classifier. The proposed algorithm learns the features from both labeled and unlabeled lightcurves, overcoming the bias using only labeled data. We test our method on data sets from the Massive Compact Halo Object survey and the Optical Gravitational Lensing Experiment; the results show that our classification performance is as good as and in some cases better than the performance achieved using traditional statistical features, while the computational cost is significantly lower. With these promising results, we believe that our method constitutes a significant step toward the automation of the lightcurve classification pipeline.

Deformably registering and annotating whole CLARITY brains to an atlas via masked LDDMM

NASA Astrophysics Data System (ADS)

Kutten, Kwame S.; Vogelstein, Joshua T.; Charon, Nicolas; Ye, Li; Deisseroth, Karl; Miller, Michael I.

2016-04-01

The CLARITY method renders brains optically transparent to enable high-resolution imaging in the structurally intact brain. Anatomically annotating CLARITY brains is necessary for discovering which regions contain signals of interest. Manually annotating whole-brain, terabyte CLARITY images is difficult, time-consuming, subjective, and error-prone. Automatically registering CLARITY images to a pre-annotated brain atlas offers a solution, but is difficult for several reasons. Removal of the brain from the skull and subsequent storage and processing cause variable non-rigid deformations, thus compounding inter-subject anatomical variability. Additionally, the signal in CLARITY images arises from various biochemical contrast agents which only sparsely label brain structures. This sparse labeling challenges the most commonly used registration algorithms that need to match image histogram statistics to the more densely labeled histological brain atlases. The standard method is a multiscale Mutual Information B-spline algorithm that dynamically generates an average template as an intermediate registration target. We determined that this method performs poorly when registering CLARITY brains to the Allen Institute's Mouse Reference Atlas (ARA), because the image histogram statistics are poorly matched. Therefore, we developed a method (Mask-LDDMM) for registering CLARITY images, that automatically finds the brain boundary and learns the optimal deformation between the brain and atlas masks. Using Mask-LDDMM without an average template provided better results than the standard approach when registering CLARITY brains to the ARA. The LDDMM pipelines developed here provide a fast automated way to anatomically annotate CLARITY images; our code is available as open source software at http://NeuroData.io.

Discriminative confidence estimation for probabilistic multi-atlas label fusion.

PubMed

Benkarim, Oualid M; Piella, Gemma; González Ballester, Miguel Angel; Sanroma, Gerard

2017-12-01

Quantitative neuroimaging analyses often rely on the accurate segmentation of anatomical brain structures. In contrast to manual segmentation, automatic methods offer reproducible outputs and provide scalability to study large databases. Among existing approaches, multi-atlas segmentation has recently shown to yield state-of-the-art performance in automatic segmentation of brain images. It consists in propagating the labelmaps from a set of atlases to the anatomy of a target image using image registration, and then fusing these multiple warped labelmaps into a consensus segmentation on the target image. Accurately estimating the contribution of each atlas labelmap to the final segmentation is a critical step for the success of multi-atlas segmentation. Common approaches to label fusion either rely on local patch similarity, probabilistic statistical frameworks or a combination of both. In this work, we propose a probabilistic label fusion framework based on atlas label confidences computed at each voxel of the structure of interest. Maximum likelihood atlas confidences are estimated using a supervised approach, explicitly modeling the relationship between local image appearances and segmentation errors produced by each of the atlases. We evaluate different spatial pooling strategies for modeling local segmentation errors. We also present a novel type of label-dependent appearance features based on atlas labelmaps that are used during confidence estimation to increase the accuracy of our label fusion. Our approach is evaluated on the segmentation of seven subcortical brain structures from the MICCAI 2013 SATA Challenge dataset and the hippocampi from the ADNI dataset. Overall, our results indicate that the proposed label fusion framework achieves superior performance to state-of-the-art approaches in the majority of the evaluated brain structures and shows more robustness to registration errors. Copyright © 2017 Elsevier B.V. All rights reserved.

Semi-Supervised Active Learning for Sound Classification in Hybrid Learning Environments.

PubMed

Han, Wenjing; Coutinho, Eduardo; Ruan, Huabin; Li, Haifeng; Schuller, Björn; Yu, Xiaojie; Zhu, Xuan

2016-01-01

Coping with scarcity of labeled data is a common problem in sound classification tasks. Approaches for classifying sounds are commonly based on supervised learning algorithms, which require labeled data which is often scarce and leads to models that do not generalize well. In this paper, we make an efficient combination of confidence-based Active Learning and Self-Training with the aim of minimizing the need for human annotation for sound classification model training. The proposed method pre-processes the instances that are ready for labeling by calculating their classifier confidence scores, and then delivers the candidates with lower scores to human annotators, and those with high scores are automatically labeled by the machine. We demonstrate the feasibility and efficacy of this method in two practical scenarios: pool-based and stream-based processing. Extensive experimental results indicate that our approach requires significantly less labeled instances to reach the same performance in both scenarios compared to Passive Learning, Active Learning and Self-Training. A reduction of 52.2% in human labeled instances is achieved in both of the pool-based and stream-based scenarios on a sound classification task considering 16,930 sound instances.

A Multiple-Label Guided Clustering Algorithm for Historical Document Dating and Localization.

PubMed

He, Sheng; Samara, Petros; Burgers, Jan; Schomaker, Lambert

2016-11-01

It is of essential importance for historians to know the date and place of origin of the documents they study. It would be a huge advancement for historical scholars if it would be possible to automatically estimate the geographical and temporal provenance of a handwritten document by inferring them from the handwriting style of such a document. We propose a multiple-label guided clustering algorithm to discover the correlations between the concrete low-level visual elements in historical documents and abstract labels, such as date and location. First, a novel descriptor, called histogram of orientations of handwritten strokes, is proposed to extract and describe the visual elements, which is built on a scale-invariant polar-feature space. In addition, the multi-label self-organizing map (MLSOM) is proposed to discover the correlations between the low-level visual elements and their labels in a single framework. Our proposed MLSOM can be used to predict the labels directly. Moreover, the MLSOM can also be considered as a pre-structured clustering method to build a codebook, which contains more discriminative information on date and geography. The experimental results on the medieval paleographic scale data set demonstrate that our method achieves state-of-the-art results.

Semi-Supervised Active Learning for Sound Classification in Hybrid Learning Environments

PubMed Central

Han, Wenjing; Coutinho, Eduardo; Li, Haifeng; Schuller, Björn; Yu, Xiaojie; Zhu, Xuan

2016-01-01

Coping with scarcity of labeled data is a common problem in sound classification tasks. Approaches for classifying sounds are commonly based on supervised learning algorithms, which require labeled data which is often scarce and leads to models that do not generalize well. In this paper, we make an efficient combination of confidence-based Active Learning and Self-Training with the aim of minimizing the need for human annotation for sound classification model training. The proposed method pre-processes the instances that are ready for labeling by calculating their classifier confidence scores, and then delivers the candidates with lower scores to human annotators, and those with high scores are automatically labeled by the machine. We demonstrate the feasibility and efficacy of this method in two practical scenarios: pool-based and stream-based processing. Extensive experimental results indicate that our approach requires significantly less labeled instances to reach the same performance in both scenarios compared to Passive Learning, Active Learning and Self-Training. A reduction of 52.2% in human labeled instances is achieved in both of the pool-based and stream-based scenarios on a sound classification task considering 16,930 sound instances. PMID:27627768

Automatic detection and recognition of multiple macular lesions in retinal optical coherence tomography images with multi-instance multilabel learning

NASA Astrophysics Data System (ADS)

Fang, Leyuan; Yang, Liumao; Li, Shutao; Rabbani, Hossein; Liu, Zhimin; Peng, Qinghua; Chen, Xiangdong

2017-06-01

Detection and recognition of macular lesions in optical coherence tomography (OCT) are very important for retinal diseases diagnosis and treatment. As one kind of retinal disease (e.g., diabetic retinopathy) may contain multiple lesions (e.g., edema, exudates, and microaneurysms) and eye patients may suffer from multiple retinal diseases, multiple lesions often coexist within one retinal image. Therefore, one single-lesion-based detector may not support the diagnosis of clinical eye diseases. To address this issue, we propose a multi-instance multilabel-based lesions recognition (MIML-LR) method for the simultaneous detection and recognition of multiple lesions. The proposed MIML-LR method consists of the following steps: (1) segment the regions of interest (ROIs) for different lesions, (2) compute descriptive instances (features) for each lesion region, (3) construct multilabel detectors, and (4) recognize each ROI with the detectors. The proposed MIML-LR method was tested on 823 clinically labeled OCT images with normal macular and macular with three common lesions: epiretinal membrane, edema, and drusen. For each input OCT image, our MIML-LR method can automatically identify the number of lesions and assign the class labels, achieving the average accuracy of 88.72% for the cases with multiple lesions, which better assists macular disease diagnosis and treatment.

Automatic classification of retinal vessels into arteries and veins

NASA Astrophysics Data System (ADS)

Niemeijer, Meindert; van Ginneken, Bram; Abràmoff, Michael D.

2009-02-01

Separating the retinal vascular tree into arteries and veins is important for quantifying vessel changes that preferentially affect either the veins or the arteries. For example the ratio of arterial to venous diameter, the retinal a/v ratio, is well established to be predictive of stroke and other cardiovascular events in adults, as well as the staging of retinopathy of prematurity in premature infants. This work presents a supervised, automatic method that can determine whether a vessel is an artery or a vein based on intensity and derivative information. After thinning of the vessel segmentation, vessel crossing and bifurcation points are removed leaving a set of vessel segments containing centerline pixels. A set of features is extracted from each centerline pixel and using these each is assigned a soft label indicating the likelihood that it is part of a vein. As all centerline pixels in a connected segment should be the same type we average the soft labels and assign this average label to each centerline pixel in the segment. We train and test the algorithm using the data (40 color fundus photographs) from the DRIVE database1 with an enhanced reference standard. In the enhanced reference standard a fellowship trained retinal specialist (MDA) labeled all vessels for which it was possible to visually determine whether it was a vein or an artery. After applying the proposed method to the 20 images of the DRIVE test set we obtained an area under the receiver operator characteristic (ROC) curve of 0.88 for correctly assigning centerline pixels to either the vein or artery classes.

Automatically Identifying and Predicting Unplanned Wind Turbine Stoppages Using SCADA and Alarms System Data: Case Study and Results

NASA Astrophysics Data System (ADS)

Leahy, Kevin; Gallagher, Colm; Bruton, Ken; O'Donovan, Peter; O'Sullivan, Dominic T. J.

2017-11-01

Using 10-minute wind turbine SCADA data for fault prediction offers an attractive way of gaining additional prognostic capabilities without needing to invest in extra hardware. To use these data-driven methods effectively, the historical SCADA data must be labelled with the periods when the turbine was in faulty operation as well the sub-system the fault was attributed to. Manually identifying faults using maintenance logs can be effective, but is also highly time consuming and tedious due to the disparate nature of these logs across manufacturers, operators and even individual maintenance events. Turbine alarm systems can help to identify these periods, but the sheer volume of alarms and false positives generated makes analysing them on an individual basis ineffective. In this work, we present a new method for automatically identifying historical stoppages on the turbine using SCADA and alarms data. Each stoppage is associated with either a fault in one of the turbine’s sub-systems, a routine maintenance activity, a grid-related event or a number of other categories. This is then checked against maintenance logs for accuracy and the labelled data fed into a classifier for predicting when these stoppages will occur. Results show that the automated labelling process correctly identifies each type of stoppage, and can be effectively used for SCADA-based prediction of turbine faults.

An algorithm for optimal fusion of atlases with different labeling protocols

PubMed Central

Iglesias, Juan Eugenio; Sabuncu, Mert Rory; Aganj, Iman; Bhatt, Priyanka; Casillas, Christen; Salat, David; Boxer, Adam; Fischl, Bruce; Van Leemput, Koen

2014-01-01

In this paper we present a novel label fusion algorithm suited for scenarios in which different manual delineation protocols with potentially disparate structures have been used to annotate the training scans (hereafter referred to as “atlases”). Such scenarios arise when atlases have missing structures, when they have been labeled with different levels of detail, or when they have been taken from different heterogeneous databases. The proposed algorithm can be used to automatically label a novel scan with any of the protocols from the training data. Further, it enables us to generate new labels that are not present in any delineation protocol by defining intersections on the underling labels. We first use probabilistic models of label fusion to generalize three popular label fusion techniques to the multi-protocol setting: majority voting, semi-locally weighted voting and STAPLE. Then, we identify some shortcomings of the generalized methods, namely the inability to produce meaningful posterior probabilities for the different labels (majority voting, semi-locally weighted voting) and to exploit the similarities between the atlases (all three methods). Finally, we propose a novel generative label fusion model that can overcome these drawbacks. We use the proposed method to combine four brain MRI datasets labeled with different protocols (with a total of 102 unique labeled structures) to produce segmentations of 148 brain regions. Using cross-validation, we show that the proposed algorithm outperforms the generalizations of majority voting, semi-locally weighted voting and STAPLE (mean Dice score 83%, vs. 77%, 80% and 79%, respectively). We also evaluated the proposed algorithm in an aging study, successfully reproducing some well-known results in cortical and subcortical structures. PMID:25463466

The white matter query language: a novel approach for describing human white matter anatomy

PubMed Central

Makris, Nikos; Rathi, Yogesh; Shenton, Martha; Kikinis, Ron; Kubicki, Marek; Westin, Carl-Fredrik

2016-01-01

We have developed a novel method to describe human white matter anatomy using an approach that is both intuitive and simple to use, and which automatically extracts white matter tracts from diffusion MRI volumes. Further, our method simplifies the quantification and statistical analysis of white matter tracts on large diffusion MRI databases. This work reflects the careful syntactical definition of major white matter fiber tracts in the human brain based on a neuroanatomist’s expert knowledge. The framework is based on a novel query language with a near-to-English textual syntax. This query language makes it possible to construct a dictionary of anatomical definitions that describe white matter tracts. The definitions include adjacent gray and white matter regions, and rules for spatial relations. This novel method makes it possible to automatically label white matter anatomy across subjects. After describing this method, we provide an example of its implementation where we encode anatomical knowledge in human white matter for ten association and 15 projection tracts per hemisphere, along with seven commissural tracts. Importantly, this novel method is comparable in accuracy to manual labeling. Finally, we present results applying this method to create a white matter atlas from 77 healthy subjects, and we use this atlas in a small proof-of-concept study to detect changes in association tracts that characterize schizophrenia. PMID:26754839

The white matter query language: a novel approach for describing human white matter anatomy.

PubMed

Wassermann, Demian; Makris, Nikos; Rathi, Yogesh; Shenton, Martha; Kikinis, Ron; Kubicki, Marek; Westin, Carl-Fredrik

2016-12-01

We have developed a novel method to describe human white matter anatomy using an approach that is both intuitive and simple to use, and which automatically extracts white matter tracts from diffusion MRI volumes. Further, our method simplifies the quantification and statistical analysis of white matter tracts on large diffusion MRI databases. This work reflects the careful syntactical definition of major white matter fiber tracts in the human brain based on a neuroanatomist's expert knowledge. The framework is based on a novel query language with a near-to-English textual syntax. This query language makes it possible to construct a dictionary of anatomical definitions that describe white matter tracts. The definitions include adjacent gray and white matter regions, and rules for spatial relations. This novel method makes it possible to automatically label white matter anatomy across subjects. After describing this method, we provide an example of its implementation where we encode anatomical knowledge in human white matter for ten association and 15 projection tracts per hemisphere, along with seven commissural tracts. Importantly, this novel method is comparable in accuracy to manual labeling. Finally, we present results applying this method to create a white matter atlas from 77 healthy subjects, and we use this atlas in a small proof-of-concept study to detect changes in association tracts that characterize schizophrenia.

Recurrent neural network based virtual detection line

NASA Astrophysics Data System (ADS)

Kadikis, Roberts

2018-04-01

The paper proposes an efficient method for detection of moving objects in the video. The objects are detected when they cross a virtual detection line. Only the pixels of the detection line are processed, which makes the method computationally efficient. A Recurrent Neural Network processes these pixels. The machine learning approach allows one to train a model that works in different and changing outdoor conditions. Also, the same network can be trained for various detection tasks, which is demonstrated by the tests on vehicle and people counting. In addition, the paper proposes a method for semi-automatic acquisition of labeled training data. The labeling method is used to create training and testing datasets, which in turn are used to train and evaluate the accuracy and efficiency of the detection method. The method shows similar accuracy as the alternative efficient methods but provides greater adaptability and usability for different tasks.

Cross-language opinion lexicon extraction using mutual-reinforcement label propagation.

PubMed

Lin, Zheng; Tan, Songbo; Liu, Yue; Cheng, Xueqi; Xu, Xueke

2013-01-01

There is a growing interest in automatically building opinion lexicon from sources such as product reviews. Most of these methods depend on abundant external resources such as WordNet, which limits the applicability of these methods. Unsupervised or semi-supervised learning provides an optional solution to multilingual opinion lexicon extraction. However, the datasets are imbalanced in different languages. For some languages, the high-quality corpora are scarce or hard to obtain, which limits the research progress. To solve the above problems, we explore a mutual-reinforcement label propagation framework. First, for each language, a label propagation algorithm is applied to a word relation graph, and then a bilingual dictionary is used as a bridge to transfer information between two languages. A key advantage of this model is its ability to make two languages learn from each other and boost each other. The experimental results show that the proposed approach outperforms baseline significantly.

MS lesion segmentation using a multi-channel patch-based approach with spatial consistency

NASA Astrophysics Data System (ADS)

Mechrez, Roey; Goldberger, Jacob; Greenspan, Hayit

2015-03-01

This paper presents an automatic method for segmentation of Multiple Sclerosis (MS) in Magnetic Resonance Images (MRI) of the brain. The approach is based on similarities between multi-channel patches (T1, T2 and FLAIR). An MS lesion patch database is built using training images for which the label maps are known. For each patch in the testing image, k similar patches are retrieved from the database. The matching labels for these k patches are then combined to produce an initial segmentation map for the test case. Finally a novel iterative patch-based label refinement process based on the initial segmentation map is performed to ensure spatial consistency of the detected lesions. A leave-one-out evaluation is done for each testing image in the MS lesion segmentation challenge of MICCAI 2008. Results are shown to compete with the state-of-the-art methods on the MICCAI 2008 challenge.

Cross-Language Opinion Lexicon Extraction Using Mutual-Reinforcement Label Propagation

PubMed Central

Lin, Zheng; Tan, Songbo; Liu, Yue; Cheng, Xueqi; Xu, Xueke

2013-01-01

There is a growing interest in automatically building opinion lexicon from sources such as product reviews. Most of these methods depend on abundant external resources such as WordNet, which limits the applicability of these methods. Unsupervised or semi-supervised learning provides an optional solution to multilingual opinion lexicon extraction. However, the datasets are imbalanced in different languages. For some languages, the high-quality corpora are scarce or hard to obtain, which limits the research progress. To solve the above problems, we explore a mutual-reinforcement label propagation framework. First, for each language, a label propagation algorithm is applied to a word relation graph, and then a bilingual dictionary is used as a bridge to transfer information between two languages. A key advantage of this model is its ability to make two languages learn from each other and boost each other. The experimental results show that the proposed approach outperforms baseline significantly. PMID:24260190

Automated torso organ segmentation from 3D CT images using structured perceptron and dual decomposition

NASA Astrophysics Data System (ADS)

Nimura, Yukitaka; Hayashi, Yuichiro; Kitasaka, Takayuki; Mori, Kensaku

2015-03-01

This paper presents a method for torso organ segmentation from abdominal CT images using structured perceptron and dual decomposition. A lot of methods have been proposed to enable automated extraction of organ regions from volumetric medical images. However, it is necessary to adjust empirical parameters of them to obtain precise organ regions. This paper proposes an organ segmentation method using structured output learning. Our method utilizes a graphical model and binary features which represent the relationship between voxel intensities and organ labels. Also we optimize the weights of the graphical model by structured perceptron and estimate the best organ label for a given image by dynamic programming and dual decomposition. The experimental result revealed that the proposed method can extract organ regions automatically using structured output learning. The error of organ label estimation was 4.4%. The DICE coefficients of left lung, right lung, heart, liver, spleen, pancreas, left kidney, right kidney, and gallbladder were 0.91, 0.95, 0.77, 0.81, 0.74, 0.08, 0.83, 0.84, and 0.03, respectively.

Random Deep Belief Networks for Recognizing Emotions from Speech Signals.

PubMed

Wen, Guihua; Li, Huihui; Huang, Jubing; Li, Danyang; Xun, Eryang

2017-01-01

Now the human emotions can be recognized from speech signals using machine learning methods; however, they are challenged by the lower recognition accuracies in real applications due to lack of the rich representation ability. Deep belief networks (DBN) can automatically discover the multiple levels of representations in speech signals. To make full of its advantages, this paper presents an ensemble of random deep belief networks (RDBN) method for speech emotion recognition. It firstly extracts the low level features of the input speech signal and then applies them to construct lots of random subspaces. Each random subspace is then provided for DBN to yield the higher level features as the input of the classifier to output an emotion label. All outputted emotion labels are then fused through the majority voting to decide the final emotion label for the input speech signal. The conducted experimental results on benchmark speech emotion databases show that RDBN has better accuracy than the compared methods for speech emotion recognition.

Random Deep Belief Networks for Recognizing Emotions from Speech Signals

PubMed Central

Li, Huihui; Huang, Jubing; Li, Danyang; Xun, Eryang

2017-01-01

Now the human emotions can be recognized from speech signals using machine learning methods; however, they are challenged by the lower recognition accuracies in real applications due to lack of the rich representation ability. Deep belief networks (DBN) can automatically discover the multiple levels of representations in speech signals. To make full of its advantages, this paper presents an ensemble of random deep belief networks (RDBN) method for speech emotion recognition. It firstly extracts the low level features of the input speech signal and then applies them to construct lots of random subspaces. Each random subspace is then provided for DBN to yield the higher level features as the input of the classifier to output an emotion label. All outputted emotion labels are then fused through the majority voting to decide the final emotion label for the input speech signal. The conducted experimental results on benchmark speech emotion databases show that RDBN has better accuracy than the compared methods for speech emotion recognition. PMID:28356908

An automatic agricultural zone classification procedure for crop inventory satellite images

NASA Technical Reports Server (NTRS)

Parada, N. D. J. (Principal Investigator); Kux, H. J.; Velasco, F. R. D.; Deoliveira, M. O. B.

1982-01-01

A classification procedure for assessing crop areal proportion in multispectral scanner image is discussed. The procedure is into four parts: labeling; classification; proportion estimation; and evaluation. The procedure also has the following characteristics: multitemporal classification; the need for a minimum field information; and verification capability between automatic classification and analyst labeling. The processing steps and the main algorithms involved are discussed. An outlook on the future of this technology is also presented.

Exploiting Acoustic and Syntactic Features for Automatic Prosody Labeling in a Maximum Entropy Framework

PubMed Central

Sridhar, Vivek Kumar Rangarajan; Bangalore, Srinivas; Narayanan, Shrikanth S.

2009-01-01

In this paper, we describe a maximum entropy-based automatic prosody labeling framework that exploits both language and speech information. We apply the proposed framework to both prominence and phrase structure detection within the Tones and Break Indices (ToBI) annotation scheme. Our framework utilizes novel syntactic features in the form of supertags and a quantized acoustic–prosodic feature representation that is similar to linear parameterizations of the prosodic contour. The proposed model is trained discriminatively and is robust in the selection of appropriate features for the task of prosody detection. The proposed maximum entropy acoustic–syntactic model achieves pitch accent and boundary tone detection accuracies of 86.0% and 93.1% on the Boston University Radio News corpus, and, 79.8% and 90.3% on the Boston Directions corpus. The phrase structure detection through prosodic break index labeling provides accuracies of 84% and 87% on the two corpora, respectively. The reported results are significantly better than previously reported results and demonstrate the strength of maximum entropy model in jointly modeling simple lexical, syntactic, and acoustic features for automatic prosody labeling. PMID:19603083

Improving labeling efficiency in automatic quality control of MRSI data.

PubMed

Pedrosa de Barros, Nuno; McKinley, Richard; Wiest, Roland; Slotboom, Johannes

2017-12-01

To improve the efficiency of the labeling task in automatic quality control of MR spectroscopy imaging data. 28'432 short and long echo time (TE) spectra (1.5 tesla; point resolved spectroscopy (PRESS); repetition time (TR)= 1,500 ms) from 18 different brain tumor patients were labeled by two experts as either accept or reject, depending on their quality. For each spectrum, 47 signal features were extracted. The data was then used to run several simulations and test an active learning approach using uncertainty sampling. The performance of the classifiers was evaluated as a function of the number of patients in the training set, number of spectra in the training set, and a parameter α used to control the level of classification uncertainty required for a new spectrum to be selected for labeling. The results showed that the proposed strategy allows reductions of up to 72.97% for short TE and 62.09% for long TE in the amount of data that needs to be labeled, without significant impact in classification accuracy. Further reductions are possible with significant but minimal impact in performance. Active learning using uncertainty sampling is an effective way to increase the labeling efficiency for training automatic quality control classifiers. Magn Reson Med 78:2399-2405, 2017. © 2017 International Society for Magnetic Resonance in Medicine. © 2017 International Society for Magnetic Resonance in Medicine.

Automatic multi-label annotation of abdominal CT images using CBIR

NASA Astrophysics Data System (ADS)

Xue, Zhiyun; Antani, Sameer; Long, L. Rodney; Thoma, George R.

2017-03-01

We present a technique to annotate multiple organs shown in 2-D abdominal/pelvic CT images using CBIR. This annotation task is motivated by our research interests in visual question-answering (VQA). We aim to apply results from this effort in Open-iSM, a multimodal biomedical search engine developed by the National Library of Medicine (NLM). Understanding visual content of biomedical images is a necessary step for VQA. Though sufficient annotational information about an image may be available in related textual metadata, not all may be useful as descriptive tags, particularly for anatomy on the image. In this paper, we develop and evaluate a multi-label image annotation method using CBIR. We evaluate our method on two 2-D CT image datasets we generated from 3-D volumetric data obtained from a multi-organ segmentation challenge hosted in MICCAI 2015. Shape and spatial layout information is used to encode visual characteristics of the anatomy. We adapt a weighted voting scheme to assign multiple labels to the query image by combining the labels of the images identified as similar by the method. Key parameters that may affect the annotation performance, such as the number of images used in the label voting and the threshold for excluding labels that have low weights, are studied. The method proposes a coarse-to-fine retrieval strategy which integrates the classification with the nearest-neighbor search. Results from our evaluation (using the MICCAI CT image datasets as well as figures from Open-i) are presented.

Towards Automatic Classification of Exoplanet-Transit-Like Signals: A Case Study on Kepler Mission Data

NASA Astrophysics Data System (ADS)

Valizadegan, Hamed; Martin, Rodney; McCauliff, Sean D.; Jenkins, Jon Michael; Catanzarite, Joseph; Oza, Nikunj C.

2015-08-01

Building new catalogues of planetary candidates, astrophysical false alarms, and non-transiting phenomena is a challenging task that currently requires a reviewing team of astrophysicists and astronomers. These scientists need to examine more than 100 diagnostic metrics and associated graphics for each candidate exoplanet-transit-like signal to classify it into one of the three classes. Considering that the NASA Explorer Program's TESS mission and ESA's PLATO mission survey even a larger area of space, the classification of their transit-like signals is more time-consuming for human agents and a bottleneck to successfully construct the new catalogues in a timely manner. This encourages building automatic classification tools that can quickly and reliably classify the new signal data from these missions. The standard tool for building automatic classification systems is the supervised machine learning that requires a large set of highly accurate labeled examples in order to build an effective classifier. This requirement cannot be easily met for classifying transit-like signals because not only are existing labeled signals very limited, but also the current labels may not be reliable (because the labeling process is a subjective task). Our experiments with using different supervised classifiers to categorize transit-like signals verifies that the labeled signals are not rich enough to provide the classifier with enough power to generalize well beyond the observed cases (e.g. to unseen or test signals). That motivated us to utilize a new category of learning techniques, so-called semi-supervised learning, that combines the label information from the costly labeled signals, and distribution information from the cheaply available unlabeled signals in order to construct more effective classifiers. Our study on the Kepler Mission data shows that semi-supervised learning can significantly improve the result of multiple base classifiers (e.g. Support Vector Machines, AdaBoost, and Decision Tree) and is a good technique for automatic classification of exoplanet-transit-like signal.

Classification of mislabelled microarrays using robust sparse logistic regression.

PubMed

Bootkrajang, Jakramate; Kabán, Ata

2013-04-01

Previous studies reported that labelling errors are not uncommon in microarray datasets. In such cases, the training set may become misleading, and the ability of classifiers to make reliable inferences from the data is compromised. Yet, few methods are currently available in the bioinformatics literature to deal with this problem. The few existing methods focus on data cleansing alone, without reference to classification, and their performance crucially depends on some tuning parameters. In this article, we develop a new method to detect mislabelled arrays simultaneously with learning a sparse logistic regression classifier. Our method may be seen as a label-noise robust extension of the well-known and successful Bayesian logistic regression classifier. To account for possible mislabelling, we formulate a label-flipping process as part of the classifier. The regularization parameter is automatically set using Bayesian regularization, which not only saves the computation time that cross-validation would take, but also eliminates any unwanted effects of label noise when setting the regularization parameter. Extensive experiments with both synthetic data and real microarray datasets demonstrate that our approach is able to counter the bad effects of labelling errors in terms of predictive performance, it is effective at identifying marker genes and simultaneously it detects mislabelled arrays to high accuracy. The code is available from http://cs.bham.ac.uk/∼jxb008. Supplementary data are available at Bioinformatics online.

Toward knowledge-enhanced viewing using encyclopedias and model-based segmentation

NASA Astrophysics Data System (ADS)

Kneser, Reinhard; Lehmann, Helko; Geller, Dieter; Qian, Yue-Chen; Weese, Jürgen

2009-02-01

To make accurate decisions based on imaging data, radiologists must associate the viewed imaging data with the corresponding anatomical structures. Furthermore, given a disease hypothesis possible image findings which verify the hypothesis must be considered and where and how they are expressed in the viewed images. If rare anatomical variants, rare pathologies, unfamiliar protocols, or ambiguous findings are present, external knowledge sources such as medical encyclopedias are consulted. These sources are accessed using keywords typically describing anatomical structures, image findings, pathologies. In this paper we present our vision of how a patient's imaging data can be automatically enhanced with anatomical knowledge as well as knowledge about image findings. On one hand, we propose the automatic annotation of the images with labels from a standard anatomical ontology. These labels are used as keywords for a medical encyclopedia such as STATdx to access anatomical descriptions, information about pathologies and image findings. On the other hand we envision encyclopedias to contain links to region- and finding-specific image processing algorithms. Then a finding is evaluated on an image by applying the respective algorithm in the associated anatomical region. Towards realization of our vision, we present our method and results of automatic annotation of anatomical structures in 3D MRI brain images. Thereby we develop a complex surface mesh model incorporating major structures of the brain and a model-based segmentation method. We demonstrate the validity by analyzing the results of several training and segmentation experiments with clinical data focusing particularly on the visual pathway.

Automatic quality control in clinical (1)H MRSI of brain cancer.

PubMed

Pedrosa de Barros, Nuno; McKinley, Richard; Knecht, Urspeter; Wiest, Roland; Slotboom, Johannes

2016-05-01

MRSI grids frequently show spectra with poor quality, mainly because of the high sensitivity of MRS to field inhomogeneities. These poor quality spectra are prone to quantification and/or interpretation errors that can have a significant impact on the clinical use of spectroscopic data. Therefore, quality control of the spectra should always precede their clinical use. When performed manually, quality assessment of MRSI spectra is not only a tedious and time-consuming task, but is also affected by human subjectivity. Consequently, automatic, fast and reliable methods for spectral quality assessment are of utmost interest. In this article, we present a new random forest-based method for automatic quality assessment of (1)H MRSI brain spectra, which uses a new set of MRS signal features. The random forest classifier was trained on spectra from 40 MRSI grids that were classified as acceptable or non-acceptable by two expert spectroscopists. To account for the effects of intra-rater reliability, each spectrum was rated for quality three times by each rater. The automatic method classified these spectra with an area under the curve (AUC) of 0.976. Furthermore, in the subset of spectra containing only the cases that were classified every time in the same way by the spectroscopists, an AUC of 0.998 was obtained. Feature importance for the classification was also evaluated. Frequency domain skewness and kurtosis, as well as time domain signal-to-noise ratios (SNRs) in the ranges 50-75 ms and 75-100 ms, were the most important features. Given that the method is able to assess a whole MRSI grid faster than a spectroscopist (approximately 3 s versus approximately 3 min), and without loss of accuracy (agreement between classifier trained with just one session and any of the other labelling sessions, 89.88%; agreement between any two labelling sessions, 89.03%), the authors suggest its implementation in the clinical routine. The method presented in this article was implemented in jMRUI's SpectrIm plugin. Copyright © 2016 John Wiley & Sons, Ltd.

Micro-bead injection spectroscopy for label-free automated determination of immunoglobulin G in human serum.

PubMed

Ramos, Inês I; Magalhães, Luís M; Barreiros, Luisa; Reis, Salette; Lima, José L F C; Segundo, Marcela A

2018-01-01

Immunoglobulin G (IgG) represents the major fraction of antibodies in healthy adult human serum, and deviations from physiological levels are a generic marker of disease corresponding to different pathologies. Therefore, screening methods for IgG evaluation are a valuable aid to diagnostics. The present work proposes a rapid, automatic, and miniaturized method based on UV-vis micro-bead injection spectroscopy (μ-BIS) for the real-time determination of human serum IgG with label-free detection. Relying on attachment of IgG in rec-protein G immobilized in Sepharose 4B, a bioaffinity column is automatically assembled, where IgG is selectively retained and determined by on-column optical density measurement. A "dilution-and-shoot" approach (50 to 200 times) was implemented without further sample treatment because interferences were flushed out of the column upon sample loading, with minimization of carryover and cross-contamination by automatically discarding the sorbent (0.2 mg) after each determination. No interference from human serum albumin at 60 mg mL -1 in undiluted sample was found. The method allowed IgG determination in the range 100-300 μg mL -1 (corresponding to 5.0-60 mg mL -1 in undiluted samples), with a detection limit of 33 μg mL -1 (1.7 mg mL -1 for samples, dilution factor of 50). RSD values were < 9.4 and < 11.7%, for intra and inter-assay precision, respectively, while recovery values for human serum spiked with IgG at high pathological levels were 97.8-101.4%. Comparison to commercial ELISA kit showed no significant difference for tested samples (n = 8). Moreover, time-to-result decreased from several hours to < 5 min and analysis cost decreased 10 times, showing the potential of the proposed approach as a point-of-care method. Graphical abstract Micro-Bead Injection Spectroscopy method for real time, automated and label-free determination of total serum human Immunoglobulin G (IgG). The method was designed for Lab-on-Valve (LOV) platforms using a miniaturised protein G bioaffinity separative approach. IgG are separated from serum matrix components upon quantification with low non-specific binding in less than 5 min.

Automatic Testing and Assessment of Neuroanatomy Using a Digital Brain Atlas: Method and Development of Computer- and Mobile-Based Applications

ERIC Educational Resources Information Center

Nowinski, Wieslaw L.; Thirunavuukarasuu, Arumugam; Ananthasubramaniam, Anand; Chua, Beng Choon; Qian, Guoyu; Nowinska, Natalia G.; Marchenko, Yevgen; Volkau, Ihar

2009-01-01

Preparation of tests and student's assessment by the instructor are time consuming. We address these two tasks in neuroanatomy education by employing a digital media application with a three-dimensional (3D), interactive, fully segmented, and labeled brain atlas. The anatomical and vascular models in the atlas are linked to "Terminologia…

Refining Automatically Extracted Knowledge Bases Using Crowdsourcing

PubMed Central

Xian, Xuefeng; Cui, Zhiming

2017-01-01

Machine-constructed knowledge bases often contain noisy and inaccurate facts. There exists significant work in developing automated algorithms for knowledge base refinement. Automated approaches improve the quality of knowledge bases but are far from perfect. In this paper, we leverage crowdsourcing to improve the quality of automatically extracted knowledge bases. As human labelling is costly, an important research challenge is how we can use limited human resources to maximize the quality improvement for a knowledge base. To address this problem, we first introduce a concept of semantic constraints that can be used to detect potential errors and do inference among candidate facts. Then, based on semantic constraints, we propose rank-based and graph-based algorithms for crowdsourced knowledge refining, which judiciously select the most beneficial candidate facts to conduct crowdsourcing and prune unnecessary questions. Our experiments show that our method improves the quality of knowledge bases significantly and outperforms state-of-the-art automatic methods under a reasonable crowdsourcing cost. PMID:28588611

A univocal definition of the neuronal soma morphology using Gaussian mixture models.

PubMed

Luengo-Sanchez, Sergio; Bielza, Concha; Benavides-Piccione, Ruth; Fernaud-Espinosa, Isabel; DeFelipe, Javier; Larrañaga, Pedro

2015-01-01

The definition of the soma is fuzzy, as there is no clear line demarcating the soma of the labeled neurons and the origin of the dendrites and axon. Thus, the morphometric analysis of the neuronal soma is highly subjective. In this paper, we provide a mathematical definition and an automatic segmentation method to delimit the neuronal soma. We applied this method to the characterization of pyramidal cells, which are the most abundant neurons in the cerebral cortex. Since there are no benchmarks with which to compare the proposed procedure, we validated the goodness of this automatic segmentation method against manual segmentation by neuroanatomists to set up a framework for comparison. We concluded that there were no significant differences between automatically and manually segmented somata, i.e., the proposed procedure segments the neurons similarly to how a neuroanatomist does. It also provides univocal, justifiable and objective cutoffs. Thus, this study is a means of characterizing pyramidal neurons in order to objectively compare the morphometry of the somata of these neurons in different cortical areas and species.

Contour-Driven Atlas-Based Segmentation

PubMed Central

Wachinger, Christian; Fritscher, Karl; Sharp, Greg; Golland, Polina

2016-01-01

We propose new methods for automatic segmentation of images based on an atlas of manually labeled scans and contours in the image. First, we introduce a Bayesian framework for creating initial label maps from manually annotated training images. Within this framework, we model various registration- and patch-based segmentation techniques by changing the deformation field prior. Second, we perform contour-driven regression on the created label maps to refine the segmentation. Image contours and image parcellations give rise to non-stationary kernel functions that model the relationship between image locations. Setting the kernel to the covariance function in a Gaussian process establishes a distribution over label maps supported by image structures. Maximum a posteriori estimation of the distribution over label maps conditioned on the outcome of the atlas-based segmentation yields the refined segmentation. We evaluate the segmentation in two clinical applications: the segmentation of parotid glands in head and neck CT scans and the segmentation of the left atrium in cardiac MR angiography images. PMID:26068202

Interactive prostate segmentation using atlas-guided semi-supervised learning and adaptive feature selection

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

Park, Sang Hyun; Gao, Yaozong, E-mail: yzgao@cs.unc.edu; Shi, Yinghuan, E-mail: syh@nju.edu.cn

Purpose: Accurate prostate segmentation is necessary for maximizing the effectiveness of radiation therapy of prostate cancer. However, manual segmentation from 3D CT images is very time-consuming and often causes large intra- and interobserver variations across clinicians. Many segmentation methods have been proposed to automate this labor-intensive process, but tedious manual editing is still required due to the limited performance. In this paper, the authors propose a new interactive segmentation method that can (1) flexibly generate the editing result with a few scribbles or dots provided by a clinician, (2) fast deliver intermediate results to the clinician, and (3) sequentially correctmore » the segmentations from any type of automatic or interactive segmentation methods. Methods: The authors formulate the editing problem as a semisupervised learning problem which can utilize a priori knowledge of training data and also the valuable information from user interactions. Specifically, from a region of interest near the given user interactions, the appropriate training labels, which are well matched with the user interactions, can be locally searched from a training set. With voting from the selected training labels, both confident prostate and background voxels, as well as unconfident voxels can be estimated. To reflect informative relationship between voxels, location-adaptive features are selected from the confident voxels by using regression forest and Fisher separation criterion. Then, the manifold configuration computed in the derived feature space is enforced into the semisupervised learning algorithm. The labels of unconfident voxels are then predicted by regularizing semisupervised learning algorithm. Results: The proposed interactive segmentation method was applied to correct automatic segmentation results of 30 challenging CT images. The correction was conducted three times with different user interactions performed at different time periods, in order to evaluate both the efficiency and the robustness. The automatic segmentation results with the original average Dice similarity coefficient of 0.78 were improved to 0.865–0.872 after conducting 55–59 interactions by using the proposed method, where each editing procedure took less than 3 s. In addition, the proposed method obtained the most consistent editing results with respect to different user interactions, compared to other methods. Conclusions: The proposed method obtains robust editing results with few interactions for various wrong segmentation cases, by selecting the location-adaptive features and further imposing the manifold regularization. The authors expect the proposed method to largely reduce the laborious burdens of manual editing, as well as both the intra- and interobserver variability across clinicians.« less

Automated processing of label-free Raman microscope images of macrophage cells with standardized regression for high-throughput analysis.

PubMed

Milewski, Robert J; Kumagai, Yutaro; Fujita, Katsumasa; Standley, Daron M; Smith, Nicholas I

2010-11-19

Macrophages represent the front lines of our immune system; they recognize and engulf pathogens or foreign particles thus initiating the immune response. Imaging macrophages presents unique challenges, as most optical techniques require labeling or staining of the cellular compartments in order to resolve organelles, and such stains or labels have the potential to perturb the cell, particularly in cases where incomplete information exists regarding the precise cellular reaction under observation. Label-free imaging techniques such as Raman microscopy are thus valuable tools for studying the transformations that occur in immune cells upon activation, both on the molecular and organelle levels. Due to extremely low signal levels, however, Raman microscopy requires sophisticated image processing techniques for noise reduction and signal extraction. To date, efficient, automated algorithms for resolving sub-cellular features in noisy, multi-dimensional image sets have not been explored extensively. We show that hybrid z-score normalization and standard regression (Z-LSR) can highlight the spectral differences within the cell and provide image contrast dependent on spectral content. In contrast to typical Raman imaging processing methods using multivariate analysis, such as single value decomposition (SVD), our implementation of the Z-LSR method can operate nearly in real-time. In spite of its computational simplicity, Z-LSR can automatically remove background and bias in the signal, improve the resolution of spatially distributed spectral differences and enable sub-cellular features to be resolved in Raman microscopy images of mouse macrophage cells. Significantly, the Z-LSR processed images automatically exhibited subcellular architectures whereas SVD, in general, requires human assistance in selecting the components of interest. The computational efficiency of Z-LSR enables automated resolution of sub-cellular features in large Raman microscopy data sets without compromise in image quality or information loss in associated spectra. These results motivate further use of label free microscopy techniques in real-time imaging of live immune cells.

Automaticity of Basic-Level Categorization Accounts for Labeling Effects in Visual Recognition Memory

ERIC Educational Resources Information Center

Richler, Jennifer J.; Gauthier, Isabel; Palmeri, Thomas J.

2011-01-01

Are there consequences of calling objects by their names? Lupyan (2008) suggested that overtly labeling objects impairs subsequent recognition memory because labeling shifts stored memory representations of objects toward the category prototype (representational shift hypothesis). In Experiment 1, we show that processing objects at the basic…

16 CFR 1211.25 - Product certification and labeling by importers.

Code of Federal Regulations, 2010 CFR

2010-01-01

... 16 Commercial Practices 2 2010-01-01 2010-01-01 false Product certification and labeling by importers. 1211.25 Section 1211.25 Commercial Practices CONSUMER PRODUCT SAFETY COMMISSION CONSUMER PRODUCT... § 1211.25 Product certification and labeling by importers. (a) General. The importer of any automatic...

Human Expert Labeling Process (HELP): Towards a Reliable Higher-Order User State Labeling Process and Tool to Assess Student Engagement

ERIC Educational Resources Information Center

Aslan, Sinem; Mete, Sinem Emine; Okur, Eda; Oktay, Ece; Alyuz, Nese; Genc, Utku Ergin; Stanhill, David; Esme, Asli Arslan

2017-01-01

In a series of longitudinal research studies, researchers at Intel Corporation in Turkey have been working towards an adaptive learning system automatically detecting student engagement as a higher-order user state in real-time. The labeled data necessary for supervised learning can be obtained through labeling conducted by human experts. Using…

Textural-Contextual Labeling and Metadata Generation for Remote Sensing Applications

NASA Technical Reports Server (NTRS)

Kiang, Richard K.

1999-01-01

Despite the extensive research and the advent of several new information technologies in the last three decades, machine labeling of ground categories using remotely sensed data has not become a routine process. Considerable amount of human intervention is needed to achieve a level of acceptable labeling accuracy. A number of fundamental reasons may explain why machine labeling has not become automatic. In addition, there may be shortcomings in the methodology for labeling ground categories. The spatial information of a pixel, whether textural or contextual, relates a pixel to its surroundings. This information should be utilized to improve the performance of machine labeling of ground categories. Landsat-4 Thematic Mapper (TM) data taken in July 1982 over an area in the vicinity of Washington, D.C. are used in this study. On-line texture extraction by neural networks may not be the most efficient way to incorporate textural information into the labeling process. Texture features are pre-computed from cooccurrence matrices and then combined with a pixel's spectral and contextual information as the input to a neural network. The improvement in labeling accuracy with spatial information included is significant. The prospect of automatic generation of metadata consisting of ground categories, textural and contextual information is discussed.

Improving condition severity classification with an efficient active learning based framework.

PubMed

Nissim, Nir; Boland, Mary Regina; Tatonetti, Nicholas P; Elovici, Yuval; Hripcsak, George; Shahar, Yuval; Moskovitch, Robert

2016-06-01

Classification of condition severity can be useful for discriminating among sets of conditions or phenotypes, for example when prioritizing patient care or for other healthcare purposes. Electronic Health Records (EHRs) represent a rich source of labeled information that can be harnessed for severity classification. The labeling of EHRs is expensive and in many cases requires employing professionals with high level of expertise. In this study, we demonstrate the use of Active Learning (AL) techniques to decrease expert labeling efforts. We employ three AL methods and demonstrate their ability to reduce labeling efforts while effectively discriminating condition severity. We incorporate three AL methods into a new framework based on the original CAESAR (Classification Approach for Extracting Severity Automatically from Electronic Health Records) framework to create the Active Learning Enhancement framework (CAESAR-ALE). We applied CAESAR-ALE to a dataset containing 516 conditions of varying severity levels that were manually labeled by seven experts. Our dataset, called the "CAESAR dataset," was created from the medical records of 1.9 million patients treated at Columbia University Medical Center (CUMC). All three AL methods decreased labelers' efforts compared to the learning methods applied by the original CAESER framework in which the classifier was trained on the entire set of conditions; depending on the AL strategy used in the current study, the reduction ranged from 48% to 64% that can result in significant savings, both in time and money. As for the PPV (precision) measure, CAESAR-ALE achieved more than 13% absolute improvement in the predictive capabilities of the framework when classifying conditions as severe. These results demonstrate the potential of AL methods to decrease the labeling efforts of medical experts, while increasing accuracy given the same (or even a smaller) number of acquired conditions. We also demonstrated that the methods included in the CAESAR-ALE framework (Exploitation and Combination_XA) are more robust to the use of human labelers with different levels of professional expertise. Copyright © 2016 Elsevier Inc. All rights reserved.

A Machine Learning-based Method for Question Type Classification in Biomedical Question Answering.

PubMed

Sarrouti, Mourad; Ouatik El Alaoui, Said

2017-05-18

Biomedical question type classification is one of the important components of an automatic biomedical question answering system. The performance of the latter depends directly on the performance of its biomedical question type classification system, which consists of assigning a category to each question in order to determine the appropriate answer extraction algorithm. This study aims to automatically classify biomedical questions into one of the four categories: (1) yes/no, (2) factoid, (3) list, and (4) summary. In this paper, we propose a biomedical question type classification method based on machine learning approaches to automatically assign a category to a biomedical question. First, we extract features from biomedical questions using the proposed handcrafted lexico-syntactic patterns. Then, we feed these features for machine-learning algorithms. Finally, the class label is predicted using the trained classifiers. Experimental evaluations performed on large standard annotated datasets of biomedical questions, provided by the BioASQ challenge, demonstrated that our method exhibits significant improved performance when compared to four baseline systems. The proposed method achieves a roughly 10-point increase over the best baseline in terms of accuracy. Moreover, the obtained results show that using handcrafted lexico-syntactic patterns as features' provider of support vector machine (SVM) lead to the highest accuracy of 89.40 %. The proposed method can automatically classify BioASQ questions into one of the four categories: yes/no, factoid, list, and summary. Furthermore, the results demonstrated that our method produced the best classification performance compared to four baseline systems.

Image Quality Assessment of JPEG Compressed Mars Science Laboratory Mastcam Images using Convolutional Neural Networks

NASA Astrophysics Data System (ADS)

Kerner, H. R.; Bell, J. F., III; Ben Amor, H.

2017-12-01

The Mastcam color imaging system on the Mars Science Laboratory Curiosity rover acquires images within Gale crater for a variety of geologic and atmospheric studies. Images are often JPEG compressed before being downlinked to Earth. While critical for transmitting images on a low-bandwidth connection, this compression can result in image artifacts most noticeable as anomalous brightness or color changes within or near JPEG compression block boundaries. In images with significant high-frequency detail (e.g., in regions showing fine layering or lamination in sedimentary rocks), the image might need to be re-transmitted losslessly to enable accurate scientific interpretation of the data. The process of identifying which images have been adversely affected by compression artifacts is performed manually by the Mastcam science team, costing significant expert human time. To streamline the tedious process of identifying which images might need to be re-transmitted, we present an input-efficient neural network solution for predicting the perceived quality of a compressed Mastcam image. Most neural network solutions require large amounts of hand-labeled training data for the model to learn the target mapping between input (e.g. distorted images) and output (e.g. quality assessment). We propose an automatic labeling method using joint entropy between a compressed and uncompressed image to avoid the need for domain experts to label thousands of training examples by hand. We use automatically labeled data to train a convolutional neural network to estimate the probability that a Mastcam user would find the quality of a given compressed image acceptable for science analysis. We tested our model on a variety of Mastcam images and found that the proposed method correlates well with image quality perception by science team members. When assisted by our proposed method, we estimate that a Mastcam investigator could reduce the time spent reviewing images by a minimum of 70%.

Label fusion based brain MR image segmentation via a latent selective model

NASA Astrophysics Data System (ADS)

Liu, Gang; Guo, Xiantang; Zhu, Kai; Liao, Hengxu

2018-04-01

Multi-atlas segmentation is an effective approach and increasingly popular for automatically labeling objects of interest in medical images. Recently, segmentation methods based on generative models and patch-based techniques have become the two principal branches of label fusion. However, these generative models and patch-based techniques are only loosely related, and the requirement for higher accuracy, faster segmentation, and robustness is always a great challenge. In this paper, we propose novel algorithm that combines the two branches using global weighted fusion strategy based on a patch latent selective model to perform segmentation of specific anatomical structures for human brain magnetic resonance (MR) images. In establishing this probabilistic model of label fusion between the target patch and patch dictionary, we explored the Kronecker delta function in the label prior, which is more suitable than other models, and designed a latent selective model as a membership prior to determine from which training patch the intensity and label of the target patch are generated at each spatial location. Because the image background is an equally important factor for segmentation, it is analyzed in label fusion procedure and we regard it as an isolated label to keep the same privilege between the background and the regions of interest. During label fusion with the global weighted fusion scheme, we use Bayesian inference and expectation maximization algorithm to estimate the labels of the target scan to produce the segmentation map. Experimental results indicate that the proposed algorithm is more accurate and robust than the other segmentation methods.

Automatic metro map layout using multicriteria optimization.

PubMed

Stott, Jonathan; Rodgers, Peter; Martínez-Ovando, Juan Carlos; Walker, Stephen G

2011-01-01

This paper describes an automatic mechanism for drawing metro maps. We apply multicriteria optimization to find effective placement of stations with a good line layout and to label the map unambiguously. A number of metrics are defined, which are used in a weighted sum to find a fitness value for a layout of the map. A hill climbing optimizer is used to reduce the fitness value, and find improved map layouts. To avoid local minima, we apply clustering techniques to the map-the hill climber moves both stations and clusters when finding improved layouts. We show the method applied to a number of metro maps, and describe an empirical study that provides some quantitative evidence that automatically-drawn metro maps can help users to find routes more efficiently than either published maps or undistorted maps. Moreover, we have found that, in these cases, study subjects indicate a preference for automatically-drawn maps over the alternatives. © 2011 IEEE Published by the IEEE Computer Society

Alzheimer's disease detection via automatic 3D caudate nucleus segmentation using coupled dictionary learning with level set formulation.

PubMed

Al-Shaikhli, Saif Dawood Salman; Yang, Michael Ying; Rosenhahn, Bodo

2016-12-01

This paper presents a novel method for Alzheimer's disease classification via an automatic 3D caudate nucleus segmentation. The proposed method consists of segmentation and classification steps. In the segmentation step, we propose a novel level set cost function. The proposed cost function is constrained by a sparse representation of local image features using a dictionary learning method. We present coupled dictionaries: a feature dictionary of a grayscale brain image and a label dictionary of a caudate nucleus label image. Using online dictionary learning, the coupled dictionaries are learned from the training data. The learned coupled dictionaries are embedded into a level set function. In the classification step, a region-based feature dictionary is built. The region-based feature dictionary is learned from shape features of the caudate nucleus in the training data. The classification is based on the measure of the similarity between the sparse representation of region-based shape features of the segmented caudate in the test image and the region-based feature dictionary. The experimental results demonstrate the superiority of our method over the state-of-the-art methods by achieving a high segmentation (91.5%) and classification (92.5%) accuracy. In this paper, we find that the study of the caudate nucleus atrophy gives an advantage over the study of whole brain structure atrophy to detect Alzheimer's disease. Copyright © 2016 Elsevier Ireland Ltd. All rights reserved.

Segmentation and labeling of the ventricular system in normal pressure hydrocephalus using patch-based tissue classification and multi-atlas labeling

NASA Astrophysics Data System (ADS)

Ellingsen, Lotta M.; Roy, Snehashis; Carass, Aaron; Blitz, Ari M.; Pham, Dzung L.; Prince, Jerry L.

2016-03-01

Normal pressure hydrocephalus (NPH) affects older adults and is thought to be caused by obstruction of the normal flow of cerebrospinal fluid (CSF). NPH typically presents with cognitive impairment, gait dysfunction, and urinary incontinence, and may account for more than five percent of all cases of dementia. Unlike most other causes of dementia, NPH can potentially be treated and the neurological dysfunction reversed by shunt surgery or endoscopic third ventriculostomy (ETV), which drain excess CSF. However, a major diagnostic challenge remains to robustly identify shunt-responsive NPH patients from patients with enlarged ventricles due to other neurodegenerative diseases. Currently, radiologists grade the severity of NPH by detailed examination and measurement of the ventricles based on stacks of 2D magnetic resonance images (MRIs). Here we propose a new method to automatically segment and label different compartments of the ventricles in NPH patients from MRIs. While this task has been achieved in healthy subjects, the ventricles in NPH are both enlarged and deformed, causing current algorithms to fail. Here we combine a patch-based tissue classification method with a registration-based multi-atlas labeling method to generate a novel algorithm that labels the lateral, third, and fourth ventricles in subjects with ventriculomegaly. The method is also applicable to other neurodegenerative diseases such as Alzheimer's disease; a condition considered in the differential diagnosis of NPH. Comparison with state of the art segmentation techniques demonstrate substantial improvements in labeling the enlarged ventricles, indicating that this strategy may be a viable option for the diagnosis and characterization of NPH.

21 CFR 801.40 - Form of a unique device identifier.

Code of Federal Regulations, 2014 CFR

2014-04-01

...) Automatic identification and data capture (AIDC) technology. (b) The UDI must include a device identifier... evident upon visual examination of the label or device package, the label or device package must disclose... label and device packages is deemed to meet all requirements of subpart B of this part. The UPC will...

A mixture model with a reference-based automatic selection of components for disease classification from protein and/or gene expression levels

PubMed Central

2011-01-01

Background Bioinformatics data analysis is often using linear mixture model representing samples as additive mixture of components. Properly constrained blind matrix factorization methods extract those components using mixture samples only. However, automatic selection of extracted components to be retained for classification analysis remains an open issue. Results The method proposed here is applied to well-studied protein and genomic datasets of ovarian, prostate and colon cancers to extract components for disease prediction. It achieves average sensitivities of: 96.2 (sd = 2.7%), 97.6% (sd = 2.8%) and 90.8% (sd = 5.5%) and average specificities of: 93.6% (sd = 4.1%), 99% (sd = 2.2%) and 79.4% (sd = 9.8%) in 100 independent two-fold cross-validations. Conclusions We propose an additive mixture model of a sample for feature extraction using, in principle, sparseness constrained factorization on a sample-by-sample basis. As opposed to that, existing methods factorize complete dataset simultaneously. The sample model is composed of a reference sample representing control and/or case (disease) groups and a test sample. Each sample is decomposed into two or more components that are selected automatically (without using label information) as control specific, case specific and not differentially expressed (neutral). The number of components is determined by cross-validation. Automatic assignment of features (m/z ratios or genes) to particular component is based on thresholds estimated from each sample directly. Due to the locality of decomposition, the strength of the expression of each feature across the samples can vary. Yet, they will still be allocated to the related disease and/or control specific component. Since label information is not used in the selection process, case and control specific components can be used for classification. That is not the case with standard factorization methods. Moreover, the component selected by proposed method as disease specific can be interpreted as a sub-mode and retained for further analysis to identify potential biomarkers. As opposed to standard matrix factorization methods this can be achieved on a sample (experiment)-by-sample basis. Postulating one or more components with indifferent features enables their removal from disease and control specific components on a sample-by-sample basis. This yields selected components with reduced complexity and generally, it increases prediction accuracy. PMID:22208882

Performing label-fusion-based segmentation using multiple automatically generated templates.

PubMed

Chakravarty, M Mallar; Steadman, Patrick; van Eede, Matthijs C; Calcott, Rebecca D; Gu, Victoria; Shaw, Philip; Raznahan, Armin; Collins, D Louis; Lerch, Jason P

2013-10-01

Classically, model-based segmentation procedures match magnetic resonance imaging (MRI) volumes to an expertly labeled atlas using nonlinear registration. The accuracy of these techniques are limited due to atlas biases, misregistration, and resampling error. Multi-atlas-based approaches are used as a remedy and involve matching each subject to a number of manually labeled templates. This approach yields numerous independent segmentations that are fused using a voxel-by-voxel label-voting procedure. In this article, we demonstrate how the multi-atlas approach can be extended to work with input atlases that are unique and extremely time consuming to construct by generating a library of multiple automatically generated templates of different brains (MAGeT Brain). We demonstrate the efficacy of our method for the mouse and human using two different nonlinear registration algorithms (ANIMAL and ANTs). The input atlases consist a high-resolution mouse brain atlas and an atlas of the human basal ganglia and thalamus derived from serial histological data. MAGeT Brain segmentation improves the identification of the mouse anterior commissure (mean Dice Kappa values (κ = 0.801), but may be encountering a ceiling effect for hippocampal segmentations. Applying MAGeT Brain to human subcortical structures improves segmentation accuracy for all structures compared to regular model-based techniques (κ = 0.845, 0.752, and 0.861 for the striatum, globus pallidus, and thalamus, respectively). Experiments performed with three manually derived input templates suggest that MAGeT Brain can approach or exceed the accuracy of multi-atlas label-fusion segmentation (κ = 0.894, 0.815, and 0.895 for the striatum, globus pallidus, and thalamus, respectively). Copyright © 2012 Wiley Periodicals, Inc.

OpenCL based machine learning labeling of biomedical datasets

NASA Astrophysics Data System (ADS)

Amoros, Oscar; Escalera, Sergio; Puig, Anna

2011-03-01

In this paper, we propose a two-stage labeling method of large biomedical datasets through a parallel approach in a single GPU. Diagnostic methods, structures volume measurements, and visualization systems are of major importance for surgery planning, intra-operative imaging and image-guided surgery. In all cases, to provide an automatic and interactive method to label or to tag different structures contained into input data becomes imperative. Several approaches to label or segment biomedical datasets has been proposed to discriminate different anatomical structures in an output tagged dataset. Among existing methods, supervised learning methods for segmentation have been devised to easily analyze biomedical datasets by a non-expert user. However, they still have some problems concerning practical application, such as slow learning and testing speeds. In addition, recent technological developments have led to widespread availability of multi-core CPUs and GPUs, as well as new software languages, such as NVIDIA's CUDA and OpenCL, allowing to apply parallel programming paradigms in conventional personal computers. Adaboost classifier is one of the most widely applied methods for labeling in the Machine Learning community. In a first stage, Adaboost trains a binary classifier from a set of pre-labeled samples described by a set of features. This binary classifier is defined as a weighted combination of weak classifiers. Each weak classifier is a simple decision function estimated on a single feature value. Then, at the testing stage, each weak classifier is independently applied on the features of a set of unlabeled samples. In this work, we propose an alternative representation of the Adaboost binary classifier. We use this proposed representation to define a new GPU-based parallelized Adaboost testing stage using OpenCL. We provide numerical experiments based on large available data sets and we compare our results to CPU-based strategies in terms of time and labeling speeds.

Improving condition severity classification with an efficient active learning based framework

PubMed Central

Nissim, Nir; Boland, Mary Regina; Tatonetti, Nicholas P.; Elovici, Yuval; Hripcsak, George; Shahar, Yuval; Moskovitch, Robert

2017-01-01

Classification of condition severity can be useful for discriminating among sets of conditions or phenotypes, for example when prioritizing patient care or for other healthcare purposes. Electronic Health Records (EHRs) represent a rich source of labeled information that can be harnessed for severity classification. The labeling of EHRs is expensive and in many cases requires employing professionals with high level of expertise. In this study, we demonstrate the use of Active Learning (AL) techniques to decrease expert labeling efforts. We employ three AL methods and demonstrate their ability to reduce labeling efforts while effectively discriminating condition severity. We incorporate three AL methods into a new framework based on the original CAESAR (Classification Approach for Extracting Severity Automatically from Electronic Health Records) framework to create the Active Learning Enhancement framework (CAESAR-ALE). We applied CAESAR-ALE to a dataset containing 516 conditions of varying severity levels that were manually labeled by seven experts. Our dataset, called the “CAESAR dataset,” was created from the medical records of 1.9 million patients treated at Columbia University Medical Center (CUMC). All three AL methods decreased labelers’ efforts compared to the learning methods applied by the original CAESER framework in which the classifier was trained on the entire set of conditions; depending on the AL strategy used in the current study, the reduction ranged from 48% to 64% that can result in significant savings, both in time and money. As for the PPV (precision) measure, CAESAR-ALE achieved more than 13% absolute improvement in the predictive capabilities of the framework when classifying conditions as severe. These results demonstrate the potential of AL methods to decrease the labeling efforts of medical experts, while increasing accuracy given the same (or even a smaller) number of acquired conditions. We also demonstrated that the methods included in the CAESAR-ALE framework (Exploitation and Combination_XA) are more robust to the use of human labelers with different levels of professional expertise. PMID:27016383

Segmentation of whole cells and cell nuclei from 3-D optical microscope images using dynamic programming.

PubMed

McCullough, D P; Gudla, P R; Harris, B S; Collins, J A; Meaburn, K J; Nakaya, M A; Yamaguchi, T P; Misteli, T; Lockett, S J

2008-05-01

Communications between cells in large part drive tissue development and function, as well as disease-related processes such as tumorigenesis. Understanding the mechanistic bases of these processes necessitates quantifying specific molecules in adjacent cells or cell nuclei of intact tissue. However, a major restriction on such analyses is the lack of an efficient method that correctly segments each object (cell or nucleus) from 3-D images of an intact tissue specimen. We report a highly reliable and accurate semi-automatic algorithmic method for segmenting fluorescence-labeled cells or nuclei from 3-D tissue images. Segmentation begins with semi-automatic, 2-D object delineation in a user-selected plane, using dynamic programming (DP) to locate the border with an accumulated intensity per unit length greater that any other possible border around the same object. Then the two surfaces of the object in planes above and below the selected plane are found using an algorithm that combines DP and combinatorial searching. Following segmentation, any perceived errors can be interactively corrected. Segmentation accuracy is not significantly affected by intermittent labeling of object surfaces, diffuse surfaces, or spurious signals away from surfaces. The unique strength of the segmentation method was demonstrated on a variety of biological tissue samples where all cells, including irregularly shaped cells, were accurately segmented based on visual inspection.

Reproducibility of Brain Morphometry from Short-Term Repeat Clinical MRI Examinations: A Retrospective Study

PubMed Central

Liu, Hon-Man; Chen, Shan-Kai; Chen, Ya-Fang; Lee, Chung-Wei; Yeh, Lee-Ren

2016-01-01

Purpose To assess the inter session reproducibility of automatic segmented MRI-derived measures by FreeSurfer in a group of subjects with normal-appearing MR images. Materials and Methods After retrospectively reviewing a brain MRI database from our institute consisting of 14,758 adults, those subjects who had repeat scans and had no history of neurodegenerative disorders were selected for morphometry analysis using FreeSurfer. A total of 34 subjects were grouped by MRI scanner model. After automatic segmentation using FreeSurfer, label-wise comparison (involving area, thickness, and volume) was performed on all segmented results. An intraclass correlation coefficient was used to estimate the agreement between sessions. Wilcoxon signed rank test was used to assess the population mean rank differences across sessions. Mean-difference analysis was used to evaluate the difference intervals across scanners. Absolute percent difference was used to estimate the reproducibility errors across the MRI models. Kruskal-Wallis test was used to determine the across-scanner effect. Results The agreement in segmentation results for area, volume, and thickness measurements of all segmented anatomical labels was generally higher in Signa Excite and Verio models when compared with Sonata and TrioTim models. There were significant rank differences found across sessions in some labels of different measures. Smaller difference intervals in global volume measurements were noted on images acquired by Signa Excite and Verio models. For some brain regions, significant MRI model effects were observed on certain segmentation results. Conclusions Short-term scan-rescan reliability of automatic brain MRI morphometry is feasible in the clinical setting. However, since repeatability of software performance is contingent on the reproducibility of the scanner performance, the scanner performance must be calibrated before conducting such studies or before using such software for retrospective reviewing. PMID:26812647

An Automatic Segmentation Method Combining an Active Contour Model and a Classification Technique for Detecting Polycomb-group Proteinsin High-Throughput Microscopy Images.

PubMed

Gregoretti, Francesco; Cesarini, Elisa; Lanzuolo, Chiara; Oliva, Gennaro; Antonelli, Laura

2016-01-01

The large amount of data generated in biological experiments that rely on advanced microscopy can be handled only with automated image analysis. Most analyses require a reliable cell image segmentation eventually capable of detecting subcellular structures.We present an automatic segmentation method to detect Polycomb group (PcG) proteins areas isolated from nuclei regions in high-resolution fluorescent cell image stacks. It combines two segmentation algorithms that use an active contour model and a classification technique serving as a tool to better understand the subcellular three-dimensional distribution of PcG proteins in live cell image sequences. We obtained accurate results throughout several cell image datasets, coming from different cell types and corresponding to different fluorescent labels, without requiring elaborate adjustments to each dataset.

Disease named entity recognition from biomedical literature using a novel convolutional neural network.

PubMed

Zhao, Zhehuan; Yang, Zhihao; Luo, Ling; Wang, Lei; Zhang, Yin; Lin, Hongfei; Wang, Jian

2017-12-28

Automatic disease named entity recognition (DNER) is of utmost importance for development of more sophisticated BioNLP tools. However, most conventional CRF based DNER systems rely on well-designed features whose selection is labor intensive and time-consuming. Though most deep learning methods can solve NER problems with little feature engineering, they employ additional CRF layer to capture the correlation information between labels in neighborhoods which makes them much complicated. In this paper, we propose a novel multiple label convolutional neural network (MCNN) based disease NER approach. In this approach, instead of the CRF layer, a multiple label strategy (MLS) first introduced by us, is employed. First, the character-level embedding, word-level embedding and lexicon feature embedding are concatenated. Then several convolutional layers are stacked over the concatenated embedding. Finally, MLS strategy is applied to the output layer to capture the correlation information between neighboring labels. As shown by the experimental results, MCNN can achieve the state-of-the-art performance on both NCBI and CDR corpora. The proposed MCNN based disease NER method achieves the state-of-the-art performance with little feature engineering. And the experimental results show the MLS strategy's effectiveness of capturing the correlation information between labels in the neighborhood.

Active Learning Strategies for Phenotypic Profiling of High-Content Screens.

PubMed

Smith, Kevin; Horvath, Peter

2014-06-01

High-content screening is a powerful method to discover new drugs and carry out basic biological research. Increasingly, high-content screens have come to rely on supervised machine learning (SML) to perform automatic phenotypic classification as an essential step of the analysis. However, this comes at a cost, namely, the labeled examples required to train the predictive model. Classification performance increases with the number of labeled examples, and because labeling examples demands time from an expert, the training process represents a significant time investment. Active learning strategies attempt to overcome this bottleneck by presenting the most relevant examples to the annotator, thereby achieving high accuracy while minimizing the cost of obtaining labeled data. In this article, we investigate the impact of active learning on single-cell-based phenotype recognition, using data from three large-scale RNA interference high-content screens representing diverse phenotypic profiling problems. We consider several combinations of active learning strategies and popular SML methods. Our results show that active learning significantly reduces the time cost and can be used to reveal the same phenotypic targets identified using SML. We also identify combinations of active learning strategies and SML methods which perform better than others on the phenotypic profiling problems we studied. © 2014 Society for Laboratory Automation and Screening.

A review of automatic patient identification options for public health care centers with restricted budgets.

PubMed

García-Betances, Rebeca I; Huerta, Mónica K

2012-01-01

A comparative review is presented of available technologies suitable for automatic reading of patient identification bracelet tags. Existing technologies' backgrounds, characteristics, advantages and disadvantages, are described in relation to their possible use by public health care centers with budgetary limitations. A comparative assessment is presented of suitable automatic identification systems based on graphic codes, both one- (1D) and two-dimensional (2D), printed on labels, as well as those based on radio frequency identification (RFID) tags. The analysis looks at the tradeoffs of these technologies to provide guidance to hospital administrator looking to deploy patient identification technology. The results suggest that affordable automatic patient identification systems can be easily and inexpensively implemented using 2D code printed on low cost bracelet labels, which can then be read and automatically decoded by ordinary mobile smart phones. Because of mobile smart phones' present versatility and ubiquity, the implantation and operation of 2D code, and especially Quick Response® (QR) Code, technology emerges as a very attractive alternative to automate the patients' identification processes in low-budget situations.

A Review of Automatic Patient Identification Options for Public Health Care Centers with Restricted Budgets

PubMed Central

García-Betances, Rebeca I.; Huerta, Mónica K.

2012-01-01

A comparative review is presented of available technologies suitable for automatic reading of patient identification bracelet tags. Existing technologies’ backgrounds, characteristics, advantages and disadvantages, are described in relation to their possible use by public health care centers with budgetary limitations. A comparative assessment is presented of suitable automatic identification systems based on graphic codes, both one- (1D) and two-dimensional (2D), printed on labels, as well as those based on radio frequency identification (RFID) tags. The analysis looks at the tradeoffs of these technologies to provide guidance to hospital administrator looking to deploy patient identification technology. The results suggest that affordable automatic patient identification systems can be easily and inexpensively implemented using 2D code printed on low cost bracelet labels, which can then be read and automatically decoded by ordinary mobile smart phones. Because of mobile smart phones’ present versatility and ubiquity, the implantation and operation of 2D code, and especially Quick Response® (QR) Code, technology emerges as a very attractive alternative to automate the patients’ identification processes in low-budget situations. PMID:23569629

Automatic crack detection method for loaded coal in vibration failure process

PubMed Central

Li, Chengwu

2017-01-01

In the coal mining process, the destabilization of loaded coal mass is a prerequisite for coal and rock dynamic disaster, and surface cracks of the coal and rock mass are important indicators, reflecting the current state of the coal body. The detection of surface cracks in the coal body plays an important role in coal mine safety monitoring. In this paper, a method for detecting the surface cracks of loaded coal by a vibration failure process is proposed based on the characteristics of the surface cracks of coal and support vector machine (SVM). A large number of cracked images are obtained by establishing a vibration-induced failure test system and industrial camera. Histogram equalization and a hysteresis threshold algorithm were used to reduce the noise and emphasize the crack; then, 600 images and regions, including cracks and non-cracks, were manually labelled. In the crack feature extraction stage, eight features of the cracks are extracted to distinguish cracks from other objects. Finally, a crack identification model with an accuracy over 95% was trained by inputting the labelled sample images into the SVM classifier. The experimental results show that the proposed algorithm has a higher accuracy than the conventional algorithm and can effectively identify cracks on the surface of the coal and rock mass automatically. PMID:28973032

Automatic crack detection method for loaded coal in vibration failure process.

PubMed

Li, Chengwu; Ai, Dihao

2017-01-01

In the coal mining process, the destabilization of loaded coal mass is a prerequisite for coal and rock dynamic disaster, and surface cracks of the coal and rock mass are important indicators, reflecting the current state of the coal body. The detection of surface cracks in the coal body plays an important role in coal mine safety monitoring. In this paper, a method for detecting the surface cracks of loaded coal by a vibration failure process is proposed based on the characteristics of the surface cracks of coal and support vector machine (SVM). A large number of cracked images are obtained by establishing a vibration-induced failure test system and industrial camera. Histogram equalization and a hysteresis threshold algorithm were used to reduce the noise and emphasize the crack; then, 600 images and regions, including cracks and non-cracks, were manually labelled. In the crack feature extraction stage, eight features of the cracks are extracted to distinguish cracks from other objects. Finally, a crack identification model with an accuracy over 95% was trained by inputting the labelled sample images into the SVM classifier. The experimental results show that the proposed algorithm has a higher accuracy than the conventional algorithm and can effectively identify cracks on the surface of the coal and rock mass automatically.

A Hybrid Probabilistic Model for Unified Collaborative and Content-Based Image Tagging.

PubMed

Zhou, Ning; Cheung, William K; Qiu, Guoping; Xue, Xiangyang

2011-07-01

The increasing availability of large quantities of user contributed images with labels has provided opportunities to develop automatic tools to tag images to facilitate image search and retrieval. In this paper, we present a novel hybrid probabilistic model (HPM) which integrates low-level image features and high-level user provided tags to automatically tag images. For images without any tags, HPM predicts new tags based solely on the low-level image features. For images with user provided tags, HPM jointly exploits both the image features and the tags in a unified probabilistic framework to recommend additional tags to label the images. The HPM framework makes use of the tag-image association matrix (TIAM). However, since the number of images is usually very large and user-provided tags are diverse, TIAM is very sparse, thus making it difficult to reliably estimate tag-to-tag co-occurrence probabilities. We developed a collaborative filtering method based on nonnegative matrix factorization (NMF) for tackling this data sparsity issue. Also, an L1 norm kernel method is used to estimate the correlations between image features and semantic concepts. The effectiveness of the proposed approach has been evaluated using three databases containing 5,000 images with 371 tags, 31,695 images with 5,587 tags, and 269,648 images with 5,018 tags, respectively.

An Automatic Segmentation and Classification Framework Based on PCNN Model for Single Tooth in MicroCT Images.

PubMed

Wang, Liansheng; Li, Shusheng; Chen, Rongzhen; Liu, Sze-Yu; Chen, Jyh-Cheng

2016-01-01

Accurate segmentation and classification of different anatomical structures of teeth from medical images plays an essential role in many clinical applications. Usually, the anatomical structures of teeth are manually labelled by experienced clinical doctors, which is time consuming. However, automatic segmentation and classification is a challenging task because the anatomical structures and surroundings of the tooth in medical images are rather complex. Therefore, in this paper, we propose an effective framework which is designed to segment the tooth with a Selective Binary and Gaussian Filtering Regularized Level Set (GFRLS) method improved by fully utilizing three dimensional (3D) information, and classify the tooth by employing unsupervised learning Pulse Coupled Neural Networks (PCNN) model. In order to evaluate the proposed method, the experiments are conducted on the different datasets of mandibular molars and the experimental results show that our method can achieve better accuracy and robustness compared to other four state of the art clustering methods.

Distant Supervision with Transductive Learning for Adverse Drug Reaction Identification from Electronic Medical Records

PubMed Central

Ikeda, Mitsuru

2017-01-01

Information extraction and knowledge discovery regarding adverse drug reaction (ADR) from large-scale clinical texts are very useful and needy processes. Two major difficulties of this task are the lack of domain experts for labeling examples and intractable processing of unstructured clinical texts. Even though most previous works have been conducted on these issues by applying semisupervised learning for the former and a word-based approach for the latter, they face with complexity in an acquisition of initial labeled data and ignorance of structured sequence of natural language. In this study, we propose automatic data labeling by distant supervision where knowledge bases are exploited to assign an entity-level relation label for each drug-event pair in texts, and then, we use patterns for characterizing ADR relation. The multiple-instance learning with expectation-maximization method is employed to estimate model parameters. The method applies transductive learning to iteratively reassign a probability of unknown drug-event pair at the training time. By investigating experiments with 50,998 discharge summaries, we evaluate our method by varying large number of parameters, that is, pattern types, pattern-weighting models, and initial and iterative weightings of relations for unlabeled data. Based on evaluations, our proposed method outperforms the word-based feature for NB-EM (iEM), MILR, and TSVM with F1 score of 11.3%, 9.3%, and 6.5% improvement, respectively. PMID:29090077

Automatic corpus callosum segmentation for standardized MR brain scanning

NASA Astrophysics Data System (ADS)

Xu, Qing; Chen, Hong; Zhang, Li; Novak, Carol L.

2007-03-01

Magnetic Resonance (MR) brain scanning is often planned manually with the goal of aligning the imaging plane with key anatomic landmarks. The planning is time-consuming and subject to inter- and intra- operator variability. An automatic and standardized planning of brain scans is highly useful for clinical applications, and for maximum utility should work on patients of all ages. In this study, we propose a method for fully automatic planning that utilizes the landmarks from two orthogonal images to define the geometry of the third scanning plane. The corpus callosum (CC) is segmented in sagittal images by an active shape model (ASM), and the result is further improved by weighting the boundary movement with confidence scores and incorporating region based refinement. Based on the extracted contour of the CC, several important landmarks are located and then combined with landmarks from the coronal or transverse plane to define the geometry of the third plane. Our automatic method is tested on 54 MR images from 24 patients and 3 healthy volunteers, with ages ranging from 4 months to 70 years old. The average accuracy with respect to two manually labeled points on the CC is 3.54 mm and 4.19 mm, and differed by an average of 2.48 degrees from the orientation of the line connecting them, demonstrating that our method is sufficiently accurate for clinical use.

Object-Location-Aware Hashing for Multi-Label Image Retrieval via Automatic Mask Learning.

PubMed

Huang, Chang-Qin; Yang, Shang-Ming; Pan, Yan; Lai, Han-Jiang

2018-09-01

Learning-based hashing is a leading approach of approximate nearest neighbor search for large-scale image retrieval. In this paper, we develop a deep supervised hashing method for multi-label image retrieval, in which we propose to learn a binary "mask" map that can identify the approximate locations of objects in an image, so that we use this binary "mask" map to obtain length-limited hash codes which mainly focus on an image's objects but ignore the background. The proposed deep architecture consists of four parts: 1) a convolutional sub-network to generate effective image features; 2) a binary "mask" sub-network to identify image objects' approximate locations; 3) a weighted average pooling operation based on the binary "mask" to obtain feature representations and hash codes that pay most attention to foreground objects but ignore the background; and 4) the combination of a triplet ranking loss designed to preserve relative similarities among images and a cross entropy loss defined on image labels. We conduct comprehensive evaluations on four multi-label image data sets. The results indicate that the proposed hashing method achieves superior performance gains over the state-of-the-art supervised or unsupervised hashing baselines.

Deep learning based beat event detection in action movie franchises

NASA Astrophysics Data System (ADS)

Ejaz, N.; Khan, U. A.; Martínez-del-Amor, M. A.; Sparenberg, H.

2018-04-01

Automatic understanding and interpretation of movies can be used in a variety of ways to semantically manage the massive volumes of movies data. "Action Movie Franchises" dataset is a collection of twenty Hollywood action movies from five famous franchises with ground truth annotations at shot and beat level of each movie. In this dataset, the annotations are provided for eleven semantic beat categories. In this work, we propose a deep learning based method to classify shots and beat-events on this dataset. The training dataset for each of the eleven beat categories is developed and then a Convolution Neural Network is trained. After finding the shot boundaries, key frames are extracted for each shot and then three classification labels are assigned to each key frame. The classification labels for each of the key frames in a particular shot are then used to assign a unique label to each shot. A simple sliding window based method is then used to group adjacent shots having the same label in order to find a particular beat event. The results of beat event classification are presented based on criteria of precision, recall, and F-measure. The results are compared with the existing technique and significant improvements are recorded.

Characterizing artifacts in RR stress test time series.

PubMed

Astudillo-Salinas, Fabian; Palacio-Baus, Kenneth; Solano-Quinde, Lizandro; Medina, Ruben; Wong, Sara

2016-08-01

Electrocardiographic stress test records have a lot of artifacts. In this paper we explore a simple method to characterize the amount of artifacts present in unprocessed RR stress test time series. Four time series classes were defined: Very good lead, Good lead, Low quality lead and Useless lead. 65 ECG, 8 lead, records of stress test series were analyzed. Firstly, RR-time series were annotated by two experts. The automatic methodology is based on dividing the RR-time series in non-overlapping windows. Each window is marked as noisy whenever it exceeds an established standard deviation threshold (SDT). Series are classified according to the percentage of windows that exceeds a given value, based upon the first manual annotation. Different SDT were explored. Results show that SDT close to 20% (as a percentage of the mean) provides the best results. The coincidence between annotators classification is 70.77% whereas, the coincidence between the second annotator and the automatic method providing the best matches is larger than 63%. Leads classified as Very good leads and Good leads could be combined to improve automatic heartbeat labeling.

Label-free sensor for automatic identification of erythrocytes using digital in-line holographic microscopy and machine learning.

PubMed

Go, Taesik; Byeon, Hyeokjun; Lee, Sang Joon

2018-04-30

Cell types of erythrocytes should be identified because they are closely related to their functionality and viability. Conventional methods for classifying erythrocytes are time consuming and labor intensive. Therefore, an automatic and accurate erythrocyte classification system is indispensable in healthcare and biomedical fields. In this study, we proposed a new label-free sensor for automatic identification of erythrocyte cell types using a digital in-line holographic microscopy (DIHM) combined with machine learning algorithms. A total of 12 features, including information on intensity distributions, morphological descriptors, and optical focusing characteristics, is quantitatively obtained from numerically reconstructed holographic images. All individual features for discocytes, echinocytes, and spherocytes are statistically different. To improve the performance of cell type identification, we adopted several machine learning algorithms, such as decision tree model, support vector machine, linear discriminant classification, and k-nearest neighbor classification. With the aid of these machine learning algorithms, the extracted features are effectively utilized to distinguish erythrocytes. Among the four tested algorithms, the decision tree model exhibits the best identification performance for the training sets (n = 440, 98.18%) and test sets (n = 190, 97.37%). This proposed methodology, which smartly combined DIHM and machine learning, would be helpful for sensing abnormal erythrocytes and computer-aided diagnosis of hematological diseases in clinic. Copyright © 2017 Elsevier B.V. All rights reserved.

9 CFR 112.6 - Packaging biological products.

Code of Federal Regulations, 2014 CFR

2014-01-01

... AGRICULTURE VIRUSES, SERUMS, TOXINS, AND ANALOGOUS PRODUCTS; ORGANISMS AND VECTORS PACKAGING AND LABELING... Disease Vaccine. (2) Poultry vaccines administered to individual birds using automatic vaccinating..., unless each final container bears, or is packaged in a carton with, complete and approved labeling which...

9 CFR 112.6 - Packaging biological products.

Code of Federal Regulations, 2013 CFR

2013-01-01

... AGRICULTURE VIRUSES, SERUMS, TOXINS, AND ANALOGOUS PRODUCTS; ORGANISMS AND VECTORS PACKAGING AND LABELING... Disease Vaccine. (2) Poultry vaccines administered to individual birds using automatic vaccinating..., unless each final container bears, or is packaged in a carton with, complete and approved labeling which...

9 CFR 112.6 - Packaging biological products.

Code of Federal Regulations, 2012 CFR

2012-01-01

... AGRICULTURE VIRUSES, SERUMS, TOXINS, AND ANALOGOUS PRODUCTS; ORGANISMS AND VECTORS PACKAGING AND LABELING... Disease Vaccine. (2) Poultry vaccines administered to individual birds using automatic vaccinating..., unless each final container bears, or is packaged in a carton with, complete and approved labeling which...

Detecting experimental techniques and selecting relevant documents for protein-protein interactions from biomedical literature.

PubMed

Wang, Xinglong; Rak, Rafal; Restificar, Angelo; Nobata, Chikashi; Rupp, C J; Batista-Navarro, Riza Theresa B; Nawaz, Raheel; Ananiadou, Sophia

2011-10-03

The selection of relevant articles for curation, and linking those articles to experimental techniques confirming the findings became one of the primary subjects of the recent BioCreative III contest. The contest's Protein-Protein Interaction (PPI) task consisted of two sub-tasks: Article Classification Task (ACT) and Interaction Method Task (IMT). ACT aimed to automatically select relevant documents for PPI curation, whereas the goal of IMT was to recognise the methods used in experiments for identifying the interactions in full-text articles. We proposed and compared several classification-based methods for both tasks, employing rich contextual features as well as features extracted from external knowledge sources. For IMT, a new method that classifies pair-wise relations between every text phrase and candidate interaction method obtained promising results with an F1 score of 64.49%, as tested on the task's development dataset. We also explored ways to combine this new approach and more conventional, multi-label document classification methods. For ACT, our classifiers exploited automatically detected named entities and other linguistic information. The evaluation results on the BioCreative III PPI test datasets showed that our systems were very competitive: one of our IMT methods yielded the best performance among all participants, as measured by F1 score, Matthew's Correlation Coefficient and AUC iP/R; whereas for ACT, our best classifier was ranked second as measured by AUC iP/R, and also competitive according to other metrics. Our novel approach that converts the multi-class, multi-label classification problem to a binary classification problem showed much promise in IMT. Nevertheless, on the test dataset the best performance was achieved by taking the union of the output of this method and that of a multi-class, multi-label document classifier, which indicates that the two types of systems complement each other in terms of recall. For ACT, our system exploited a rich set of features and also obtained encouraging results. We examined the features with respect to their contributions to the classification results, and concluded that contextual words surrounding named entities, as well as the MeSH headings associated with the documents were among the main contributors to the performance.

Automatic segmentation method of pelvic floor levator hiatus in ultrasound using a self-normalizing neural network

PubMed Central

Dietz, Hans Peter; D’hooge, Jan; Barratt, Dean; Deprest, Jan

2018-01-01

Abstract. Segmentation of the levator hiatus in ultrasound allows the extraction of biometrics, which are of importance for pelvic floor disorder assessment. We present a fully automatic method using a convolutional neural network (CNN) to outline the levator hiatus in a two-dimensional image extracted from a three-dimensional ultrasound volume. In particular, our method uses a recently developed scaled exponential linear unit (SELU) as a nonlinear self-normalizing activation function, which for the first time has been applied in medical imaging with CNN. SELU has important advantages such as being parameter-free and mini-batch independent, which may help to overcome memory constraints during training. A dataset with 91 images from 35 patients during Valsalva, contraction, and rest, all labeled by three operators, is used for training and evaluation in a leave-one-patient-out cross validation. Results show a median Dice similarity coefficient of 0.90 with an interquartile range of 0.08, with equivalent performance to the three operators (with a Williams’ index of 1.03), and outperforming a U-Net architecture without the need for batch normalization. We conclude that the proposed fully automatic method achieved equivalent accuracy in segmenting the pelvic floor levator hiatus compared to a previous semiautomatic approach. PMID:29340289

Automatic segmentation method of pelvic floor levator hiatus in ultrasound using a self-normalizing neural network.

PubMed

Bonmati, Ester; Hu, Yipeng; Sindhwani, Nikhil; Dietz, Hans Peter; D'hooge, Jan; Barratt, Dean; Deprest, Jan; Vercauteren, Tom

2018-04-01

Segmentation of the levator hiatus in ultrasound allows the extraction of biometrics, which are of importance for pelvic floor disorder assessment. We present a fully automatic method using a convolutional neural network (CNN) to outline the levator hiatus in a two-dimensional image extracted from a three-dimensional ultrasound volume. In particular, our method uses a recently developed scaled exponential linear unit (SELU) as a nonlinear self-normalizing activation function, which for the first time has been applied in medical imaging with CNN. SELU has important advantages such as being parameter-free and mini-batch independent, which may help to overcome memory constraints during training. A dataset with 91 images from 35 patients during Valsalva, contraction, and rest, all labeled by three operators, is used for training and evaluation in a leave-one-patient-out cross validation. Results show a median Dice similarity coefficient of 0.90 with an interquartile range of 0.08, with equivalent performance to the three operators (with a Williams' index of 1.03), and outperforming a U-Net architecture without the need for batch normalization. We conclude that the proposed fully automatic method achieved equivalent accuracy in segmenting the pelvic floor levator hiatus compared to a previous semiautomatic approach.

Multi-atlas and label fusion approach for patient-specific MRI based skull estimation.

PubMed

Torrado-Carvajal, Angel; Herraiz, Joaquin L; Hernandez-Tamames, Juan A; San Jose-Estepar, Raul; Eryaman, Yigitcan; Rozenholc, Yves; Adalsteinsson, Elfar; Wald, Lawrence L; Malpica, Norberto

2016-04-01

MRI-based skull segmentation is a useful procedure for many imaging applications. This study describes a methodology for automatic segmentation of the complete skull from a single T1-weighted volume. The skull is estimated using a multi-atlas segmentation approach. Using a whole head computed tomography (CT) scan database, the skull in a new MRI volume is detected by nonrigid image registration of the volume to every CT, and combination of the individual segmentations by label-fusion. We have compared Majority Voting, Simultaneous Truth and Performance Level Estimation (STAPLE), Shape Based Averaging (SBA), and the Selective and Iterative Method for Performance Level Estimation (SIMPLE) algorithms. The pipeline has been evaluated quantitatively using images from the Retrospective Image Registration Evaluation database (reaching an overlap of 72.46 ± 6.99%), a clinical CT-MR dataset (maximum overlap of 78.31 ± 6.97%), and a whole head CT-MRI pair (maximum overlap 78.68%). A qualitative evaluation has also been performed on MRI acquisition of volunteers. It is possible to automatically segment the complete skull from MRI data using a multi-atlas and label fusion approach. This will allow the creation of complete MRI-based tissue models that can be used in electromagnetic dosimetry applications and attenuation correction in PET/MR. © 2015 Wiley Periodicals, Inc.

Graph Learning in Knowledge Bases

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

Goldberg, Sean; Wang, Daisy Zhe

The amount of text data has been growing exponentially in recent years, giving rise to automatic information extraction methods that store text annotations in a database. The current state-of-theart structured prediction methods, however, are likely to contain errors and it’s important to be able to manage the overall uncertainty of the database. On the other hand, the advent of crowdsourcing has enabled humans to aid machine algorithms at scale. As part of this project we introduced pi-CASTLE , a system that optimizes and integrates human and machine computing as applied to a complex structured prediction problem involving conditional random fieldsmore » (CRFs). We proposed strategies grounded in information theory to select a token subset, formulate questions for the crowd to label, and integrate these labelings back into the database using a method of constrained inference. On both a text segmentation task over academic citations and a named entity recognition task over tweets we showed an order of magnitude improvement in accuracy gain over baseline methods.« less

Automatic ground control point recognition with parallel associative memory

NASA Technical Reports Server (NTRS)

Al-Tahir, Raid; Toth, Charles K.; Schenck, Anton F.

1990-01-01

The basic principle of the associative memory is to match the unknown input pattern against a stored training set, and responding with the 'closest match' and the corresponding label. Generally, an associative memory system requires two preparatory steps: selecting attributes of the pattern class, and training the system by associating patterns with labels. Experimental results gained from using Parallel Associative Memory are presented. The primary concern is an automatic search for ground control points in aerial photographs. Synthetic patterns are tested followed by real data. The results are encouraging as a relatively high level of correct matches is reached.

Joint Patch and Multi-label Learning for Facial Action Unit Detection

PubMed Central

Zhao, Kaili; Chu, Wen-Sheng; De la Torre, Fernando; Cohn, Jeffrey F.; Zhang, Honggang

2016-01-01

The face is one of the most powerful channel of nonverbal communication. The most commonly used taxonomy to describe facial behaviour is the Facial Action Coding System (FACS). FACS segments the visible effects of facial muscle activation into 30+ action units (AUs). AUs, which may occur alone and in thousands of combinations, can describe nearly all-possible facial expressions. Most existing methods for automatic AU detection treat the problem using one-vs-all classifiers and fail to exploit dependencies among AU and facial features. We introduce joint-patch and multi-label learning (JPML) to address these issues. JPML leverages group sparsity by selecting a sparse subset of facial patches while learning a multi-label classifier. In four of five comparisons on three diverse datasets, CK+, GFT, and BP4D, JPML produced the highest average F1 scores in comparison with state-of-the art. PMID:27382243

Automatic identification of IASLC-defined mediastinal lymph node stations on CT scans using multi-atlas organ segmentation

NASA Astrophysics Data System (ADS)

Hoffman, Joanne; Liu, Jiamin; Turkbey, Evrim; Kim, Lauren; Summers, Ronald M.

2015-03-01

Station-labeling of mediastinal lymph nodes is typically performed to identify the location of enlarged nodes for cancer staging. Stations are usually assigned in clinical radiology practice manually by qualitative visual assessment on CT scans, which is time consuming and highly variable. In this paper, we developed a method that automatically recognizes the lymph node stations in thoracic CT scans based on the anatomical organs in the mediastinum. First, the trachea, lungs, and spines are automatically segmented to locate the mediastinum region. Then, eight more anatomical organs are simultaneously identified by multi-atlas segmentation. Finally, with the segmentation of those anatomical organs, we convert the text definitions of the International Association for the Study of Lung Cancer (IASLC) lymph node map into patient-specific color-coded CT image maps. Thus, a lymph node station is automatically assigned to each lymph node. We applied this system to CT scans of 86 patients with 336 mediastinal lymph nodes measuring equal or greater than 10 mm. 84.8% of mediastinal lymph nodes were correctly mapped to their stations.

Semantic labeling of high-resolution aerial images using an ensemble of fully convolutional networks

NASA Astrophysics Data System (ADS)

Sun, Xiaofeng; Shen, Shuhan; Lin, Xiangguo; Hu, Zhanyi

2017-10-01

High-resolution remote sensing data classification has been a challenging and promising research topic in the community of remote sensing. In recent years, with the rapid advances of deep learning, remarkable progress has been made in this field, which facilitates a transition from hand-crafted features designing to an automatic end-to-end learning. A deep fully convolutional networks (FCNs) based ensemble learning method is proposed to label the high-resolution aerial images. To fully tap the potentials of FCNs, both the Visual Geometry Group network and a deeper residual network, ResNet, are employed. Furthermore, to enlarge training samples with diversity and gain better generalization, in addition to the commonly used data augmentation methods (e.g., rotation, multiscale, and aspect ratio) in the literature, aerial images from other datasets are also collected for cross-scene learning. Finally, we combine these learned models to form an effective FCN ensemble and refine the results using a fully connected conditional random field graph model. Experiments on the ISPRS 2-D Semantic Labeling Contest dataset show that our proposed end-to-end classification method achieves an overall accuracy of 90.7%, a state-of-the-art in the field.

Comparison of computer systems and ranking criteria for automatic melanoma detection in dermoscopic images.

PubMed

Møllersen, Kajsa; Zortea, Maciel; Schopf, Thomas R; Kirchesch, Herbert; Godtliebsen, Fred

2017-01-01

Melanoma is the deadliest form of skin cancer, and early detection is crucial for patient survival. Computer systems can assist in melanoma detection, but are not widespread in clinical practice. In 2016, an open challenge in classification of dermoscopic images of skin lesions was announced. A training set of 900 images with corresponding class labels and semi-automatic/manual segmentation masks was released for the challenge. An independent test set of 379 images, of which 75 were of melanomas, was used to rank the participants. This article demonstrates the impact of ranking criteria, segmentation method and classifier, and highlights the clinical perspective. We compare five different measures for diagnostic accuracy by analysing the resulting ranking of the computer systems in the challenge. Choice of performance measure had great impact on the ranking. Systems that were ranked among the top three for one measure, dropped to the bottom half when changing performance measure. Nevus Doctor, a computer system previously developed by the authors, was used to participate in the challenge, and investigate the impact of segmentation and classifier. The diagnostic accuracy when using an automatic versus the semi-automatic/manual segmentation is investigated. The unexpected small impact of segmentation method suggests that improvements of the automatic segmentation method w.r.t. resemblance to semi-automatic/manual segmentation will not improve diagnostic accuracy substantially. A small set of similar classification algorithms are used to investigate the impact of classifier on the diagnostic accuracy. The variability in diagnostic accuracy for different classifier algorithms was larger than the variability for segmentation methods, and suggests a focus for future investigations. From a clinical perspective, the misclassification of a melanoma as benign has far greater cost than the misclassification of a benign lesion. For computer systems to have clinical impact, their performance should be ranked by a high-sensitivity measure.

Unsupervised semantic indoor scene classification for robot vision based on context of features using Gist and HSV-SIFT

NASA Astrophysics Data System (ADS)

Madokoro, H.; Yamanashi, A.; Sato, K.

2013-08-01

This paper presents an unsupervised scene classification method for actualizing semantic recognition of indoor scenes. Background and foreground features are respectively extracted using Gist and color scale-invariant feature transform (SIFT) as feature representations based on context. We used hue, saturation, and value SIFT (HSV-SIFT) because of its simple algorithm with low calculation costs. Our method creates bags of features for voting visual words created from both feature descriptors to a two-dimensional histogram. Moreover, our method generates labels as candidates of categories for time-series images while maintaining stability and plasticity together. Automatic labeling of category maps can be realized using labels created using adaptive resonance theory (ART) as teaching signals for counter propagation networks (CPNs). We evaluated our method for semantic scene classification using KTH's image database for robot localization (KTH-IDOL), which is popularly used for robot localization and navigation. The mean classification accuracies of Gist, gray SIFT, one class support vector machines (OC-SVM), position-invariant robust features (PIRF), and our method are, respectively, 39.7, 58.0, 56.0, 63.6, and 79.4%. The result of our method is 15.8% higher than that of PIRF. Moreover, we applied our method for fine classification using our original mobile robot. We obtained mean classification accuracy of 83.2% for six zones.

SEGMA: An Automatic SEGMentation Approach for Human Brain MRI Using Sliding Window and Random Forests

PubMed Central

Serag, Ahmed; Wilkinson, Alastair G.; Telford, Emma J.; Pataky, Rozalia; Sparrow, Sarah A.; Anblagan, Devasuda; Macnaught, Gillian; Semple, Scott I.; Boardman, James P.

2017-01-01

Quantitative volumes from brain magnetic resonance imaging (MRI) acquired across the life course may be useful for investigating long term effects of risk and resilience factors for brain development and healthy aging, and for understanding early life determinants of adult brain structure. Therefore, there is an increasing need for automated segmentation tools that can be applied to images acquired at different life stages. We developed an automatic segmentation method for human brain MRI, where a sliding window approach and a multi-class random forest classifier were applied to high-dimensional feature vectors for accurate segmentation. The method performed well on brain MRI data acquired from 179 individuals, analyzed in three age groups: newborns (38–42 weeks gestational age), children and adolescents (4–17 years) and adults (35–71 years). As the method can learn from partially labeled datasets, it can be used to segment large-scale datasets efficiently. It could also be applied to different populations and imaging modalities across the life course. PMID:28163680

Calibration-free gaze tracking for automatic measurement of visual acuity in human infants.

PubMed

Xiong, Chunshui; Huang, Lei; Liu, Changping

2014-01-01

Most existing vision-based methods for gaze tracking need a tedious calibration process. In this process, subjects are required to fixate on a specific point or several specific points in space. However, it is hard to cooperate, especially for children and human infants. In this paper, a new calibration-free gaze tracking system and method is presented for automatic measurement of visual acuity in human infants. As far as I know, it is the first time to apply the vision-based gaze tracking in the measurement of visual acuity. Firstly, a polynomial of pupil center-cornea reflections (PCCR) vector is presented to be used as the gaze feature. Then, Gaussian mixture models (GMM) is employed for gaze behavior classification, which is trained offline using labeled data from subjects with healthy eyes. Experimental results on several subjects show that the proposed method is accurate, robust and sufficient for the application of measurement of visual acuity in human infants.

Automatic corn-soybean classification using Landsat MSS data. I - Near-harvest crop proportion estimation. II - Early season crop proportion estimation

NASA Technical Reports Server (NTRS)

Badhwar, G. D.

1984-01-01

The techniques used initially for the identification of cultivated crops from Landsat imagery depended greatly on the iterpretation of film products by a human analyst. This approach was not very effective and objective. Since 1978, new methods for crop identification are being developed. Badhwar et al. (1982) showed that multitemporal-multispectral data could be reduced to a simple feature space of alpha and beta and that these features would separate corn and soybean very well. However, there are disadvantages related to the use of alpha and beta parameters. The present investigation is concerned with a suitable method for extracting the required features. Attention is given to a profile model for crop discrimination, corn-soybean separation using profile parameters, and an automatic labeling (target recognition) method. The developed technique is extended to obtain a procedure which makes it possible to estimate the crop proportion of corn and soybean from Landsat data early in the growing season.

Can a CNN recognize Catalan diet?

NASA Astrophysics Data System (ADS)

Herruzo, P.; Bolaños, M.; Radeva, P.

2016-10-01

Nowadays, we can find several diseases related to the unhealthy diet habits of the population, such as diabetes, obesity, anemia, bulimia and anorexia. In many cases, these diseases are related to the food consumption of people. Mediterranean diet is scientifically known as a healthy diet that helps to prevent many metabolic diseases. In particular, our work focuses on the recognition of Mediterranean food and dishes. The development of this methodology would allow to analise the daily habits of users with wearable cameras, within the topic of lifelogging. By using automatic mechanisms we could build an objective tool for the analysis of the patient's behavior, allowing specialists to discover unhealthy food patterns and understand the user's lifestyle. With the aim to automatically recognize a complete diet, we introduce a challenging multi-labeled dataset related to Mediter-ranean diet called FoodCAT. The first type of label provided consists of 115 food classes with an average of 400 images per dish, and the second one consists of 12 food categories with an average of 3800 pictures per class. This dataset will serve as a basis for the development of automatic diet recognition. In this context, deep learning and more specifically, Convolutional Neural Networks (CNNs), currently are state-of-the-art methods for automatic food recognition. In our work, we compare several architectures for image classification, with the purpose of diet recognition. Applying the best model for recognising food categories, we achieve a top-1 accuracy of 72.29%, and top-5 of 97.07%. In a complete diet recognition of dishes from Mediterranean diet, enlarged with the Food-101 dataset for international dishes recognition, we achieve a top-1 accuracy of 68.07%, and top-5 of 89.53%, for a total of 115+101 food classes.

Identification of fracture zones and its application in automatic bone fracture reduction.

PubMed

Paulano-Godino, Félix; Jiménez-Delgado, Juan J

2017-04-01

The preoperative planning of bone fractures using information from CT scans increases the probability of obtaining satisfactory results, since specialists are provided with additional information before surgery. The reduction of complex bone fractures requires solving a 3D puzzle in order to place each fragment into its correct position. Computer-assisted solutions may aid in this process by identifying the number of fragments and their location, by calculating the fracture zones or even by computing the correct position of each fragment. The main goal of this paper is the development of an automatic method to calculate contact zones between fragments and thus to ease the computation of bone fracture reduction. In this paper, an automatic method to calculate the contact zone between two bone fragments is presented. In a previous step, bone fragments are segmented and labelled from CT images and a point cloud is generated for each bone fragment. The calculated contact zones enable the automatic reduction of complex fractures. To that end, an automatic method to match bone fragments in complex fractures is also presented. The proposed method has been successfully applied in the calculation of the contact zone of 4 different bones from the ankle area. The calculated fracture zones enabled the reduction of all the tested cases using the presented matching algorithm. The performed tests show that the reduction of these fractures using the proposed methods leaded to a small overlapping between fragments. The presented method makes the application of puzzle-solving strategies easier, since it does not obtain the entire fracture zone but the contact area between each pair of fragments. Therefore, it is not necessary to find correspondences between fracture zones and fragments may be aligned two by two. The developed algorithms have been successfully applied in different fracture cases in the ankle area. The small overlapping error obtained in the performed tests demonstrates the absence of visual overlapping in the figures. Copyright © 2016 Elsevier Ireland Ltd. All rights reserved.

ACM-based automatic liver segmentation from 3-D CT images by combining multiple atlases and improved mean-shift techniques.

PubMed

Ji, Hongwei; He, Jiangping; Yang, Xin; Deklerck, Rudi; Cornelis, Jan

2013-05-01

In this paper, we present an autocontext model(ACM)-based automatic liver segmentation algorithm, which combines ACM, multiatlases, and mean-shift techniques to segment liver from 3-D CT images. Our algorithm is a learning-based method and can be divided into two stages. At the first stage, i.e., the training stage, ACM is performed to learn a sequence of classifiers in each atlas space (based on each atlas and other aligned atlases). With the use of multiple atlases, multiple sequences of ACM-based classifiers are obtained. At the second stage, i.e., the segmentation stage, the test image will be segmented in each atlas space by applying each sequence of ACM-based classifiers. The final segmentation result will be obtained by fusing segmentation results from all atlas spaces via a multiclassifier fusion technique. Specially, in order to speed up segmentation, given a test image, we first use an improved mean-shift algorithm to perform over-segmentation and then implement the region-based image labeling instead of the original inefficient pixel-based image labeling. The proposed method is evaluated on the datasets of MICCAI 2007 liver segmentation challenge. The experimental results show that the average volume overlap error and the average surface distance achieved by our method are 8.3% and 1.5 m, respectively, which are comparable to the results reported in the existing state-of-the-art work on liver segmentation.

Deep learning and texture-based semantic label fusion for brain tumor segmentation

NASA Astrophysics Data System (ADS)

Vidyaratne, L.; Alam, M.; Shboul, Z.; Iftekharuddin, K. M.

2018-02-01

Brain tumor segmentation is a fundamental step in surgical treatment and therapy. Many hand-crafted and learning based methods have been proposed for automatic brain tumor segmentation from MRI. Studies have shown that these approaches have their inherent advantages and limitations. This work proposes a semantic label fusion algorithm by combining two representative state-of-the-art segmentation algorithms: texture based hand-crafted, and deep learning based methods to obtain robust tumor segmentation. We evaluate the proposed method using publicly available BRATS 2017 brain tumor segmentation challenge dataset. The results show that the proposed method offers improved segmentation by alleviating inherent weaknesses: extensive false positives in texture based method, and the false tumor tissue classification problem in deep learning method, respectively. Furthermore, we investigate the effect of patient's gender on the segmentation performance using a subset of validation dataset. Note the substantial improvement in brain tumor segmentation performance proposed in this work has recently enabled us to secure the first place by our group in overall patient survival prediction task at the BRATS 2017 challenge.

Deep Learning and Texture-Based Semantic Label Fusion for Brain Tumor Segmentation.

PubMed

Vidyaratne, L; Alam, M; Shboul, Z; Iftekharuddin, K M

2018-01-01

Brain tumor segmentation is a fundamental step in surgical treatment and therapy. Many hand-crafted and learning based methods have been proposed for automatic brain tumor segmentation from MRI. Studies have shown that these approaches have their inherent advantages and limitations. This work proposes a semantic label fusion algorithm by combining two representative state-of-the-art segmentation algorithms: texture based hand-crafted, and deep learning based methods to obtain robust tumor segmentation. We evaluate the proposed method using publicly available BRATS 2017 brain tumor segmentation challenge dataset. The results show that the proposed method offers improved segmentation by alleviating inherent weaknesses: extensive false positives in texture based method, and the false tumor tissue classification problem in deep learning method, respectively. Furthermore, we investigate the effect of patient's gender on the segmentation performance using a subset of validation dataset. Note the substantial improvement in brain tumor segmentation performance proposed in this work has recently enabled us to secure the first place by our group in overall patient survival prediction task at the BRATS 2017 challenge.

Multi-stage 3D-2D registration for correction of anatomical deformation in image-guided spine surgery

NASA Astrophysics Data System (ADS)

Ketcha, M. D.; De Silva, T.; Uneri, A.; Jacobson, M. W.; Goerres, J.; Kleinszig, G.; Vogt, S.; Wolinsky, J.-P.; Siewerdsen, J. H.

2017-06-01

A multi-stage image-based 3D-2D registration method is presented that maps annotations in a 3D image (e.g. point labels annotating individual vertebrae in preoperative CT) to an intraoperative radiograph in which the patient has undergone non-rigid anatomical deformation due to changes in patient positioning or due to the intervention itself. The proposed method (termed msLevelCheck) extends a previous rigid registration solution (LevelCheck) to provide an accurate mapping of vertebral labels in the presence of spinal deformation. The method employs a multi-stage series of rigid 3D-2D registrations performed on sets of automatically determined and increasingly localized sub-images, with the final stage achieving a rigid mapping for each label to yield a locally rigid yet globally deformable solution. The method was evaluated first in a phantom study in which a CT image of the spine was acquired followed by a series of 7 mobile radiographs with increasing degree of deformation applied. Second, the method was validated using a clinical data set of patients exhibiting strong spinal deformation during thoracolumbar spine surgery. Registration accuracy was assessed using projection distance error (PDE) and failure rate (PDE  >  20 mm—i.e. label registered outside vertebra). The msLevelCheck method was able to register all vertebrae accurately for all cases of deformation in the phantom study, improving the maximum PDE of the rigid method from 22.4 mm to 3.9 mm. The clinical study demonstrated the feasibility of the approach in real patient data by accurately registering all vertebral labels in each case, eliminating all instances of failure encountered in the conventional rigid method. The multi-stage approach demonstrated accurate mapping of vertebral labels in the presence of strong spinal deformation. The msLevelCheck method maintains other advantageous aspects of the original LevelCheck method (e.g. compatibility with standard clinical workflow, large capture range, and robustness against mismatch in image content) and extends capability to cases exhibiting strong changes in spinal curvature.

FreeSurfer-initiated fully-automated subcortical brain segmentation in MRI using Large Deformation Diffeomorphic Metric Mapping.

PubMed

Khan, Ali R; Wang, Lei; Beg, Mirza Faisal

2008-07-01

Fully-automated brain segmentation methods have not been widely adopted for clinical use because of issues related to reliability, accuracy, and limitations of delineation protocol. By combining the probabilistic-based FreeSurfer (FS) method with the Large Deformation Diffeomorphic Metric Mapping (LDDMM)-based label-propagation method, we are able to increase reliability and accuracy, and allow for flexibility in template choice. Our method uses the automated FreeSurfer subcortical labeling to provide a coarse-to-fine introduction of information in the LDDMM template-based segmentation resulting in a fully-automated subcortical brain segmentation method (FS+LDDMM). One major advantage of the FS+LDDMM-based approach is that the automatically generated segmentations generated are inherently smooth, thus subsequent steps in shape analysis can directly follow without manual post-processing or loss of detail. We have evaluated our new FS+LDDMM method on several databases containing a total of 50 subjects with different pathologies, scan sequences and manual delineation protocols for labeling the basal ganglia, thalamus, and hippocampus. In healthy controls we report Dice overlap measures of 0.81, 0.83, 0.74, 0.86 and 0.75 for the right caudate nucleus, putamen, pallidum, thalamus and hippocampus respectively. We also find statistically significant improvement of accuracy in FS+LDDMM over FreeSurfer for the caudate nucleus and putamen of Huntington's disease and Tourette's syndrome subjects, and the right hippocampus of Schizophrenia subjects.

Deep learning of the sectional appearances of 3D CT images for anatomical structure segmentation based on an FCN voting method.

PubMed

Zhou, Xiangrong; Takayama, Ryosuke; Wang, Song; Hara, Takeshi; Fujita, Hiroshi

2017-10-01

We propose a single network trained by pixel-to-label deep learning to address the general issue of automatic multiple organ segmentation in three-dimensional (3D) computed tomography (CT) images. Our method can be described as a voxel-wise multiple-class classification scheme for automatically assigning labels to each pixel/voxel in a 2D/3D CT image. We simplify the segmentation algorithms of anatomical structures (including multiple organs) in a CT image (generally in 3D) to a majority voting scheme over the semantic segmentation of multiple 2D slices drawn from different viewpoints with redundancy. The proposed method inherits the spirit of fully convolutional networks (FCNs) that consist of "convolution" and "deconvolution" layers for 2D semantic image segmentation, and expands the core structure with 3D-2D-3D transformations to adapt to 3D CT image segmentation. All parameters in the proposed network are trained pixel-to-label from a small number of CT cases with human annotations as the ground truth. The proposed network naturally fulfills the requirements of multiple organ segmentations in CT cases of different sizes that cover arbitrary scan regions without any adjustment. The proposed network was trained and validated using the simultaneous segmentation of 19 anatomical structures in the human torso, including 17 major organs and two special regions (lumen and content inside of stomach). Some of these structures have never been reported in previous research on CT segmentation. A database consisting of 240 (95% for training and 5% for testing) 3D CT scans, together with their manually annotated ground-truth segmentations, was used in our experiments. The results show that the 19 structures of interest were segmented with acceptable accuracy (88.1% and 87.9% voxels in the training and testing datasets, respectively, were labeled correctly) against the ground truth. We propose a single network based on pixel-to-label deep learning to address the challenging issue of anatomical structure segmentation in 3D CT cases. The novelty of this work is the policy of deep learning of the different 2D sectional appearances of 3D anatomical structures for CT cases and the majority voting of the 3D segmentation results from multiple crossed 2D sections to achieve availability and reliability with better efficiency, generality, and flexibility than conventional segmentation methods, which must be guided by human expertise. © 2017 The Authors. Medical Physics published by Wiley Periodicals, Inc. on behalf of American Association of Physicists in Medicine.

Infrared Cephalic-Vein to Assist Blood Extraction Tasks: Automatic Projection and Recognition

NASA Astrophysics Data System (ADS)

Lagüela, S.; Gesto, M.; Riveiro, B.; González-Aguilera, D.

2017-05-01

Thermal infrared band is not commonly used in photogrammetric and computer vision algorithms, mainly due to the low spatial resolution of this type of imagery. However, this band captures sub-superficial information, increasing the capabilities of visible bands regarding applications. This fact is especially important in biomedicine and biometrics, allowing the geometric characterization of interior organs and pathologies with photogrammetric principles, as well as the automatic identification and labelling using computer vision algorithms. This paper presents advances of close-range photogrammetry and computer vision applied to thermal infrared imagery, with the final application of Augmented Reality in order to widen its application in the biomedical field. In this case, the thermal infrared image of the arm is acquired and simultaneously projected on the arm, together with the identification label of the cephalic-vein. This way, blood analysts are assisted in finding the vein for blood extraction, especially in those cases where the identification by the human eye is a complex task. Vein recognition is performed based on the Gaussian temperature distribution in the area of the vein, while the calibration between projector and thermographic camera is developed through feature extraction and pattern recognition. The method is validated through its application to a set of volunteers, with different ages and genres, in such way that different conditions of body temperature and vein depth are covered for the applicability and reproducibility of the method.

Tools for Protecting the Privacy of Specific Individuals in Video

NASA Astrophysics Data System (ADS)

Chen, Datong; Chang, Yi; Yan, Rong; Yang, Jie

2007-12-01

This paper presents a system for protecting the privacy of specific individuals in video recordings. We address the following two problems: automatic people identification with limited labeled data, and human body obscuring with preserved structure and motion information. In order to address the first problem, we propose a new discriminative learning algorithm to improve people identification accuracy using limited training data labeled from the original video and imperfect pairwise constraints labeled from face obscured video data. We employ a robust face detection and tracking algorithm to obscure human faces in the video. Our experiments in a nursing home environment show that the system can obtain a high accuracy of people identification using limited labeled data and noisy pairwise constraints. The study result indicates that human subjects can perform reasonably well in labeling pairwise constraints with the face masked data. For the second problem, we propose a novel method of body obscuring, which removes the appearance information of the people while preserving rich structure and motion information. The proposed approach provides a way to minimize the risk of exposing the identities of the protected people while maximizing the use of the captured data for activity/behavior analysis.

Segmentation and Quantification for Angle-Closure Glaucoma Assessment in Anterior Segment OCT.

PubMed

Fu, Huazhu; Xu, Yanwu; Lin, Stephen; Zhang, Xiaoqin; Wong, Damon Wing Kee; Liu, Jiang; Frangi, Alejandro F; Baskaran, Mani; Aung, Tin

2017-09-01

Angle-closure glaucoma is a major cause of irreversible visual impairment and can be identified by measuring the anterior chamber angle (ACA) of the eye. The ACA can be viewed clearly through anterior segment optical coherence tomography (AS-OCT), but the imaging characteristics and the shapes and locations of major ocular structures can vary significantly among different AS-OCT modalities, thus complicating image analysis. To address this problem, we propose a data-driven approach for automatic AS-OCT structure segmentation, measurement, and screening. Our technique first estimates initial markers in the eye through label transfer from a hand-labeled exemplar data set, whose images are collected over different patients and AS-OCT modalities. These initial markers are then refined by using a graph-based smoothing method that is guided by AS-OCT structural information. These markers facilitate segmentation of major clinical structures, which are used to recover standard clinical parameters. These parameters can be used not only to support clinicians in making anatomical assessments, but also to serve as features for detecting anterior angle closure in automatic glaucoma screening algorithms. Experiments on Visante AS-OCT and Cirrus high-definition-OCT data sets demonstrate the effectiveness of our approach.

WCE video segmentation using textons

NASA Astrophysics Data System (ADS)

Gallo, Giovanni; Granata, Eliana

2010-03-01

Wireless Capsule Endoscopy (WCE) integrates wireless transmission with image and video technology. It has been used to examine the small intestine non invasively. Medical specialists look for signicative events in the WCE video by direct visual inspection manually labelling, in tiring and up to one hour long sessions, clinical relevant frames. This limits the WCE usage. To automatically discriminate digestive organs such as esophagus, stomach, small intestine and colon is of great advantage. In this paper we propose to use textons for the automatic discrimination of abrupt changes within a video. In particular, we consider, as features, for each frame hue, saturation, value, high-frequency energy content and the responses to a bank of Gabor filters. The experiments have been conducted on ten video segments extracted from WCE videos, in which the signicative events have been previously labelled by experts. Results have shown that the proposed method may eliminate up to 70% of the frames from further investigations. The direct analysis of the doctors may hence be concentrated only on eventful frames. A graphical tool showing sudden changes in the textons frequencies for each frame is also proposed as a visual aid to find clinically relevant segments of the video.

Detection of exudates in fundus images using a Markovian segmentation model.

PubMed

Harangi, Balazs; Hajdu, Andras

2014-01-01

Diabetic retinopathy (DR) is one of the most common causing of vision loss in developed countries. In early stage of DR, some signs like exudates appear in the retinal images. An automatic screening system must be capable to detect these signs properly so that the treatment of the patients may begin in time. The appearance of exudates shows a rich variety regarding their shape and size making automatic detection more challenging. We propose a way for the automatic segmentation of exudates consisting of a candidate extraction step followed by exact contour detection and region-wise classification. More specifically, we extract possible exudate candidates using grayscale morphology and their proper shape is determined by a Markovian segmentation model considering edge information. Finally, we label the candidates as true or false ones by an optimally adjusted SVM classifier. For testing purposes, we considered the publicly available database DiaretDB1, where the proposed method outperformed several state-of-the-art exudate detectors.

Drawing for Traffic Marking Using Bidirectional Gradient-Based Detection with MMS LIDAR Intensity

NASA Astrophysics Data System (ADS)

Takahashi, G.; Takeda, H.; Nakamura, K.

2016-06-01

Recently, the development of autonomous cars is accelerating on the integration of highly advanced artificial intelligence, which increases demand for a digital map with high accuracy. In particular, traffic markings are required to be precisely digitized since automatic driving utilizes them for position detection. To draw traffic markings, we benefit from Mobile Mapping Systems (MMS) equipped with high-density Laser imaging Detection and Ranging (LiDAR) scanners, which produces large amount of data efficiently with XYZ coordination along with reflectance intensity. Digitizing this data, on the other hand, conventionally has been dependent on human operation, which thus suffers from human errors, subjectivity errors, and low reproductivity. We have tackled this problem by means of automatic extraction of traffic marking, which partially accomplished to draw several traffic markings (G. Takahashi et al., 2014). The key idea of the method was extracting lines using the Hough transform strategically focused on changes in local reflection intensity along scan lines. However, it failed to extract traffic markings properly in a densely marked area, especially when local changing points are close each other. In this paper, we propose a bidirectional gradient-based detection method where local changing points are labelled with plus or minus group. Given that each label corresponds to the boundary between traffic markings and background, we can identify traffic markings explicitly, meaning traffic lines are differentiated correctly by the proposed method. As such, our automated method, a highly accurate and non-human-operator-dependent method using bidirectional gradient-based algorithm, can successfully extract traffic lines composed of complex shapes such as a cross walk, resulting in minimizing cost and obtaining highly accurate results.

Automatic segmentation and supervised learning-based selection of nuclei in cancer tissue images.

PubMed

Nandy, Kaustav; Gudla, Prabhakar R; Amundsen, Ryan; Meaburn, Karen J; Misteli, Tom; Lockett, Stephen J

2012-09-01

Analysis of preferential localization of certain genes within the cell nuclei is emerging as a new technique for the diagnosis of breast cancer. Quantitation requires accurate segmentation of 100-200 cell nuclei in each tissue section to draw a statistically significant result. Thus, for large-scale analysis, manual processing is too time consuming and subjective. Fortuitously, acquired images generally contain many more nuclei than are needed for analysis. Therefore, we developed an integrated workflow that selects, following automatic segmentation, a subpopulation of accurately delineated nuclei for positioning of fluorescence in situ hybridization-labeled genes of interest. Segmentation was performed by a multistage watershed-based algorithm and screening by an artificial neural network-based pattern recognition engine. The performance of the workflow was quantified in terms of the fraction of automatically selected nuclei that were visually confirmed as well segmented and by the boundary accuracy of the well-segmented nuclei relative to a 2D dynamic programming-based reference segmentation method. Application of the method was demonstrated for discriminating normal and cancerous breast tissue sections based on the differential positioning of the HES5 gene. Automatic results agreed with manual analysis in 11 out of 14 cancers, all four normal cases, and all five noncancerous breast disease cases, thus showing the accuracy and robustness of the proposed approach. Published 2012 Wiley Periodicals, Inc.

Generation of Ground Truth Datasets for the Analysis of 3d Point Clouds in Urban Scenes Acquired via Different Sensors

NASA Astrophysics Data System (ADS)

Xu, Y.; Sun, Z.; Boerner, R.; Koch, T.; Hoegner, L.; Stilla, U.

2018-04-01

In this work, we report a novel way of generating ground truth dataset for analyzing point cloud from different sensors and the validation of algorithms. Instead of directly labeling large amount of 3D points requiring time consuming manual work, a multi-resolution 3D voxel grid for the testing site is generated. Then, with the help of a set of basic labeled points from the reference dataset, we can generate a 3D labeled space of the entire testing site with different resolutions. Specifically, an octree-based voxel structure is applied to voxelize the annotated reference point cloud, by which all the points are organized by 3D grids of multi-resolutions. When automatically annotating the new testing point clouds, a voting based approach is adopted to the labeled points within multiple resolution voxels, in order to assign a semantic label to the 3D space represented by the voxel. Lastly, robust line- and plane-based fast registration methods are developed for aligning point clouds obtained via various sensors. Benefiting from the labeled 3D spatial information, we can easily create new annotated 3D point clouds of different sensors of the same scene directly by considering the corresponding labels of 3D space the points located, which would be convenient for the validation and evaluation of algorithms related to point cloud interpretation and semantic segmentation.

Temporal Cyber Attack Detection.

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

Ingram, Joey Burton; Draelos, Timothy J.; Galiardi, Meghan

Rigorous characterization of the performance and generalization ability of cyber defense systems is extremely difficult, making it hard to gauge uncertainty, and thus, confidence. This difficulty largely stems from a lack of labeled attack data that fully explores the potential adversarial space. Currently, performance of cyber defense systems is typically evaluated in a qualitative manner by manually inspecting the results of the system on live data and adjusting as needed. Additionally, machine learning has shown promise in deriving models that automatically learn indicators of compromise that are more robust than analyst-derived detectors. However, to generate these models, most algorithms requiremore » large amounts of labeled data (i.e., examples of attacks). Algorithms that do not require annotated data to derive models are similarly at a disadvantage, because labeled data is still necessary when evaluating performance. In this work, we explore the use of temporal generative models to learn cyber attack graph representations and automatically generate data for experimentation and evaluation. Training and evaluating cyber systems and machine learning models requires significant, annotated data, which is typically collected and labeled by hand for one-off experiments. Automatically generating such data helps derive/evaluate detection models and ensures reproducibility of results. Experimentally, we demonstrate the efficacy of generative sequence analysis techniques on learning the structure of attack graphs, based on a realistic example. These derived models can then be used to generate more data. Additionally, we provide a roadmap for future research efforts in this area.« less

Automatic and hierarchical segmentation of the human skeleton in CT images.

PubMed

Fu, Yabo; Liu, Shi; Li, Harold; Yang, Deshan

2017-04-07

Accurate segmentation of each bone of the human skeleton is useful in many medical disciplines. The results of bone segmentation could facilitate bone disease diagnosis and post-treatment assessment, and support planning and image guidance for many treatment modalities including surgery and radiation therapy. As a medium level medical image processing task, accurate bone segmentation can facilitate automatic internal organ segmentation by providing stable structural reference for inter- or intra-patient registration and internal organ localization. Even though bones in CT images can be visually observed with minimal difficulty due to the high image contrast between the bony structures and surrounding soft tissues, automatic and precise segmentation of individual bones is still challenging due to the many limitations of the CT images. The common limitations include low signal-to-noise ratio, insufficient spatial resolution, and indistinguishable image intensity between spongy bones and soft tissues. In this study, a novel and automatic method is proposed to segment all the major individual bones of the human skeleton above the upper legs in CT images based on an articulated skeleton atlas. The reported method is capable of automatically segmenting 62 major bones, including 24 vertebrae and 24 ribs, by traversing a hierarchical anatomical tree and by using both rigid and deformable image registration. The degrees of freedom of femora and humeri are modeled to support patients in different body and limb postures. The segmentation results are evaluated using the Dice coefficient and point-to-surface error (PSE) against manual segmentation results as the ground-truth. The results suggest that the reported method can automatically segment and label the human skeleton into detailed individual bones with high accuracy. The overall average Dice coefficient is 0.90. The average PSEs are 0.41 mm for the mandible, 0.62 mm for cervical vertebrae, 0.92 mm for thoracic vertebrae, and 1.45 mm for pelvis bones.

Automatic and hierarchical segmentation of the human skeleton in CT images

NASA Astrophysics Data System (ADS)

Fu, Yabo; Liu, Shi; Li, H. Harold; Yang, Deshan

2017-04-01

Accurate segmentation of each bone of the human skeleton is useful in many medical disciplines. The results of bone segmentation could facilitate bone disease diagnosis and post-treatment assessment, and support planning and image guidance for many treatment modalities including surgery and radiation therapy. As a medium level medical image processing task, accurate bone segmentation can facilitate automatic internal organ segmentation by providing stable structural reference for inter- or intra-patient registration and internal organ localization. Even though bones in CT images can be visually observed with minimal difficulty due to the high image contrast between the bony structures and surrounding soft tissues, automatic and precise segmentation of individual bones is still challenging due to the many limitations of the CT images. The common limitations include low signal-to-noise ratio, insufficient spatial resolution, and indistinguishable image intensity between spongy bones and soft tissues. In this study, a novel and automatic method is proposed to segment all the major individual bones of the human skeleton above the upper legs in CT images based on an articulated skeleton atlas. The reported method is capable of automatically segmenting 62 major bones, including 24 vertebrae and 24 ribs, by traversing a hierarchical anatomical tree and by using both rigid and deformable image registration. The degrees of freedom of femora and humeri are modeled to support patients in different body and limb postures. The segmentation results are evaluated using the Dice coefficient and point-to-surface error (PSE) against manual segmentation results as the ground-truth. The results suggest that the reported method can automatically segment and label the human skeleton into detailed individual bones with high accuracy. The overall average Dice coefficient is 0.90. The average PSEs are 0.41 mm for the mandible, 0.62 mm for cervical vertebrae, 0.92 mm for thoracic vertebrae, and 1.45 mm for pelvis bones.

Detecting experimental techniques and selecting relevant documents for protein-protein interactions from biomedical literature

PubMed Central

2011-01-01

Background The selection of relevant articles for curation, and linking those articles to experimental techniques confirming the findings became one of the primary subjects of the recent BioCreative III contest. The contest’s Protein-Protein Interaction (PPI) task consisted of two sub-tasks: Article Classification Task (ACT) and Interaction Method Task (IMT). ACT aimed to automatically select relevant documents for PPI curation, whereas the goal of IMT was to recognise the methods used in experiments for identifying the interactions in full-text articles. Results We proposed and compared several classification-based methods for both tasks, employing rich contextual features as well as features extracted from external knowledge sources. For IMT, a new method that classifies pair-wise relations between every text phrase and candidate interaction method obtained promising results with an F1 score of 64.49%, as tested on the task’s development dataset. We also explored ways to combine this new approach and more conventional, multi-label document classification methods. For ACT, our classifiers exploited automatically detected named entities and other linguistic information. The evaluation results on the BioCreative III PPI test datasets showed that our systems were very competitive: one of our IMT methods yielded the best performance among all participants, as measured by F1 score, Matthew’s Correlation Coefficient and AUC iP/R; whereas for ACT, our best classifier was ranked second as measured by AUC iP/R, and also competitive according to other metrics. Conclusions Our novel approach that converts the multi-class, multi-label classification problem to a binary classification problem showed much promise in IMT. Nevertheless, on the test dataset the best performance was achieved by taking the union of the output of this method and that of a multi-class, multi-label document classifier, which indicates that the two types of systems complement each other in terms of recall. For ACT, our system exploited a rich set of features and also obtained encouraging results. We examined the features with respect to their contributions to the classification results, and concluded that contextual words surrounding named entities, as well as the MeSH headings associated with the documents were among the main contributors to the performance. PMID:22151769

A new label dosimetry system based on pentacosa-diynoic acid monomer for low dose applications

NASA Astrophysics Data System (ADS)

Abdel-Fattah, A. A.; Abdel-Rehim, F.; Soliman, Y. S.

2012-01-01

The dosimetric characteristics of γ-radiation sensitive labels based on polyvinyl butyral (PVB) and a conjugated diacetylene monomer, 10,12-pentacosa-diynoic acid (PCDA) have been investigated using reflectance colorimeter. Two types of labels (colourless and yellow) based on PCDA monomer were prepared using an Automatic Film Applicator System. Upon γ-ray exposure, the colourless label turns progressively blue, while the yellow colour label turns to green then to dark blue. The colour intensity of the labels is proportional to the radiation absorbed dose. The useful dose range was 15 Gy-2 kGy depending on PCDA monomer concentration. The expanded uncertainty of dose measurement of the colourless label was 6.06 (2 σ).

Automatic Localization of Vertebral Levels in X-Ray Fluoroscopy Using 3D-2D Registration: A Tool to Reduce Wrong-Site Surgery

PubMed Central

Otake, Y.; Schafer, S.; Stayman, J. W.; Zbijewski, W.; Kleinszig, G.; Graumann, R.; Khanna, A. J.; Siewerdsen, J. H.

2012-01-01

Surgical targeting of the incorrect vertebral level (“wrong-level” surgery) is among the more common wrong-site surgical errors, attributed primarily to a lack of uniquely identifiable radiographic landmarks in the mid-thoracic spine. Conventional localization method involves manual counting of vertebral bodies under fluoroscopy, is prone to human error, and carries additional time and dose. We propose an image registration and visualization system (referred to as LevelCheck), for decision support in spine surgery by automatically labeling vertebral levels in fluoroscopy using a GPU-accelerated, intensity-based 3D-2D (viz., CT-to-fluoroscopy) registration. A gradient information (GI) similarity metric and CMA-ES optimizer were chosen due to their robustness and inherent suitability for parallelization. Simulation studies involved 10 patient CT datasets from which 50,000 simulated fluoroscopic images were generated from C-arm poses selected to approximate C-arm operator and positioning variability. Physical experiments used an anthropomorphic chest phantom imaged under real fluoroscopy. The registration accuracy was evaluated as the mean projection distance (mPD) between the estimated and true center of vertebral levels. Trials were defined as successful if the estimated position was within the projection of the vertebral body (viz., mPD < 5mm). Simulation studies showed a success rate of 99.998% (1 failure in 50,000 trials) and computation time of 4.7 sec on a midrange GPU. Analysis of failure modes identified cases of false local optima in the search space arising from longitudinal periodicity in vertebral structures. Physical experiments demonstrated robustness of the algorithm against quantum noise and x-ray scatter. The ability to automatically localize target anatomy in fluoroscopy in near-real-time could be valuable in reducing the occurrence of wrong-site surgery while helping to reduce radiation exposure. The method is applicable beyond the specific case of vertebral labeling, since any structure defined in pre-operative (or intra-operative) CT or cone-beam CT can be automatically registered to the fluoroscopic scene. PMID:22864366

Extracting rate changes in transcriptional regulation from MEDLINE abstracts.

PubMed

Liu, Wenting; Miao, Kui; Li, Guangxia; Chang, Kuiyu; Zheng, Jie; Rajapakse, Jagath C

2014-01-01

Time delays are important factors that are often neglected in gene regulatory network (GRN) inference models. Validating time delays from knowledge bases is a challenge since the vast majority of biological databases do not record temporal information of gene regulations. Biological knowledge and facts on gene regulations are typically extracted from bio-literature with specialized methods that depend on the regulation task. In this paper, we mine evidences for time delays related to the transcriptional regulation of yeast from the PubMed abstracts. Since the vast majority of abstracts lack quantitative time information, we can only collect qualitative evidences of time delays. Specifically, the speed-up or delay in transcriptional regulation rate can provide evidences for time delays (shorter or longer) in GRN. Thus, we focus on deriving events related to rate changes in transcriptional regulation. A corpus of yeast regulation related abstracts was manually labeled with such events. In order to capture these events automatically, we create an ontology of sub-processes that are likely to result in transcription rate changes by combining textual patterns and biological knowledge. We also propose effective feature extraction methods based on the created ontology to identify the direct evidences with specific details of these events. Our ontologies outperform existing state-of-the-art gene regulation ontologies in the automatic rule learning method applied to our corpus. The proposed deterministic ontology rule-based method can achieve comparable performance to the automatic rule learning method based on decision trees. This demonstrates the effectiveness of our ontology in identifying rate-changing events. We also tested the effectiveness of the proposed feature mining methods on detecting direct evidence of events. Experimental results show that the machine learning method on these features achieves an F1-score of 71.43%. The manually labeled corpus of events relating to rate changes in transcriptional regulation for yeast is available in https://sites.google.com/site/wentingntu/data. The created ontologies summarized both biological causes of rate changes in transcriptional regulation and corresponding positive and negative textual patterns from the corpus. They are demonstrated to be effective in identifying rate-changing events, which shows the benefits of combining textual patterns and biological knowledge on extracting complex biological events.

The cleaning and disinfection by heat of bedpans in automatic and semi-automatic machines.

PubMed Central

Mostafa, A. B.; Chackett, K. F.

1976-01-01

This work is concerned with the cleaning and disinfection by heat of stainless-steel and polypropylene bedpans, which had been soiled with either a biological contaminant, human serum albumin (HSA) labelled with technetium-99m 99m(Tc), or a bacteriological contaminant, streptococcus faecalis mixed with Tc-labelled HSA. Results of cleaning and disinfection achieved with a Test Machine and those achieved by procedures adopted in eight different wards of a general hospital are reported. Bedpan washers installed in wards were found to be less efficient than the Test Machine, at least partly because of inadequate maintenance. Stainless-steel and polypropylene bedpans gave essentially the same results. PMID:6591

A fully automatic end-to-end method for content-based image retrieval of CT scans with similar liver lesion annotations.

PubMed

Spanier, A B; Caplan, N; Sosna, J; Acar, B; Joskowicz, L

2018-01-01

The goal of medical content-based image retrieval (M-CBIR) is to assist radiologists in the decision-making process by retrieving medical cases similar to a given image. One of the key interests of radiologists is lesions and their annotations, since the patient treatment depends on the lesion diagnosis. Therefore, a key feature of M-CBIR systems is the retrieval of scans with the most similar lesion annotations. To be of value, M-CBIR systems should be fully automatic to handle large case databases. We present a fully automatic end-to-end method for the retrieval of CT scans with similar liver lesion annotations. The input is a database of abdominal CT scans labeled with liver lesions, a query CT scan, and optionally one radiologist-specified lesion annotation of interest. The output is an ordered list of the database CT scans with the most similar liver lesion annotations. The method starts by automatically segmenting the liver in the scan. It then extracts a histogram-based features vector from the segmented region, learns the features' relative importance, and ranks the database scans according to the relative importance measure. The main advantages of our method are that it fully automates the end-to-end querying process, that it uses simple and efficient techniques that are scalable to large datasets, and that it produces quality retrieval results using an unannotated CT scan. Our experimental results on 9 CT queries on a dataset of 41 volumetric CT scans from the 2014 Image CLEF Liver Annotation Task yield an average retrieval accuracy (Normalized Discounted Cumulative Gain index) of 0.77 and 0.84 without/with annotation, respectively. Fully automatic end-to-end retrieval of similar cases based on image information alone, rather that on disease diagnosis, may help radiologists to better diagnose liver lesions.

Automated Analysis of Human Sperm Number and Concentration (Oligospermia) Using Otsu Threshold Method and Labelling

NASA Astrophysics Data System (ADS)

Susrama, I. G.; Purnama, K. E.; Purnomo, M. H.

2016-01-01

Oligospermia is a male fertility issue defined as a low sperm concentration in the ejaculate. Normally the sperm concentration is 20-120 million/ml, while Oligospermia patients has sperm concentration less than 20 million/ml. Sperm test done in the fertility laboratory to determine oligospermia by checking fresh sperm according to WHO standards in 2010 [9]. The sperm seen in a microscope using a Neubauer improved counting chamber and manually count the number of sperm. In order to be counted automatically, this research made an automation system to analyse and count the sperm concentration called Automated Analysis of Sperm Concentration Counters (A2SC2) using Otsu threshold segmentation process and morphology. Data sperm used is the fresh sperm directly in the analysis in the laboratory from 10 people. The test results using A2SC2 method obtained an accuracy of 91%. Thus in this study, A2SC2 can be used to calculate the amount and concentration of sperm automatically

Automatic patient-adaptive bleeding detection in a capsule endoscopy

NASA Astrophysics Data System (ADS)

Jung, Yun Sub; Kim, Yong Ho; Lee, Dong Ha; Lee, Sang Ho; Song, Jeong Joo; Kim, Jong Hyo

2009-02-01

We present a method for patient-adaptive detection of bleeding region for a Capsule Endoscopy (CE) images. The CE system has 320x320 resolution and transmits 3 images per second to receiver during around 10-hour. We have developed a technique to detect the bleeding automatically utilizing color spectrum transformation (CST) method. However, because of irregular conditions like organ difference, patient difference and illumination condition, detection performance is not uniform. To solve this problem, the detection method in this paper include parameter compensation step which compensate irregular image condition using color balance index (CBI). We have investigated color balance through sequential 2 millions images. Based on this pre-experimental result, we defined ΔCBI to represent deviate of color balance compared with standard small bowel color balance. The ΔCBI feature value is extracted from each image and used in CST method as parameter compensation constant. After candidate pixels were detected using CST method, they were labeled and examined with a bleeding character. We tested our method with 4,800 images in 12 patient data set (9 abnormal, 3 normal). Our experimental results show the proposed method achieves (before patient adaptive method : 80.87% and 74.25%, after patient adaptive method : 94.87% and 96.12%) of sensitivity and specificity.

Automation of motor dexterity assessment.

PubMed

Heyer, Patrick; Castrejon, Luis R; Orihuela-Espina, Felipe; Sucar, Luis Enrique

2017-07-01

Motor dexterity assessment is regularly performed in rehabilitation wards to establish patient status and automatization for such routinary task is sought. A system for automatizing the assessment of motor dexterity based on the Fugl-Meyer scale and with loose restrictions on sensing technologies is presented. The system consists of two main elements: 1) A data representation that abstracts the low level information obtained from a variety of sensors, into a highly separable low dimensionality encoding employing t-distributed Stochastic Neighbourhood Embedding, and, 2) central to this communication, a multi-label classifier that boosts classification rates by exploiting the fact that the classes corresponding to the individual exercises are naturally organized as a network. Depending on the targeted therapeutic movement class labels i.e. exercises scores, are highly correlated-patients who perform well in one, tends to perform well in related exercises-; and critically no node can be used as proxy of others - an exercise does not encode the information of other exercises. Over data from a cohort of 20 patients, the novel classifier outperforms classical Naive Bayes, random forest and variants of support vector machines (ANOVA: p < 0.001). The novel multi-label classification strategy fulfills an automatic system for motor dexterity assessment, with implications for lessening therapist's workloads, reducing healthcare costs and providing support for home-based virtual rehabilitation and telerehabilitation alternatives.

A new semi-supervised learning model combined with Cox and SP-AFT models in cancer survival analysis.

PubMed

Chai, Hua; Li, Zi-Na; Meng, De-Yu; Xia, Liang-Yong; Liang, Yong

2017-10-12

Gene selection is an attractive and important task in cancer survival analysis. Most existing supervised learning methods can only use the labeled biological data, while the censored data (weakly labeled data) far more than the labeled data are ignored in model building. Trying to utilize such information in the censored data, a semi-supervised learning framework (Cox-AFT model) combined with Cox proportional hazard (Cox) and accelerated failure time (AFT) model was used in cancer research, which has better performance than the single Cox or AFT model. This method, however, is easily affected by noise. To alleviate this problem, in this paper we combine the Cox-AFT model with self-paced learning (SPL) method to more effectively employ the information in the censored data in a self-learning way. SPL is a kind of reliable and stable learning mechanism, which is recently proposed for simulating the human learning process to help the AFT model automatically identify and include samples of high confidence into training, minimizing interference from high noise. Utilizing the SPL method produces two direct advantages: (1) The utilization of censored data is further promoted; (2) the noise delivered to the model is greatly decreased. The experimental results demonstrate the effectiveness of the proposed model compared to the traditional Cox-AFT model.

Audio-video feature correlation: faces and speech

NASA Astrophysics Data System (ADS)

Durand, Gwenael; Montacie, Claude; Caraty, Marie-Jose; Faudemay, Pascal

1999-08-01

This paper presents a study of the correlation of features automatically extracted from the audio stream and the video stream of audiovisual documents. In particular, we were interested in finding out whether speech analysis tools could be combined with face detection methods, and to what extend they should be combined. A generic audio signal partitioning algorithm as first used to detect Silence/Noise/Music/Speech segments in a full length movie. A generic object detection method was applied to the keyframes extracted from the movie in order to detect the presence or absence of faces. The correlation between the presence of a face in the keyframes and of the corresponding voice in the audio stream was studied. A third stream, which is the script of the movie, is warped on the speech channel in order to automatically label faces appearing in the keyframes with the name of the corresponding character. We naturally found that extracted audio and video features were related in many cases, and that significant benefits can be obtained from the joint use of audio and video analysis methods.

GeneTopics - interpretation of gene sets via literature-driven topic models

PubMed Central

2013-01-01

Background Annotation of a set of genes is often accomplished through comparison to a library of labelled gene sets such as biological processes or canonical pathways. However, this approach might fail if the employed libraries are not up to date with the latest research, don't capture relevant biological themes or are curated at a different level of granularity than is required to appropriately analyze the input gene set. At the same time, the vast biomedical literature offers an unstructured repository of the latest research findings that can be tapped to provide thematic sub-groupings for any input gene set. Methods Our proposed method relies on a gene-specific text corpus and extracts commonalities between documents in an unsupervised manner using a topic model approach. We automatically determine the number of topics summarizing the corpus and calculate a gene relevancy score for each topic allowing us to eliminate non-specific topics. As a result we obtain a set of literature topics in which each topic is associated with a subset of the input genes providing directly interpretable keywords and corresponding documents for literature research. Results We validate our method based on labelled gene sets from the KEGG metabolic pathway collection and the genetic association database (GAD) and show that the approach is able to detect topics consistent with the labelled annotation. Furthermore, we discuss the results on three different types of experimentally derived gene sets, (1) differentially expressed genes from a cardiac hypertrophy experiment in mice, (2) altered transcript abundance in human pancreatic beta cells, and (3) genes implicated by GWA studies to be associated with metabolite levels in a healthy population. In all three cases, we are able to replicate findings from the original papers in a quick and semi-automated manner. Conclusions Our approach provides a novel way of automatically generating meaningful annotations for gene sets that are directly tied to relevant articles in the literature. Extending a general topic model method, the approach introduced here establishes a workflow for the interpretation of gene sets generated from diverse experimental scenarios that can complement the classical approach of comparison to reference gene sets. PMID:24564875

Automatic Detection of Clouds and Shadows Using High Resolution Satellite Image Time Series

NASA Astrophysics Data System (ADS)

Champion, Nicolas

2016-06-01

Detecting clouds and their shadows is one of the primaries steps to perform when processing satellite images because they may alter the quality of some products such as large-area orthomosaics. The main goal of this paper is to present the automatic method developed at IGN-France for detecting clouds and shadows in a sequence of satellite images. In our work, surface reflectance orthoimages are used. They were processed from initial satellite images using a dedicated software. The cloud detection step consists of a region-growing algorithm. Seeds are firstly extracted. For that purpose and for each input ortho-image to process, we select the other ortho-images of the sequence that intersect it. The pixels of the input ortho-image are secondly labelled seeds if the difference of reflectance (in the blue channel) with overlapping ortho-images is bigger than a given threshold. Clouds are eventually delineated using a region-growing method based on a radiometric and homogeneity criterion. Regarding the shadow detection, our method is based on the idea that a shadow pixel is darker when comparing to the other images of the time series. The detection is basically composed of three steps. Firstly, we compute a synthetic ortho-image covering the whole study area. Its pixels have a value corresponding to the median value of all input reflectance ortho-images intersecting at that pixel location. Secondly, for each input ortho-image, a pixel is labelled shadows if the difference of reflectance (in the NIR channel) with the synthetic ortho-image is below a given threshold. Eventually, an optional region-growing step may be used to refine the results. Note that pixels labelled clouds during the cloud detection are not used for computing the median value in the first step; additionally, the NIR input data channel is used to perform the shadow detection, because it appeared to better discriminate shadow pixels. The method was tested on times series of Landsat 8 and Pléiades-HR images and our first experiments show the feasibility to automate the detection of shadows and clouds in satellite image sequences.

The Use of Error Data to Study the Development of Verbal Encoding of Pictorial Stimuli.

ERIC Educational Resources Information Center

Cramer, Phebe

If older children automatically label pictorial stimuli, then their performance should be impaired on tasks in which such labeling would increase the error rate. Children were asked to learn pairs of verbal or pictorial stimuli which, when combined, formed a different compound word (BUTTER-FLY). Subsequently, a false recognition test that included…

Polyphonic Music Information Retrieval Based on Multi-Label Cascade Classification System

ERIC Educational Resources Information Center

Jiang, Wenxin

2009-01-01

Recognition and separation of sounds played by various instruments is very useful in labeling audio files with semantic information. This is a non-trivial task requiring sound analysis, but the results can aid automatic indexing and browsing music data when searching for melodies played by user specified instruments. Melody match based on pitch…

Automated labeling of log features in CT imagery of multiple hardwood species

Treesearch

Daniel L. Schmoldt; Jing He; A. Lynn Abbott

2000-01-01

Before noninvasive scanning, e.g., computed tomography (CT), becomes feasible in industrial saw-mill operations, we need a procedure that can automatically interpret scan information in order to provide the saw operator with information necessary to make proper sawing decisions. To this end, we have worked to develop an approach for automatic analysis of CT images of...

A multilingual gold-standard corpus for biomedical concept recognition: the Mantra GSC

PubMed Central

Clematide, Simon; Akhondi, Saber A; van Mulligen, Erik M; Rebholz-Schuhmann, Dietrich

2015-01-01

Objective To create a multilingual gold-standard corpus for biomedical concept recognition. Materials and methods We selected text units from different parallel corpora (Medline abstract titles, drug labels, biomedical patent claims) in English, French, German, Spanish, and Dutch. Three annotators per language independently annotated the biomedical concepts, based on a subset of the Unified Medical Language System and covering a wide range of semantic groups. To reduce the annotation workload, automatically generated preannotations were provided. Individual annotations were automatically harmonized and then adjudicated, and cross-language consistency checks were carried out to arrive at the final annotations. Results The number of final annotations was 5530. Inter-annotator agreement scores indicate good agreement (median F-score 0.79), and are similar to those between individual annotators and the gold standard. The automatically generated harmonized annotation set for each language performed equally well as the best annotator for that language. Discussion The use of automatic preannotations, harmonized annotations, and parallel corpora helped to keep the manual annotation efforts manageable. The inter-annotator agreement scores provide a reference standard for gauging the performance of automatic annotation techniques. Conclusion To our knowledge, this is the first gold-standard corpus for biomedical concept recognition in languages other than English. Other distinguishing features are the wide variety of semantic groups that are being covered, and the diversity of text genres that were annotated. PMID:25948699

EnzML: multi-label prediction of enzyme classes using InterPro signatures

PubMed Central

2012-01-01

Background Manual annotation of enzymatic functions cannot keep up with automatic genome sequencing. In this work we explore the capacity of InterPro sequence signatures to automatically predict enzymatic function. Results We present EnzML, a multi-label classification method that can efficiently account also for proteins with multiple enzymatic functions: 50,000 in UniProt. EnzML was evaluated using a standard set of 300,747 proteins for which the manually curated Swiss-Prot and KEGG databases have agreeing Enzyme Commission (EC) annotations. EnzML achieved more than 98% subset accuracy (exact match of all correct Enzyme Commission classes of a protein) for the entire dataset and between 87 and 97% subset accuracy in reannotating eight entire proteomes: human, mouse, rat, mouse-ear cress, fruit fly, the S. pombe yeast, the E. coli bacterium and the M. jannaschii archaebacterium. To understand the role played by the dataset size, we compared the cross-evaluation results of smaller datasets, either constructed at random or from specific taxonomic domains such as archaea, bacteria, fungi, invertebrates, plants and vertebrates. The results were confirmed even when the redundancy in the dataset was reduced using UniRef100, UniRef90 or UniRef50 clusters. Conclusions InterPro signatures are a compact and powerful attribute space for the prediction of enzymatic function. This representation makes multi-label machine learning feasible in reasonable time (30 minutes to train on 300,747 instances with 10,852 attributes and 2,201 class values) using the Mulan Binary Relevance Nearest Neighbours algorithm implementation (BR-kNN). PMID:22533924

ASAP (Automatic Software for ASL Processing): A toolbox for processing Arterial Spin Labeling images.

PubMed

Mato Abad, Virginia; García-Polo, Pablo; O'Daly, Owen; Hernández-Tamames, Juan Antonio; Zelaya, Fernando

2016-04-01

The method of Arterial Spin Labeling (ASL) has experienced a significant rise in its application to functional imaging, since it is the only technique capable of measuring blood perfusion in a truly non-invasive manner. Currently, there are no commercial packages for processing ASL data and there is no recognized standard for normalizing ASL data to a common frame of reference. This work describes a new Automated Software for ASL Processing (ASAP) that can automatically process several ASL datasets. ASAP includes functions for all stages of image pre-processing: quantification, skull-stripping, co-registration, partial volume correction and normalization. To assess the applicability and validity of the toolbox, this work shows its application in the study of hypoperfusion in a sample of healthy subjects at risk of progressing to Alzheimer's disease. ASAP requires limited user intervention, minimizing the possibility of random and systematic errors, and produces cerebral blood flow maps that are ready for statistical group analysis. The software is easy to operate and results in excellent quality of spatial normalization. The results found in this evaluation study are consistent with previous studies that find decreased perfusion in Alzheimer's patients in similar regions and demonstrate the applicability of ASAP. Copyright © 2015 Elsevier Inc. All rights reserved.

Image processing and machine learning techniques to automate diagnosis of Lugol's iodine cervigrams for a low-cost point-of-care digital colposcope

NASA Astrophysics Data System (ADS)

Asiedu, Mercy Nyamewaa; Simhal, Anish; Lam, Christopher T.; Mueller, Jenna; Chaudhary, Usamah; Schmitt, John W.; Sapiro, Guillermo; Ramanujam, Nimmi

2018-02-01

The world health organization recommends visual inspection with acetic acid (VIA) and/or Lugol's Iodine (VILI) for cervical cancer screening in low-resource settings. Human interpretation of diagnostic indicators for visual inspection is qualitative, subjective, and has high inter-observer discordance, which could lead both to adverse outcomes for the patient and unnecessary follow-ups. In this work, we a simple method for automatic feature extraction and classification for Lugol's Iodine cervigrams acquired with a low-cost, miniature, digital colposcope. Algorithms to preprocess expert physician-labelled cervigrams and to extract simple but powerful color-based features are introduced. The features are used to train a support vector machine model to classify cervigrams based on expert physician labels. The selected framework achieved a sensitivity, specificity, and accuracy of 89.2%, 66.7% and 80.6% with majority diagnosis of the expert physicians in discriminating cervical intraepithelial neoplasia (CIN +) relative to normal tissues. The proposed classifier also achieved an area under the curve of 84 when trained with majority diagnosis of the expert physicians. The results suggest that utilizing simple color-based features may enable unbiased automation of VILI cervigrams, opening the door to a full system of low-cost data acquisition complemented with automatic interpretation.

Whole Organism High-Content Screening by Label-Free, Image-Based Bayesian Classification for Parasitic Diseases

PubMed Central

Paveley, Ross A.; Mansour, Nuha R.; Hallyburton, Irene; Bleicher, Leo S.; Benn, Alex E.; Mikic, Ivana; Guidi, Alessandra; Gilbert, Ian H.; Hopkins, Andrew L.; Bickle, Quentin D.

2012-01-01

Sole reliance on one drug, Praziquantel, for treatment and control of schistosomiasis raises concerns about development of widespread resistance, prompting renewed interest in the discovery of new anthelmintics. To discover new leads we designed an automated label-free, high content-based, high throughput screen (HTS) to assess drug-induced effects on in vitro cultured larvae (schistosomula) using bright-field imaging. Automatic image analysis and Bayesian prediction models define morphological damage, hit/non-hit prediction and larval phenotype characterization. Motility was also assessed from time-lapse images. In screening a 10,041 compound library the HTS correctly detected 99.8% of the hits scored visually. A proportion of these larval hits were also active in an adult worm ex-vivo screen and are the subject of ongoing studies. The method allows, for the first time, screening of large compound collections against schistosomes and the methods are adaptable to other whole organism and cell-based screening by morphology and motility phenotyping. PMID:22860151

Change detection and classification of land cover in multispectral satellite imagery using clustering of sparse approximations (CoSA) over learned feature dictionaries

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

Moody, Daniela I.; Brumby, Steven P.; Rowland, Joel C.

Neuromimetic machine vision and pattern recognition algorithms are of great interest for landscape characterization and change detection in satellite imagery in support of global climate change science and modeling. We present results from an ongoing effort to extend machine vision methods to the environmental sciences, using adaptive sparse signal processing combined with machine learning. A Hebbian learning rule is used to build multispectral, multiresolution dictionaries from regional satellite normalized band difference index data. Land cover labels are automatically generated via our CoSA algorithm: Clustering of Sparse Approximations, using a clustering distance metric that combines spectral and spatial textural characteristics tomore » help separate geologic, vegetative, and hydrologie features. We demonstrate our method on example Worldview-2 satellite images of an Arctic region, and use CoSA labels to detect seasonal surface changes. In conclusion, our results suggest that neuroscience-based models are a promising approach to practical pattern recognition and change detection problems in remote sensing.« less

Change detection and classification of land cover in multispectral satellite imagery using clustering of sparse approximations (CoSA) over learned feature dictionaries

DOE PAGES

Moody, Daniela I.; Brumby, Steven P.; Rowland, Joel C.; ...

2014-10-01

Neuromimetic machine vision and pattern recognition algorithms are of great interest for landscape characterization and change detection in satellite imagery in support of global climate change science and modeling. We present results from an ongoing effort to extend machine vision methods to the environmental sciences, using adaptive sparse signal processing combined with machine learning. A Hebbian learning rule is used to build multispectral, multiresolution dictionaries from regional satellite normalized band difference index data. Land cover labels are automatically generated via our CoSA algorithm: Clustering of Sparse Approximations, using a clustering distance metric that combines spectral and spatial textural characteristics tomore » help separate geologic, vegetative, and hydrologie features. We demonstrate our method on example Worldview-2 satellite images of an Arctic region, and use CoSA labels to detect seasonal surface changes. In conclusion, our results suggest that neuroscience-based models are a promising approach to practical pattern recognition and change detection problems in remote sensing.« less

A novel design for a dual stable isotope continuous labeling chamber: results on labeling efficiency and C and N allocation in Andropogon gerardii

NASA Astrophysics Data System (ADS)

Soong, J.; Stewart, C.; Reuss, D.; Pinney, C.; Cotrufo, F. M.

2010-12-01

The use of stable isotope enriched plant material can provide an unobstructed method of studying ecosystem nutrient dynamics between plants, soil, and atmosphere. However, the production of uniformly labeled perennial plant material is challenging due to plant physiological constraints and the mechanics of building and operating an isotope labeling system. In this study we present the design of a novel dual 13C and 15N continuous isotope labeling chamber located at Colorado State University. The chamber is equipped with automatic controls for CO2 concentration, temperature, and humidity, and has successfully been used to grow and label the tallgrass perennial Andropogon gerardii in pots from rhizomes. Three different nitrogen fertilization levels were applied to assess how substrate availability may alter growth and overall performance in the system. The efficiency of the 13C and 15N labeling chamber, its design and overall performance, as well as a full C, N, 13C, and 15N budget of the aboveground biomass, belowground biomass, and soil will be presented. Solid samples were analyzed on an EA-IRMS, while air samples from the chamber were analyzed using a precon-GC-IRMS system. The dual stable isotope labeled A. gerardii produced from this chamber will be used in a decomposition experiment to quantify the relative contribution of aboveground litter derived C to soil respiration, dissolved organic carbon, and various soil organic matter pools. Based on the results of our A. gerardii 13C and 15N labeling experiment we believe that this chamber design can be used to successfully produce dual stable isotope labeled plants for a wide variety of terrestrial nutrient flux experiments.

Identification of forensic samples by using an infrared-based automatic DNA sequencer.

PubMed

Ricci, Ugo; Sani, Ilaria; Klintschar, Michael; Cerri, Nicoletta; De Ferrari, Francesco; Giovannucci Uzielli, Maria Luisa

2003-06-01

We have recently introduced a new protocol for analyzing all core loci of the Federal Bureau of Investigation's (FBI) Combined DNA Index System (CODIS) with an infrared (IR) automatic DNA sequencer (LI-COR 4200). The amplicons were labeled with forward oligonucleotide primers, covalently linked to a new infrared fluorescent molecule (IRDye 800). The alleles were displayed as familiar autoradiogram-like images with real-time detection. This protocol was employed for paternity testing, population studies, and identification of degraded forensic samples. We extensively analyzed some simulated forensic samples and mixed stains (blood, semen, saliva, bones, and fixed archival embedded tissues), comparing the results with donor samples. Sensitivity studies were also performed for the four multiplex systems. Our results show the efficiency, reliability, and accuracy of the IR system for the analysis of forensic samples. We also compared the efficiency of the multiplex protocol with ultraviolet (UV) technology. Paternity tests, undegraded DNA samples, and real forensic samples were analyzed with this approach based on IR technology and with UV-based automatic sequencers in combination with commercially-available kits. The comparability of the results with the widespread UV methods suggests that it is possible to exchange data between laboratories using the same core group of markers but different primer sets and detection methods.

Automatic Human Movement Assessment With Switching Linear Dynamic System: Motion Segmentation and Motor Performance.

PubMed

de Souza Baptista, Roberto; Bo, Antonio P L; Hayashibe, Mitsuhiro

2017-06-01

Performance assessment of human movement is critical in diagnosis and motor-control rehabilitation. Recent developments in portable sensor technology enable clinicians to measure spatiotemporal aspects to aid in the neurological assessment. However, the extraction of quantitative information from such measurements is usually done manually through visual inspection. This paper presents a novel framework for automatic human movement assessment that executes segmentation and motor performance parameter extraction in time-series of measurements from a sequence of human movements. We use the elements of a Switching Linear Dynamic System model as building blocks to translate formal definitions and procedures from human movement analysis. Our approach provides a method for users with no expertise in signal processing to create models for movements using labeled dataset and later use it for automatic assessment. We validated our framework on preliminary tests involving six healthy adult subjects that executed common movements in functional tests and rehabilitation exercise sessions, such as sit-to-stand and lateral elevation of the arms and five elderly subjects, two of which with limited mobility, that executed the sit-to-stand movement. The proposed method worked on random motion sequences for the dual purpose of movement segmentation (accuracy of 72%-100%) and motor performance assessment (mean error of 0%-12%).

Landmark-guided diffeomorphic demons algorithm and its application to automatic segmentation of the whole spine and pelvis in CT images.

PubMed

Hanaoka, Shouhei; Masutani, Yoshitaka; Nemoto, Mitsutaka; Nomura, Yukihiro; Miki, Soichiro; Yoshikawa, Takeharu; Hayashi, Naoto; Ohtomo, Kuni; Shimizu, Akinobu

2017-03-01

A fully automatic multiatlas-based method for segmentation of the spine and pelvis in a torso CT volume is proposed. A novel landmark-guided diffeomorphic demons algorithm is used to register a given CT image to multiple atlas volumes. This algorithm can utilize both grayscale image information and given landmark coordinate information optimally. The segmentation has four steps. Firstly, 170 bony landmarks are detected in the given volume. Using these landmark positions, an atlas selection procedure is performed to reduce the computational cost of the following registration. Then the chosen atlas volumes are registered to the given CT image. Finally, voxelwise label voting is performed to determine the final segmentation result. The proposed method was evaluated using 50 torso CT datasets as well as the public SpineWeb dataset. As a result, a mean distance error of [Formula: see text] and a mean Dice coefficient of [Formula: see text] were achieved for the whole spine and the pelvic bones, which are competitive with other state-of-the-art methods. From the experimental results, the usefulness of the proposed segmentation method was validated.

Automatic discrimination between safe and unsafe swallowing using a reputation-based classifier

PubMed Central

2011-01-01

Background Swallowing accelerometry has been suggested as a potential non-invasive tool for bedside dysphagia screening. Various vibratory signal features and complementary measurement modalities have been put forth in the literature for the potential discrimination between safe and unsafe swallowing. To date, automatic classification of swallowing accelerometry has exclusively involved a single-axis of vibration although a second axis is known to contain additional information about the nature of the swallow. Furthermore, the only published attempt at automatic classification in adult patients has been based on a small sample of swallowing vibrations. Methods In this paper, a large corpus of dual-axis accelerometric signals were collected from 30 older adults (aged 65.47 ± 13.4 years, 15 male) referred to videofluoroscopic examination on the suspicion of dysphagia. We invoked a reputation-based classifier combination to automatically categorize the dual-axis accelerometric signals into safe and unsafe swallows, as labeled via videofluoroscopic review. From these participants, a total of 224 swallowing samples were obtained, 164 of which were labeled as unsafe swallows (swallows where the bolus entered the airway) and 60 as safe swallows. Three separate support vector machine (SVM) classifiers and eight different features were selected for classification. Results With selected time, frequency and information theoretic features, the reputation-based algorithm distinguished between safe and unsafe swallowing with promising accuracy (80.48 ± 5.0%), high sensitivity (97.1 ± 2%) and modest specificity (64 ± 8.8%). Interpretation of the most discriminatory features revealed that in general, unsafe swallows had lower mean vibration amplitude and faster autocorrelation decay, suggestive of decreased hyoid excursion and compromised coordination, respectively. Further, owing to its performance-based weighting of component classifiers, the static reputation-based algorithm outperformed the democratic majority voting algorithm on this clinical data set. Conclusion Given its computational efficiency and high sensitivity, reputation-based classification of dual-axis accelerometry ought to be considered in future developments of a point-of-care swallow assessment where clinical informatics are desired. PMID:22085802

Semantic Labelling of Road Furniture in Mobile Laser Scanning Data

NASA Astrophysics Data System (ADS)

Li, F.; Oude Elberink, S.; Vosselman, G.

2017-09-01

Road furniture semantic labelling is vital for large scale mapping and autonomous driving systems. Much research has been investigated on road furniture interpretation in both 2D images and 3D point clouds. Precise interpretation of road furniture in mobile laser scanning data still remains unexplored. In this paper, a novel method is proposed to interpret road furniture based on their logical relations and functionalities. Our work represents the most detailed interpretation of road furniture in mobile laser scanning data. 93.3 % of poles are correctly extracted and all of them are correctly recognised. 94.3 % of street light heads are detected and 76.9 % of them are correctly identified. Despite errors arising from the recognition of other components, our framework provides a promising solution to automatically map road furniture at a detailed level in urban environments.

Size ratio performance in detecting cerebral aneurysm rupture status is insensitive to small vessel removal.

PubMed

Lauric, Alexandra; Baharoglu, Merih I; Malek, Adel M

2013-04-01

The variable definition of size ratio (SR) for sidewall (SW) vs bifurcation (BIF) aneurysms raises confusion for lesions harboring small branches, such as carotid ophthalmic or posterior communicating locations. These aneurysms are considered SW by many clinicians, but SR methodology classifies them as BIF. To evaluate the effect of ignoring small vessels and SW vs stringent BIF labeling on SR ruptured aneurysm detection performance in borderline aneurysms with small branches, and to reconcile SR-based labeling with clinical SW/BIF classification. Catheter rotational angiographic datasets of 134 consecutive aneurysms (60 ruptured) were automatically measured in 3-dimensional. Stringent BIF labeling was applied to clinically labeled aneurysms, with 21 aneurysms switching label from SW to BIF. Parent vessel size was evaluated both taking into account, and ignoring, small vessels. SR was defined accordingly as the ratio between aneurysm and parent vessel sizes. Univariate and multivariate statistics identified significant features. The square of the correlation coefficient (R(2)) was reported for bivariate analysis of alternative SR calculations. Regardless of SW/BIF labeling method, SR was equally significant in discriminating aneurysm ruptured status (P < .001). Bivariate analysis of alternative SR had a high correlation of R(2) = 0.94 on the whole dataset, and R = 0.98 on the 21 borderline aneurysms. Ignoring small branches from SR calculation maintains rupture status detection performance, while reducing postprocessing complexity and removing labeling ambiguity. Aneurysms adjacent to these vessels can be considered SW for morphometric analysis. It is reasonable to use the clinical SW/BIF labeling when using SR for rupture risk evaluation.

Machine learning for medical images analysis.

PubMed

Criminisi, A

2016-10-01

This article discusses the application of machine learning for the analysis of medical images. Specifically: (i) We show how a special type of learning models can be thought of as automatically optimized, hierarchically-structured, rule-based algorithms, and (ii) We discuss how the issue of collecting large labelled datasets applies to both conventional algorithms as well as machine learning techniques. The size of the training database is a function of model complexity rather than a characteristic of machine learning methods. Crown Copyright © 2016. Published by Elsevier B.V. All rights reserved.

ADMAP (automatic data manipulation program)

NASA Technical Reports Server (NTRS)

Mann, F. I.

1971-01-01

Instructions are presented on the use of ADMAP, (automatic data manipulation program) an aerospace data manipulation computer program. The program was developed to aid in processing, reducing, plotting, and publishing electric propulsion trajectory data generated by the low thrust optimization program, HILTOP. The program has the option of generating SC4020 electric plots, and therefore requires the SC4020 routines to be available at excution time (even if not used). Several general routines are present, including a cubic spline interpolation routine, electric plotter dash line drawing routine, and single parameter and double parameter sorting routines. Many routines are tailored for the manipulation and plotting of electric propulsion data, including an automatic scale selection routine, an automatic curve labelling routine, and an automatic graph titling routine. Data are accepted from either punched cards or magnetic tape.

Automatic 3D kidney segmentation based on shape constrained GC-OAAM

NASA Astrophysics Data System (ADS)

Chen, Xinjian; Summers, Ronald M.; Yao, Jianhua

2011-03-01

The kidney can be classified into three main tissue types: renal cortex, renal medulla and renal pelvis (or collecting system). Dysfunction of different renal tissue types may cause different kidney diseases. Therefore, accurate and efficient segmentation of kidney into different tissue types plays a very important role in clinical research. In this paper, we propose an automatic 3D kidney segmentation method which segments the kidney into the three different tissue types: renal cortex, medulla and pelvis. The proposed method synergistically combines active appearance model (AAM), live wire (LW) and graph cut (GC) methods, GC-OAAM for short. Our method consists of two main steps. First, a pseudo 3D segmentation method is employed for kidney initialization in which the segmentation is performed slice-by-slice via a multi-object oriented active appearance model (OAAM) method. An improved iterative model refinement algorithm is proposed for the AAM optimization, which synergistically combines the AAM and LW method. Multi-object strategy is applied to help the object initialization. The 3D model constraints are applied to the initialization result. Second, the object shape information generated from the initialization step is integrated into the GC cost computation. A multi-label GC method is used to segment the kidney into cortex, medulla and pelvis. The proposed method was tested on 19 clinical arterial phase CT data sets. The preliminary results showed the feasibility and efficiency of the proposed method.

The study of infrared target recognition at sea background based on visual attention computational model

NASA Astrophysics Data System (ADS)

Wang, Deng-wei; Zhang, Tian-xu; Shi, Wen-jun; Wei, Long-sheng; Wang, Xiao-ping; Ao, Guo-qing

2009-07-01

Infrared images at sea background are notorious for the low signal-to-noise ratio, therefore, the target recognition of infrared image through traditional methods is very difficult. In this paper, we present a novel target recognition method based on the integration of visual attention computational model and conventional approach (selective filtering and segmentation). The two distinct techniques for image processing are combined in a manner to utilize the strengths of both. The visual attention algorithm searches the salient regions automatically, and represented them by a set of winner points, at the same time, demonstrated the salient regions in terms of circles centered at these winner points. This provides a priori knowledge for the filtering and segmentation process. Based on the winner point, we construct a rectangular region to facilitate the filtering and segmentation, then the labeling operation will be added selectively by requirement. Making use of the labeled information, from the final segmentation result we obtain the positional information of the interested region, label the centroid on the corresponding original image, and finish the localization for the target. The cost time does not depend on the size of the image but the salient regions, therefore the consumed time is greatly reduced. The method is used in the recognition of several kinds of real infrared images, and the experimental results reveal the effectiveness of the algorithm presented in this paper.

Intelligent and automatic in vivo detection and quantification of transplanted cells in MRI.

PubMed

Afridi, Muhammad Jamal; Ross, Arun; Liu, Xiaoming; Bennewitz, Margaret F; Shuboni, Dorela D; Shapiro, Erik M

2017-11-01

Magnetic resonance imaging (MRI)-based cell tracking has emerged as a useful tool for identifying the location of transplanted cells, and even their migration. Magnetically labeled cells appear as dark contrast in T2*-weighted MRI, with sensitivities of individual cells. One key hurdle to the widespread use of MRI-based cell tracking is the inability to determine the number of transplanted cells based on this contrast feature. In the case of single cell detection, manual enumeration of spots in three-dimensional (3D) MRI in principle is possible; however, it is a tedious and time-consuming task that is prone to subjectivity and inaccuracy on a large scale. This research presents the first comprehensive study on how a computer-based intelligent, automatic, and accurate cell quantification approach can be designed for spot detection in MRI scans. Magnetically labeled mesenchymal stem cells (MSCs) were transplanted into rats using an intracardiac injection, accomplishing single cell seeding in the brain. T2*-weighted MRI of these rat brains were performed where labeled MSCs appeared as spots. Using machine learning and computer vision paradigms, approaches were designed to systematically explore the possibility of automatic detection of these spots in MRI. Experiments were validated against known in vitro scenarios. Using the proposed deep convolutional neural network (CNN) architecture, an in vivo accuracy up to 97.3% and in vitro accuracy of up to 99.8% was achieved for automated spot detection in MRI data. The proposed approach for automatic quantification of MRI-based cell tracking will facilitate the use of MRI in large-scale cell therapy studies. Magn Reson Med 78:1991-2002, 2017. © 2016 International Society for Magnetic Resonance in Medicine. © 2016 International Society for Magnetic Resonance in Medicine.

GLISTR: Glioma Image Segmentation and Registration

PubMed Central

Pohl, Kilian M.; Bilello, Michel; Cirillo, Luigi; Biros, George; Melhem, Elias R.; Davatzikos, Christos

2015-01-01

We present a generative approach for simultaneously registering a probabilistic atlas of a healthy population to brain magnetic resonance (MR) scans showing glioma and segmenting the scans into tumor as well as healthy tissue labels. The proposed method is based on the expectation maximization (EM) algorithm that incorporates a glioma growth model for atlas seeding, a process which modifies the original atlas into one with tumor and edema adapted to best match a given set of patient’s images. The modified atlas is registered into the patient space and utilized for estimating the posterior probabilities of various tissue labels. EM iteratively refines the estimates of the posterior probabilities of tissue labels, the deformation field and the tumor growth model parameters. Hence, in addition to segmentation, the proposed method results in atlas registration and a low-dimensional description of the patient scans through estimation of tumor model parameters. We validate the method by automatically segmenting 10 MR scans and comparing the results to those produced by clinical experts and two state-of-the-art methods. The resulting segmentations of tumor and edema outperform the results of the reference methods, and achieve a similar accuracy from a second human rater. We additionally apply the method to 122 patients scans and report the estimated tumor model parameters and their relations with segmentation and registration results. Based on the results from this patient population, we construct a statistical atlas of the glioma by inverting the estimated deformation fields to warp the tumor segmentations of patients scans into a common space. PMID:22907965

Automated identification of ERP peaks through Dynamic Time Warping: an application to developmental dyslexia.

PubMed

Assecondi, Sara; Bianchi, A M; Hallez, H; Staelens, S; Casarotto, S; Lemahieu, I; Chiarenza, G A

2009-10-01

This article proposes a method to automatically identify and label event-related potential (ERP) components with high accuracy and precision. We present a framework, referred to as peak-picking Dynamic Time Warping (ppDTW), where a priori knowledge about the ERPs under investigation is used to define a reference signal. We developed a combination of peak-picking and Dynamic Time Warping (DTW) that makes the temporal intervals for peak-picking adaptive on the basis of the morphology of the data. We tested the procedure on experimental data recorded from a control group and from children diagnosed with developmental dyslexia. We compared our results with the traditional peak-picking. We demonstrated that our method achieves better performance than peak-picking, with an overall precision, recall and F-score of 93%, 86% and 89%, respectively, versus 93%, 80% and 85% achieved by peak-picking. We showed that our hybrid method outperforms peak-picking, when dealing with data involving several peaks of interest. The proposed method can reliably identify and label ERP components in challenging event-related recordings, thus assisting the clinician in an objective assessment of amplitudes and latencies of peaks of clinical interest.

An immune-inspired semi-supervised algorithm for breast cancer diagnosis.

PubMed

Peng, Lingxi; Chen, Wenbin; Zhou, Wubai; Li, Fufang; Yang, Jin; Zhang, Jiandong

2016-10-01

Breast cancer is the most frequently and world widely diagnosed life-threatening cancer, which is the leading cause of cancer death among women. Early accurate diagnosis can be a big plus in treating breast cancer. Researchers have approached this problem using various data mining and machine learning techniques such as support vector machine, artificial neural network, etc. The computer immunology is also an intelligent method inspired by biological immune system, which has been successfully applied in pattern recognition, combination optimization, machine learning, etc. However, most of these diagnosis methods belong to a supervised diagnosis method. It is very expensive to obtain labeled data in biology and medicine. In this paper, we seamlessly integrate the state-of-the-art research on life science with artificial intelligence, and propose a semi-supervised learning algorithm to reduce the need for labeled data. We use two well-known benchmark breast cancer datasets in our study, which are acquired from the UCI machine learning repository. Extensive experiments are conducted and evaluated on those two datasets. Our experimental results demonstrate the effectiveness and efficiency of our proposed algorithm, which proves that our algorithm is a promising automatic diagnosis method for breast cancer. Copyright © 2016 Elsevier Ireland Ltd. All rights reserved.

TU-G-204-02: Automatic Sclerotic Bone Metastases Detection in the Pelvic Region From Dual Energy CT

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

Fehr, D; Schmidtlein, C; Hwang, S

Purpose: To automatically detect sclerotic bone metastases in the pelvic region using dual energy computed tomography (DECT). Methods: We developed a two stage algorithm to automatically detect sclerotic bone metastases in the pelvis from DECT for patients with multiple bone metastatic lesions and with hip implants. The first stage consists of extracting the bone and marrow regions by using a support vector machine (SVM) classifier. We employed a novel representation of the DECT images using multi-material decomposition, which represents each voxel as a mixture of different physical materials (e.g. bone+water+fat). Following the extraction of bone and marrow, in the secondmore » stage, a bi -histogram equalization method was employed to enhance the contrast to reveal the bone metastases. Next, meanshift segmentation was performed to separate the voxels by their intensity levels. Finally, shape-based filtering was performed to extract the possible locations of the metastatic lesions using multiple shape criteria. We used the following shape parameters: area, eccentricity, major and minor axis, perimeter and skeleton. Results: A radiologist with several years of experience with DECT manually labeled 64 regions consisting of metastatic lesions from 10 different patients. However, the patients had many more metastasic lesions throughout the pelvis. Our method correctly identified 46 of the marked 64 regions (72%). In addition, our method also identified several other lesions, which can then be validated by the radiologist. The missed lesions were typically very large elongated regions consisting of several islands of very small (<4mm) lesions. Conclusion: We developed an algorithm to automatically detect sclerotic lesions in the pelvic region from DECT. Preliminary assessment shows that our algorithm generated lesions agreeing with the radiologist generated candidate regions. Furthermore, our method reveals additional lesions that can be inspected by the radiologist, thereby, reducing radiologist effort in identifying all the lesions with poor contrast from the DECT images.« less

Automatic and Reproducible Positioning of Phase-Contrast MRI for the Quantification of Global Cerebral Blood Flow

PubMed Central

Liu, Peiying; Lu, Hanzhang; Filbey, Francesca M.; Pinkham, Amy E.; McAdams, Carrie J.; Adinoff, Bryon; Daliparthi, Vamsi; Cao, Yan

2014-01-01

Phase-Contrast MRI (PC-MRI) is a noninvasive technique to measure blood flow. In particular, global but highly quantitative cerebral blood flow (CBF) measurement using PC-MRI complements several other CBF mapping methods such as arterial spin labeling and dynamic susceptibility contrast MRI by providing a calibration factor. The ability to estimate blood supply in physiological units also lays a foundation for assessment of brain metabolic rate. However, a major obstacle before wider applications of this method is that the slice positioning of the scan, ideally placed perpendicular to the feeding arteries, requires considerable expertise and can present a burden to the operator. In the present work, we proposed that the majority of PC-MRI scans can be positioned using an automatic algorithm, leaving only a small fraction of arteries requiring manual positioning. We implemented and evaluated an algorithm for this purpose based on feature extraction of a survey angiogram, which is of minimal operator dependence. In a comparative test-retest study with 7 subjects, the blood flow measurement using this algorithm showed an inter-session coefficient of variation (CoV) of . The Bland-Altman method showed that the automatic method differs from the manual method by between and , for of the CBF measurements. This is comparable to the variance in CBF measurement using manually-positioned PC MRI alone. In a further application of this algorithm to 157 consecutive subjects from typical clinical cohorts, the algorithm provided successful positioning in 89.7% of the arteries. In 79.6% of the subjects, all four arteries could be planned using the algorithm. Chi-square tests of independence showed that the success rate was not dependent on the age or gender, but the patients showed a trend of lower success rate (p = 0.14) compared to healthy controls. In conclusion, this automatic positioning algorithm could improve the application of PC-MRI in CBF quantification. PMID:24787742

Image Based Hair Segmentation Algorithm for the Application of Automatic Facial Caricature Synthesis

PubMed Central

Peng, Zhenyun; Zhang, Yaohui

2014-01-01

Hair is a salient feature in human face region and are one of the important cues for face analysis. Accurate detection and presentation of hair region is one of the key components for automatic synthesis of human facial caricature. In this paper, an automatic hair detection algorithm for the application of automatic synthesis of facial caricature based on a single image is proposed. Firstly, hair regions in training images are labeled manually and then the hair position prior distributions and hair color likelihood distribution function are estimated from these labels efficiently. Secondly, the energy function of the test image is constructed according to the estimated prior distributions of hair location and hair color likelihood. This energy function is further optimized according to graph cuts technique and initial hair region is obtained. Finally, K-means algorithm and image postprocessing techniques are applied to the initial hair region so that the final hair region can be segmented precisely. Experimental results show that the average processing time for each image is about 280 ms and the average hair region detection accuracy is above 90%. The proposed algorithm is applied to a facial caricature synthesis system. Experiments proved that with our proposed hair segmentation algorithm the facial caricatures are vivid and satisfying. PMID:24592182

Biomedical literature classification using encyclopedic knowledge: a Wikipedia-based bag-of-concepts approach.

PubMed

Mouriño García, Marcos Antonio; Pérez Rodríguez, Roberto; Anido Rifón, Luis E

2015-01-01

Automatic classification of text documents into a set of categories has a lot of applications. Among those applications, the automatic classification of biomedical literature stands out as an important application for automatic document classification strategies. Biomedical staff and researchers have to deal with a lot of literature in their daily activities, so it would be useful a system that allows for accessing to documents of interest in a simple and effective way; thus, it is necessary that these documents are sorted based on some criteria-that is to say, they have to be classified. Documents to classify are usually represented following the bag-of-words (BoW) paradigm. Features are words in the text-thus suffering from synonymy and polysemy-and their weights are just based on their frequency of occurrence. This paper presents an empirical study of the efficiency of a classifier that leverages encyclopedic background knowledge-concretely Wikipedia-in order to create bag-of-concepts (BoC) representations of documents, understanding concept as "unit of meaning", and thus tackling synonymy and polysemy. Besides, the weighting of concepts is based on their semantic relevance in the text. For the evaluation of the proposal, empirical experiments have been conducted with one of the commonly used corpora for evaluating classification and retrieval of biomedical information, OHSUMED, and also with a purpose-built corpus of MEDLINE biomedical abstracts, UVigoMED. Results obtained show that the Wikipedia-based bag-of-concepts representation outperforms the classical bag-of-words representation up to 157% in the single-label classification problem and up to 100% in the multi-label problem for OHSUMED corpus, and up to 122% in the single-label classification problem and up to 155% in the multi-label problem for UVigoMED corpus.

Biomedical literature classification using encyclopedic knowledge: a Wikipedia-based bag-of-concepts approach

PubMed Central

Pérez Rodríguez, Roberto; Anido Rifón, Luis E.

2015-01-01

Automatic classification of text documents into a set of categories has a lot of applications. Among those applications, the automatic classification of biomedical literature stands out as an important application for automatic document classification strategies. Biomedical staff and researchers have to deal with a lot of literature in their daily activities, so it would be useful a system that allows for accessing to documents of interest in a simple and effective way; thus, it is necessary that these documents are sorted based on some criteria—that is to say, they have to be classified. Documents to classify are usually represented following the bag-of-words (BoW) paradigm. Features are words in the text—thus suffering from synonymy and polysemy—and their weights are just based on their frequency of occurrence. This paper presents an empirical study of the efficiency of a classifier that leverages encyclopedic background knowledge—concretely Wikipedia—in order to create bag-of-concepts (BoC) representations of documents, understanding concept as “unit of meaning”, and thus tackling synonymy and polysemy. Besides, the weighting of concepts is based on their semantic relevance in the text. For the evaluation of the proposal, empirical experiments have been conducted with one of the commonly used corpora for evaluating classification and retrieval of biomedical information, OHSUMED, and also with a purpose-built corpus of MEDLINE biomedical abstracts, UVigoMED. Results obtained show that the Wikipedia-based bag-of-concepts representation outperforms the classical bag-of-words representation up to 157% in the single-label classification problem and up to 100% in the multi-label problem for OHSUMED corpus, and up to 122% in the single-label classification problem and up to 155% in the multi-label problem for UVigoMED corpus. PMID:26468436

Tumor propagation model using generalized hidden Markov model

NASA Astrophysics Data System (ADS)

Park, Sun Young; Sargent, Dustin

2017-02-01

Tumor tracking and progression analysis using medical images is a crucial task for physicians to provide accurate and efficient treatment plans, and monitor treatment response. Tumor progression is tracked by manual measurement of tumor growth performed by radiologists. Several methods have been proposed to automate these measurements with segmentation, but many current algorithms are confounded by attached organs and vessels. To address this problem, we present a new generalized tumor propagation model considering time-series prior images and local anatomical features using a Hierarchical Hidden Markov model (HMM) for tumor tracking. First, we apply the multi-atlas segmentation technique to identify organs/sub-organs using pre-labeled atlases. Second, we apply a semi-automatic direct 3D segmentation method to label the initial boundary between the lesion and neighboring structures. Third, we detect vessels in the ROI surrounding the lesion. Finally, we apply the propagation model with the labeled organs and vessels to accurately segment and measure the target lesion. The algorithm has been designed in a general way to be applicable to various body parts and modalities. In this paper, we evaluate the proposed algorithm on lung and lung nodule segmentation and tracking. We report the algorithm's performance by comparing the longest diameter and nodule volumes using the FDA lung Phantom data and a clinical dataset.

Automatic construction of a recurrent neural network based classifier for vehicle passage detection

NASA Astrophysics Data System (ADS)

Burnaev, Evgeny; Koptelov, Ivan; Novikov, German; Khanipov, Timur

2017-03-01

Recurrent Neural Networks (RNNs) are extensively used for time-series modeling and prediction. We propose an approach for automatic construction of a binary classifier based on Long Short-Term Memory RNNs (LSTM-RNNs) for detection of a vehicle passage through a checkpoint. As an input to the classifier we use multidimensional signals of various sensors that are installed on the checkpoint. Obtained results demonstrate that the previous approach to handcrafting a classifier, consisting of a set of deterministic rules, can be successfully replaced by an automatic RNN training on an appropriately labelled data.

Automatic exudate detection by fusing multiple active contours and regionwise classification.

PubMed

Harangi, Balazs; Hajdu, Andras

2014-11-01

In this paper, we propose a method for the automatic detection of exudates in digital fundus images. Our approach can be divided into three stages: candidate extraction, precise contour segmentation and the labeling of candidates as true or false exudates. For candidate detection, we borrow a grayscale morphology-based method to identify possible regions containing these bright lesions. Then, to extract the precise boundary of the candidates, we introduce a complex active contour-based method. Namely, to increase the accuracy of segmentation, we extract additional possible contours by taking advantage of the diverse behavior of different pre-processing methods. After selecting an appropriate combination of the extracted contours, a region-wise classifier is applied to remove the false exudate candidates. For this task, we consider several region-based features, and extract an appropriate feature subset to train a Naïve-Bayes classifier optimized further by an adaptive boosting technique. Regarding experimental studies, the method was tested on publicly available databases both to measure the accuracy of the segmentation of exudate regions and to recognize their presence at image-level. In a proper quantitative evaluation on publicly available datasets the proposed approach outperformed several state-of-the-art exudate detector algorithms. Copyright © 2014 Elsevier Ltd. All rights reserved.

Beyond Retinal Layers: A Deep Voting Model for Automated Geographic Atrophy Segmentation in SD-OCT Images

PubMed Central

Ji, Zexuan; Chen, Qiang; Niu, Sijie; Leng, Theodore; Rubin, Daniel L.

2018-01-01

Purpose To automatically and accurately segment geographic atrophy (GA) in spectral-domain optical coherence tomography (SD-OCT) images by constructing a voting system with deep neural networks without the use of retinal layer segmentation. Methods An automatic GA segmentation method for SD-OCT images based on the deep network was constructed. The structure of the deep network was composed of five layers, including one input layer, three hidden layers, and one output layer. During the training phase, the labeled A-scans with 1024 features were directly fed into the network as the input layer to obtain the deep representations. Then a soft-max classifier was trained to determine the label of each individual pixel. Finally, a voting decision strategy was used to refine the segmentation results among 10 trained models. Results Two image data sets with GA were used to evaluate the model. For the first dataset, our algorithm obtained a mean overlap ratio (OR) 86.94% ± 8.75%, absolute area difference (AAD) 11.49% ± 11.50%, and correlation coefficients (CC) 0.9857; for the second dataset, the mean OR, AAD, and CC of the proposed method were 81.66% ± 10.93%, 8.30% ± 9.09%, and 0.9952, respectively. The proposed algorithm was capable of improving over 5% and 10% segmentation accuracy, respectively, when compared with several state-of-the-art algorithms on two data sets. Conclusions Without retinal layer segmentation, the proposed algorithm could produce higher segmentation accuracy and was more stable when compared with state-of-the-art methods that relied on retinal layer segmentation results. Our model may provide reliable GA segmentations from SD-OCT images and be useful in the clinical diagnosis of advanced nonexudative AMD. Translational Relevance Based on the deep neural networks, this study presents an accurate GA segmentation method for SD-OCT images without using any retinal layer segmentation results, and may contribute to improved understanding of advanced nonexudative AMD. PMID:29302382

101 Labeled Brain Images and a Consistent Human Cortical Labeling Protocol

PubMed Central

Klein, Arno; Tourville, Jason

2012-01-01

We introduce the Mindboggle-101 dataset, the largest and most complete set of free, publicly accessible, manually labeled human brain images. To manually label the macroscopic anatomy in magnetic resonance images of 101 healthy participants, we created a new cortical labeling protocol that relies on robust anatomical landmarks and minimal manual edits after initialization with automated labels. The “Desikan–Killiany–Tourville” (DKT) protocol is intended to improve the ease, consistency, and accuracy of labeling human cortical areas. Given how difficult it is to label brains, the Mindboggle-101 dataset is intended to serve as brain atlases for use in labeling other brains, as a normative dataset to establish morphometric variation in a healthy population for comparison against clinical populations, and contribute to the development, training, testing, and evaluation of automated registration and labeling algorithms. To this end, we also introduce benchmarks for the evaluation of such algorithms by comparing our manual labels with labels automatically generated by probabilistic and multi-atlas registration-based approaches. All data and related software and updated information are available on the http://mindboggle.info/data website. PMID:23227001

Labeled Graph Kernel for Behavior Analysis.

PubMed

Zhao, Ruiqi; Martinez, Aleix M

2016-08-01

Automatic behavior analysis from video is a major topic in many areas of research, including computer vision, multimedia, robotics, biology, cognitive science, social psychology, psychiatry, and linguistics. Two major problems are of interest when analyzing behavior. First, we wish to automatically categorize observed behaviors into a discrete set of classes (i.e., classification). For example, to determine word production from video sequences in sign language. Second, we wish to understand the relevance of each behavioral feature in achieving this classification (i.e., decoding). For instance, to know which behavior variables are used to discriminate between the words apple and onion in American Sign Language (ASL). The present paper proposes to model behavior using a labeled graph, where the nodes define behavioral features and the edges are labels specifying their order (e.g., before, overlaps, start). In this approach, classification reduces to a simple labeled graph matching. Unfortunately, the complexity of labeled graph matching grows exponentially with the number of categories we wish to represent. Here, we derive a graph kernel to quickly and accurately compute this graph similarity. This approach is very general and can be plugged into any kernel-based classifier. Specifically, we derive a Labeled Graph Support Vector Machine (LGSVM) and a Labeled Graph Logistic Regressor (LGLR) that can be readily employed to discriminate between many actions (e.g., sign language concepts). The derived approach can be readily used for decoding too, yielding invaluable information for the understanding of a problem (e.g., to know how to teach a sign language). The derived algorithms allow us to achieve higher accuracy results than those of state-of-the-art algorithms in a fraction of the time. We show experimental results on a variety of problems and datasets, including multimodal data.

Development of a novel constellation based landmark detection algorithm

NASA Astrophysics Data System (ADS)

Ghayoor, Ali; Vaidya, Jatin G.; Johnson, Hans J.

2013-03-01

Anatomical landmarks such as the anterior commissure (AC) and posterior commissure (PC) are commonly used by researchers for co-registration of images. In this paper, we present a novel, automated approach for landmark detection that combines morphometric constraining and statistical shape models to provide accurate estimation of landmark points. This method is made robust to large rotations in initial head orientation by extracting extra information of the eye centers using a radial Hough transform and exploiting the centroid of head mass (CM) using a novel estimation approach. To evaluate the effectiveness of this method, the algorithm is trained on a set of 20 images with manually selected landmarks, and a test dataset is used to compare the automatically detected against the manually detected landmark locations of the AC, PC, midbrain-pons junction (MPJ), and fourth ventricle notch (VN4). The results show that the proposed method is accurate as the average error between the automatically and manually labeled landmark points is less than 1 mm. Also, the algorithm is highly robust as it was successfully run on a large dataset that included different kinds of images with various orientation, spacing, and origin.

A convolutional neural network for intracranial hemorrhage detection in non-contrast CT

NASA Astrophysics Data System (ADS)

Patel, Ajay; Manniesing, Rashindra

2018-02-01

The assessment of the presence of intracranial hemorrhage is a crucial step in the work-up of patients requiring emergency care. Fast and accurate detection of intracranial hemorrhage can aid treating physicians by not only expediting and guiding diagnosis, but also supporting choices for secondary imaging, treatment and intervention. However, the automatic detection of intracranial hemorrhage is complicated by the variation in appearance on non-contrast CT images as a result of differences in etiology and location. We propose a method using a convolutional neural network (CNN) for the automatic detection of intracranial hemorrhage. The method is trained on a dataset comprised of cerebral CT studies for which the presence of hemorrhage has been labeled for each axial slice. A separate test dataset of 20 images is used for quantitative evaluation and shows a sensitivity of 0.87, specificity of 0.97 and accuracy of 0.95. The average processing time for a single three-dimensional (3D) CT volume was 2.7 seconds. The proposed method is capable of fast and automated detection of intracranial hemorrhages in non-contrast CT without being limited to a specific subtype of pathology.

[The laboratory of tomorrow. Particular reference to hematology].

PubMed

Cazal, P

1985-01-01

A serious prediction can only be an extrapolation of recent developments. To be exact, the development has to continue in the same direction, which is only a probability. Probable development of hematological technology: Progress in methods. Development of new labelling methods: radio-elements, antibodies. Monoclonal antibodies. Progress in equipment: Cell counters and their adaptation to routine hemograms is a certainty. From analyzers: a promise that will perhaps become reality. Coagulometers: progress still to be made. Hemagglutination detectors and their application to grouping: good achievements, but the market is too limited. Computerization and automation: What form will the computerizing take? What will the computer do? Who will the computer control? What should the automatic analyzers be? Two current levels. Relationships between the automatic analysers and the computer. rapidity, fidelity and above all, reliability. Memory: large capacity and easy access. Disadvantages: conservatism and technical dependency. How can they be avoided? Development of the environment: Laboratory input: outside supplies, electricity, reagents, consumables. Samples and their identification. Output: distribution of results and communication problems. Centralization or decentralization? What will tomorrow's laboratory be? 3 hypotheses: optimistic, pessimistic, and balanced.

Active learning approach for detection of hard exudates, cotton wool spots, and drusen in retinal images

NASA Astrophysics Data System (ADS)

Sánchez, Clara I.; Niemeijer, Meindert; Kockelkorn, Thessa; Abràmoff, Michael D.; van Ginneken, Bram

2009-02-01

Computer-aided Diagnosis (CAD) systems for the automatic identification of abnormalities in retinal images are gaining importance in diabetic retinopathy screening programs. A huge amount of retinal images are collected during these programs and they provide a starting point for the design of machine learning algorithms. However, manual annotations of retinal images are scarce and expensive to obtain. This paper proposes a dynamic CAD system based on active learning for the automatic identification of hard exudates, cotton wool spots and drusen in retinal images. An uncertainty sampling method is applied to select samples that need to be labeled by an expert from an unlabeled set of 4000 retinal images. It reduces the number of training samples needed to obtain an optimum accuracy by dynamically selecting the most informative samples. Results show that the proposed method increases the classification accuracy compared to alternative techniques, achieving an area under the ROC curve of 0.87, 0.82 and 0.78 for the detection of hard exudates, cotton wool spots and drusen, respectively.

MultiMap: A Tool to Automatically Extract and Analyse Spatial Microscopic Data From Large Stacks of Confocal Microscopy Images

PubMed Central

Varando, Gherardo; Benavides-Piccione, Ruth; Muñoz, Alberto; Kastanauskaite, Asta; Bielza, Concha; Larrañaga, Pedro; DeFelipe, Javier

2018-01-01

The development of 3D visualization and reconstruction methods to analyse microscopic structures at different levels of resolutions is of great importance to define brain microorganization and connectivity. MultiMap is a new tool that allows the visualization, 3D segmentation and quantification of fluorescent structures selectively in the neuropil from large stacks of confocal microscopy images. The major contribution of this tool is the posibility to easily navigate and create regions of interest of any shape and size within a large brain area that will be automatically 3D segmented and quantified to determine the density of puncta in the neuropil. As a proof of concept, we focused on the analysis of glutamatergic and GABAergic presynaptic axon terminals in the mouse hippocampal region to demonstrate its use as a tool to provide putative excitatory and inhibitory synaptic maps. The segmentation and quantification method has been validated over expert labeled images of the mouse hippocampus and over two benchmark datasets, obtaining comparable results to the expert detections. PMID:29875639

MultiMap: A Tool to Automatically Extract and Analyse Spatial Microscopic Data From Large Stacks of Confocal Microscopy Images.

PubMed

Varando, Gherardo; Benavides-Piccione, Ruth; Muñoz, Alberto; Kastanauskaite, Asta; Bielza, Concha; Larrañaga, Pedro; DeFelipe, Javier

2018-01-01

The development of 3D visualization and reconstruction methods to analyse microscopic structures at different levels of resolutions is of great importance to define brain microorganization and connectivity. MultiMap is a new tool that allows the visualization, 3D segmentation and quantification of fluorescent structures selectively in the neuropil from large stacks of confocal microscopy images. The major contribution of this tool is the posibility to easily navigate and create regions of interest of any shape and size within a large brain area that will be automatically 3D segmented and quantified to determine the density of puncta in the neuropil. As a proof of concept, we focused on the analysis of glutamatergic and GABAergic presynaptic axon terminals in the mouse hippocampal region to demonstrate its use as a tool to provide putative excitatory and inhibitory synaptic maps. The segmentation and quantification method has been validated over expert labeled images of the mouse hippocampus and over two benchmark datasets, obtaining comparable results to the expert detections.

An automatic search of Alzheimer patterns using a nonnegative matrix factorization

NASA Astrophysics Data System (ADS)

Giraldo, Diana L.; García-Arteaga, Juan D.; Romero, Eduardo

2013-11-01

This paper presents a fully automatic method that condenses relevant morphometric information from a database of magnetic resonance images (MR) labeled as either normal (NC) or Alzheimer's disease (AD). The proposed method generates class templates using Nonnegative Matrix Factorization (NMF) which will be used to develop an NC/AD classi cator. It then nds regions of interest (ROI) with discerning inter-class properties. by inspecting the di erence volume of the two class templates. From these templates local probability distribution functions associated to low level features such as intensities, orientation and edges within the found ROI are calculated. A sample brain volume can then be characterized by a similarity measure in the ROI to both the normal and the pathological templates. These characteristics feed a simple binary SVM classi er which, when tested with an experimental group extracted from a public brain MR dataset (OASIS), reveals an equal error rate measure which is better than the state-of-the-art tested on the same dataset (0:9 in the former and 0:8 in the latter).

Automatic computational labeling of glomerular textural boundaries

NASA Astrophysics Data System (ADS)

Ginley, Brandon; Tomaszewski, John E.; Sarder, Pinaki

2017-03-01

The glomerulus, a specialized bundle of capillaries, is the blood filtering unit of the kidney. Each human kidney contains about 1 million glomeruli. Structural damages in the glomerular micro-compartments give rise to several renal conditions; most severe of which is proteinuria, where excessive blood proteins flow freely to the urine. The sole way to confirm glomerular structural damage in renal pathology is by examining histopathological or immunofluorescence stained needle biopsies under a light microscope. However, this method is extremely tedious and time consuming, and requires manual scoring on the number and volume of structures. Computational quantification of equivalent features promises to greatly ease this manual burden. The largest obstacle to computational quantification of renal tissue is the ability to recognize complex glomerular textural boundaries automatically. Here we present a computational pipeline to accurately identify glomerular boundaries with high precision and accuracy. The computational pipeline employs an integrated approach composed of Gabor filtering, Gaussian blurring, statistical F-testing, and distance transform, and performs significantly better than standard Gabor based textural segmentation method. Our integrated approach provides mean accuracy/precision of 0.89/0.97 on n = 200Hematoxylin and Eosin (HE) glomerulus images, and mean 0.88/0.94 accuracy/precision on n = 200 Periodic Acid Schiff (PAS) glomerulus images. Respective accuracy/precision of the Gabor filter bank based method is 0.83/0.84 for HE and 0.78/0.8 for PAS. Our method will simplify computational partitioning of glomerular micro-compartments hidden within dense textural boundaries. Automatic quantification of glomeruli will streamline structural analysis in clinic, and can help realize real time diagnoses and interventions.

A Customized Attention-Based Long Short-Term Memory Network for Distant Supervised Relation Extraction.

PubMed

He, Dengchao; Zhang, Hongjun; Hao, Wenning; Zhang, Rui; Cheng, Kai

2017-07-01

Distant supervision, a widely applied approach in the field of relation extraction can automatically generate large amounts of labeled training corpus with minimal manual effort. However, the labeled training corpus may have many false-positive data, which would hurt the performance of relation extraction. Moreover, in traditional feature-based distant supervised approaches, extraction models adopt human design features with natural language processing. It may also cause poor performance. To address these two shortcomings, we propose a customized attention-based long short-term memory network. Our approach adopts word-level attention to achieve better data representation for relation extraction without manually designed features to perform distant supervision instead of fully supervised relation extraction, and it utilizes instance-level attention to tackle the problem of false-positive data. Experimental results demonstrate that our proposed approach is effective and achieves better performance than traditional methods.

Semi-supervised Learning for Phenotyping Tasks.

PubMed

Dligach, Dmitriy; Miller, Timothy; Savova, Guergana K

2015-01-01

Supervised learning is the dominant approach to automatic electronic health records-based phenotyping, but it is expensive due to the cost of manual chart review. Semi-supervised learning takes advantage of both scarce labeled and plentiful unlabeled data. In this work, we study a family of semi-supervised learning algorithms based on Expectation Maximization (EM) in the context of several phenotyping tasks. We first experiment with the basic EM algorithm. When the modeling assumptions are violated, basic EM leads to inaccurate parameter estimation. Augmented EM attenuates this shortcoming by introducing a weighting factor that downweights the unlabeled data. Cross-validation does not always lead to the best setting of the weighting factor and other heuristic methods may be preferred. We show that accurate phenotyping models can be trained with only a few hundred labeled (and a large number of unlabeled) examples, potentially providing substantial savings in the amount of the required manual chart review.

Neural Network for Nanoscience Scanning Electron Microscope Image Recognition.

PubMed

Modarres, Mohammad Hadi; Aversa, Rossella; Cozzini, Stefano; Ciancio, Regina; Leto, Angelo; Brandino, Giuseppe Piero

2017-10-16

In this paper we applied transfer learning techniques for image recognition, automatic categorization, and labeling of nanoscience images obtained by scanning electron microscope (SEM). Roughly 20,000 SEM images were manually classified into 10 categories to form a labeled training set, which can be used as a reference set for future applications of deep learning enhanced algorithms in the nanoscience domain. The categories chosen spanned the range of 0-Dimensional (0D) objects such as particles, 1D nanowires and fibres, 2D films and coated surfaces, and 3D patterned surfaces such as pillars. The training set was used to retrain on the SEM dataset and to compare many convolutional neural network models (Inception-v3, Inception-v4, ResNet). We obtained compatible results by performing a feature extraction of the different models on the same dataset. We performed additional analysis of the classifier on a second test set to further investigate the results both on particular cases and from a statistical point of view. Our algorithm was able to successfully classify around 90% of a test dataset consisting of SEM images, while reduced accuracy was found in the case of images at the boundary between two categories or containing elements of multiple categories. In these cases, the image classification did not identify a predominant category with a high score. We used the statistical outcomes from testing to deploy a semi-automatic workflow able to classify and label images generated by the SEM. Finally, a separate training was performed to determine the volume fraction of coherently aligned nanowires in SEM images. The results were compared with what was obtained using the Local Gradient Orientation method. This example demonstrates the versatility and the potential of transfer learning to address specific tasks of interest in nanoscience applications.

Mediastinal lymph node detection and station mapping on chest CT using spatial priors and random forest

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

Liu, Jiamin; Hoffman, Joanne; Zhao, Jocelyn

2016-07-15

Purpose: To develop an automated system for mediastinal lymph node detection and station mapping for chest CT. Methods: The contextual organs, trachea, lungs, and spine are first automatically identified to locate the region of interest (ROI) (mediastinum). The authors employ shape features derived from Hessian analysis, local object scale, and circular transformation that are computed per voxel in the ROI. Eight more anatomical structures are simultaneously segmented by multiatlas label fusion. Spatial priors are defined as the relative multidimensional distance vectors corresponding to each structure. Intensity, shape, and spatial prior features are integrated and parsed by a random forest classifiermore » for lymph node detection. The detected candidates are then segmented by the following curve evolution process. Texture features are computed on the segmented lymph nodes and a support vector machine committee is used for final classification. For lymph node station labeling, based on the segmentation results of the above anatomical structures, the textual definitions of mediastinal lymph node map according to the International Association for the Study of Lung Cancer are converted into patient-specific color-coded CT image, where the lymph node station can be automatically assigned for each detected node. Results: The chest CT volumes from 70 patients with 316 enlarged mediastinal lymph nodes are used for validation. For lymph node detection, their system achieves 88% sensitivity at eight false positives per patient. For lymph node station labeling, 84.5% of lymph nodes are correctly assigned to their stations. Conclusions: Multiple-channel shape, intensity, and spatial prior features aggregated by a random forest classifier improve mediastinal lymph node detection on chest CT. Using the location information of segmented anatomic structures from the multiatlas formulation enables accurate identification of lymph node stations.« less

Non-imaged based method for matching brains in a common anatomical space for cellular imagery.

PubMed

Midroit, Maëllie; Thevenet, Marc; Fournel, Arnaud; Sacquet, Joelle; Bensafi, Moustafa; Breton, Marine; Chalençon, Laura; Cavelius, Matthias; Didier, Anne; Mandairon, Nathalie

2018-04-22

Cellular imagery using histology sections is one of the most common techniques used in Neuroscience. However, this inescapable technique has severe limitations due to the need to delineate regions of interest on each brain, which is time consuming and variable across experimenters. We developed algorithms based on a vectors field elastic registration allowing fast, automatic realignment of experimental brain sections and associated labeling in a brain atlas with high accuracy and in a streamlined way. Thereby, brain areas of interest can be finely identified without outlining them and different experimental groups can be easily analyzed using conventional tools. This method directly readjusts labeling in the brain atlas without any intermediate manipulation of images. We mapped the expression of cFos, in the mouse brain (C57Bl/6J) after olfactory stimulation or a non-stimulated control condition and found an increased density of cFos-positive cells in the primary olfactory cortex but not in non-olfactory areas of the odor-stimulated animals compared to the controls. Existing methods of matching are based on image registration which often requires expensive material (two-photon tomography mapping or imaging with iDISCO) or are less accurate since they are based on mutual information contained in the images. Our new method is non-imaged based and relies only on the positions of detected labeling and the external contours of sections. We thus provide a new method that permits automated matching of histology sections of experimental brains with a brain reference atlas. Copyright © 2018 Elsevier B.V. All rights reserved.

User Guide for the Anvil Threat Cooridor Forecast Tool V2.4 for AWIPS

NASA Technical Reports Server (NTRS)

Barett, Joe H., III; Bauman, William H., III

2008-01-01

The Anvil Tool GUI allows users to select a Data Type, toggle the map refresh on/off, place labels, and choose the Profiler Type (source of the KSC 50 MHz profiler data), the Date- Time of the data, the Center of Plot, and the Station (location of the RAOB or 50 MHz profiler). If the Data Type is Models, the user selects a Fcst Hour (forecast hour) instead of Station. There are menus for User Profiles, Circle Label Options, and Frame Label Options. Labels can be placed near the center circle of the plot and/or at a specified distance and direction from the center of the circle (Center of Plot). The default selection for the map refresh is "ON". When the user creates a new Anvil Tool map with Refresh Map "ON, the plot is automatically displayed in the AWIPS frame. If another Anvil Tool map is already displayed and the user does not change the existing map number shown at the bottom of the GUI, the new Anvil Tool map will overwrite the old one. If the user turns the Refresh Map "OFF", the new Anvil Tool map is created but not automatically displayed. The user can still display the Anvil Tool map through the Maps dropdown menu* as shown in Figure 4.

Exploring the nature of facial affect processing deficits in schizophrenia.

PubMed

van 't Wout, Mascha; Aleman, André; Kessels, Roy P C; Cahn, Wiepke; de Haan, Edward H F; Kahn, René S

2007-04-15

Schizophrenia has been associated with deficits in facial affect processing, especially negative emotions. However, the exact nature of the deficit remains unclear. The aim of the present study was to investigate whether schizophrenia patients have problems in automatic allocation of attention as well as in controlled evaluation of facial affect. Thirty-seven patients with schizophrenia were compared with 41 control subjects on incidental facial affect processing (gender decision of faces with a fearful, angry, happy, disgusted, and neutral expression) and degraded facial affect labeling (labeling of fearful, angry, happy, and neutral faces). The groups were matched on estimates of verbal and performance intelligence (National Adult Reading Test; Raven's Matrices), general face recognition ability (Benton Face Recognition), and other demographic variables. The results showed that patients with schizophrenia as well as control subjects demonstrate the normal threat-related interference during incidental facial affect processing. Conversely, on controlled evaluation patients were specifically worse in the labeling of fearful faces. In particular, patients with high levels of negative symptoms may be characterized by deficits in labeling fear. We suggest that patients with schizophrenia show no evidence of deficits in the automatic allocation of attention resources to fearful (threat-indicating) faces, but have a deficit in the controlled processing of facial emotions that may be specific for fearful faces.

An Example-Based Multi-Atlas Approach to Automatic Labeling of White Matter Tracts

PubMed Central

Yoo, Sang Wook; Guevara, Pamela; Jeong, Yong; Yoo, Kwangsun; Shin, Joseph S.; Mangin, Jean-Francois; Seong, Joon-Kyung

2015-01-01

We present an example-based multi-atlas approach for classifying white matter (WM) tracts into anatomic bundles. Our approach exploits expert-provided example data to automatically classify the WM tracts of a subject. Multiple atlases are constructed to model the example data from multiple subjects in order to reflect the individual variability of bundle shapes and trajectories over subjects. For each example subject, an atlas is maintained to allow the example data of a subject to be added or deleted flexibly. A voting scheme is proposed to facilitate the multi-atlas exploitation of example data. For conceptual simplicity, we adopt the same metrics in both example data construction and WM tract labeling. Due to the huge number of WM tracts in a subject, it is time-consuming to label each WM tract individually. Thus, the WM tracts are grouped according to their shape similarity, and WM tracts within each group are labeled simultaneously. To further enhance the computational efficiency, we implemented our approach on the graphics processing unit (GPU). Through nested cross-validation we demonstrated that our approach yielded high classification performance. The average sensitivities for bundles in the left and right hemispheres were 89.5% and 91.0%, respectively, and their average false discovery rates were 14.9% and 14.2%, respectively. PMID:26225419

An Example-Based Multi-Atlas Approach to Automatic Labeling of White Matter Tracts.

PubMed

Yoo, Sang Wook; Guevara, Pamela; Jeong, Yong; Yoo, Kwangsun; Shin, Joseph S; Mangin, Jean-Francois; Seong, Joon-Kyung

2015-01-01

We present an example-based multi-atlas approach for classifying white matter (WM) tracts into anatomic bundles. Our approach exploits expert-provided example data to automatically classify the WM tracts of a subject. Multiple atlases are constructed to model the example data from multiple subjects in order to reflect the individual variability of bundle shapes and trajectories over subjects. For each example subject, an atlas is maintained to allow the example data of a subject to be added or deleted flexibly. A voting scheme is proposed to facilitate the multi-atlas exploitation of example data. For conceptual simplicity, we adopt the same metrics in both example data construction and WM tract labeling. Due to the huge number of WM tracts in a subject, it is time-consuming to label each WM tract individually. Thus, the WM tracts are grouped according to their shape similarity, and WM tracts within each group are labeled simultaneously. To further enhance the computational efficiency, we implemented our approach on the graphics processing unit (GPU). Through nested cross-validation we demonstrated that our approach yielded high classification performance. The average sensitivities for bundles in the left and right hemispheres were 89.5% and 91.0%, respectively, and their average false discovery rates were 14.9% and 14.2%, respectively.

Automatic, sterile, and apyrogenic delivery of PET radiotracers from the cyclotron to the patient

NASA Astrophysics Data System (ADS)

Votaw, J. R.; Cashion, D. B.; Clanton, J. A.

1991-05-01

An automatic delivery remote injection system has been developed to administer either 13N-labelled ammonia, or 15O-labelled water or 18F-labelled FDG to patients. Automation increases the throughout and efficiency of the PET center, and remote dose administration ensures patient safety and reduces the radiation exposure to the technologist supervising the radiopharmaceutical injection. The remote dose administration apparatus utilizes a syringe pump to transfer liquid activity and a solenoid three-way valve to switch between lines connected to a patient and a receiving vial. To ensure apyrogenicity and sterility of the injected product, the entire system is washed with sterile water before it is used. Since the tracer is delivered in an ~ 8 ml bolus of water, the next delivery through the system is considered safe for injection if pyrogens are not detected at a threshold of 3 endotoxin units per ml (EU/ml) in the wash. Time delayed tests shows that the system may be left unused for up to 6 h before the wash must be repeated.

A Fast Method for the Segmentation of Synaptic Junctions and Mitochondria in Serial Electron Microscopic Images of the Brain.

PubMed

Márquez Neila, Pablo; Baumela, Luis; González-Soriano, Juncal; Rodríguez, Jose-Rodrigo; DeFelipe, Javier; Merchán-Pérez, Ángel

2016-04-01

Recent electron microscopy (EM) imaging techniques permit the automatic acquisition of a large number of serial sections from brain samples. Manual segmentation of these images is tedious, time-consuming and requires a high degree of user expertise. Therefore, there is considerable interest in developing automatic segmentation methods. However, currently available methods are computationally demanding in terms of computer time and memory usage, and to work properly many of them require image stacks to be isotropic, that is, voxels must have the same size in the X, Y and Z axes. We present a method that works with anisotropic voxels and that is computationally efficient allowing the segmentation of large image stacks. Our approach involves anisotropy-aware regularization via conditional random field inference and surface smoothing techniques to improve the segmentation and visualization. We have focused on the segmentation of mitochondria and synaptic junctions in EM stacks from the cerebral cortex, and have compared the results to those obtained by other methods. Our method is faster than other methods with similar segmentation results. Our image regularization procedure introduces high-level knowledge about the structure of labels. We have also reduced memory requirements with the introduction of energy optimization in overlapping partitions, which permits the regularization of very large image stacks. Finally, the surface smoothing step improves the appearance of three-dimensional renderings of the segmented volumes.

iElectrodes: A Comprehensive Open-Source Toolbox for Depth and Subdural Grid Electrode Localization.

PubMed

Blenkmann, Alejandro O; Phillips, Holly N; Princich, Juan P; Rowe, James B; Bekinschtein, Tristan A; Muravchik, Carlos H; Kochen, Silvia

2017-01-01

The localization of intracranial electrodes is a fundamental step in the analysis of invasive electroencephalography (EEG) recordings in research and clinical practice. The conclusions reached from the analysis of these recordings rely on the accuracy of electrode localization in relationship to brain anatomy. However, currently available techniques for localizing electrodes from magnetic resonance (MR) and/or computerized tomography (CT) images are time consuming and/or limited to particular electrode types or shapes. Here we present iElectrodes, an open-source toolbox that provides robust and accurate semi-automatic localization of both subdural grids and depth electrodes. Using pre- and post-implantation images, the method takes 2-3 min to localize the coordinates in each electrode array and automatically number the electrodes. The proposed pre-processing pipeline allows one to work in a normalized space and to automatically obtain anatomical labels of the localized electrodes without neuroimaging experts. We validated the method with data from 22 patients implanted with a total of 1,242 electrodes. We show that localization distances were within 0.56 mm of those achieved by experienced manual evaluators. iElectrodes provided additional advantages in terms of robustness (even with severe perioperative cerebral distortions), speed (less than half the operator time compared to expert manual localization), simplicity, utility across multiple electrode types (surface and depth electrodes) and all brain regions.

iElectrodes: A Comprehensive Open-Source Toolbox for Depth and Subdural Grid Electrode Localization

PubMed Central

Blenkmann, Alejandro O.; Phillips, Holly N.; Princich, Juan P.; Rowe, James B.; Bekinschtein, Tristan A.; Muravchik, Carlos H.; Kochen, Silvia

2017-01-01

The localization of intracranial electrodes is a fundamental step in the analysis of invasive electroencephalography (EEG) recordings in research and clinical practice. The conclusions reached from the analysis of these recordings rely on the accuracy of electrode localization in relationship to brain anatomy. However, currently available techniques for localizing electrodes from magnetic resonance (MR) and/or computerized tomography (CT) images are time consuming and/or limited to particular electrode types or shapes. Here we present iElectrodes, an open-source toolbox that provides robust and accurate semi-automatic localization of both subdural grids and depth electrodes. Using pre- and post-implantation images, the method takes 2–3 min to localize the coordinates in each electrode array and automatically number the electrodes. The proposed pre-processing pipeline allows one to work in a normalized space and to automatically obtain anatomical labels of the localized electrodes without neuroimaging experts. We validated the method with data from 22 patients implanted with a total of 1,242 electrodes. We show that localization distances were within 0.56 mm of those achieved by experienced manual evaluators. iElectrodes provided additional advantages in terms of robustness (even with severe perioperative cerebral distortions), speed (less than half the operator time compared to expert manual localization), simplicity, utility across multiple electrode types (surface and depth electrodes) and all brain regions. PMID:28303098

Find Pairs: The Module for Protein Quantification of the PeakQuant Software Suite

PubMed Central

Eisenacher, Martin; Kohl, Michael; Wiese, Sebastian; Hebeler, Romano; Meyer, Helmut E.

2012-01-01

Abstract Accurate quantification of proteins is one of the major tasks in current proteomics research. To address this issue, a wide range of stable isotope labeling techniques have been developed, allowing one to quantitatively study thousands of proteins by means of mass spectrometry. In this article, the FindPairs module of the PeakQuant software suite is detailed. It facilitates the automatic determination of protein abundance ratios based on the automated analysis of stable isotope-coded mass spectrometric data. Furthermore, it implements statistical methods to determine outliers due to biological as well as technical variance of proteome data obtained in replicate experiments. This provides an important means to evaluate the significance in obtained protein expression data. For demonstrating the high applicability of FindPairs, we focused on the quantitative analysis of proteome data acquired in 14N/15N labeling experiments. We further provide a comprehensive overview of the features of the FindPairs software, and compare these with existing quantification packages. The software presented here supports a wide range of proteomics applications, allowing one to quantitatively assess data derived from different stable isotope labeling approaches, such as 14N/15N labeling, SILAC, and iTRAQ. The software is publicly available at http://www.medizinisches-proteom-center.de/software and free for academic use. PMID:22909347

3D variational brain tumor segmentation using Dirichlet priors on a clustered feature set.

PubMed

Popuri, Karteek; Cobzas, Dana; Murtha, Albert; Jägersand, Martin

2012-07-01

Brain tumor segmentation is a required step before any radiation treatment or surgery. When performed manually, segmentation is time consuming and prone to human errors. Therefore, there have been significant efforts to automate the process. But, automatic tumor segmentation from MRI data is a particularly challenging task. Tumors have a large diversity in shape and appearance with intensities overlapping the normal brain tissues. In addition, an expanding tumor can also deflect and deform nearby tissue. In our work, we propose an automatic brain tumor segmentation method that addresses these last two difficult problems. We use the available MRI modalities (T1, T1c, T2) and their texture characteristics to construct a multidimensional feature set. Then, we extract clusters which provide a compact representation of the essential information in these features. The main idea in this work is to incorporate these clustered features into the 3D variational segmentation framework. In contrast to previous variational approaches, we propose a segmentation method that evolves the contour in a supervised fashion. The segmentation boundary is driven by the learned region statistics in the cluster space. We incorporate prior knowledge about the normal brain tissue appearance during the estimation of these region statistics. In particular, we use a Dirichlet prior that discourages the clusters from the normal brain region to be in the tumor region. This leads to a better disambiguation of the tumor from brain tissue. We evaluated the performance of our automatic segmentation method on 15 real MRI scans of brain tumor patients, with tumors that are inhomogeneous in appearance, small in size and in proximity to the major structures in the brain. Validation with the expert segmentation labels yielded encouraging results: Jaccard (58%), Precision (81%), Recall (67%), Hausdorff distance (24 mm). Using priors on the brain/tumor appearance, our proposed automatic 3D variational segmentation method was able to better disambiguate the tumor from the surrounding tissue.

Achieving Accurate Automatic Sleep Staging on Manually Pre-processed EEG Data Through Synchronization Feature Extraction and Graph Metrics.

PubMed

Chriskos, Panteleimon; Frantzidis, Christos A; Gkivogkli, Polyxeni T; Bamidis, Panagiotis D; Kourtidou-Papadeli, Chrysoula

2018-01-01

Sleep staging, the process of assigning labels to epochs of sleep, depending on the stage of sleep they belong, is an arduous, time consuming and error prone process as the initial recordings are quite often polluted by noise from different sources. To properly analyze such data and extract clinical knowledge, noise components must be removed or alleviated. In this paper a pre-processing and subsequent sleep staging pipeline for the sleep analysis of electroencephalographic signals is described. Two novel methods of functional connectivity estimation (Synchronization Likelihood/SL and Relative Wavelet Entropy/RWE) are comparatively investigated for automatic sleep staging through manually pre-processed electroencephalographic recordings. A multi-step process that renders signals suitable for further analysis is initially described. Then, two methods that rely on extracting synchronization features from electroencephalographic recordings to achieve computerized sleep staging are proposed, based on bivariate features which provide a functional overview of the brain network, contrary to most proposed methods that rely on extracting univariate time and frequency features. Annotation of sleep epochs is achieved through the presented feature extraction methods by training classifiers, which are in turn able to accurately classify new epochs. Analysis of data from sleep experiments on a randomized, controlled bed-rest study, which was organized by the European Space Agency and was conducted in the "ENVIHAB" facility of the Institute of Aerospace Medicine at the German Aerospace Center (DLR) in Cologne, Germany attains high accuracy rates, over 90% based on ground truth that resulted from manual sleep staging by two experienced sleep experts. Therefore, it can be concluded that the above feature extraction methods are suitable for semi-automatic sleep staging.

Achieving Accurate Automatic Sleep Staging on Manually Pre-processed EEG Data Through Synchronization Feature Extraction and Graph Metrics

PubMed Central

Chriskos, Panteleimon; Frantzidis, Christos A.; Gkivogkli, Polyxeni T.; Bamidis, Panagiotis D.; Kourtidou-Papadeli, Chrysoula

2018-01-01

Sleep staging, the process of assigning labels to epochs of sleep, depending on the stage of sleep they belong, is an arduous, time consuming and error prone process as the initial recordings are quite often polluted by noise from different sources. To properly analyze such data and extract clinical knowledge, noise components must be removed or alleviated. In this paper a pre-processing and subsequent sleep staging pipeline for the sleep analysis of electroencephalographic signals is described. Two novel methods of functional connectivity estimation (Synchronization Likelihood/SL and Relative Wavelet Entropy/RWE) are comparatively investigated for automatic sleep staging through manually pre-processed electroencephalographic recordings. A multi-step process that renders signals suitable for further analysis is initially described. Then, two methods that rely on extracting synchronization features from electroencephalographic recordings to achieve computerized sleep staging are proposed, based on bivariate features which provide a functional overview of the brain network, contrary to most proposed methods that rely on extracting univariate time and frequency features. Annotation of sleep epochs is achieved through the presented feature extraction methods by training classifiers, which are in turn able to accurately classify new epochs. Analysis of data from sleep experiments on a randomized, controlled bed-rest study, which was organized by the European Space Agency and was conducted in the “ENVIHAB” facility of the Institute of Aerospace Medicine at the German Aerospace Center (DLR) in Cologne, Germany attains high accuracy rates, over 90% based on ground truth that resulted from manual sleep staging by two experienced sleep experts. Therefore, it can be concluded that the above feature extraction methods are suitable for semi-automatic sleep staging. PMID:29628883

Automatic detection and quantitative analysis of cells in the mouse primary motor cortex

NASA Astrophysics Data System (ADS)

Meng, Yunlong; He, Yong; Wu, Jingpeng; Chen, Shangbin; Li, Anan; Gong, Hui

2014-09-01

Neuronal cells play very important role on metabolism regulation and mechanism control, so cell number is a fundamental determinant of brain function. Combined suitable cell-labeling approaches with recently proposed three-dimensional optical imaging techniques, whole mouse brain coronal sections can be acquired with 1-μm voxel resolution. We have developed a completely automatic pipeline to perform cell centroids detection, and provided three-dimensional quantitative information of cells in the primary motor cortex of C57BL/6 mouse. It involves four principal steps: i) preprocessing; ii) image binarization; iii) cell centroids extraction and contour segmentation; iv) laminar density estimation. Investigations on the presented method reveal promising detection accuracy in terms of recall and precision, with average recall rate 92.1% and average precision rate 86.2%. We also analyze laminar density distribution of cells from pial surface to corpus callosum from the output vectorizations of detected cell centroids in mouse primary motor cortex, and find significant cellular density distribution variations in different layers. This automatic cell centroids detection approach will be beneficial for fast cell-counting and accurate density estimation, as time-consuming and error-prone manual identification is avoided.

An Automated Self-Learning Quantification System to Identify Visible Areas in Capsule Endoscopy Images.

PubMed

Hashimoto, Shinichi; Ogihara, Hiroyuki; Suenaga, Masato; Fujita, Yusuke; Terai, Shuji; Hamamoto, Yoshihiko; Sakaida, Isao

2017-08-01

Visibility in capsule endoscopic images is presently evaluated through intermittent analysis of frames selected by a physician. It is thus subjective and not quantitative. A method to automatically quantify the visibility on capsule endoscopic images has not been reported. Generally, when designing automated image recognition programs, physicians must provide a training image; this process is called supervised learning. We aimed to develop a novel automated self-learning quantification system to identify visible areas on capsule endoscopic images. The technique was developed using 200 capsule endoscopic images retrospectively selected from each of three patients. The rate of detection of visible areas on capsule endoscopic images between a supervised learning program, using training images labeled by a physician, and our novel automated self-learning program, using unlabeled training images without intervention by a physician, was compared. The rate of detection of visible areas was equivalent for the supervised learning program and for our automatic self-learning program. The visible areas automatically identified by self-learning program correlated to the areas identified by an experienced physician. We developed a novel self-learning automated program to identify visible areas in capsule endoscopic images.

Global disulfide bond profiling for crude snake venom using dimethyl labeling coupled with mass spectrometry and RADAR algorithm.

PubMed

Huang, Sheng Yu; Chen, Sung Fang; Chen, Chun Hao; Huang, Hsuan Wei; Wu, Wen Guey; Sung, Wang Chou

2014-09-02

Snake venom consists of toxin proteins with multiple disulfide linkages to generate unique structures and biological functions. Determination of these cysteine connections usually requires the purification of each protein followed by structural analysis. In this study, dimethyl labeling coupled with LC-MS/MS and RADAR algorithm was developed to identify the disulfide bonds in crude snake venom. Without any protein separation, the disulfide linkages of several cytotoxins and PLA2 could be solved, including more than 20 disulfide bonds. The results show that this method is capable of analyzing protein mixture. In addition, the approach was also used to compare native cytotoxin 3 (CTX III) and its scrambled isomer, another category of protein mixture, for unknown disulfide bonds. Two disulfide-linked peptides were observed in the native CTX III, and 10 in its scrambled form, X-CTX III. This is the first study that reports a platform for the global cysteine connection analysis on a protein mixture. The proposed method is simple and automatic, offering an efficient tool for structural and functional studies of venom proteins.

Beyond Retinal Layers: A Deep Voting Model for Automated Geographic Atrophy Segmentation in SD-OCT Images.

PubMed

Ji, Zexuan; Chen, Qiang; Niu, Sijie; Leng, Theodore; Rubin, Daniel L

2018-01-01

To automatically and accurately segment geographic atrophy (GA) in spectral-domain optical coherence tomography (SD-OCT) images by constructing a voting system with deep neural networks without the use of retinal layer segmentation. An automatic GA segmentation method for SD-OCT images based on the deep network was constructed. The structure of the deep network was composed of five layers, including one input layer, three hidden layers, and one output layer. During the training phase, the labeled A-scans with 1024 features were directly fed into the network as the input layer to obtain the deep representations. Then a soft-max classifier was trained to determine the label of each individual pixel. Finally, a voting decision strategy was used to refine the segmentation results among 10 trained models. Two image data sets with GA were used to evaluate the model. For the first dataset, our algorithm obtained a mean overlap ratio (OR) 86.94% ± 8.75%, absolute area difference (AAD) 11.49% ± 11.50%, and correlation coefficients (CC) 0.9857; for the second dataset, the mean OR, AAD, and CC of the proposed method were 81.66% ± 10.93%, 8.30% ± 9.09%, and 0.9952, respectively. The proposed algorithm was capable of improving over 5% and 10% segmentation accuracy, respectively, when compared with several state-of-the-art algorithms on two data sets. Without retinal layer segmentation, the proposed algorithm could produce higher segmentation accuracy and was more stable when compared with state-of-the-art methods that relied on retinal layer segmentation results. Our model may provide reliable GA segmentations from SD-OCT images and be useful in the clinical diagnosis of advanced nonexudative AMD. Based on the deep neural networks, this study presents an accurate GA segmentation method for SD-OCT images without using any retinal layer segmentation results, and may contribute to improved understanding of advanced nonexudative AMD.

TH-CD-206-02: BEST IN PHYSICS (IMAGING): 3D Prostate Segmentation in MR Images Using Patch-Based Anatomical Signature

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

Yang, X; Jani, A; Rossi, P

Purpose: MRI has shown promise in identifying prostate tumors with high sensitivity and specificity for the detection of prostate cancer. Accurate segmentation of the prostate plays a key role various tasks: to accurately localize prostate boundaries for biopsy needle placement and radiotherapy, to initialize multi-modal registration algorithms or to obtain the region of interest for computer-aided detection of prostate cancer. However, manual segmentation during biopsy or radiation therapy can be time consuming and subject to inter- and intra-observer variation. This study’s purpose it to develop an automated method to address this technical challenge. Methods: We present an automated multi-atlas segmentationmore » for MR prostate segmentation using patch-based label fusion. After an initial preprocessing for all images, all the atlases are non-rigidly registered to a target image. And then, the resulting transformation is used to propagate the anatomical structure labels of the atlas into the space of the target image. The top L similar atlases are further chosen by measuring intensity and structure difference in the region of interest around prostate. Finally, using voxel weighting based on patch-based anatomical signature, the label that the majority of all warped labels predict for each voxel is used for the final segmentation of the target image. Results: This segmentation technique was validated with a clinical study of 13 patients. The accuracy of our approach was assessed using the manual segmentation (gold standard). The mean volume Dice Overlap Coefficient was 89.5±2.9% between our and manual segmentation, which indicate that the automatic segmentation method works well and could be used for 3D MRI-guided prostate intervention. Conclusion: We have developed a new prostate segmentation approach based on the optimal feature learning label fusion framework, demonstrated its clinical feasibility, and validated its accuracy. This segmentation technique could be a useful tool in image-guided interventions for prostate-cancer diagnosis and treatment.« less

Fully automatic detection and visualization of patient specific coronary supply regions

NASA Astrophysics Data System (ADS)

Fritz, Dominik; Wiedemann, Alexander; Dillmann, Ruediger; Scheuering, Michael

2008-03-01

Coronary territory maps, which associate myocardial regions with the corresponding coronary artery that supply them, are a common visualization technique to assist the physician in the diagnosis of coronary artery disease. However, the commonly used visualization is based on the AHA-17-segment model, which is an empirical population based model. Therefore, it does not necessarily cope with the often highly individual coronary anatomy of a specific patient. In this paper we introduce a novel fully automatic approach to compute the patient individual coronary supply regions in CTA datasets. This approach is divided in three consecutive steps. First, the aorta is fully automatically located in the dataset with a combination of a Hough transform and a cylindrical model matching approach. Having the location of the aorta, a segmentation and skeletonization of the coronary tree is triggered. In the next step, the three main branches (LAD, LCX and RCX) are automatically labeled, based on the knowledge of the pose of the aorta and the left ventricle. In the last step the labeled coronary tree is projected on the left ventricular surface, which can afterward be subdivided into the coronary supply regions, based on a Voronoi transform. The resulting supply regions can be either shown in 3D on the epicardiac surface of the left ventricle, or as a subdivision of a polarmap.

Segmentation of MR images via discriminative dictionary learning and sparse coding: application to hippocampus labeling.

PubMed

Tong, Tong; Wolz, Robin; Coupé, Pierrick; Hajnal, Joseph V; Rueckert, Daniel

2013-08-01

We propose a novel method for the automatic segmentation of brain MRI images by using discriminative dictionary learning and sparse coding techniques. In the proposed method, dictionaries and classifiers are learned simultaneously from a set of brain atlases, which can then be used for the reconstruction and segmentation of an unseen target image. The proposed segmentation strategy is based on image reconstruction, which is in contrast to most existing atlas-based labeling approaches that rely on comparing image similarities between atlases and target images. In addition, we propose a Fixed Discriminative Dictionary Learning for Segmentation (F-DDLS) strategy, which can learn dictionaries offline and perform segmentations online, enabling a significant speed-up in the segmentation stage. The proposed method has been evaluated for the hippocampus segmentation of 80 healthy ICBM subjects and 202 ADNI images. The robustness of the proposed method, especially of our F-DDLS strategy, was validated by training and testing on different subject groups in the ADNI database. The influence of different parameters was studied and the performance of the proposed method was also compared with that of the nonlocal patch-based approach. The proposed method achieved a median Dice coefficient of 0.879 on 202 ADNI images and 0.890 on 80 ICBM subjects, which is competitive compared with state-of-the-art methods. Copyright © 2013 Elsevier Inc. All rights reserved.

Exploiting Attribute Correlations: A Novel Trace Lasso-Based Weakly Supervised Dictionary Learning Method.

PubMed

Wu, Lin; Wang, Yang; Pan, Shirui

2017-12-01

It is now well established that sparse representation models are working effectively for many visual recognition tasks, and have pushed forward the success of dictionary learning therein. Recent studies over dictionary learning focus on learning discriminative atoms instead of purely reconstructive ones. However, the existence of intraclass diversities (i.e., data objects within the same category but exhibit large visual dissimilarities), and interclass similarities (i.e., data objects from distinct classes but share much visual similarities), makes it challenging to learn effective recognition models. To this end, a large number of labeled data objects are required to learn models which can effectively characterize these subtle differences. However, labeled data objects are always limited to access, committing it difficult to learn a monolithic dictionary that can be discriminative enough. To address the above limitations, in this paper, we propose a weakly-supervised dictionary learning method to automatically learn a discriminative dictionary by fully exploiting visual attribute correlations rather than label priors. In particular, the intrinsic attribute correlations are deployed as a critical cue to guide the process of object categorization, and then a set of subdictionaries are jointly learned with respect to each category. The resulting dictionary is highly discriminative and leads to intraclass diversity aware sparse representations. Extensive experiments on image classification and object recognition are conducted to show the effectiveness of our approach.

Non-rigid registration of 3D ultrasound for neurosurgery using automatic feature detection and matching.

PubMed

Machado, Inês; Toews, Matthew; Luo, Jie; Unadkat, Prashin; Essayed, Walid; George, Elizabeth; Teodoro, Pedro; Carvalho, Herculano; Martins, Jorge; Golland, Polina; Pieper, Steve; Frisken, Sarah; Golby, Alexandra; Wells, William

2018-06-04

The brain undergoes significant structural change over the course of neurosurgery, including highly nonlinear deformation and resection. It can be informative to recover the spatial mapping between structures identified in preoperative surgical planning and the intraoperative state of the brain. We present a novel feature-based method for achieving robust, fully automatic deformable registration of intraoperative neurosurgical ultrasound images. A sparse set of local image feature correspondences is first estimated between ultrasound image pairs, after which rigid, affine and thin-plate spline models are used to estimate dense mappings throughout the image. Correspondences are derived from 3D features, distinctive generic image patterns that are automatically extracted from 3D ultrasound images and characterized in terms of their geometry (i.e., location, scale, and orientation) and a descriptor of local image appearance. Feature correspondences between ultrasound images are achieved based on a nearest-neighbor descriptor matching and probabilistic voting model similar to the Hough transform. Experiments demonstrate our method on intraoperative ultrasound images acquired before and after opening of the dura mater, during resection and after resection in nine clinical cases. A total of 1620 automatically extracted 3D feature correspondences were manually validated by eleven experts and used to guide the registration. Then, using manually labeled corresponding landmarks in the pre- and post-resection ultrasound images, we show that our feature-based registration reduces the mean target registration error from an initial value of 3.3 to 1.5 mm. This result demonstrates that the 3D features promise to offer a robust and accurate solution for 3D ultrasound registration and to correct for brain shift in image-guided neurosurgery.

Automatic determination of the artery vein ratio in retinal images

NASA Astrophysics Data System (ADS)

Niemeijer, Meindert; van Ginneken, Bram; Abràmoff, Michael D.

2010-03-01

A lower ratio between the width of the arteries and veins (Arteriolar-to-Venular diameter Ratio, AVR) on the retina, is well established to be predictive of stroke and other cardiovascular events in adults, as well as an increased risk of retinopathy of prematurity in premature infants. This work presents an automatic method that detects the location of the optic disc, determines the appropriate region of interest (ROI), classifies the vessels in the ROI into arteries and veins, measures their widths and calculates the AVR. After vessel segmentation and vessel width determination the optic disc is located and the system eliminates all vessels outside the AVR measurement ROI. The remaining vessels are thinned, vessel crossing and bifurcation points are removed leaving a set of vessel segments containing centerline pixels. Features are extracted from each centerline pixel that are used to assign them a soft label indicating the likelihood the pixel is part of a vein. As all centerline pixels in a connected segment should be the same type, the median soft label is assigned to each centerline pixel in the segment. Next artery vein pairs are matched using an iterative algorithm and the widths of the vessels is used to calculate the AVR. We train and test the algorithm using a set of 25 high resolution digital color fundus photographs a reference standard that indicates for the major vessels in the images whether they are an artery or a vein. We compared the AVR values produced by our system with those determined using a computer assisted method in 15 high resolution digital color fundus photographs and obtained a correlation coefficient of 0.881.

Objective automated quantification of fluorescence signal in histological sections of rat lens.

PubMed

Talebizadeh, Nooshin; Hagström, Nanna Zhou; Yu, Zhaohua; Kronschläger, Martin; Söderberg, Per; Wählby, Carolina

2017-08-01

Visual quantification and classification of fluorescent signals is the gold standard in microscopy. The purpose of this study was to develop an automated method to delineate cells and to quantify expression of fluorescent signal of biomarkers in each nucleus and cytoplasm of lens epithelial cells in a histological section. A region of interest representing the lens epithelium was manually demarcated in each input image. Thereafter, individual cell nuclei within the region of interest were automatically delineated based on watershed segmentation and thresholding with an algorithm developed in Matlab™. Fluorescence signal was quantified within nuclei, cytoplasms and juxtaposed backgrounds. The classification of cells as labelled or not labelled was based on comparison of the fluorescence signal within cells with local background. The classification rule was thereafter optimized as compared with visual classification of a limited dataset. The performance of the automated classification was evaluated by asking 11 independent blinded observers to classify all cells (n = 395) in one lens image. Time consumed by the automatic algorithm and visual classification of cells was recorded. On an average, 77% of the cells were correctly classified as compared with the majority vote of the visual observers. The average agreement among visual observers was 83%. However, variation among visual observers was high, and agreement between two visual observers was as low as 71% in the worst case. Automated classification was on average 10 times faster than visual scoring. The presented method enables objective and fast detection of lens epithelial cells and quantification of expression of fluorescent signal with an accuracy comparable with the variability among visual observers. © 2017 International Society for Advancement of Cytometry. © 2017 International Society for Advancement of Cytometry.

Predicting human activities in sequences of actions in RGB-D videos

NASA Astrophysics Data System (ADS)

Jardim, David; Nunes, Luís.; Dias, Miguel

2017-03-01

In our daily activities we perform prediction or anticipation when interacting with other humans or with objects. Prediction of human activity made by computers has several potential applications: surveillance systems, human computer interfaces, sports video analysis, human-robot-collaboration, games and health-care. We propose a system capable of recognizing and predicting human actions using supervised classifiers trained with automatically labeled data evaluated in our human activity RGB-D dataset (recorded with a Kinect sensor) and using only the position of the main skeleton joints to extract features. Using conditional random fields (CRFs) to model the sequential nature of actions in a sequence has been used before, but where other approaches try to predict an outcome or anticipate ahead in time (seconds), we try to predict what will be the next action of a subject. Our results show an activity prediction accuracy of 89.9% using an automatically labeled dataset.

Science information systems: Archive, access, and retrieval

NASA Technical Reports Server (NTRS)

Campbell, William J.

1991-01-01

The objective of this research is to develop technology for the automated characterization and interactive retrieval and visualization of very large, complex scientific data sets. Technologies will be developed for the following specific areas: (1) rapidly archiving data sets; (2) automatically characterizing and labeling data in near real-time; (3) providing users with the ability to browse contents of databases efficiently and effectively; (4) providing users with the ability to access and retrieve system independent data sets electronically; and (5) automatically alerting scientists to anomalies detected in data.

Efficient organ localization using multi-label convolutional neural networks in thorax-abdomen CT scans

NASA Astrophysics Data System (ADS)

Efrain Humpire-Mamani, Gabriel; Arindra Adiyoso Setio, Arnaud; van Ginneken, Bram; Jacobs, Colin

2018-04-01

Automatic localization of organs and other structures in medical images is an important preprocessing step that can improve and speed up other algorithms such as organ segmentation, lesion detection, and registration. This work presents an efficient method for simultaneous localization of multiple structures in 3D thorax-abdomen CT scans. Our approach predicts the location of multiple structures using a single multi-label convolutional neural network for each orthogonal view. Each network takes extra slices around the current slice as input to provide extra context. A sigmoid layer is used to perform multi-label classification. The output of the three networks is subsequently combined to compute a 3D bounding box for each structure. We used our approach to locate 11 structures of interest. The neural network was trained and evaluated on a large set of 1884 thorax-abdomen CT scans from patients undergoing oncological workup. Reference bounding boxes were annotated by human observers. The performance of our method was evaluated by computing the wall distance to the reference bounding boxes. The bounding boxes annotated by the first human observer were used as the reference standard for the test set. Using the best configuration, we obtained an average wall distance of 3.20~+/-~7.33 mm in the test set. The second human observer achieved 1.23~+/-~3.39 mm. For all structures, the results were better than those reported in previously published studies. In conclusion, we proposed an efficient method for the accurate localization of multiple organs. Our method uses multiple slices as input to provide more context around the slice under analysis, and we have shown that this improves performance. This method can easily be adapted to handle more organs.

Constrained Active Learning for Anchor Link Prediction Across Multiple Heterogeneous Social Networks

PubMed Central

Zhu, Junxing; Zhang, Jiawei; Wu, Quanyuan; Jia, Yan; Zhou, Bin; Wei, Xiaokai; Yu, Philip S.

2017-01-01

Nowadays, people are usually involved in multiple heterogeneous social networks simultaneously. Discovering the anchor links between the accounts owned by the same users across different social networks is crucial for many important inter-network applications, e.g., cross-network link transfer and cross-network recommendation. Many different supervised models have been proposed to predict anchor links so far, but they are effective only when the labeled anchor links are abundant. However, in real scenarios, such a requirement can hardly be met and most anchor links are unlabeled, since manually labeling the inter-network anchor links is quite costly and tedious. To overcome such a problem and utilize the numerous unlabeled anchor links in model building, in this paper, we introduce the active learning based anchor link prediction problem. Different from the traditional active learning problems, due to the one-to-one constraint on anchor links, if an unlabeled anchor link a=(u,v) is identified as positive (i.e., existing), all the other unlabeled anchor links incident to account u or account v will be negative (i.e., non-existing) automatically. Viewed in such a perspective, asking for the labels of potential positive anchor links in the unlabeled set will be rewarding in the active anchor link prediction problem. Various novel anchor link information gain measures are defined in this paper, based on which several constraint active anchor link prediction methods are introduced. Extensive experiments have been done on real-world social network datasets to compare the performance of these methods with state-of-art anchor link prediction methods. The experimental results show that the proposed Mean-entropy-based Constrained Active Learning (MC) method can outperform other methods with significant advantages. PMID:28771201

Constrained Active Learning for Anchor Link Prediction Across Multiple Heterogeneous Social Networks.

PubMed

Zhu, Junxing; Zhang, Jiawei; Wu, Quanyuan; Jia, Yan; Zhou, Bin; Wei, Xiaokai; Yu, Philip S

2017-08-03

Nowadays, people are usually involved in multiple heterogeneous social networks simultaneously. Discovering the anchor links between the accounts owned by the same users across different social networks is crucial for many important inter-network applications, e.g., cross-network link transfer and cross-network recommendation. Many different supervised models have been proposed to predict anchor links so far, but they are effective only when the labeled anchor links are abundant. However, in real scenarios, such a requirement can hardly be met and most anchor links are unlabeled, since manually labeling the inter-network anchor links is quite costly and tedious. To overcome such a problem and utilize the numerous unlabeled anchor links in model building, in this paper, we introduce the active learning based anchor link prediction problem. Different from the traditional active learning problems, due to the one-to-one constraint on anchor links, if an unlabeled anchor link a = ( u , v ) is identified as positive (i.e., existing), all the other unlabeled anchor links incident to account u or account v will be negative (i.e., non-existing) automatically. Viewed in such a perspective, asking for the labels of potential positive anchor links in the unlabeled set will be rewarding in the active anchor link prediction problem. Various novel anchor link information gain measures are defined in this paper, based on which several constraint active anchor link prediction methods are introduced. Extensive experiments have been done on real-world social network datasets to compare the performance of these methods with state-of-art anchor link prediction methods. The experimental results show that the proposed Mean-entropy-based Constrained Active Learning (MC) method can outperform other methods with significant advantages.

Improved automatic steam distillation combined with oscillation-type densimetry for determining alcoholic strength in spirits and liqueurs.

PubMed

Lachenmeier, Dirk W; Plato, Leander; Suessmann, Manuela; Di Carmine, Matthew; Krueger, Bjoern; Kukuck, Armin; Kranz, Markus

2015-01-01

The determination of the alcoholic strength in spirits and liqueurs is required to control the labelling of alcoholic beverages. The reference methodology prescribes a distillation step followed by densimetric measurement. The classic distillation using a Vigreux rectifying column and a West condenser is time consuming and error-prone, especially for liqueurs that may have problems with entrainment and charring. For this reason, this methodology suggests the use of an automated steam distillation device as alternative. The novel instrument comprises an increased steam power, a redesigned geometry of the condenser and a larger cooling coil with controllable flow, compared to previously available devices. Method optimization applying D-optimal and central composite designs showed significant influence of sample volume, distillation time and coolant flow, while other investigated parameters such as steam power, receiver volume, or the use of pipettes or flasks for sample measurement did not significantly influence the results. The method validation was conducted using the following settings: steam power 70 %, sample volume 25 mL transferred using pipettes, receiver volume 50 mL, coolant flow 7 L/min, and distillation time as long as possible just below the calibration mark. For four different liqueurs covering the typical range of these products between 15 and 35 % vol, the method showed an adequate precision, with relative standard deviations below 0.4 % (intraday) and below 0.6 % (interday). The absolute standard deviations were between 0.06 % vol and 0.08 % vol (intraday) and between 0.07 % vol and 0.10 % vol (interday). The improved automatic steam distillation devices offer an excellent alternative for sample cleanup of volatiles from complex matrices. A major advantage are the low costs for consumables per analysis (only distilled water is needed). For alcoholic strength determination, the method has become more rugged than before, and there are only few influences that would lead to incomplete distillation. Our validation parameters have shown that the performance of the method corresponds to the data presented for the reference method and we believe that automated steam distillation, can be used for the purpose of labelling control of alcoholic beverages.

Fidelity of Automatic Speech Processing for Adult and Child Talker Classifications.

PubMed

VanDam, Mark; Silbert, Noah H

2016-01-01

Automatic speech processing (ASP) has recently been applied to very large datasets of naturalistically collected, daylong recordings of child speech via an audio recorder worn by young children. The system developed by the LENA Research Foundation analyzes children's speech for research and clinical purposes, with special focus on of identifying and tagging family speech dynamics and the at-home acoustic environment from the auditory perspective of the child. A primary issue for researchers, clinicians, and families using the Language ENvironment Analysis (LENA) system is to what degree the segment labels are valid. This classification study evaluates the performance of the computer ASP output against 23 trained human judges who made about 53,000 judgements of classification of segments tagged by the LENA ASP. Results indicate performance consistent with modern ASP such as those using HMM methods, with acoustic characteristics of fundamental frequency and segment duration most important for both human and machine classifications. Results are likely to be important for interpreting and improving ASP output.

Fidelity of Automatic Speech Processing for Adult and Child Talker Classifications

PubMed Central

2016-01-01

Automatic speech processing (ASP) has recently been applied to very large datasets of naturalistically collected, daylong recordings of child speech via an audio recorder worn by young children. The system developed by the LENA Research Foundation analyzes children's speech for research and clinical purposes, with special focus on of identifying and tagging family speech dynamics and the at-home acoustic environment from the auditory perspective of the child. A primary issue for researchers, clinicians, and families using the Language ENvironment Analysis (LENA) system is to what degree the segment labels are valid. This classification study evaluates the performance of the computer ASP output against 23 trained human judges who made about 53,000 judgements of classification of segments tagged by the LENA ASP. Results indicate performance consistent with modern ASP such as those using HMM methods, with acoustic characteristics of fundamental frequency and segment duration most important for both human and machine classifications. Results are likely to be important for interpreting and improving ASP output. PMID:27529813

An Automated Classification Technique for Detecting Defects in Battery Cells

NASA Technical Reports Server (NTRS)

McDowell, Mark; Gray, Elizabeth

2006-01-01

Battery cell defect classification is primarily done manually by a human conducting a visual inspection to determine if the battery cell is acceptable for a particular use or device. Human visual inspection is a time consuming task when compared to an inspection process conducted by a machine vision system. Human inspection is also subject to human error and fatigue over time. We present a machine vision technique that can be used to automatically identify defective sections of battery cells via a morphological feature-based classifier using an adaptive two-dimensional fast Fourier transformation technique. The initial area of interest is automatically classified as either an anode or cathode cell view as well as classified as an acceptable or a defective battery cell. Each battery cell is labeled and cataloged for comparison and analysis. The result is the implementation of an automated machine vision technique that provides a highly repeatable and reproducible method of identifying and quantifying defects in battery cells.

Multimodality animal rotation imaging system (Mars) for in vivo detection of intraperitoneal tumors.

PubMed

Pizzonia, John; Holmberg, Jennie; Orton, Sean; Alvero, Ayesha; Viteri, Oscar; McLaughlin, William; Feke, Gil; Mor, Gil

2012-01-01

PROBLEM Ovarian cancer stem cells (OCSCs) have been postulated as the potential source of recurrence and chemoresistance. Therefore identification of OvCSC and their complete removal is a pivotal stage for the treatment of ovarian cancer. The objective of the following study was to develop a new in vivo imaging model that allows for the detection and monitoring of OCSCs. METHOD OF STUDY  OCSCs were labeled with X-Sight 761 Nanospheres and injected intra-peritoneally (i.p.) and sub-cutaneously (s.c.) to Athymic nude mice. The Carestream In-Vivo Imaging System FX was used to obtain X-ray and, concurrently, near-infrared fluorescence images. Tumor images in the mouse were observed from different angles by automatic rotation of the mouse. RESULTS  X-Sight 761 Nanospheres labeled almost 100% of the cells. No difference on growth rate was observed between labeled and unlabeled cells. Tumors were observed and monitoring revealed strong signaling up to 21 days. CONCLUSION  We describe the use of near-infrared nanoparticle probes for in vivo imaging of metastatic ovarian cancer models. Visualization of multiple sites around the animals was enhanced with the use of the Carestream Multimodal Animal Rotation System. © 2011 John Wiley & Sons A/S.

Approaching the axiomatic enrichment of the Gene Ontology from a lexical perspective.

PubMed

Quesada-Martínez, Manuel; Mikroyannidi, Eleni; Fernández-Breis, Jesualdo Tomás; Stevens, Robert

2015-09-01

The main goal of this work is to measure how lexical regularities in biomedical ontology labels can be used for the automatic creation of formal relationships between classes, and to evaluate the results of applying our approach to the Gene Ontology (GO). In recent years, we have developed a method for the lexical analysis of regularities in biomedical ontology labels, and we showed that the labels can present a high degree of regularity. In this work, we extend our method with a cross-products extension (CPE) metric, which estimates the potential interest of a specific regularity for axiomatic enrichment in the lexical analysis, using information on exact matches in external ontologies. The GO consortium recently enriched the GO by using so-called cross-product extensions. Cross-products are generated by establishing axioms that relate a given GO class with classes from the GO or other biomedical ontologies. We apply our method to the GO and study how its lexical analysis can identify and reconstruct the cross-products that are defined by the GO consortium. The label of the classes of the GO are highly regular in lexical terms, and the exact matches with labels of external ontologies affect 80% of the GO classes. The CPE metric reveals that 31.48% of the classes that exhibit regularities have fragments that are classes into two external ontologies that are selected for our experiment, namely, the Cell Ontology and the Chemical Entities of Biological Interest ontology, and 18.90% of them are fully decomposable into smaller parts. Our results show that the CPE metric permits our method to detect GO cross-product extensions with a mean recall of 62% and a mean precision of 28%. The study is completed with an analysis of false positives to explain this precision value. We think that our results support the claim that our lexical approach can contribute to the axiomatic enrichment of biomedical ontologies and that it can provide new insights into the engineering of biomedical ontologies. Copyright © 2014 Elsevier B.V. All rights reserved.

Automatic Earthquake Detection by Active Learning

NASA Astrophysics Data System (ADS)

Bergen, K.; Beroza, G. C.

2017-12-01

In recent years, advances in machine learning have transformed fields such as image recognition, natural language processing and recommender systems. Many of these performance gains have relied on the availability of large, labeled data sets to train high-accuracy models; labeled data sets are those for which each sample includes a target class label, such as waveforms tagged as either earthquakes or noise. Earthquake seismologists are increasingly leveraging machine learning and data mining techniques to detect and analyze weak earthquake signals in large seismic data sets. One of the challenges in applying machine learning to seismic data sets is the limited labeled data problem; learning algorithms need to be given examples of earthquake waveforms, but the number of known events, taken from earthquake catalogs, may be insufficient to build an accurate detector. Furthermore, earthquake catalogs are known to be incomplete, resulting in training data that may be biased towards larger events and contain inaccurate labels. This challenge is compounded by the class imbalance problem; the events of interest, earthquakes, are infrequent relative to noise in continuous data sets, and many learning algorithms perform poorly on rare classes. In this work, we investigate the use of active learning for automatic earthquake detection. Active learning is a type of semi-supervised machine learning that uses a human-in-the-loop approach to strategically supplement a small initial training set. The learning algorithm incorporates domain expertise through interaction between a human expert and the algorithm, with the algorithm actively posing queries to the user to improve detection performance. We demonstrate the potential of active machine learning to improve earthquake detection performance with limited available training data.

Multi-template analysis of human perirhinal cortex in brain MRI: Explicitly accounting for anatomical variability

PubMed Central

Xie, Long; Pluta, John B.; Das, Sandhitsu R.; Wisse, Laura E.M.; Wang, Hongzhi; Mancuso, Lauren; Kliot, Dasha; Avants, Brian B.; Ding, Song-Lin; Manjón, José V.; Wolk, David A.; Yushkevich, Paul A.

2016-01-01

Rational The human perirhinal cortex (PRC) plays critical roles in episodic and semantic memory and visual perception. The PRC consists of Brodmann areas 35 and 36 (BA35, BA36). In Alzheimer's disease (AD), BA35 is the first cortical site affected by neurofibrillary tangle pathology, which is closely linked to neural injury in AD. Large anatomical variability, manifested in the form of different cortical folding and branching patterns, makes it difficult to segment the PRC in MRI scans. Pathology studies have found that in ~97% of specimens, the PRC falls into one of three discrete anatomical variants. However, current methods for PRC segmentation and morphometry in MRI are based on single-template approaches, which may not be able to accurately model these discrete variants Methods A multi-template analysis pipeline that explicitly accounts for anatomical variability is used to automatically label the PRC and measure its thickness in T2-weighted MRI scans. The pipeline uses multi-atlas segmentation to automatically label medial temporal lobe cortices including entorhinal cortex, PRC and the parahippocampal cortex. Pairwise registration between label maps and clustering based on residual dissimilarity after registration are used to construct separate templates for the anatomical variants of the PRC. An optimal path of deformations linking these templates is used to establish correspondences between all the subjects. Experimental evaluation focuses on the ability of single-template and multi-template analyses to detect differences in the thickness of medial temporal lobe cortices between patients with amnestic mild cognitive impairment (aMCI, n=41) and age-matched controls (n=44). Results The proposed technique is able to generate templates that recover the three dominant discrete variants of PRC and establish more meaningful correspondences between subjects than a single-template approach. The largest reduction in thickness associated with aMCI, in absolute terms, was found in left BA35 using both regional and summary thickness measures. Further, statistical maps of regional thickness difference between aMCI and controls revealed different patterns for the three anatomical variants. PMID:27702610

Automatic Classification of High Resolution Satellite Imagery - a Case Study for Urban Areas in the Kingdom of Saudi Arabia

NASA Astrophysics Data System (ADS)

Maas, A.; Alrajhi, M.; Alobeid, A.; Heipke, C.

2017-05-01

Updating topographic geospatial databases is often performed based on current remotely sensed images. To automatically extract the object information (labels) from the images, supervised classifiers are being employed. Decisions to be taken in this process concern the definition of the classes which should be recognised, the features to describe each class and the training data necessary in the learning part of classification. With a view to large scale topographic databases for fast developing urban areas in the Kingdom of Saudi Arabia we conducted a case study, which investigated the following two questions: (a) which set of features is best suitable for the classification?; (b) what is the added value of height information, e.g. derived from stereo imagery? Using stereoscopic GeoEye and Ikonos satellite data we investigate these two questions based on our research on label tolerant classification using logistic regression and partly incorrect training data. We show that in between five and ten features can be recommended to obtain a stable solution, that height information consistently yields an improved overall classification accuracy of about 5%, and that label noise can be successfully modelled and thus only marginally influences the classification results.

Automatic co-segmentation of lung tumor based on random forest in PET-CT images

NASA Astrophysics Data System (ADS)

Jiang, Xueqing; Xiang, Dehui; Zhang, Bin; Zhu, Weifang; Shi, Fei; Chen, Xinjian

2016-03-01

In this paper, a fully automatic method is proposed to segment the lung tumor in clinical 3D PET-CT images. The proposed method effectively combines PET and CT information to make full use of the high contrast of PET images and superior spatial resolution of CT images. Our approach consists of three main parts: (1) initial segmentation, in which spines are removed in CT images and initial connected regions achieved by thresholding based segmentation in PET images; (2) coarse segmentation, in which monotonic downhill function is applied to rule out structures which have similar standardized uptake values (SUV) to the lung tumor but do not satisfy a monotonic property in PET images; (3) fine segmentation, random forests method is applied to accurately segment the lung tumor by extracting effective features from PET and CT images simultaneously. We validated our algorithm on a dataset which consists of 24 3D PET-CT images from different patients with non-small cell lung cancer (NSCLC). The average TPVF, FPVF and accuracy rate (ACC) were 83.65%, 0.05% and 99.93%, respectively. The correlation analysis shows our segmented lung tumor volumes has strong correlation ( average 0.985) with the ground truth 1 and ground truth 2 labeled by a clinical expert.

Natural Language-based Machine Learning Models for the Annotation of Clinical Radiology Reports.

PubMed

Zech, John; Pain, Margaret; Titano, Joseph; Badgeley, Marcus; Schefflein, Javin; Su, Andres; Costa, Anthony; Bederson, Joshua; Lehar, Joseph; Oermann, Eric Karl

2018-05-01

Purpose To compare different methods for generating features from radiology reports and to develop a method to automatically identify findings in these reports. Materials and Methods In this study, 96 303 head computed tomography (CT) reports were obtained. The linguistic complexity of these reports was compared with that of alternative corpora. Head CT reports were preprocessed, and machine-analyzable features were constructed by using bag-of-words (BOW), word embedding, and Latent Dirichlet allocation-based approaches. Ultimately, 1004 head CT reports were manually labeled for findings of interest by physicians, and a subset of these were deemed critical findings. Lasso logistic regression was used to train models for physician-assigned labels on 602 of 1004 head CT reports (60%) using the constructed features, and the performance of these models was validated on a held-out 402 of 1004 reports (40%). Models were scored by area under the receiver operating characteristic curve (AUC), and aggregate AUC statistics were reported for (a) all labels, (b) critical labels, and (c) the presence of any critical finding in a report. Sensitivity, specificity, accuracy, and F1 score were reported for the best performing model's (a) predictions of all labels and (b) identification of reports containing critical findings. Results The best-performing model (BOW with unigrams, bigrams, and trigrams plus average word embeddings vector) had a held-out AUC of 0.966 for identifying the presence of any critical head CT finding and an average 0.957 AUC across all head CT findings. Sensitivity and specificity for identifying the presence of any critical finding were 92.59% (175 of 189) and 89.67% (191 of 213), respectively. Average sensitivity and specificity across all findings were 90.25% (1898 of 2103) and 91.72% (18 351 of 20 007), respectively. Simpler BOW methods achieved results competitive with those of more sophisticated approaches, with an average AUC for presence of any critical finding of 0.951 for unigram BOW versus 0.966 for the best-performing model. The Yule I of the head CT corpus was 34, markedly lower than that of the Reuters corpus (at 103) or I2B2 discharge summaries (at 271), indicating lower linguistic complexity. Conclusion Automated methods can be used to identify findings in radiology reports. The success of this approach benefits from the standardized language of these reports. With this method, a large labeled corpus can be generated for applications such as deep learning. © RSNA, 2018 Online supplemental material is available for this article.

Use of a systematic risk analysis method to improve safety in the production of paediatric parenteral nutrition solutions

PubMed Central

Bonnabry, P; Cingria, L; Sadeghipour, F; Ing, H; Fonzo-Christe, C; Pfister, R

2005-01-01

Background: Until recently, the preparation of paediatric parenteral nutrition formulations in our institution included re-transcription and manual compounding of the mixture. Although no significant clinical problems have occurred, re-engineering of this high risk activity was undertaken to improve its safety. Several changes have been implemented including new prescription software, direct recording on a server, automatic printing of the labels, and creation of a file used to pilot a BAXA MM 12 automatic compounder. The objectives of this study were to compare the risks associated with the old and new processes, to quantify the improved safety with the new process, and to identify the major residual risks. Methods: A failure modes, effects, and criticality analysis (FMECA) was performed by a multidisciplinary team. A cause-effect diagram was built, the failure modes were defined, and the criticality index (CI) was determined for each of them on the basis of the likelihood of occurrence, the severity of the potential effect, and the detection probability. The CIs for each failure mode were compared for the old and new processes and the risk reduction was quantified. Results: The sum of the CIs of all 18 identified failure modes was 3415 for the old process and 1397 for the new (reduction of 59%). The new process reduced the CIs of the different failure modes by a mean factor of 7. The CI was smaller with the new process for 15 failure modes, unchanged for two, and slightly increased for one. The greatest reduction (by a factor of 36) concerned re-transcription errors, followed by readability problems (by a factor of 30) and chemical cross contamination (by a factor of 10). The most critical steps in the new process were labelling mistakes (CI 315, maximum 810), failure to detect a dosage or product mistake (CI 288), failure to detect a typing error during the prescription (CI 175), and microbial contamination (CI 126). Conclusions: Modification of the process resulted in a significant risk reduction as shown by risk analysis. Residual failure opportunities were also quantified, allowing additional actions to be taken to reduce the risk of labelling mistakes. This study illustrates the usefulness of prospective risk analysis methods in healthcare processes. More systematic use of risk analysis is needed to guide continuous safety improvement of high risk activities. PMID:15805453

Landmark Image Retrieval by Jointing Feature Refinement and Multimodal Classifier Learning.

PubMed

Zhang, Xiaoming; Wang, Senzhang; Li, Zhoujun; Ma, Shuai; Xiaoming Zhang; Senzhang Wang; Zhoujun Li; Shuai Ma; Ma, Shuai; Zhang, Xiaoming; Wang, Senzhang; Li, Zhoujun

2018-06-01

Landmark retrieval is to return a set of images with their landmarks similar to those of the query images. Existing studies on landmark retrieval focus on exploiting the geometries of landmarks for visual similarity matches. However, the visual content of social images is of large diversity in many landmarks, and also some images share common patterns over different landmarks. On the other side, it has been observed that social images usually contain multimodal contents, i.e., visual content and text tags, and each landmark has the unique characteristic of both visual content and text content. Therefore, the approaches based on similarity matching may not be effective in this environment. In this paper, we investigate whether the geographical correlation among the visual content and the text content could be exploited for landmark retrieval. In particular, we propose an effective multimodal landmark classification paradigm to leverage the multimodal contents of social image for landmark retrieval, which integrates feature refinement and landmark classifier with multimodal contents by a joint model. The geo-tagged images are automatically labeled for classifier learning. Visual features are refined based on low rank matrix recovery, and multimodal classification combined with group sparse is learned from the automatically labeled images. Finally, candidate images are ranked by combining classification result and semantic consistence measuring between the visual content and text content. Experiments on real-world datasets demonstrate the superiority of the proposed approach as compared to existing methods.

Automatic three-dimensional rib centerline extraction from CT scans for enhanced visualization and anatomical context

NASA Astrophysics Data System (ADS)

Ramakrishnan, Sowmya; Alvino, Christopher; Grady, Leo; Kiraly, Atilla

2011-03-01

We present a complete automatic system to extract 3D centerlines of ribs from thoracic CT scans. Our rib centerline system determines the positional information for the rib cage consisting of extracted rib centerlines, spinal canal centerline, pairing and labeling of ribs. We show an application of this output to produce an enhanced visualization of the rib cage by the method of Kiraly et al., in which the ribs are digitally unfolded along their centerlines. The centerline extraction consists of three stages: (a) pre-trace processing for rib localization, (b) rib centerline tracing, and (c) post-trace processing to merge the rib traces. Then we classify ribs from non-ribs and determine anatomical rib labeling. Our novel centerline tracing technique uses the Random Walker algorithm to segment the structural boundary of the rib in successive 2D cross sections orthogonal to the longitudinal direction of the ribs. Then the rib centerline is progressively traced along the rib using a 3D Kalman filter. The rib centerline extraction framework was evaluated on 149 CT datasets with varying slice spacing, dose, and under a variety of reconstruction kernels. The results of the evaluation are presented. The extraction takes approximately 20 seconds on a modern radiology workstation and performs robustly even in the presence of partial volume effects or rib pathologies such as bone metastases or fractures, making the system suitable for assisting clinicians in expediting routine rib reading for oncology and trauma applications.

Unsupervised daily routine and activity discovery in smart homes.

PubMed

Jie Yin; Qing Zhang; Karunanithi, Mohan

2015-08-01

The ability to accurately recognize daily activities of residents is a core premise of smart homes to assist with remote health monitoring. Most of the existing methods rely on a supervised model trained from a preselected and manually labeled set of activities, which are often time-consuming and costly to obtain in practice. In contrast, this paper presents an unsupervised method for discovering daily routines and activities for smart home residents. Our proposed method first uses a Markov chain to model a resident's locomotion patterns at different times of day and discover clusters of daily routines at the macro level. For each routine cluster, it then drills down to further discover room-level activities at the micro level. The automatic identification of daily routines and activities is useful for understanding indicators of functional decline of elderly people and suggesting timely interventions.

Repliscan: a tool for classifying replication timing regions.

PubMed

Zynda, Gregory J; Song, Jawon; Concia, Lorenzo; Wear, Emily E; Hanley-Bowdoin, Linda; Thompson, William F; Vaughn, Matthew W

2017-08-07

Replication timing experiments that use label incorporation and high throughput sequencing produce peaked data similar to ChIP-Seq experiments. However, the differences in experimental design, coverage density, and possible results make traditional ChIP-Seq analysis methods inappropriate for use with replication timing. To accurately detect and classify regions of replication across the genome, we present Repliscan. Repliscan robustly normalizes, automatically removes outlying and uninformative data points, and classifies Repli-seq signals into discrete combinations of replication signatures. The quality control steps and self-fitting methods make Repliscan generally applicable and more robust than previous methods that classify regions based on thresholds. Repliscan is simple and effective to use on organisms with different genome sizes. Even with analysis window sizes as small as 1 kilobase, reliable profiles can be generated with as little as 2.4x coverage.

Automated branching pattern report generation for laparoscopic surgery assistance

NASA Astrophysics Data System (ADS)

Oda, Masahiro; Matsuzaki, Tetsuro; Hayashi, Yuichiro; Kitasaka, Takayuki; Misawa, Kazunari; Mori, Kensaku

2015-05-01

This paper presents a method for generating branching pattern reports of abdominal blood vessels for laparoscopic gastrectomy. In gastrectomy, it is very important to understand branching structure of abdominal arteries and veins, which feed and drain specific abdominal organs including the stomach, the liver and the pancreas. In the real clinical stage, a surgeon creates a diagnostic report of the patient anatomy. This report summarizes the branching patterns of the blood vessels related to the stomach. The surgeon decides actual operative procedure. This paper shows an automated method to generate a branching pattern report for abdominal blood vessels based on automated anatomical labeling. The report contains 3D rendering showing important blood vessels and descriptions of branching patterns of each vessel. We have applied this method for fifty cases of 3D abdominal CT scans and confirmed the proposed method can automatically generate branching pattern reports of abdominal arteries.

Investigation on microfluidic particles manipulation by holographic 3D tracking strategies

NASA Astrophysics Data System (ADS)

Cacace, Teresa; Paturzo, Melania; Memmolo, Pasquale; Vassalli, Massimo; Fraldi, Massimiliano; Mensitieri, Giuseppe; Ferraro, Pietro

2017-06-01

We demonstrate a 3D holographic tracking method to investigate particles motion in a microfluidic channel while unperturbed while inducing their migration through microfluidic manipulation. Digital holography (DH) in microscopy is a full-field, label-free imaging technique able to provide quantitative phase-contrast. The employed 3D tracking method is articulated in steps. First, the displacements along the optical axis are assessed by numerical refocusing criteria. In particular, an automatic refocusing method to recover the particles axial position is implemented employing a contrast-based refocusing criterion. Then, the transverse position of the in-focus object is evaluated through quantitative phase map segmentation methods and centroid-based 2D tracking strategy. The introduction of DH is thus suggested as a powerful approach for control of particles and biological samples manipulation, as well as a possible aid to precise design and implementation of advanced lab-on-chip microfluidic devices.

Automatic Clustering and Thickness Measurement of Anatomical Variants of the Human Perirhinal Cortex

PubMed Central

Xie, Long; Pluta, John; Wang, Hongzhi; Das, Sandhitsu R.; Mancuso, Lauren; Kliot, Dasha; Avants, Brian B.; Ding, Song-Lin; Wolk, David A.; Yushkevich, Paul A.

2015-01-01

The entorhinal cortex (ERC) and the perirhinal cortex (PRC) are subregions of the medial temporal lobe (MTL) that play important roles in episodic memory representations, as well as serving as a conduit between other neocortical areas and the hippocampus. They are also the sites where neuronal damage first occurs in Alzheimer’s disease (AD). The ability to automatically quantify the volume and thickness of the ERC and PRC is desirable because these localized measures can potentially serve as better imaging biomarkers for AD and other neurodegenerative diseases. However, large anatomical variation in the PRC makes it a challenging area for analysis. In order to address this problem, we propose an automatic segmentation, clustering, and thickness measurement approach that explicitly accounts for anatomical variation. The approach is targeted to highly anisotropic (0.4×0.4×2.0mm3) T2-weighted MRI scans that are preferred by many authors for detailed imaging of the MTL, but which pose challenges for segmentation and shape analysis. After automatically labeling MTL substructures using multi-atlas segmentation, our method clusters subjects into groups based on the shape of the PRC, constructs unbiased population templates for each group, and uses the smooth surface representations obtained during template construction to extract regional thickness measurements in the space of each subject. The proposed thickness measures are evaluated in the context of discrimination between patients with Mild Cognitive Impairment (MCI) and normal controls (NC). PMID:25320785

Unsupervised Transfer Learning via Multi-Scale Convolutional Sparse Coding for Biomedical Applications

PubMed Central

Chang, Hang; Han, Ju; Zhong, Cheng; Snijders, Antoine M.; Mao, Jian-Hua

2017-01-01

The capabilities of (I) learning transferable knowledge across domains; and (II) fine-tuning the pre-learned base knowledge towards tasks with considerably smaller data scale are extremely important. Many of the existing transfer learning techniques are supervised approaches, among which deep learning has the demonstrated power of learning domain transferrable knowledge with large scale network trained on massive amounts of labeled data. However, in many biomedical tasks, both the data and the corresponding label can be very limited, where the unsupervised transfer learning capability is urgently needed. In this paper, we proposed a novel multi-scale convolutional sparse coding (MSCSC) method, that (I) automatically learns filter banks at different scales in a joint fashion with enforced scale-specificity of learned patterns; and (II) provides an unsupervised solution for learning transferable base knowledge and fine-tuning it towards target tasks. Extensive experimental evaluation of MSCSC demonstrates the effectiveness of the proposed MSCSC in both regular and transfer learning tasks in various biomedical domains. PMID:28129148

Automatic recognition of conceptualization zones in scientific articles and two life science applications.

PubMed

Liakata, Maria; Saha, Shyamasree; Dobnik, Simon; Batchelor, Colin; Rebholz-Schuhmann, Dietrich

2012-04-01

Scholarly biomedical publications report on the findings of a research investigation. Scientists use a well-established discourse structure to relate their work to the state of the art, express their own motivation and hypotheses and report on their methods, results and conclusions. In previous work, we have proposed ways to explicitly annotate the structure of scientific investigations in scholarly publications. Here we present the means to facilitate automatic access to the scientific discourse of articles by automating the recognition of 11 categories at the sentence level, which we call Core Scientific Concepts (CoreSCs). These include: Hypothesis, Motivation, Goal, Object, Background, Method, Experiment, Model, Observation, Result and Conclusion. CoreSCs provide the structure and context to all statements and relations within an article and their automatic recognition can greatly facilitate biomedical information extraction by characterizing the different types of facts, hypotheses and evidence available in a scientific publication. We have trained and compared machine learning classifiers (support vector machines and conditional random fields) on a corpus of 265 full articles in biochemistry and chemistry to automatically recognize CoreSCs. We have evaluated our automatic classifications against a manually annotated gold standard, and have achieved promising accuracies with 'Experiment', 'Background' and 'Model' being the categories with the highest F1-scores (76%, 62% and 53%, respectively). We have analysed the task of CoreSC annotation both from a sentence classification as well as sequence labelling perspective and we present a detailed feature evaluation. The most discriminative features are local sentence features such as unigrams, bigrams and grammatical dependencies while features encoding the document structure, such as section headings, also play an important role for some of the categories. We discuss the usefulness of automatically generated CoreSCs in two biomedical applications as well as work in progress. A web-based tool for the automatic annotation of articles with CoreSCs and corresponding documentation is available online at http://www.sapientaproject.com/software http://www.sapientaproject.com also contains detailed information pertaining to CoreSC annotation and links to annotation guidelines as well as a corpus of manually annotated articles, which served as our training data. liakata@ebi.ac.uk Supplementary data are available at Bioinformatics online.

Automated segmentation of serous pigment epithelium detachment in SD-OCT images

NASA Astrophysics Data System (ADS)

Sun, Zhuli; Shi, Fei; Xiang, Dehui; Chen, Haoyu; Chen, Xinjian

2015-03-01

Pigment epithelium detachment (PED) is an important clinical manifestation of multiple chorio-retinal disease processes, which can cause the loss of central vision. A 3-D method is proposed to automatically segment serous PED in SD-OCT images. The proposed method consists of five steps: first, a curvature anisotropic diffusion filter is applied to remove speckle noise. Second, the graph search method is applied for abnormal retinal layer segmentation associated with retinal pigment epithelium (RPE) deformation. During this process, Bruch's membrane, which doesn't show in the SD-OCT images, is estimated with the convex hull algorithm. Third, the foreground and background seeds are automatically obtained from retinal layer segmentation result. Fourth, the serous PED is segmented based on the graph cut method. Finally, a post-processing step is applied to remove false positive regions based on mathematical morphology. The proposed method was tested on 20 SD-OCT volumes from 20 patients diagnosed with serous PED. The average true positive volume fraction (TPVF), false positive volume fraction (FPVF), dice similarity coefficient (DSC) and positive predictive value (PPV) are 97.19%, 0.03%, 96.34% and 95.59%, respectively. Linear regression analysis shows a strong correlation (r = 0.975) comparing the segmented PED volumes with the ground truth labeled by an ophthalmology expert. The proposed method can provide clinicians with accurate quantitative information, including shape, size and position of the PED regions, which can assist diagnose and treatment.

Product Recommendation System Based on Personal Preference Model Using CAM

NASA Astrophysics Data System (ADS)

Murakami, Tomoko; Yoshioka, Nobukazu; Orihara, Ryohei; Furukawa, Koichi

Product recommendation system is realized by applying business rules acquired by data maining techniques. Business rules such as demographical patterns of purchase, are able to cover the groups of users that have a tendency to purchase products, but it is difficult to recommend products adaptive to various personal preferences only by utilizing them. In addition to that, it is very costly to gather the large volume of high quality survey data, which is necessary for good recommendation based on personal preference model. A method collecting kansei information automatically without questionnaire survey is required. The constructing personal preference model from less favor data is also necessary, since it is costly for the user to input favor data. In this paper, we propose product recommendation system based on kansei information extracted by text mining and user's preference model constructed by Category-guided Adaptive Modeling, CAM for short. CAM is a feature construction method that can generate new features constructing the space where same labeled examples are close and different labeled examples are far away from some labeled examples. It is possible to construct personal preference model by CAM despite less information of likes and dislikes categories. In the system, retrieval agent gathers the products' specification and user agent manages preference model, user's likes and dislikes. Kansei information of the products is gained by applying text mining technique to the reputation documents about the products on the web site. We carry out some experimental studies to make sure that prefrence model obtained by our method performs effectively.

What’s Wrong with the Murals at the Mogao Grottoes: A Near-Infrared Hyperspectral Imaging Method

PubMed Central

Sun, Meijun; Zhang, Dong; Wang, Zheng; Ren, Jinchang; Chai, Bolong; Sun, Jizhou

2015-01-01

Although a significant amount of work has been performed to preserve the ancient murals in the Mogao Grottoes by Dunhuang Cultural Research, non-contact methods need to be developed to effectively evaluate the degree of flaking of the murals. In this study, we propose to evaluate the flaking by automatically analyzing hyperspectral images that were scanned at the site. Murals with various degrees of flaking were scanned in the 126th cave using a near-infrared (NIR) hyperspectral camera with a spectral range of approximately 900 to 1700 nm. The regions of interest (ROIs) of the murals were manually labeled and grouped into four levels: normal, slight, moderate, and severe. The average spectral data from each ROI and its group label were used to train our classification model. To predict the degree of flaking, we adopted four algorithms: deep belief networks (DBNs), partial least squares regression (PLSR), principal component analysis with a support vector machine (PCA + SVM) and principal component analysis with an artificial neural network (PCA + ANN). The experimental results show the effectiveness of our method. In particular, better results are obtained using DBNs when the training data contain a significant amount of striping noise. PMID:26394926

Watermarking and copyright labeling of printed images

NASA Astrophysics Data System (ADS)

Hel-Or, Hagit Z.

2001-07-01

Digital watermarking is a labeling technique for digital images which embeds a code into the digital data so the data are marked. Watermarking techniques previously developed deal with on-line digital data. These techniques have been developed to withstand digital attacks such as image processing, image compression and geometric transformations. However, one must also consider the readily available attack of printing and scanning. The available watermarking techniques are not reliable under printing and scanning. In fact, one must consider the availability of watermarks for printed images as well as for digital images. An important issue is to intercept and prevent forgery in printed material such as currency notes, back checks, etc. and to track and validate sensitive and secrete printed material. Watermarking in such printed material can be used not only for verification of ownership but as an indicator of date and type of transaction or date and source of the printed data. In this work we propose a method of embedding watermarks in printed images by inherently taking advantage of the printing process. The method is visually unobtrusive to the printed image, the watermark is easily extracted and is robust under reconstruction errors. The decoding algorithm is automatic given the watermarked image.

Machine for Automatic Bacteriological Pour Plate Preparation

PubMed Central

Sharpe, A. N.; Biggs, D. R.; Oliver, R. J.

1972-01-01

A fully automatic system for preparing poured plates for bacteriological analyses has been constructed and tested. The machine can make decimal dilutions of bacterial suspensions, dispense measured amounts into petri dishes, add molten agar, mix the dish contents, and label the dishes with sample and dilution numbers at the rate of 2,000 dishes per 8-hr day. In addition, the machine can be programmed to select different media so that plates for different types of bacteriological analysis may be made automatically from the same sample. The machine uses only the components of the media and sterile polystyrene petri dishes; requirements for all other materials, such as sterile pipettes and capped bottles of diluents and agar, are eliminated. Images PMID:4560475

A study of the effectiveness of machine learning methods for classification of clinical interview fragments into a large number of categories.

PubMed

Hasan, Mehedi; Kotov, Alexander; Carcone, April; Dong, Ming; Naar, Sylvie; Hartlieb, Kathryn Brogan

2016-08-01

This study examines the effectiveness of state-of-the-art supervised machine learning methods in conjunction with different feature types for the task of automatic annotation of fragments of clinical text based on codebooks with a large number of categories. We used a collection of motivational interview transcripts consisting of 11,353 utterances, which were manually annotated by two human coders as the gold standard, and experimented with state-of-art classifiers, including Naïve Bayes, J48 Decision Tree, Support Vector Machine (SVM), Random Forest (RF), AdaBoost, DiscLDA, Conditional Random Fields (CRF) and Convolutional Neural Network (CNN) in conjunction with lexical, contextual (label of the previous utterance) and semantic (distribution of words in the utterance across the Linguistic Inquiry and Word Count dictionaries) features. We found out that, when the number of classes is large, the performance of CNN and CRF is inferior to SVM. When only lexical features were used, interview transcripts were automatically annotated by SVM with the highest classification accuracy among all classifiers of 70.8%, 61% and 53.7% based on the codebooks consisting of 17, 20 and 41 codes, respectively. Using contextual and semantic features, as well as their combination, in addition to lexical ones, improved the accuracy of SVM for annotation of utterances in motivational interview transcripts with a codebook consisting of 17 classes to 71.5%, 74.2%, and 75.1%, respectively. Our results demonstrate the potential of using machine learning methods in conjunction with lexical, semantic and contextual features for automatic annotation of clinical interview transcripts with near-human accuracy. Copyright © 2016 Elsevier Inc. All rights reserved.

Technical Note: PLASTIMATCH MABS, an open source tool for automatic image segmentation

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

Zaffino, Paolo; Spadea, Maria Francesca

Purpose: Multiatlas based segmentation is largely used in many clinical and research applications. Due to its good performances, it has recently been included in some commercial platforms for radiotherapy planning and surgery guidance. Anyway, to date, a software with no restrictions about the anatomical district and image modality is still missing. In this paper we introduce PLASTIMATCH MABS, an open source software that can be used with any image modality for automatic segmentation. Methods: PLASTIMATCH MABS workflow consists of two main parts: (1) an offline phase, where optimal registration and voting parameters are tuned and (2) an online phase, wheremore » a new patient is labeled from scratch by using the same parameters as identified in the former phase. Several registration strategies, as well as different voting criteria can be selected. A flexible atlas selection scheme is also available. To prove the effectiveness of the proposed software across anatomical districts and image modalities, it was tested on two very different scenarios: head and neck (H&N) CT segmentation for radiotherapy application, and magnetic resonance image brain labeling for neuroscience investigation. Results: For the neurological study, minimum dice was equal to 0.76 (investigated structures: left and right caudate, putamen, thalamus, and hippocampus). For head and neck case, minimum dice was 0.42 for the most challenging structures (optic nerves and submandibular glands) and 0.62 for the other ones (mandible, brainstem, and parotid glands). Time required to obtain the labels was compatible with a real clinical workflow (35 and 120 min). Conclusions: The proposed software fills a gap in the multiatlas based segmentation field, since all currently available tools (both for commercial and for research purposes) are restricted to a well specified application. Furthermore, it can be adopted as a platform for exploring MABS parameters and as a reference implementation for comparing against other segmentation algorithms.« less

Facilitating Analysis of Multiple Partial Data Streams

NASA Technical Reports Server (NTRS)

Maimone, Mark W.; Liebersbach, Robert R.

2008-01-01

Robotic Operations Automation: Mechanisms, Imaging, Navigation report Generation (ROAMING) is a set of computer programs that facilitates and accelerates both tactical and strategic analysis of time-sampled data especially the disparate and often incomplete streams of Mars Explorer Rover (MER) telemetry data described in the immediately preceding article. As used here, tactical refers to the activities over a relatively short time (one Martian day in the original MER application) and strategic refers to a longer time (the entire multi-year MER missions in the original application). Prior to installation, ROAMING must be configured with the types of data of interest, and parsers must be modified to understand the format of the input data (many example parsers are provided, including for general CSV files). Thereafter, new data from multiple disparate sources are automatically resampled into a single common annotated spreadsheet stored in a readable space-separated format, and these data can be processed or plotted at any time scale. Such processing or plotting makes it possible to study not only the details of a particular activity spanning only a few seconds, but also longer-term trends. ROAMING makes it possible to generate mission-wide plots of multiple engineering quantities [e.g., vehicle tilt as in Figure 1(a), motor current, numbers of images] that, heretofore could be found only in thousands of separate files. ROAMING also supports automatic annotation of both images and graphs. In the MER application, labels given to terrain features by rover scientists and engineers are automatically plotted in all received images based on their associated camera models (see Figure 2), times measured in seconds are mapped to Mars local time, and command names or arbitrary time-labeled events can be used to label engineering plots, as in Figure 1(b).

Towards Automatic Semantic Labelling of 3D City Models

NASA Astrophysics Data System (ADS)

Rook, M.; Biljecki, F.; Diakité, A. A.

2016-10-01

The lack of semantic information in many 3D city models is a considerable limiting factor in their use, as a lot of applications rely on semantics. Such information is not always available, since it is not collected at all times, it might be lost due to data transformation, or its lack may be caused by non-interoperability in data integration from other sources. This research is a first step in creating an automatic workflow that semantically labels plain 3D city model represented by a soup of polygons, with semantic and thematic information, as defined in the CityGML standard. The first step involves the reconstruction of the topology, which is used in a region growing algorithm that clusters upward facing adjacent triangles. Heuristic rules, embedded in a decision tree, are used to compute a likeliness score for these regions that either represent the ground (terrain) or a RoofSurface. Regions with a high likeliness score, to one of the two classes, are used to create a decision space, which is used in a support vector machine (SVM). Next, topological relations are utilised to select seeds that function as a start in a region growing algorithm, to create regions of triangles of other semantic classes. The topological relationships of the regions are used in the aggregation of the thematic building features. Finally, the level of detail is detected to generate the correct output in CityGML. The results show an accuracy between 85 % and 99 % in the automatic semantic labelling on four different test datasets. The paper is concluded by indicating problems and difficulties implying the next steps in the research.

Segmentation of Image Data from Complex Organotypic 3D Models of Cancer Tissues with Markov Random Fields

PubMed Central

Robinson, Sean; Guyon, Laurent; Nevalainen, Jaakko; Toriseva, Mervi

2015-01-01

Organotypic, three dimensional (3D) cell culture models of epithelial tumour types such as prostate cancer recapitulate key aspects of the architecture and histology of solid cancers. Morphometric analysis of multicellular 3D organoids is particularly important when additional components such as the extracellular matrix and tumour microenvironment are included in the model. The complexity of such models has so far limited their successful implementation. There is a great need for automatic, accurate and robust image segmentation tools to facilitate the analysis of such biologically relevant 3D cell culture models. We present a segmentation method based on Markov random fields (MRFs) and illustrate our method using 3D stack image data from an organotypic 3D model of prostate cancer cells co-cultured with cancer-associated fibroblasts (CAFs). The 3D segmentation output suggests that these cell types are in physical contact with each other within the model, which has important implications for tumour biology. Segmentation performance is quantified using ground truth labels and we show how each step of our method increases segmentation accuracy. We provide the ground truth labels along with the image data and code. Using independent image data we show that our segmentation method is also more generally applicable to other types of cellular microscopy and not only limited to fluorescence microscopy. PMID:26630674

Segmentation of Image Data from Complex Organotypic 3D Models of Cancer Tissues with Markov Random Fields.

PubMed

Robinson, Sean; Guyon, Laurent; Nevalainen, Jaakko; Toriseva, Mervi; Åkerfelt, Malin; Nees, Matthias

2015-01-01

Organotypic, three dimensional (3D) cell culture models of epithelial tumour types such as prostate cancer recapitulate key aspects of the architecture and histology of solid cancers. Morphometric analysis of multicellular 3D organoids is particularly important when additional components such as the extracellular matrix and tumour microenvironment are included in the model. The complexity of such models has so far limited their successful implementation. There is a great need for automatic, accurate and robust image segmentation tools to facilitate the analysis of such biologically relevant 3D cell culture models. We present a segmentation method based on Markov random fields (MRFs) and illustrate our method using 3D stack image data from an organotypic 3D model of prostate cancer cells co-cultured with cancer-associated fibroblasts (CAFs). The 3D segmentation output suggests that these cell types are in physical contact with each other within the model, which has important implications for tumour biology. Segmentation performance is quantified using ground truth labels and we show how each step of our method increases segmentation accuracy. We provide the ground truth labels along with the image data and code. Using independent image data we show that our segmentation method is also more generally applicable to other types of cellular microscopy and not only limited to fluorescence microscopy.

GO-PCA: An Unsupervised Method to Explore Gene Expression Data Using Prior Knowledge

PubMed Central

Wagner, Florian

2015-01-01

Method Genome-wide expression profiling is a widely used approach for characterizing heterogeneous populations of cells, tissues, biopsies, or other biological specimen. The exploratory analysis of such data typically relies on generic unsupervised methods, e.g. principal component analysis (PCA) or hierarchical clustering. However, generic methods fail to exploit prior knowledge about the molecular functions of genes. Here, I introduce GO-PCA, an unsupervised method that combines PCA with nonparametric GO enrichment analysis, in order to systematically search for sets of genes that are both strongly correlated and closely functionally related. These gene sets are then used to automatically generate expression signatures with functional labels, which collectively aim to provide a readily interpretable representation of biologically relevant similarities and differences. The robustness of the results obtained can be assessed by bootstrapping. Results I first applied GO-PCA to datasets containing diverse hematopoietic cell types from human and mouse, respectively. In both cases, GO-PCA generated a small number of signatures that represented the majority of lineages present, and whose labels reflected their respective biological characteristics. I then applied GO-PCA to human glioblastoma (GBM) data, and recovered signatures associated with four out of five previously defined GBM subtypes. My results demonstrate that GO-PCA is a powerful and versatile exploratory method that reduces an expression matrix containing thousands of genes to a much smaller set of interpretable signatures. In this way, GO-PCA aims to facilitate hypothesis generation, design of further analyses, and functional comparisons across datasets. PMID:26575370

HIPS: A new hippocampus subfield segmentation method.

PubMed

Romero, José E; Coupé, Pierrick; Manjón, José V

2017-12-01

The importance of the hippocampus in the study of several neurodegenerative diseases such as Alzheimer's disease makes it a structure of great interest in neuroimaging. However, few segmentation methods have been proposed to measure its subfields due to its complex structure and the lack of high resolution magnetic resonance (MR) data. In this work, we present a new pipeline for automatic hippocampus subfield segmentation using two available hippocampus subfield delineation protocols that can work with both high and standard resolution data. The proposed method is based on multi-atlas label fusion technology that benefits from a novel multi-contrast patch match search process (using high resolution T1-weighted and T2-weighted images). The proposed method also includes as post-processing a new neural network-based error correction step to minimize systematic segmentation errors. The method has been evaluated on both high and standard resolution images and compared to other state-of-the-art methods showing better results in terms of accuracy and execution time. Copyright © 2017 Elsevier Inc. All rights reserved.

Developing convolutional neural networks for measuring climate change opinions from social media data

NASA Astrophysics Data System (ADS)

Mao, H.; Bhaduri, B. L.

2016-12-01

Understanding public opinions on climate change is important for policy making. Public opinion, however, is typically measured with national surveys, which are often too expensive and thus being updated at a low frequency. Twitter has become a major platform for people to express their opinions on social and political issues. Our work attempts to understand if Twitter data can provide complimentary insights about climate change perceptions. Since the nature of social media is real-time, this data source can especially help us understand how public opinion changes over time in response to climate events and hazards, which though is very difficult to be captured by manual surveys. We use the Twitter Streaming API to collect tweets that contain keywords, "climate change" or "#climatechange". Traditional machine-learning based opinion mining algorithms require a significant amount of labeled data. Data labeling is notoriously time consuming. To address this problem, we use hashtags (a significant feature used to mark topics of tweets) to annotate tweets automatically. For example, hashtags, #climatedenial and #climatescam, are negative opinion labels, while #actonclimate and #climateaction are positive. Following this method, we can obtain a large amount of training data without human labor. This labeled dataset is used to train a deep convolutional neural network that classifies tweets into positive (i.e. believe in climate change) and negative (i.e. do not believe). Based on the positive/negative tweets obtained, we will further analyze risk perceptions and opinions towards policy support. In addition, we analyze twitter user profiles to understand the demographics of proponents and opponents of climate change. Deep learning techniques, especially convolutional deep neural networks, have achieved much success in computer vision. In this work, we propose a convolutional neural network architecture for understanding opinions within text. This method is compared with lexicon-based opinion analysis approaches. Results and the advantages/limitations of this method are to be discussed.

Stock Market Index Data and indicators for Day Trading as a Binary Classification problem.

PubMed

Bruni, Renato

2017-02-01

Classification is the attribution of labels to records according to a criterion automatically learned from a training set of labeled records. This task is needed in a huge number of practical applications, and consequently it has been studied intensively and several classification algorithms are available today. In finance, a stock market index is a measurement of value of a section of the stock market. It is often used to describe the aggregate trend of a market. One basic financial issue would be forecasting this trend. Clearly, such a stochastic value is very difficult to predict. However, technical analysis is a security analysis methodology developed to forecast the direction of prices through the study of past market data. Day trading consists in buying and selling financial instruments within the same trading day. In this case, one interesting problem is the automatic individuation of favorable days for trading. We model this problem as a binary classification problem, and we provide datasets containing daily index values, the corresponding values of a selection of technical indicators, and the class label, which is 1 if the subsequent time period is favorable for day trading and 0 otherwise. These datasets can be used to test the behavior of different approaches in solving the day trading problem.

Aggression as Positive Reinforcement in People with Intellectual Disabilities

ERIC Educational Resources Information Center

May, Michael E.

2011-01-01

From an applied behavior-analytic perspective, aggression in people with intellectual disabilities is mostly maintained by social reinforcement consequences. However, nonsocial consequences have also been identified in functional assessments on aggression. Behaviors producing their own reinforcement have been labeled "automatic" or "nonsocial" in…

Automated Detection of Privacy Sensitive Conditions in C-CDAs: Security Labeling Services at the Department of Veterans Affairs

PubMed Central

Bouhaddou, Omar; Davis, Mike; Donahue, Margaret; Mallia, Anthony; Griffin, Stephania; Teal, Jennifer; Nebeker, Jonathan

2016-01-01

Care coordination across healthcare organizations depends upon health information exchange. Various policies and laws govern permissible exchange, particularly when the information includes privacy sensitive conditions. The Department of Veterans Affairs (VA) privacy policy has required either blanket consent or manual sensitivity review prior to exchanging any health information. The VA experience has been an expensive, administratively demanding burden on staffand Veterans alike, particularly for patients without privacy sensitive conditions. Until recently, automatic sensitivity determination has not been feasible. This paper proposes a policy-driven algorithmic approach (Security Labeling Service or SLS) to health information exchange that automatically detects the presence or absence of specific privacy sensitive conditions and then, to only require a Veteran signed consent for release when actually present. The SLS was applied successfully to a sample of real patient Consolidated-Clinical Document Architecture(C-CDA) documents. The SLS identified standard terminology codes by both parsing structured entries and analyzing textual information using Natural Language Processing (NLP). PMID:28269828

Automated Detection of Privacy Sensitive Conditions in C-CDAs: Security Labeling Services at the Department of Veterans Affairs.

PubMed

Bouhaddou, Omar; Davis, Mike; Donahue, Margaret; Mallia, Anthony; Griffin, Stephania; Teal, Jennifer; Nebeker, Jonathan

2016-01-01

Care coordination across healthcare organizations depends upon health information exchange. Various policies and laws govern permissible exchange, particularly when the information includes privacy sensitive conditions. The Department of Veterans Affairs (VA) privacy policy has required either blanket consent or manual sensitivity review prior to exchanging any health information. The VA experience has been an expensive, administratively demanding burden on staffand Veterans alike, particularly for patients without privacy sensitive conditions. Until recently, automatic sensitivity determination has not been feasible. This paper proposes a policy-driven algorithmic approach (Security Labeling Service or SLS) to health information exchange that automatically detects the presence or absence of specific privacy sensitive conditions and then, to only require a Veteran signed consent for release when actually present. The SLS was applied successfully to a sample of real patient Consolidated-Clinical Document Architecture(C-CDA) documents. The SLS identified standard terminology codes by both parsing structured entries and analyzing textual information using Natural Language Processing (NLP).

Learning without labeling: domain adaptation for ultrasound transducer localization.

PubMed

Heimann, Tobias; Mountney, Peter; John, Matthias; Ionasec, Razvan

2013-01-01

The fusion of image data from trans-esophageal echography (TEE) and X-ray fluoroscopy is attracting increasing interest in minimally-invasive treatment of structural heart disease. In order to calculate the needed transform between both imaging systems, we employ a discriminative learning based approach to localize the TEE transducer in X-ray images. Instead of time-consuming manual labeling, we generate the required training data automatically from a single volumetric image of the transducer. In order to adapt this system to real X-ray data, we use unlabeled fluoroscopy images to estimate differences in feature space density and correct covariate shift by instance weighting. An evaluation on more than 1900 images reveals that our approach reduces detection failures by 95% compared to cross validation on the test set and improves the localization error from 1.5 to 0.8 mm. Due to the automatic generation of training data, the proposed system is highly flexible and can be adapted to any medical device with minimal efforts.

A Graph-Based Recovery and Decomposition of Swanson’s Hypothesis using Semantic Predications

PubMed Central

Cameron, Delroy; Bodenreider, Olivier; Yalamanchili, Hima; Danh, Tu; Vallabhaneni, Sreeram; Thirunarayan, Krishnaprasad; Sheth, Amit P.; Rindflesch, Thomas C.

2014-01-01

Objectives This paper presents a methodology for recovering and decomposing Swanson’s Raynaud Syndrome–Fish Oil Hypothesis semi-automatically. The methodology leverages the semantics of assertions extracted from biomedical literature (called semantic predications) along with structured background knowledge and graph-based algorithms to semi-automatically capture the informative associations originally discovered manually by Swanson. Demonstrating that Swanson’s manually intensive techniques can be undertaken semi-automatically, paves the way for fully automatic semantics-based hypothesis generation from scientific literature. Methods Semantic predications obtained from biomedical literature allow the construction of labeled directed graphs which contain various associations among concepts from the literature. By aggregating such associations into informative subgraphs, some of the relevant details originally articulated by Swanson has been uncovered. However, by leveraging background knowledge to bridge important knowledge gaps in the literature, a methodology for semi-automatically capturing the detailed associations originally explicated in natural language by Swanson has been developed. Results Our methodology not only recovered the 3 associations commonly recognized as Swanson’s Hypothesis, but also decomposed them into an additional 16 detailed associations, formulated as chains of semantic predications. Altogether, 14 out of the 19 associations that can be attributed to Swanson were retrieved using our approach. To the best of our knowledge, such an in-depth recovery and decomposition of Swanson’s Hypothesis has never been attempted. Conclusion In this work therefore, we presented a methodology for semi- automatically recovering and decomposing Swanson’s RS-DFO Hypothesis using semantic representations and graph algorithms. Our methodology provides new insights into potential prerequisites for semantics-driven Literature-Based Discovery (LBD). These suggest that three critical aspects of LBD include: 1) the need for more expressive representations beyond Swanson’s ABC model; 2) an ability to accurately extract semantic information from text; and 3) the semantic integration of scientific literature with structured background knowledge. PMID:23026233

Using Open Geographic Data to Generate Natural Language Descriptions for Hydrological Sensor Networks.

PubMed

Molina, Martin; Sanchez-Soriano, Javier; Corcho, Oscar

2015-07-03

Providing descriptions of isolated sensors and sensor networks in natural language, understandable by the general public, is useful to help users find relevant sensors and analyze sensor data. In this paper, we discuss the feasibility of using geographic knowledge from public databases available on the Web (such as OpenStreetMap, Geonames, or DBpedia) to automatically construct such descriptions. We present a general method that uses such information to generate sensor descriptions in natural language. The results of the evaluation of our method in a hydrologic national sensor network showed that this approach is feasible and capable of generating adequate sensor descriptions with a lower development effort compared to other approaches. In the paper we also analyze certain problems that we found in public databases (e.g., heterogeneity, non-standard use of labels, or rigid search methods) and their impact in the generation of sensor descriptions.

Programmable Regulation of DNA Conjugation to Gold Nanoparticles via Strand Displacement.

PubMed

Zhang, Cheng; Wu, Ranfeng; Li, Yifan; Zhang, Qiang; Yang, Jing

2017-10-31

Methods for conjugating DNA to gold nanoparticles (AuNPs) have recently attracted considerable attention. The ability to control such conjugation in a programmable way is of great interest. Here, we have developed a logic-based method for manipulating the conjugation of thiolated DNA species to AuNPs via cascading DNA strand displacement. Using this method, several logic-based operation systems are established and up to three kinds of DNA signals are introduced at the same time. In addition, a more sensitive catalytic logic-based operation is also achieved based on an entropy-driven process. In the experiment, all of the DNA/AuNPs conjugation results are verified by agrose gel. This strategy promises great potential for automatically conjugating DNA stands onto label-free gold nanoparticles and can be extended to constructing DNA/nanoparticle devices for applications in diagnostics, biosensing, and molecular robotics.

Using Open Geographic Data to Generate Natural Language Descriptions for Hydrological Sensor Networks

PubMed Central

Molina, Martin; Sanchez-Soriano, Javier; Corcho, Oscar

2015-01-01

Providing descriptions of isolated sensors and sensor networks in natural language, understandable by the general public, is useful to help users find relevant sensors and analyze sensor data. In this paper, we discuss the feasibility of using geographic knowledge from public databases available on the Web (such as OpenStreetMap, Geonames, or DBpedia) to automatically construct such descriptions. We present a general method that uses such information to generate sensor descriptions in natural language. The results of the evaluation of our method in a hydrologic national sensor network showed that this approach is feasible and capable of generating adequate sensor descriptions with a lower development effort compared to other approaches. In the paper we also analyze certain problems that we found in public databases (e.g., heterogeneity, non-standard use of labels, or rigid search methods) and their impact in the generation of sensor descriptions. PMID:26151211

A stacked sequential learning method for investigator name recognition from web-based medical articles

NASA Astrophysics Data System (ADS)

Zhang, Xiaoli; Zou, Jie; Le, Daniel X.; Thoma, George

2010-01-01

"Investigator Names" is a newly required field in MEDLINE citations. It consists of personal names listed as members of corporate organizations in an article. Extracting investigator names automatically is necessary because of the increasing volume of articles reporting collaborative biomedical research in which a large number of investigators participate. In this paper, we present an SVM-based stacked sequential learning method in a novel application - recognizing named entities such as the first and last names of investigators from online medical journal articles. Stacked sequential learning is a meta-learning algorithm which can boost any base learner. It exploits contextual information by adding the predicted labels of the surrounding tokens as features. We apply this method to tag words in text paragraphs containing investigator names, and demonstrate that stacked sequential learning improves the performance of a nonsequential base learner such as an SVM classifier.

Poster — Thur Eve — 70: Automatic lung bronchial and vessel bifurcations detection algorithm for deformable image registration assessment

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

Labine, Alexandre; Carrier, Jean-François; Bedwani, Stéphane

2014-08-15

Purpose: To investigate an automatic bronchial and vessel bifurcations detection algorithm for deformable image registration (DIR) assessment to improve lung cancer radiation treatment. Methods: 4DCT datasets were acquired and exported to Varian treatment planning system (TPS) EclipseTM for contouring. The lungs TPS contour was used as the prior shape for a segmentation algorithm based on hierarchical surface deformation that identifies the deformed lungs volumes of the 10 breathing phases. Hounsfield unit (HU) threshold filter was applied within the segmented lung volumes to identify blood vessels and airways. Segmented blood vessels and airways were skeletonised using a hierarchical curve-skeleton algorithm basedmore » on a generalized potential field approach. A graph representation of the computed skeleton was generated to assign one of three labels to each node: the termination node, the continuation node or the branching node. Results: 320 ± 51 bifurcations were detected in the right lung of a patient for the 10 breathing phases. The bifurcations were visually analyzed. 92 ± 10 bifurcations were found in the upper half of the lung and 228 ± 45 bifurcations were found in the lower half of the lung. Discrepancies between ten vessel trees were mainly ascribed to large deformation and in regions where the HU varies. Conclusions: We established an automatic method for DIR assessment using the morphological information of the patient anatomy. This approach allows a description of the lung's internal structure movement, which is needed to validate the DIR deformation fields for accurate 4D cancer treatment planning.« less

SAR image segmentation using skeleton-based fuzzy clustering

NASA Astrophysics Data System (ADS)

Cao, Yun Yi; Chen, Yan Qiu

2003-06-01

SAR image segmentation can be converted to a clustering problem in which pixels or small patches are grouped together based on local feature information. In this paper, we present a novel framework for segmentation. The segmentation goal is achieved by unsupervised clustering upon characteristic descriptors extracted from local patches. The mixture model of characteristic descriptor, which combines intensity and texture feature, is investigated. The unsupervised algorithm is derived from the recently proposed Skeleton-Based Data Labeling method. Skeletons are constructed as prototypes of clusters to represent arbitrary latent structures in image data. Segmentation using Skeleton-Based Fuzzy Clustering is able to detect the types of surfaces appeared in SAR images automatically without any user input.

Real-time ultrasound transducer localization in fluoroscopy images by transfer learning from synthetic training data.

PubMed

Heimann, Tobias; Mountney, Peter; John, Matthias; Ionasec, Razvan

2014-12-01

The fusion of image data from trans-esophageal echography (TEE) and X-ray fluoroscopy is attracting increasing interest in minimally-invasive treatment of structural heart disease. In order to calculate the needed transformation between both imaging systems, we employ a discriminative learning (DL) based approach to localize the TEE transducer in X-ray images. The successful application of DL methods is strongly dependent on the available training data, which entails three challenges: (1) the transducer can move with six degrees of freedom meaning it requires a large number of images to represent its appearance, (2) manual labeling is time consuming, and (3) manual labeling has inherent errors. This paper proposes to generate the required training data automatically from a single volumetric image of the transducer. In order to adapt this system to real X-ray data, we use unlabeled fluoroscopy images to estimate differences in feature space density and correct covariate shift by instance weighting. Two approaches for instance weighting, probabilistic classification and Kullback-Leibler importance estimation (KLIEP), are evaluated for different stages of the proposed DL pipeline. An analysis on more than 1900 images reveals that our approach reduces detection failures from 7.3% in cross validation on the test set to zero and improves the localization error from 1.5 to 0.8mm. Due to the automatic generation of training data, the proposed system is highly flexible and can be adapted to any medical device with minimal efforts. Copyright © 2014 Elsevier B.V. All rights reserved.

16 CFR Appendix A1 to Part 305 - Refrigerators With Automatic Defrost

Code of Federal Regulations, 2010 CFR

2010-01-01

... CONGRESS RULE CONCERNING DISCLOSURES REGARDING ENERGY CONSUMPTION AND WATER USE OF CERTAIN HOME APPLIANCES AND OTHER PRODUCTS REQUIRED UNDER THE ENERGY POLICY AND CONSERVATION ACT (âAPPLIANCE LABELING RULEâ... (*) No data submitted for units meeting the Department of Energy's Energy Conservation Standards...

16 CFR Appendix B2 to Part 305 - Upright Freezers With Automatic Defrost

Code of Federal Regulations, 2012 CFR

2012-01-01

... CONGRESS RULE CONCERNING DISCLOSURES REGARDING ENERGY CONSUMPTION AND WATER USE OF CERTAIN HOME APPLIANCES AND OTHER PRODUCTS REQUIRED UNDER THE ENERGY POLICY AND CONSERVATION ACT (âAPPLIANCE LABELING RULEâ... (*) (*) (*) No data submitted for units meeting the Department of Energy's Energy Conservation Standards...

16 CFR Appendix A1 to Part 305 - Refrigerators With Automatic Defrost

Code of Federal Regulations, 2012 CFR

2012-01-01

... CONGRESS RULE CONCERNING DISCLOSURES REGARDING ENERGY CONSUMPTION AND WATER USE OF CERTAIN HOME APPLIANCES AND OTHER PRODUCTS REQUIRED UNDER THE ENERGY POLICY AND CONSERVATION ACT (âAPPLIANCE LABELING RULEâ... (*) No data submitted for units meeting the Department of Energy's Energy Conservation Standards...

16 CFR Appendix A1 to Part 305 - Refrigerators With Automatic Defrost

Code of Federal Regulations, 2011 CFR

2011-01-01

... CONGRESS RULE CONCERNING DISCLOSURES REGARDING ENERGY CONSUMPTION AND WATER USE OF CERTAIN HOME APPLIANCES AND OTHER PRODUCTS REQUIRED UNDER THE ENERGY POLICY AND CONSERVATION ACT (âAPPLIANCE LABELING RULEâ... (*) No data submitted for units meeting the Department of Energy's Energy Conservation Standards...

16 CFR Appendix B2 to Part 305 - Upright Freezers With Automatic Defrost

Code of Federal Regulations, 2013 CFR

2013-01-01

... CONGRESS RULE CONCERNING DISCLOSURES REGARDING ENERGY CONSUMPTION AND WATER USE OF CERTAIN HOME APPLIANCES AND OTHER PRODUCTS REQUIRED UNDER THE ENERGY POLICY AND CONSERVATION ACT (âAPPLIANCE LABELING RULEâ... (*) (*) (*) No data submitted for units meeting the Department of Energy's Energy Conservation Standards...

16 CFR Appendix B2 to Part 305 - Upright Freezers With Automatic Defrost

Code of Federal Regulations, 2011 CFR

2011-01-01

... CONGRESS RULE CONCERNING DISCLOSURES REGARDING ENERGY CONSUMPTION AND WATER USE OF CERTAIN HOME APPLIANCES AND OTHER PRODUCTS REQUIRED UNDER THE ENERGY POLICY AND CONSERVATION ACT (âAPPLIANCE LABELING RULEâ... (*) (*) (*) No data submitted for units meeting the Department of Energy's Energy Conservation Standards...

16 CFR Appendix A1 to Part 305 - Refrigerators With Automatic Defrost

Code of Federal Regulations, 2013 CFR

2013-01-01

... CONGRESS RULE CONCERNING DISCLOSURES REGARDING ENERGY CONSUMPTION AND WATER USE OF CERTAIN HOME APPLIANCES AND OTHER PRODUCTS REQUIRED UNDER THE ENERGY POLICY AND CONSERVATION ACT (âAPPLIANCE LABELING RULEâ... (*) No data submitted for units meeting the Department of Energy's Energy Conservation Standards...

16 CFR Appendix B2 to Part 305 - Upright Freezers With Automatic Defrost

Code of Federal Regulations, 2010 CFR

2010-01-01

... CONGRESS RULE CONCERNING DISCLOSURES REGARDING ENERGY CONSUMPTION AND WATER USE OF CERTAIN HOME APPLIANCES AND OTHER PRODUCTS REQUIRED UNDER THE ENERGY POLICY AND CONSERVATION ACT (âAPPLIANCE LABELING RULEâ... (*) (*) (*) No data submitted for units meeting the Department of Energy's Energy Conservation Standards...

GO-PCA: An Unsupervised Method to Explore Gene Expression Data Using Prior Knowledge.

PubMed

Wagner, Florian

2015-01-01

Genome-wide expression profiling is a widely used approach for characterizing heterogeneous populations of cells, tissues, biopsies, or other biological specimen. The exploratory analysis of such data typically relies on generic unsupervised methods, e.g. principal component analysis (PCA) or hierarchical clustering. However, generic methods fail to exploit prior knowledge about the molecular functions of genes. Here, I introduce GO-PCA, an unsupervised method that combines PCA with nonparametric GO enrichment analysis, in order to systematically search for sets of genes that are both strongly correlated and closely functionally related. These gene sets are then used to automatically generate expression signatures with functional labels, which collectively aim to provide a readily interpretable representation of biologically relevant similarities and differences. The robustness of the results obtained can be assessed by bootstrapping. I first applied GO-PCA to datasets containing diverse hematopoietic cell types from human and mouse, respectively. In both cases, GO-PCA generated a small number of signatures that represented the majority of lineages present, and whose labels reflected their respective biological characteristics. I then applied GO-PCA to human glioblastoma (GBM) data, and recovered signatures associated with four out of five previously defined GBM subtypes. My results demonstrate that GO-PCA is a powerful and versatile exploratory method that reduces an expression matrix containing thousands of genes to a much smaller set of interpretable signatures. In this way, GO-PCA aims to facilitate hypothesis generation, design of further analyses, and functional comparisons across datasets.

A segmentation and classification scheme for single tooth in MicroCT images based on 3D level set and k-means+.

PubMed

Wang, Liansheng; Li, Shusheng; Chen, Rongzhen; Liu, Sze-Yu; Chen, Jyh-Cheng

2017-04-01

Accurate classification of different anatomical structures of teeth from medical images provides crucial information for the stress analysis in dentistry. Usually, the anatomical structures of teeth are manually labeled by experienced clinical doctors, which is time consuming. However, automatic segmentation and classification is a challenging task because the anatomical structures and surroundings of the tooth in medical images are rather complex. Therefore, in this paper, we propose an effective framework which is designed to segment the tooth with a Selective Binary and Gaussian Filtering Regularized Level Set (GFRLS) method improved by fully utilizing 3 dimensional (3D) information, and classify the tooth by employing unsupervised learning i.e., k-means++ method. In order to evaluate the proposed method, the experiments are conducted on the sufficient and extensive datasets of mandibular molars. The experimental results show that our method can achieve higher accuracy and robustness compared to other three clustering methods. Copyright © 2016 Elsevier Ltd. All rights reserved.

Automatic segmentation of multimodal brain tumor images based on classification of super-voxels.

PubMed

Kadkhodaei, M; Samavi, S; Karimi, N; Mohaghegh, H; Soroushmehr, S M R; Ward, K; All, A; Najarian, K

2016-08-01

Despite the rapid growth in brain tumor segmentation approaches, there are still many challenges in this field. Automatic segmentation of brain images has a critical role in decreasing the burden of manual labeling and increasing robustness of brain tumor diagnosis. We consider segmentation of glioma tumors, which have a wide variation in size, shape and appearance properties. In this paper images are enhanced and normalized to same scale in a preprocessing step. The enhanced images are then segmented based on their intensities using 3D super-voxels. Usually in images a tumor region can be regarded as a salient object. Inspired by this observation, we propose a new feature which uses a saliency detection algorithm. An edge-aware filtering technique is employed to align edges of the original image to the saliency map which enhances the boundaries of the tumor. Then, for classification of tumors in brain images, a set of robust texture features are extracted from super-voxels. Experimental results indicate that our proposed method outperforms a comparable state-of-the-art algorithm in term of dice score.

An approach for automatic classification of grouper vocalizations with passive acoustic monitoring.

PubMed

Ibrahim, Ali K; Chérubin, Laurent M; Zhuang, Hanqi; Schärer Umpierre, Michelle T; Dalgleish, Fraser; Erdol, Nurgun; Ouyang, B; Dalgleish, A

2018-02-01

Grouper, a family of marine fishes, produce distinct vocalizations associated with their reproductive behavior during spawning aggregation. These low frequencies sounds (50-350 Hz) consist of a series of pulses repeated at a variable rate. In this paper, an approach is presented for automatic classification of grouper vocalizations from ambient sounds recorded in situ with fixed hydrophones based on weighted features and sparse classifier. Group sounds were labeled initially by humans for training and testing various feature extraction and classification methods. In the feature extraction phase, four types of features were used to extract features of sounds produced by groupers. Once the sound features were extracted, three types of representative classifiers were applied to categorize the species that produced these sounds. Experimental results showed that the overall percentage of identification using the best combination of the selected feature extractor weighted mel frequency cepstral coefficients and sparse classifier achieved 82.7% accuracy. The proposed algorithm has been implemented in an autonomous platform (wave glider) for real-time detection and classification of group vocalizations.

Automatic coronary calcium scoring using noncontrast and contrast CT images

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

Yang, Guanyu, E-mail: yang.list@seu.edu.cn; Chen, Yang; Shu, Huazhong

Purpose: Calcium scoring is widely used to assess the risk of coronary heart disease (CHD). Accurate coronary artery calcification detection in noncontrast CT image is a prerequisite step for coronary calcium scoring. Currently, calcified lesions in the coronary arteries are manually identified by radiologists in clinical practice. Thus, in this paper, a fully automatic calcium scoring method was developed to alleviate the work load of the radiologists or cardiologists. Methods: The challenge of automatic coronary calcification detection is to discriminate the calcification in the coronary arteries from the calcification in the other tissues. Since the anatomy of coronary arteries ismore » difficult to be observed in the noncontrast CT images, the contrast CT image of the same patient is used to extract the regions of the aorta, heart, and coronary arteries. Then, a patient-specific region-of-interest (ROI) is generated in the noncontrast CT image according to the segmentation results in the contrast CT image. This patient-specific ROI focuses on the regions in the neighborhood of coronary arteries for calcification detection, which can eliminate the calcifications in the surrounding tissues. A support vector machine classifier is applied finally to refine the results by removing possible image noise. Furthermore, the calcified lesions in the noncontrast images belonging to the different main coronary arteries are identified automatically using the labeling results of the extracted coronary arteries. Results: Forty datasets from four different CT machine vendors were used to evaluate their algorithm, which were provided by the MICCAI 2014 Coronary Calcium Scoring (orCaScore) Challenge. The sensitivity and positive predictive value for the volume of detected calcifications are 0.989 and 0.948. Only one patient out of 40 patients had been assigned to the wrong risk category defined according to Agatston scores (0, 1–100, 101–300, >300) by comparing with the ground truth. Conclusions: The calcified lesions in the noncontrast CT images can be detected automatically by using the segmentation results of the aorta, heart, and coronary arteries obtained in the contrast CT images with a very high accuracy.« less

Automatic estimation of voice onset time for word-initial stops by applying random forest to onset detection.

PubMed

Lin, Chi-Yueh; Wang, Hsiao-Chuan

2011-07-01

The voice onset time (VOT) of a stop consonant is the interval between its burst onset and voicing onset. Among a variety of research topics on VOT, one that has been studied for years is how VOTs are efficiently measured. Manual annotation is a feasible way, but it becomes a time-consuming task when the corpus size is large. This paper proposes an automatic VOT estimation method based on an onset detection algorithm. At first, a forced alignment is applied to identify the locations of stop consonants. Then a random forest based onset detector searches each stop segment for its burst and voicing onsets to estimate a VOT. The proposed onset detection can detect the onsets in an efficient and accurate manner with only a small amount of training data. The evaluation data extracted from the TIMIT corpus were 2344 words with a word-initial stop. The experimental results showed that 83.4% of the estimations deviate less than 10 ms from their manually labeled values, and 96.5% of the estimations deviate by less than 20 ms. Some factors that influence the proposed estimation method, such as place of articulation, voicing of a stop consonant, and quality of succeeding vowel, were also investigated. © 2011 Acoustical Society of America

Epsilon-Q: An Automated Analyzer Interface for Mass Spectral Library Search and Label-Free Protein Quantification.

PubMed

Cho, Jin-Young; Lee, Hyoung-Joo; Jeong, Seul-Ki; Paik, Young-Ki

2017-12-01

Mass spectrometry (MS) is a widely used proteome analysis tool for biomedical science. In an MS-based bottom-up proteomic approach to protein identification, sequence database (DB) searching has been routinely used because of its simplicity and convenience. However, searching a sequence DB with multiple variable modification options can increase processing time, false-positive errors in large and complicated MS data sets. Spectral library searching is an alternative solution, avoiding the limitations of sequence DB searching and allowing the detection of more peptides with high sensitivity. Unfortunately, this technique has less proteome coverage, resulting in limitations in the detection of novel and whole peptide sequences in biological samples. To solve these problems, we previously developed the "Combo-Spec Search" method, which uses manually multiple references and simulated spectral library searching to analyze whole proteomes in a biological sample. In this study, we have developed a new analytical interface tool called "Epsilon-Q" to enhance the functions of both the Combo-Spec Search method and label-free protein quantification. Epsilon-Q performs automatically multiple spectral library searching, class-specific false-discovery rate control, and result integration. It has a user-friendly graphical interface and demonstrates good performance in identifying and quantifying proteins by supporting standard MS data formats and spectrum-to-spectrum matching powered by SpectraST. Furthermore, when the Epsilon-Q interface is combined with the Combo-Spec search method, called the Epsilon-Q system, it shows a synergistic function by outperforming other sequence DB search engines for identifying and quantifying low-abundance proteins in biological samples. The Epsilon-Q system can be a versatile tool for comparative proteome analysis based on multiple spectral libraries and label-free quantification.

Automatic Stem Cell Detection in Microscopic Whole Mouse Cryo-imaging

PubMed Central

Wuttisarnwattana, Patiwet; Gargesha, Madhusudhana; Hof, Wouter van’t; Cooke, Kenneth R.

2016-01-01

With its single cell sensitivity over volumes as large as or larger than a mouse, cryo-imaging enables imaging of stem cell biodistribution, homing, engraftment, and molecular mechanisms. We developed and evaluated a highly automated software tool to detect fluorescently labeled stem cells within very large (~200GB) cryo-imaging datasets. Cell detection steps are: preprocess, remove immaterial regions, spatially filter to create features, identify candidate pixels, classify pixels using bagging decision trees, segment cell patches, and perform 3D labeling. There are options for analysis and visualization. To train the classifier, we created synthetic images by placing realistic digital cell models onto cryo-images of control mice devoid of cells. Very good cell detection results were (precision=98.49%, recall=99.97%) for synthetic cryo-images, (precision=97.81%, recall=97.71%) for manually evaluated, actual cryo-images, and <1% false positives in control mice. An α-multiplier applied to features allows one to correct for experimental variations in cell brightness due to labeling. On dim cells (37% of standard brightness), with correction, we improved recall (49.26%→99.36%) without a significant drop in precision (99.99%→99.75%). With tail vein injection, multipotent adult progenitor cells in a graft-versus-host-disease model in the first days post injection were predominantly found in lung, liver, spleen, and bone marrow. Distribution was not simply related to blood flow. The lung contained clusters of cells while other tissues contained single cells. Our methods provided stem cell distribution anywhere in mouse with single cell sensitivity. Methods should provide a rational means of evaluating dosing, delivery methods, cell enhancements, and mechanisms for therapeutic cells. PMID:26552080

A Kalman filtering framework for physiological detection of anxiety-related arousal in children with autism spectrum disorder.

PubMed

Kushki, Azadeh; Khan, Ajmal; Brian, Jessica; Anagnostou, Evdokia

2015-03-01

Anxiety is associated with physiological changes that can be noninvasively measured using inexpensive and wearable sensors. These changes provide an objective and language-free measure of arousal associated with anxiety, which can complement treatment programs for clinical populations who have difficulty with introspection, communication, and emotion recognition. This motivates the development of automatic methods for detection of anxiety-related arousal using physiology signals. While several supervised learning methods have been proposed for this purpose, these methods require regular collection and updating of training data and are, therefore, not suitable for clinical populations, where obtaining labelled data may be challenging due to impairments in communication and introspection. In this context, the objective of this paper is to develop an unsupervised and real-time arousal detection algorithm. We propose a learning framework based on the Kalman filtering theory for detection of physiological arousal based on cardiac activity. The performance of the system was evaluated on data obtained from a sample of children with autism spectrum disorder. The results indicate that the system can detect anxiety-related arousal in these children with sensitivity and specificity of 99% and 92%, respectively. Our results show that the proposed method can detect physiological arousal associated with anxiety with high accuracy, providing support for technical feasibility of augmenting anxiety treatments with automatic detection techniques. This approach can ultimately lead to more effective anxiety treatment for a larger and more diverse population.

Robust multiple cue fusion-based high-speed and nonrigid object tracking algorithm for short track speed skating

NASA Astrophysics Data System (ADS)

Liu, Chenguang; Cheng, Heng-Da; Zhang, Yingtao; Wang, Yuxuan; Xian, Min

2016-01-01

This paper presents a methodology for tracking multiple skaters in short track speed skating competitions. Nonrigid skaters move at high speed with severe occlusions happening frequently among them. The camera is panned quickly in order to capture the skaters in a large and dynamic scene. To automatically track the skaters and precisely output their trajectories becomes a challenging task in object tracking. We employ the global rink information to compensate camera motion and obtain the global spatial information of skaters, utilize random forest to fuse multiple cues and predict the blob of each skater, and finally apply a silhouette- and edge-based template-matching and blob-evolving method to labelling pixels to a skater. The effectiveness and robustness of the proposed method are verified through thorough experiments.

Acetanilide 4-hydroxylase and acetanilide 2-hydroxylase activity in hepatic microsomes from induced mice.

PubMed

Lewandowski, M; Chui, Y C; Levi, P; Hodgson, E

1991-02-01

A simple and sensitive method for the separation of 14C-labelled acetanilide, 4-hydroxyacetanilide, 3-hydroxyacetanilide and 2-hydroxyacetanilide was developed using thin-layer chromatography. This separation is the basis for the assay of acetanilide 4-hydroxylase and acetanilide 2-hydroxylase activity in liver microsomes from DBA2/N male mice that had been treated with phenobarbital, 3-methylcholanthrene, isosafrole or n-butylbenzodioxole. Microsomes were incubated with [14C]acetanilide and extracted with benzene and ethyl acetate. The extract was applied to silica gel plates and developed with a hexane/isopropanol/ammonium hydroxide/water solvent system. The radiolabelled phenolic metabolites and the parent compound were detected using a Berthold Automatic TLC Linear Analyzer. Although the 4-hydroxylated metabolite was the primary product detected, this method can be used to detect other phenolic metabolites.

Food labels promote healthy choices by a decision bias in the amygdala.

PubMed

Grabenhorst, Fabian; Schulte, Frank P; Maderwald, Stefan; Brand, Matthias

2013-07-01

Food labeling is the major health policy strategy to counter rising obesity rates. Based on traditional economic theory, such strategies assume that detailed nutritional information will necessarily help individuals make better, healthier choices. However, in contrast to the well-known utility of labels in food marketing, evidence for the efficacy of nutritional labeling is mixed. Psychological and behavioral economic theories suggest that successful marketing strategies activate automatic decision biases and emotions, which involve implicit emotional brain systems. Accordingly, simple, intuitive food labels that engage these neural systems could represent a promising approach for promoting healthier choices. Here we used functional MRI to investigate this possibility. Healthy, mildly hungry subjects performed a food evaluation task and a food choice task. The main experimental manipulation was to pair identical foods with simple labels that emphasized either taste benefits or health-related food properties. We found that such labels biased food evaluations in the amygdala, a core emotional brain system. When labels biased the amygdala's evaluations towards health-related food properties, the strength of this bias predicted behavioral shifts towards healthier choices. At the time of decision-making, amygdala activity encoded key decision variables, potentially reflecting active amygdala participation in food choice. Our findings underscore the potential utility of food labeling in health policy and indicate a principal role for emotional brain systems when labels guide food choices. Copyright © 2013 Elsevier Inc. All rights reserved.

Dual-process theory and consumer response to front-of-package nutrition label formats.

PubMed

Sanjari, S Setareh; Jahn, Steffen; Boztug, Yasemin

2017-11-01

Nutrition labeling literature yields fragmented results about the effect of front-of-package (FOP) nutrition label formats on healthy food choice. Specifically, it is unclear which type of nutrition label format is effective across different shopping situations. To address this gap, the present review investigates the available nutrition labeling literature through the prism of dual-process theory, which posits that decisions are made either quickly and automatically (system 1) or slowly and deliberately (system 2). A systematically performed review of nutrition labeling literature returned 59 papers that provide findings that can be explained according to dual-process theory. The findings of these studies suggest that the effectiveness of nutrition label formats is influenced by the consumer's dominant processing system, which is a function of specific contexts and personal variables (eg, motivation, nutrition knowledge, time pressure, and depletion). Examination of reported findings through a situational processing perspective reveals that consumers might prefer different FOP nutrition label formats in different situations and can exhibit varying responses to the same label format across situations. This review offers several suggestions for policy makers and researchers to help improve current FOP nutrition label formats. © The Author(s) 2017. Published by Oxford University Press on behalf of the International Life Sciences Institute. All rights reserved. For Permissions, please e-mail: journals.permissions@oup.com.

Size-based cell sorting with a resistive pulse sensor and an electromagnetic pump in a microfluidic chip.

PubMed

Song, Yongxin; Li, Mengqi; Pan, Xinxiang; Wang, Qi; Li, Dongqing

2015-02-01

An electrokinetic microfluidic chip is developed to detect and sort target cells by size from human blood samples. Target-cell detection is achieved by a differential resistive pulse sensor (RPS) based on the size difference between the target cell and other cells. Once a target cell is detected, the detected RPS signal will automatically actuate an electromagnetic pump built in a microchannel to push the target cell into a collecting channel. This method was applied to automatically detect and sort A549 cells and T-lymphocytes from a peripheral fingertip blood sample. The viability of A549 cells sorted in the collecting well was verified by Hoechst33342 and propidium iodide staining. The results show that as many as 100 target cells per minute can be sorted out from the sample solution and thus is particularly suitable for sorting very rare target cells, such as circulating tumor cells. The actuation of the electromagnetic valve has no influence on RPS cell detection and the consequent cell-sorting process. The viability of the collected A549 cell is not impacted by the applied electric field when the cell passes the RPS detection area. The device described in this article is simple, automatic, and label-free and has wide applications in size-based rare target cell sorting for medical diagnostics. © 2014 WILEY-VCH Verlag GmbH & Co. KGaA, Weinheim.

Automatic segmentation of brain MRIs and mapping neuroanatomy across the human lifespan

NASA Astrophysics Data System (ADS)

Keihaninejad, Shiva; Heckemann, Rolf A.; Gousias, Ioannis S.; Rueckert, Daniel; Aljabar, Paul; Hajnal, Joseph V.; Hammers, Alexander

2009-02-01

A robust model for the automatic segmentation of human brain images into anatomically defined regions across the human lifespan would be highly desirable, but such structural segmentations of brain MRI are challenging due to age-related changes. We have developed a new method, based on established algorithms for automatic segmentation of young adults' brains. We used prior information from 30 anatomical atlases, which had been manually segmented into 83 anatomical structures. Target MRIs came from 80 subjects (~12 individuals/decade) from 20 to 90 years, with equal numbers of men, women; data from two different scanners (1.5T, 3T), using the IXI database. Each of the adult atlases was registered to each target MR image. By using additional information from segmentation into tissue classes (GM, WM and CSF) to initialise the warping based on label consistency similarity before feeding this into the previous normalised mutual information non-rigid registration, the registration became robust enough to accommodate atrophy and ventricular enlargement with age. The final segmentation was obtained by combination of the 30 propagated atlases using decision fusion. Kernel smoothing was used for modelling the structural volume changes with aging. Example linear correlation coefficients with age were, for lateral ventricular volume, rmale=0.76, rfemale=0.58 and, for hippocampal volume, rmale=-0.6, rfemale=-0.4 (allρ<0.01).

Automatic falx cerebri and tentorium cerebelli segmentation from magnetic resonance images

NASA Astrophysics Data System (ADS)

Glaister, Jeffrey; Carass, Aaron; Pham, Dzung L.; Butman, John A.; Prince, Jerry L.

2017-03-01

The falx cerebri and tentorium cerebelli are dural structures found in the brain. Due to the roles both structures play in constraining brain motion, the falx and tentorium must be identified and included in finite element models of the head to accurately predict brain dynamics during injury events. To date there has been very little research work on automatically segmenting these two structures, which is understandable given that their 1) thin structure challenges the resolution limits of in vivo 3D imaging, and 2) contrast with respect to surrounding tissue is low in standard magnetic resonance imaging. An automatic segmentation algorithm to find the falx and tentorium which uses the results of a multi-atlas segmentation and cortical reconstruction algorithm is proposed. Gray matter labels are used to find the location of the falx and tentorium. The proposed algorithm is applied to five datasets with manual delineations. 3D visualizations of the final results are provided, and Hausdorff distance (HD) and mean surface distance (MSD) is calculated to quantify the accuracy of the proposed method. For the falx, the mean HD is 43.84 voxels and the mean MSD is 2.78 voxels, with the largest errors occurring at the frontal inferior falx boundary. For the tentorium, the mean HD is 14.50 voxels and mean MSD is 1.38 voxels.

Automatic falx cerebri and tentorium cerebelli segmentation from Magnetic Resonance Images.

PubMed

Glaister, Jeffrey; Carass, Aaron; Pham, Dzung L; Butman, John A; Prince, Jerry L

2017-02-01

The falx cerebri and tentorium cerebelli are dural structures found in the brain. Due to the roles both structures play in constraining brain motion, the falx and tentorium must be identified and included in finite element models of the head to accurately predict brain dynamics during injury events. To date there has been very little research work on automatically segmenting these two structures, which is understandable given that their 1) thin structure challenges the resolution limits of in vivo 3D imaging, and 2) contrast with respect to surrounding tissue is low in standard magnetic resonance imaging. An automatic segmentation algorithm to find the falx and tentorium which uses the results of a multi-atlas segmentation and cortical reconstruction algorithm is proposed. Gray matter labels are used to find the location of the falx and tentorium. The proposed algorithm is applied to five datasets with manual delineations. 3D visualizations of the final results are provided, and Hausdorff distance (HD) and mean surface distance (MSD) is calculated to quantify the accuracy of the proposed method. For the falx, the mean HD is 43.84 voxels and the mean MSD is 2.78 voxels, with the largest errors occurring at the frontal inferior falx boundary. For the tentorium, the mean HD is 14.50 voxels and mean MSD is 1.38 voxels.

Exploiting the potential of unlabeled endoscopic video data with self-supervised learning.

PubMed

Ross, Tobias; Zimmerer, David; Vemuri, Anant; Isensee, Fabian; Wiesenfarth, Manuel; Bodenstedt, Sebastian; Both, Fabian; Kessler, Philip; Wagner, Martin; Müller, Beat; Kenngott, Hannes; Speidel, Stefanie; Kopp-Schneider, Annette; Maier-Hein, Klaus; Maier-Hein, Lena

2018-06-01

Surgical data science is a new research field that aims to observe all aspects of the patient treatment process in order to provide the right assistance at the right time. Due to the breakthrough successes of deep learning-based solutions for automatic image annotation, the availability of reference annotations for algorithm training is becoming a major bottleneck in the field. The purpose of this paper was to investigate the concept of self-supervised learning to address this issue. Our approach is guided by the hypothesis that unlabeled video data can be used to learn a representation of the target domain that boosts the performance of state-of-the-art machine learning algorithms when used for pre-training. Core of the method is an auxiliary task based on raw endoscopic video data of the target domain that is used to initialize the convolutional neural network (CNN) for the target task. In this paper, we propose the re-colorization of medical images with a conditional generative adversarial network (cGAN)-based architecture as auxiliary task. A variant of the method involves a second pre-training step based on labeled data for the target task from a related domain. We validate both variants using medical instrument segmentation as target task. The proposed approach can be used to radically reduce the manual annotation effort involved in training CNNs. Compared to the baseline approach of generating annotated data from scratch, our method decreases exploratively the number of labeled images by up to 75% without sacrificing performance. Our method also outperforms alternative methods for CNN pre-training, such as pre-training on publicly available non-medical (COCO) or medical data (MICCAI EndoVis2017 challenge) using the target task (in this instance: segmentation). As it makes efficient use of available (non-)public and (un-)labeled data, the approach has the potential to become a valuable tool for CNN (pre-)training.

Use of a systematic risk analysis method to improve safety in the production of paediatric parenteral nutrition solutions.

PubMed

Bonnabry, P; Cingria, L; Sadeghipour, F; Ing, H; Fonzo-Christe, C; Pfister, R E

2005-04-01

Until recently, the preparation of paediatric parenteral nutrition formulations in our institution included re-transcription and manual compounding of the mixture. Although no significant clinical problems have occurred, re-engineering of this high risk activity was undertaken to improve its safety. Several changes have been implemented including new prescription software, direct recording on a server, automatic printing of the labels, and creation of a file used to pilot a BAXA MM 12 automatic compounder. The objectives of this study were to compare the risks associated with the old and new processes, to quantify the improved safety with the new process, and to identify the major residual risks. A failure modes, effects, and criticality analysis (FMECA) was performed by a multidisciplinary team. A cause-effect diagram was built, the failure modes were defined, and the criticality index (CI) was determined for each of them on the basis of the likelihood of occurrence, the severity of the potential effect, and the detection probability. The CIs for each failure mode were compared for the old and new processes and the risk reduction was quantified. The sum of the CIs of all 18 identified failure modes was 3415 for the old process and 1397 for the new (reduction of 59%). The new process reduced the CIs of the different failure modes by a mean factor of 7. The CI was smaller with the new process for 15 failure modes, unchanged for two, and slightly increased for one. The greatest reduction (by a factor of 36) concerned re-transcription errors, followed by readability problems (by a factor of 30) and chemical cross contamination (by a factor of 10). The most critical steps in the new process were labelling mistakes (CI 315, maximum 810), failure to detect a dosage or product mistake (CI 288), failure to detect a typing error during the prescription (CI 175), and microbial contamination (CI 126). Modification of the process resulted in a significant risk reduction as shown by risk analysis. Residual failure opportunities were also quantified, allowing additional actions to be taken to reduce the risk of labelling mistakes. This study illustrates the usefulness of prospective risk analysis methods in healthcare processes. More systematic use of risk analysis is needed to guide continuous safety improvement of high risk activities.

Linguistically informed digital fingerprints for text

NASA Astrophysics Data System (ADS)

Uzuner, Özlem

2006-02-01

Digital fingerprinting, watermarking, and tracking technologies have gained importance in the recent years in response to growing problems such as digital copyright infringement. While fingerprints and watermarks can be generated in many different ways, use of natural language processing for these purposes has so far been limited. Measuring similarity of literary works for automatic copyright infringement detection requires identifying and comparing creative expression of content in documents. In this paper, we present a linguistic approach to automatically fingerprinting novels based on their expression of content. We use natural language processing techniques to generate "expression fingerprints". These fingerprints consist of both syntactic and semantic elements of language, i.e., syntactic and semantic elements of expression. Our experiments indicate that syntactic and semantic elements of expression enable accurate identification of novels and their paraphrases, providing a significant improvement over techniques used in text classification literature for automatic copy recognition. We show that these elements of expression can be used to fingerprint, label, or watermark works; they represent features that are essential to the character of works and that remain fairly consistent in the works even when works are paraphrased. These features can be directly extracted from the contents of the works on demand and can be used to recognize works that would not be correctly identified either in the absence of pre-existing labels or by verbatim-copy detectors.

An automatic taxonomy of galaxy morphology using unsupervised machine learning

NASA Astrophysics Data System (ADS)

Hocking, Alex; Geach, James E.; Sun, Yi; Davey, Neil

2018-01-01

We present an unsupervised machine learning technique that automatically segments and labels galaxies in astronomical imaging surveys using only pixel data. Distinct from previous unsupervised machine learning approaches used in astronomy we use no pre-selection or pre-filtering of target galaxy type to identify galaxies that are similar. We demonstrate the technique on the Hubble Space Telescope (HST) Frontier Fields. By training the algorithm using galaxies from one field (Abell 2744) and applying the result to another (MACS 0416.1-2403), we show how the algorithm can cleanly separate early and late type galaxies without any form of pre-directed training for what an 'early' or 'late' type galaxy is. We then apply the technique to the HST Cosmic Assembly Near-infrared Deep Extragalactic Legacy Survey (CANDELS) fields, creating a catalogue of approximately 60 000 classifications. We show how the automatic classification groups galaxies of similar morphological (and photometric) type and make the classifications public via a catalogue, a visual catalogue and galaxy similarity search. We compare the CANDELS machine-based classifications to human-classifications from the Galaxy Zoo: CANDELS project. Although there is not a direct mapping between Galaxy Zoo and our hierarchical labelling, we demonstrate a good level of concordance between human and machine classifications. Finally, we show how the technique can be used to identify rarer objects and present lensed galaxy candidates from the CANDELS imaging.

P2MP MPLS-Based Hierarchical Service Management System

NASA Astrophysics Data System (ADS)

Kumaki, Kenji; Nakagawa, Ikuo; Nagami, Kenichi; Ogishi, Tomohiko; Ano, Shigehiro

This paper proposes a point-to-multipoint (P2MP) Multi-Protocol Label Switching (MPLS) based hierarchical service management system. Traditionally, general management systems deployed in some service providers control MPLS Label Switched Paths (LSPs) (e.g., RSVP-TE and LDP) and services (e.g., L2VPN, L3VPN and IP) separately. In order for dedicated management systems for MPLS LSPs and services to cooperate with each other automatically, a hierarchical service management system has been proposed with the main focus on point-to-point (P2P) TE LSPs in MPLS path management. In the case where P2MP TE LSPs and services are deployed in MPLS networks, the dedicated management systems for P2MP TE LSPs and services must work together automatically. Therefore, this paper proposes a new algorithm that uses a correlation between P2MP TE LSPs and multicast VPN services based on a P2MP MPLS-based hierarchical service management architecture. Also, the capacity and performance of the proposed algorithm are evaluated by simulations, which are actually based on certain real MPLS production networks, and are compared to that of the algorithm for P2P TE LSPs. Results show this system is very scalable within real MPLS production networks. This system, with the automatic correlation, appears to be deployable in real MPLS production networks.

Scatter-Reducing Sounding Filtration Using a Genetic Algorithm and Mean Monthly Standard Deviation

NASA Technical Reports Server (NTRS)

Mandrake, Lukas

2013-01-01

Retrieval algorithms like that used by the Orbiting Carbon Observatory (OCO)-2 mission generate massive quantities of data of varying quality and reliability. A computationally efficient, simple method of labeling problematic datapoints or predicting soundings that will fail is required for basic operation, given that only 6% of the retrieved data may be operationally processed. This method automatically obtains a filter designed to reduce scatter based on a small number of input features. Most machine-learning filter construction algorithms attempt to predict error in the CO2 value. By using a surrogate goal of Mean Monthly STDEV, the goal is to reduce the retrieved CO2 scatter rather than solving the harder problem of reducing CO2 error. This lends itself to improved interpretability and performance. This software reduces the scatter of retrieved CO2 values globally based on a minimum number of input features. It can be used as a prefilter to reduce the number of soundings requested, or as a post-filter to label data quality. The use of the MMS (Mean Monthly Standard deviation) provides a much cleaner, clearer filter than the standard ABS(CO2-truth) metrics previously employed by competitor methods. The software's main strength lies in a clearer (i.e., fewer features required) filter that more efficiently reduces scatter in retrieved CO2 rather than focusing on the more complex (and easily removed) bias issues.

Interactive approach to segment organs at risk in radiotherapy treatment planning

NASA Astrophysics Data System (ADS)

Dolz, Jose; Kirisli, Hortense A.; Viard, Romain; Massoptier, Laurent

2014-03-01

Accurate delineation of organs at risk (OAR) is required for radiation treatment planning (RTP). However, it is a very time consuming and tedious task. The use in clinic of image guided radiation therapy (IGRT) becomes more and more popular, thus increasing the need of (semi-)automatic methods for delineation of the OAR. In this work, an interactive segmentation approach to delineate OAR is proposed and validated. The method is based on the combination of watershed transformation, which groups small areas of similar intensities in homogeneous labels, and graph cuts approach, which uses these labels to create the graph. Segmentation information can be added in any view - axial, sagittal or coronal -, making the interaction with the algorithm easy and fast. Subsequently, this information is propagated within the whole volume, providing a spatially coherent result. Manual delineations made by experts of 6 OAR - lungs, kidneys, liver, spleen, heart and aorta - over a set of 9 computed tomography (CT) scans were used as reference standard to validate the proposed approach. With a maximum of 4 interactions, a Dice similarity coefficient (DSC) higher than 0.87 was obtained, which demonstrates that, with the proposed segmentation approach, only few interactions are required to achieve similar results as the ones obtained manually. The integration of this method in the RTP process may save a considerable amount of time, and reduce the annotation complexity.

Pulmonary lobar volumetry using novel volumetric computer-aided diagnosis and computed tomography

PubMed Central

Iwano, Shingo; Kitano, Mariko; Matsuo, Keiji; Kawakami, Kenichi; Koike, Wataru; Kishimoto, Mariko; Inoue, Tsutomu; Li, Yuanzhong; Naganawa, Shinji

2013-01-01

OBJECTIVES To compare the accuracy of pulmonary lobar volumetry using the conventional number of segments method and novel volumetric computer-aided diagnosis using 3D computed tomography images. METHODS We acquired 50 consecutive preoperative 3D computed tomography examinations for lung tumours reconstructed at 1-mm slice thicknesses. We calculated the lobar volume and the emphysematous lobar volume < −950 HU of each lobe using (i) the slice-by-slice method (reference standard), (ii) number of segments method, and (iii) semi-automatic and (iv) automatic computer-aided diagnosis. We determined Pearson correlation coefficients between the reference standard and the three other methods for lobar volumes and emphysematous lobar volumes. We also compared the relative errors among the three measurement methods. RESULTS Both semi-automatic and automatic computer-aided diagnosis results were more strongly correlated with the reference standard than the number of segments method. The correlation coefficients for automatic computer-aided diagnosis were slightly lower than those for semi-automatic computer-aided diagnosis because there was one outlier among 50 cases (2%) in the right upper lobe and two outliers among 50 cases (4%) in the other lobes. The number of segments method relative error was significantly greater than those for semi-automatic and automatic computer-aided diagnosis (P < 0.001). The computational time for automatic computer-aided diagnosis was 1/2 to 2/3 than that of semi-automatic computer-aided diagnosis. CONCLUSIONS A novel lobar volumetry computer-aided diagnosis system could more precisely measure lobar volumes than the conventional number of segments method. Because semi-automatic computer-aided diagnosis and automatic computer-aided diagnosis were complementary, in clinical use, it would be more practical to first measure volumes by automatic computer-aided diagnosis, and then use semi-automatic measurements if automatic computer-aided diagnosis failed. PMID:23526418

Development of a Highly Automated and Multiplexed Targeted Proteome Pipeline and Assay for 112 Rat Brain Synaptic Proteins

PubMed Central

Colangelo, Christopher M.; Ivosev, Gordana; Chung, Lisa; Abbott, Thomas; Shifman, Mark; Sakaue, Fumika; Cox, David; Kitchen, Rob R.; Burton, Lyle; Tate, Stephen A; Gulcicek, Erol; Bonner, Ron; Rinehart, Jesse; Nairn, Angus C.; Williams, Kenneth R.

2015-01-01

We present a comprehensive workflow for large scale (>1000 transitions/run) label-free LC-MRM proteome assays. Innovations include automated MRM transition selection, intelligent retention time scheduling (xMRM) that improves Signal/Noise by >2-fold, and automatic peak modeling. Improvements to data analysis include a novel Q/C metric, Normalized Group Area Ratio (NGAR), MLR normalization, weighted regression analysis, and data dissemination through the Yale Protein Expression Database. As a proof of principle we developed a robust 90 minute LC-MRM assay for Mouse/Rat Post-Synaptic Density (PSD) fractions which resulted in the routine quantification of 337 peptides from 112 proteins based on 15 observations per protein. Parallel analyses with stable isotope dilution peptide standards (SIS), demonstrate very high correlation in retention time (1.0) and protein fold change (0.94) between the label-free and SIS analyses. Overall, our first method achieved a technical CV of 11.4% with >97.5% of the 1697 transitions being quantified without user intervention, resulting in a highly efficient, robust, and single injection LC-MRM assay. PMID:25476245

On describing human white matter anatomy: the white matter query language.

PubMed

Wassermann, Demian; Makris, Nikos; Rathi, Yogesh; Shenton, Martha; Kikinis, Ron; Kubicki, Marek; Westin, Carl-Fredrik

2013-01-01

The main contribution of this work is the careful syntactical definition of major white matter tracts in the human brain based on a neuroanatomist's expert knowledge. We present a technique to formally describe white matter tracts and to automatically extract them from diffusion MRI data. The framework is based on a novel query language with a near-to-English textual syntax. This query language allows us to construct a dictionary of anatomical definitions describing white matter tracts. The definitions include adjacent gray and white matter regions, and rules for spatial relations. This enables automated coherent labeling of white matter anatomy across subjects. We use our method to encode anatomical knowledge in human white matter describing 10 association and 8 projection tracts per hemisphere and 7 commissural tracts. The technique is shown to be comparable in accuracy to manual labeling. We present results applying this framework to create a white matter atlas from 77 healthy subjects, and we use this atlas in a proof-of-concept study to detect tract changes specific to schizophrenia.

Study on a Luminol-based Electrochemiluminescent Sensor for Label-Free DNA Sensing

PubMed Central

Chu, Hai-Hong; Yan, Ji-Lin; Tu, Yi-Feng

2010-01-01

Automatic, inexpensive, simple and sensitive methods for DNA sensing and quantification are highly desirable for biomedical research. The rapid development of both the fundamentals and applications of electrochemiluminescence (ECL) over the past years has demonstrated its potential for analytical and bio-analytical chemistry. This paper reports the quenching effect of DNA on the ECL of luminol and the further development of a DNA sensing device. With the pre-functionalization by a composite of carbon nano-tubes (CNTs) and Au nanoparticles (AuNPs), the sensor provides a novel and valuable label-free approach for DNA sensing. Here the ECL intensity was remarkably decreased when more than 1.0 × 10−12 molar of DNA were adsorbed on the sensor. Linearity of the DNA amount with the reciprocal of ECL intensity was observed. A saturated sensor caused a 92.8% quenching effect. The research also proposes the mechanism for the quenching effect which could be attributed to the interaction between luminol and DNA and the elimination of reactive oxygen species (ROSs) by DNA. PMID:22163421

Rapid detection of α-thalassaemia alleles of --(SEA)/, -α(3.7)/ and -α(4.2)/ using a dual labelling, self-quenching hybridization probe/melting curve analysis.

PubMed

Gao, Lan; Liu, Yanhui; Sun, Manna; Zhao, Ying; Xie, Rungui; He, Yi; Xu, Wanfang; Liu, Jianxin; Lin, Yangyang; Lou, Jiwu

2015-12-01

The aim of the study was to set up an alternative automatic molecular diagnostic method for deletional α-thalassaemia mutations without gel electrophoresis. Based on the sequence variation within the two Z boxes and melting curve analysis of dually labelled probes, a real-time PCR assay was developed and validated for the rapid detection of major α-genotypes (--(SEA)/αα, --(SEA)/-α(3.7), --(SEA)/-α(4.2), --(SEA)/--(SEA), -α(3.7)/-α(3.7) and -α(4.2)/-α(4.2)). Samples with the -α(3.7)/-α(3.7), -α(4.2)/-α(4.2), --(SEA)/αα, --(SEA)/-α(3.7), --(SEA)/-α(4.2), and --(SEA)/--(SEA) genotypes could be clearly distinguished. The accuracy of this technique for these samples was 100% sensitivity and specificity. This technique is rapid and reliable, demonstrating feasibility for use in large-scale population screening and prenatal diagnosis of deletional Hb H disease and Hb Bart's hydrops fetalis. Copyright © 2015 Elsevier Ltd. All rights reserved.

A simple method for the analysis by MS/MS of underivatized amino acids on dry blood spots from newborn screening.

PubMed

Wang, Chunyan; Zhang, Wenyan; Song, Fengrui; Liu, Zhiqiang; Liu, Shuying

2012-05-01

The analysis by electrospray-ionization tandem mass spectrometry of amino acids with butyl esterification and isotopically labeled internal standard is routine in newborn screening laboratories worldwide. In the present study, we established a direct analysis method of higher accuracy that uses a non-deuterated internal standard. The automatic sampler and the pump of an LC apparatus were used to inject sample and mobile phase to MS, but no LC column was needed. The dry blood spot (DBS) material was prepared at levels of low, medium and high concentration; the running time was 1 min. In parallel to the new procedure, we applied the established method to analyze nine amino acids on DBS of healthy newborns and phenylketonuria newborns. The newly proposed method of product ion confirmation scan along with multiple reaction monitoring resulted in a very accurate identification of each amino acid. Our innovative protocol had high sensitivity and specificity in the analysis of cases of suspected metabolic diseases.

Single camera photogrammetry system for EEG electrode identification and localization.

PubMed

Baysal, Uğur; Sengül, Gökhan

2010-04-01

In this study, photogrammetric coordinate measurement and color-based identification of EEG electrode positions on the human head are simultaneously implemented. A rotating, 2MP digital camera about 20 cm above the subject's head is used and the images are acquired at predefined stop points separated azimuthally at equal angular displacements. In order to realize full automation, the electrodes have been labeled by colored circular markers and an electrode recognition algorithm has been developed. The proposed method has been tested by using a plastic head phantom carrying 25 electrode markers. Electrode locations have been determined while incorporating three different methods: (i) the proposed photogrammetric method, (ii) conventional 3D radiofrequency (RF) digitizer, and (iii) coordinate measurement machine having about 6.5 mum accuracy. It is found that the proposed system automatically identifies electrodes and localizes them with a maximum error of 0.77 mm. It is suggested that this method may be used in EEG source localization applications in the human brain.

Automated glioblastoma segmentation based on a multiparametric structured unsupervised classification.

PubMed

Juan-Albarracín, Javier; Fuster-Garcia, Elies; Manjón, José V; Robles, Montserrat; Aparici, F; Martí-Bonmatí, L; García-Gómez, Juan M

2015-01-01

Automatic brain tumour segmentation has become a key component for the future of brain tumour treatment. Currently, most of brain tumour segmentation approaches arise from the supervised learning standpoint, which requires a labelled training dataset from which to infer the models of the classes. The performance of these models is directly determined by the size and quality of the training corpus, whose retrieval becomes a tedious and time-consuming task. On the other hand, unsupervised approaches avoid these limitations but often do not reach comparable results than the supervised methods. In this sense, we propose an automated unsupervised method for brain tumour segmentation based on anatomical Magnetic Resonance (MR) images. Four unsupervised classification algorithms, grouped by their structured or non-structured condition, were evaluated within our pipeline. Considering the non-structured algorithms, we evaluated K-means, Fuzzy K-means and Gaussian Mixture Model (GMM), whereas as structured classification algorithms we evaluated Gaussian Hidden Markov Random Field (GHMRF). An automated postprocess based on a statistical approach supported by tissue probability maps is proposed to automatically identify the tumour classes after the segmentations. We evaluated our brain tumour segmentation method with the public BRAin Tumor Segmentation (BRATS) 2013 Test and Leaderboard datasets. Our approach based on the GMM model improves the results obtained by most of the supervised methods evaluated with the Leaderboard set and reaches the second position in the ranking. Our variant based on the GHMRF achieves the first position in the Test ranking of the unsupervised approaches and the seventh position in the general Test ranking, which confirms the method as a viable alternative for brain tumour segmentation.

Multimodal system designed to reduce errors in recording and administration of drugs in anaesthesia: prospective randomised clinical evaluation.

PubMed

Merry, Alan F; Webster, Craig S; Hannam, Jacqueline; Mitchell, Simon J; Henderson, Robert; Reid, Papaarangi; Edwards, Kylie-Ellen; Jardim, Anisoara; Pak, Nick; Cooper, Jeremy; Hopley, Lara; Frampton, Chris; Short, Timothy G

2011-09-22

To clinically evaluate a new patented multimodal system (SAFERSleep) designed to reduce errors in the recording and administration of drugs in anaesthesia. Prospective randomised open label clinical trial. Five designated operating theatres in a major tertiary referral hospital. Eighty nine consenting anaesthetists managing 1075 cases in which there were 10,764 drug administrations. Use of the new system (which includes customised drug trays and purpose designed drug trolley drawers to promote a well organised anaesthetic workspace and aseptic technique; pre-filled syringes for commonly used anaesthetic drugs; large legible colour coded drug labels; a barcode reader linked to a computer, speakers, and touch screen to provide automatic auditory and visual verification of selected drugs immediately before each administration; automatic compilation of an anaesthetic record; an on-screen and audible warning if an antibiotic has not been administered within 15 minutes of the start of anaesthesia; and certain procedural rules-notably, scanning the label before each drug administration) versus conventional practice in drug administration with a manually compiled anaesthetic record. Primary: composite of errors in the recording and administration of intravenous drugs detected by direct observation and by detailed reconciliation of the contents of used drug vials against recorded administrations; and lapses in responding to an intermittent visual stimulus (vigilance latency task). Secondary: outcomes in patients; analyses of anaesthetists' tasks and assessments of workload; evaluation of the legibility of anaesthetic records; evaluation of compliance with the procedural rules of the new system; and questionnaire based ratings of the respective systems by participants. The overall mean rate of drug errors per 100 administrations was 9.1 (95% confidence interval 6.9 to 11.4) with the new system (one in 11 administrations) and 11.6 (9.3 to 13.9) with conventional methods (one in nine administrations) (P = 0.045 for difference). Most were recording errors, and, though fewer drug administration errors occurred with the new system, the comparison with conventional methods did not reach significance. Rates of errors in drug administration were lower when anaesthetists consistently applied two key principles of the new system (scanning the drug barcode before administering each drug and keeping the voice prompt active) than when they did not: mean 6.0 (3.1 to 8.8) errors per 100 administrations v 9.7 (8.4 to 11.1) respectively (P = 0.004). Lapses in the vigilance latency task occurred in 12% (58/471) of cases with the new system and 9% (40/473) with conventional methods (P = 0.052). The records generated by the new system were more legible, and anaesthetists preferred the new system, particularly in relation to long, complex, and emergency cases. There were no differences between new and conventional systems in respect of outcomes in patients or anaesthetists' workload. The new system was associated with a reduction in errors in the recording and administration of drugs in anaesthesia, attributable mainly to a reduction in recording errors. Automatic compilation of the anaesthetic record increased legibility but also increased lapses in a vigilance latency task and decreased time spent watching monitors. Trial registration Australian New Zealand Clinical Trials Registry No 12608000068369.

Electronic labelling in recycling of manufactured articles.

PubMed

Olejnik, Lech; Krammer, Alfred

2002-12-01

The concept of a recycling system aiming at the recovery of resources from manufactured articles is proposed. The system integrates electronic labels for product identification and internet for global data exchange. A prototype for the recycling of electric motors has been developed, which implements a condition-based recycling decision system to automatically select the environmentally and economically appropriate recycling strategy, thereby opening a potential market for second-hand motors and creating a profitable recycling process itself. The project has been designed to evaluate the feasibility of electronic identification applied on a large number of motors and to validate the system in real field conditions.

Automatic face naming by learning discriminative affinity matrices from weakly labeled images.

PubMed

Xiao, Shijie; Xu, Dong; Wu, Jianxin

2015-10-01

Given a collection of images, where each image contains several faces and is associated with a few names in the corresponding caption, the goal of face naming is to infer the correct name for each face. In this paper, we propose two new methods to effectively solve this problem by learning two discriminative affinity matrices from these weakly labeled images. We first propose a new method called regularized low-rank representation by effectively utilizing weakly supervised information to learn a low-rank reconstruction coefficient matrix while exploring multiple subspace structures of the data. Specifically, by introducing a specially designed regularizer to the low-rank representation method, we penalize the corresponding reconstruction coefficients related to the situations where a face is reconstructed by using face images from other subjects or by using itself. With the inferred reconstruction coefficient matrix, a discriminative affinity matrix can be obtained. Moreover, we also develop a new distance metric learning method called ambiguously supervised structural metric learning by using weakly supervised information to seek a discriminative distance metric. Hence, another discriminative affinity matrix can be obtained using the similarity matrix (i.e., the kernel matrix) based on the Mahalanobis distances of the data. Observing that these two affinity matrices contain complementary information, we further combine them to obtain a fused affinity matrix, based on which we develop a new iterative scheme to infer the name of each face. Comprehensive experiments demonstrate the effectiveness of our approach.

Research into automatic recognition of joints in human symmetrical movements

NASA Astrophysics Data System (ADS)

Fan, Yifang; Li, Zhiyu

2008-03-01

High speed photography is a major means of collecting data from human body movement. It enables the automatic identification of joints, which brings great significance to the research, treatment and recovery of injuries, the analysis to the diagnosis of sport techniques and the ergonomics. According to the features that when the adjacent joints of human body are in planetary motion, their distance remains the same, and according to the human body joint movement laws (such as the territory of the articular anatomy and the kinematic features), a new approach is introduced to process the image thresholding of joints filmed by the high speed camera, to automatically identify the joints and to automatically trace the joint points (by labeling markers at the joints). Based upon the closure of marking points, automatic identification can be achieved through thresholding treatment. Due to the screening frequency and the laws of human segment movement, when the marking points have been initialized, their automatic tracking can be achieved with the progressive sequential images.Then the testing results, the data from three-dimensional force platform and the characteristics that human body segment will only rotate around the closer ending segment when the segment has no boding force and only valid to the conservative force all tell that after being analyzed kinematically, the approach is approved to be valid.

CT Imaging of Hardwood Logs for Lumber Production

Treesearch

Daniel L. Schmoldt; Pei Li; A. Lynn Abbott

1996-01-01

Hardwood sawmill operators need to improve the conversion of raw material (logs) into lumber. Internal log scanning provides detailed information that can aid log processors in improving lumber recovery. However, scanner data (i.e. tomographic images) need to be analyzed prior to presentation to saw operators. Automatic labeling of computer tomography (CT) images is...

16 CFR 1211.15 - Field-installed labels.

Code of Federal Regulations, 2010 CFR

2010-01-01

... a child running toward or under a garage door. A red prohibition symbol (slash, oriented from the... automatic garage door resulting in severe injury or death.” (2) Avoidance Statements— (i) “Do not allow children to walk or run under a closing door.” (ii) “Do not allow children to operate door operator...

Exploration of Acoustic Features for Automatic Vowel Discrimination in Spontaneous Speech

ERIC Educational Resources Information Center

Tyson, Na'im R.

2012-01-01

In an attempt to understand what acoustic/auditory feature sets motivated transcribers towards certain labeling decisions, I built machine learning models that were capable of discriminating between canonical and non-canonical vowels excised from the Buckeye Corpus. Specifically, I wanted to model when the dictionary form and the transcribed-form…

Automatic Gleason grading of prostate cancer using SLIM and machine learning

NASA Astrophysics Data System (ADS)

Nguyen, Tan H.; Sridharan, Shamira; Marcias, Virgilia; Balla, Andre K.; Do, Minh N.; Popescu, Gabriel

2016-03-01

In this paper, we present an updated automatic diagnostic procedure for prostate cancer using quantitative phase imaging (QPI). In a recent report [1], we demonstrated the use of Random Forest for image segmentation on prostate cores imaged using QPI. Based on these label maps, we developed an algorithm to discriminate between regions with Gleason grade 3 and 4 prostate cancer in prostatectomy tissue. The Area-Under-Curve (AUC) of 0.79 for the Receiver Operating Curve (ROC) can be obtained for Gleason grade 4 detection in a binary classification between Grade 3 and Grade 4. Our dataset includes 280 benign cases and 141 malignant cases. We show that textural features in phase maps have strong diagnostic values since they can be used in combination with the label map to detect presence or absence of basal cells, which is a strong indicator for prostate carcinoma. A support vector machine (SVM) classifier trained on this new feature vector can classify cancer/non-cancer with an error rate of 0.23 and an AUC value of 0.83.

EpiProfile Quantifies Histone Peptides With Modifications by Extracting Retention Time and Intensity in High-resolution Mass Spectra*

PubMed Central

Yuan, Zuo-Fei; Lin, Shu; Molden, Rosalynn C.; Cao, Xing-Jun; Bhanu, Natarajan V.; Wang, Xiaoshi; Sidoli, Simone; Liu, Shichong; Garcia, Benjamin A.

2015-01-01

Histone post-translational modifications contribute to chromatin function through their chemical properties which influence chromatin structure and their ability to recruit chromatin interacting proteins. Nanoflow liquid chromatography coupled with high resolution tandem mass spectrometry (nanoLC-MS/MS) has emerged as the most suitable technology for global histone modification analysis because of the high sensitivity and the high mass accuracy of this approach that provides confident identification. However, analysis of histones with this method is even more challenging because of the large number and variety of isobaric histone peptides and the high dynamic range of histone peptide abundances. Here, we introduce EpiProfile, a software tool that discriminates isobaric histone peptides using the distinguishing fragment ions in their tandem mass spectra and extracts the chromatographic area under the curve using previous knowledge about peptide retention time. The accuracy of EpiProfile was evaluated by analysis of mixtures containing different ratios of synthetic histone peptides. In addition to label-free quantification of histone peptides, EpiProfile is flexible and can quantify different types of isotopically labeled histone peptides. EpiProfile is unique in generating layouts (i.e. relative retention time) of histone peptides when compared with manual quantification of the data and other programs (such as Skyline), filling the need of an automatic and freely available tool to quantify labeled and non-labeled modified histone peptides. In summary, EpiProfile is a valuable nanoflow liquid chromatography coupled with high resolution tandem mass spectrometry-based quantification tool for histone peptides, which can also be adapted to analyze nonhistone protein samples. PMID:25805797

Mindtagger: A Demonstration of Data Labeling in Knowledge Base Construction.

PubMed

Shin, Jaeho; Ré, Christopher; Cafarella, Michael

2015-08-01

End-to-end knowledge base construction systems using statistical inference are enabling more people to automatically extract high-quality domain-specific information from unstructured data. As a result of deploying DeepDive framework across several domains, we found new challenges in debugging and improving such end-to-end systems to construct high-quality knowledge bases. DeepDive has an iterative development cycle in which users improve the data. To help our users, we needed to develop principles for analyzing the system's error as well as provide tooling for inspecting and labeling various data products of the system. We created guidelines for error analysis modeled after our colleagues' best practices, in which data labeling plays a critical role in every step of the analysis. To enable more productive and systematic data labeling, we created Mindtagger, a versatile tool that can be configured to support a wide range of tasks. In this demonstration, we show in detail what data labeling tasks are modeled in our error analysis guidelines and how each of them is performed using Mindtagger.

Adaptive maritime video surveillance

NASA Astrophysics Data System (ADS)

Gupta, Kalyan Moy; Aha, David W.; Hartley, Ralph; Moore, Philip G.

2009-05-01

Maritime assets such as ports, harbors, and vessels are vulnerable to a variety of near-shore threats such as small-boat attacks. Currently, such vulnerabilities are addressed predominantly by watchstanders and manual video surveillance, which is manpower intensive. Automatic maritime video surveillance techniques are being introduced to reduce manpower costs, but they have limited functionality and performance. For example, they only detect simple events such as perimeter breaches and cannot predict emerging threats. They also generate too many false alerts and cannot explain their reasoning. To overcome these limitations, we are developing the Maritime Activity Analysis Workbench (MAAW), which will be a mixed-initiative real-time maritime video surveillance tool that uses an integrated supervised machine learning approach to label independent and coordinated maritime activities. It uses the same information to predict anomalous behavior and explain its reasoning; this is an important capability for watchstander training and for collecting performance feedback. In this paper, we describe MAAW's functional architecture, which includes the following pipeline of components: (1) a video acquisition and preprocessing component that detects and tracks vessels in video images, (2) a vessel categorization and activity labeling component that uses standard and relational supervised machine learning methods to label maritime activities, and (3) an ontology-guided vessel and maritime activity annotator to enable subject matter experts (e.g., watchstanders) to provide feedback and supervision to the system. We report our findings from a preliminary system evaluation on river traffic video.

An analysis of multi-type relational interactions in FMA using graph motifs with disjointness constraints.

PubMed

Zhang, Guo-Qiang; Luo, Lingyun; Ogbuji, Chime; Joslyn, Cliff; Mejino, Jose; Sahoo, Satya S

2012-01-01

The interaction of multiple types of relationships among anatomical classes in the Foundational Model of Anatomy (FMA) can provide inferred information valuable for quality assurance. This paper introduces a method called Motif Checking (MOCH) to study the effects of such multi-relation type interactions for detecting logical inconsistencies as well as other anomalies represented by the motifs. MOCH represents patterns of multi-type interaction as small labeled (with multiple types of edges) sub-graph motifs, whose nodes represent class variables, and labeled edges represent relational types. By representing FMA as an RDF graph and motifs as SPARQL queries, fragments of FMA are automatically obtained as auditing candidates. Leveraging the scalability and reconfigurability of Semantic Web Technology, we performed exhaustive analyses of a variety of labeled sub-graph motifs. The quality assurance feature of MOCH comes from the distinct use of a subset of the edges of the graph motifs as constraints for disjointness, whereby bringing in rule-based flavor to the approach as well. With possible disjointness implied by antonyms, we performed manual inspection of the resulting FMA fragments and tracked down sources of abnormal inferred conclusions (logical inconsistencies), which are amendable for programmatic revision of the FMA. Our results demonstrate that MOCH provides a unique source of valuable information for quality assurance. Since our approach is general, it is applicable to any ontological system with an OWL representation.

An Analysis of Multi-type Relational Interactions in FMA Using Graph Motifs with Disjointness Constraints

PubMed Central

Zhang, Guo-Qiang; Luo, Lingyun; Ogbuji, Chime; Joslyn, Cliff; Mejino, Jose; Sahoo, Satya S

2012-01-01

The interaction of multiple types of relationships among anatomical classes in the Foundational Model of Anatomy (FMA) can provide inferred information valuable for quality assurance. This paper introduces a method called Motif Checking (MOCH) to study the effects of such multi-relation type interactions for detecting logical inconsistencies as well as other anomalies represented by the motifs. MOCH represents patterns of multi-type interaction as small labeled (with multiple types of edges) sub-graph motifs, whose nodes represent class variables, and labeled edges represent relational types. By representing FMA as an RDF graph and motifs as SPARQL queries, fragments of FMA are automatically obtained as auditing candidates. Leveraging the scalability and reconfigurability of Semantic Web Technology, we performed exhaustive analyses of a variety of labeled sub-graph motifs. The quality assurance feature of MOCH comes from the distinct use of a subset of the edges of the graph motifs as constraints for disjointness, whereby bringing in rule-based flavor to the approach as well. With possible disjointness implied by antonyms, we performed manual inspection of the resulting FMA fragments and tracked down sources of abnormal inferred conclusions (logical inconsistencies), which are amendable for programmatic revision of the FMA. Our results demonstrate that MOCH provides a unique source of valuable information for quality assurance. Since our approach is general, it is applicable to any ontological system with an OWL representation. PMID:23304382

A robust real-time abnormal region detection framework from capsule endoscopy images

NASA Astrophysics Data System (ADS)

Cheng, Yanfen; Liu, Xu; Li, Huiping

2009-02-01

In this paper we present a novel method to detect abnormal regions from capsule endoscopy images. Wireless Capsule Endoscopy (WCE) is a recent technology where a capsule with an embedded camera is swallowed by the patient to visualize the gastrointestinal tract. One challenge is one procedure of diagnosis will send out over 50,000 images, making physicians' reviewing process expensive. Physicians' reviewing process involves in identifying images containing abnormal regions (tumor, bleeding, etc) from this large number of image sequence. In this paper we construct a novel framework for robust and real-time abnormal region detection from large amount of capsule endoscopy images. The detected potential abnormal regions can be labeled out automatically to let physicians review further, therefore, reduce the overall reviewing process. In this paper we construct an abnormal region detection framework with the following advantages: 1) Trainable. Users can define and label any type of abnormal region they want to find; The abnormal regions, such as tumor, bleeding, etc., can be pre-defined and labeled using the graphical user interface tool we provided. 2) Efficient. Due to the large number of image data, the detection speed is very important. Our system can detect very efficiently at different scales due to the integral image features we used; 3) Robust. After feature selection we use a cascade of classifiers to further enforce the detection accuracy.

Development of a Smartphone Application to Measure Physical Activity Using Sensor-Assisted Self-Report

PubMed Central

Dunton, Genevieve Fridlund; Dzubur, Eldin; Kawabata, Keito; Yanez, Brenda; Bo, Bin; Intille, Stephen

2013-01-01

Introduction: Despite the known advantages of objective physical activity monitors (e.g., accelerometers), these devices have high rates of non-wear, which leads to missing data. Objective activity monitors are also unable to capture valuable contextual information about behavior. Adolescents recruited into physical activity surveillance and intervention studies will increasingly have smartphones, which are miniature computers with built-in motion sensors. Methods: This paper describes the design and development of a smartphone application (“app”) called Mobile Teen that combines objective and self-report assessment strategies through (1) sensor-informed context-sensitive ecological momentary assessment (CS-EMA) and (2) sensor-assisted end-of-day recall. Results: The Mobile Teen app uses the mobile phone’s built-in motion sensor to automatically detect likely bouts of phone non-wear, sedentary behavior, and physical activity. The app then uses transitions between these inferred states to trigger CS-EMA self-report surveys measuring the type, purpose, and context of activity in real-time. The end of the day recall component of the Mobile Teen app allows users to interactively review and label their own physical activity data each evening using visual cues from automatically detected major activity transitions from the phone’s built-in motion sensors. Major activity transitions are identified by the app, which cues the user to label that “chunk,” or period, of time using activity categories. Conclusion: Sensor-driven CS-EMA and end-of-day recall smartphone apps can be used to augment physical activity data collected by objective activity monitors, filling in gaps during non-wear bouts and providing additional real-time data on environmental, social, and emotional correlates of behavior. Smartphone apps such as these have potential for affordable deployment in large-scale epidemiological and intervention studies. PMID:24616888

Highly Sensitive and Automated Surface Enhanced Raman Scattering-based Immunoassay for H5N1 Detection with Digital Microfluidics.

PubMed

Wang, Yang; Ruan, Qingyu; Lei, Zhi-Chao; Lin, Shui-Chao; Zhu, Zhi; Zhou, Leiji; Yang, Chaoyong

2018-04-17

Digital microfluidics (DMF) is a powerful platform for a broad range of applications, especially immunoassays having multiple steps, due to the advantages of low reagent consumption and high automatization. Surface enhanced Raman scattering (SERS) has been proven as an attractive method for highly sensitive and multiplex detection, because of its remarkable signal amplification and excellent spatial resolution. Here we propose a SERS-based immunoassay with DMF for rapid, automated, and sensitive detection of disease biomarkers. SERS tags labeled with Raman reporter 4-mercaptobenzoic acid (4-MBA) were synthesized with a core@shell nanostructure and showed strong signals, good uniformity, and high stability. A sandwich immunoassay was designed, in which magnetic beads coated with antibodies were used as solid support to capture antigens from samples to form a beads-antibody-antigen immunocomplex. By labeling the immunocomplex with a detection antibody-functionalized SERS tag, antigen can be sensitively detected through the strong SERS signal. The automation capability of DMF can greatly simplify the assay procedure while reducing the risk of exposure to hazardous samples. Quantitative detection of avian influenza virus H5N1 in buffer and human serum was implemented to demonstrate the utility of the DMF-SERS method. The DMF-SERS method shows excellent sensitivity (LOD of 74 pg/mL) and selectivity for H5N1 detection with less assay time (<1 h) and lower reagent consumption (∼30 μL) compared to the standard ELISA method. Therefore, this DMF-SERS method holds great potentials for automated and sensitive detection of a variety of infectious diseases.

3D exemplar-based random walks for tooth segmentation from cone-beam computed tomography images

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

Pei, Yuru, E-mail: peiyuru@cis.pku.edu.cn; Ai, Xin

Purpose: Tooth segmentation is an essential step in acquiring patient-specific dental geometries from cone-beam computed tomography (CBCT) images. Tooth segmentation from CBCT images is still a challenging task considering the comparatively low image quality caused by the limited radiation dose, as well as structural ambiguities from intercuspation and nearby alveolar bones. The goal of this paper is to present and discuss the latest accomplishments in semisupervised tooth segmentation with adaptive 3D shape constraints. Methods: The authors propose a 3D exemplar-based random walk method of tooth segmentation from CBCT images. The proposed method integrates semisupervised label propagation and regularization by 3Dmore » exemplar registration. To begin with, the pure random walk method is to get an initial segmentation of the teeth, which tends to be erroneous because of the structural ambiguity of CBCT images. And then, as an iterative refinement, the authors conduct a regularization by using 3D exemplar registration, as well as label propagation by random walks with soft constraints, to improve the tooth segmentation. In the first stage of the iteration, 3D exemplars with well-defined topologies are adapted to fit the tooth contours, which are obtained from the random walks based segmentation. The soft constraints on voxel labeling are defined by shape-based foreground dentine probability acquired by the exemplar registration, as well as the appearance-based probability from a support vector machine (SVM) classifier. In the second stage, the labels of the volume-of-interest (VOI) are updated by the random walks with soft constraints. The two stages are optimized iteratively. Instead of the one-shot label propagation in the VOI, an iterative refinement process can achieve a reliable tooth segmentation by virtue of exemplar-based random walks with adaptive soft constraints. Results: The proposed method was applied for tooth segmentation of twenty clinically captured CBCT images. Three metrics, including the Dice similarity coefficient (DSC), the Jaccard similarity coefficient (JSC), and the mean surface deviation (MSD), were used to quantitatively analyze the segmentation of anterior teeth including incisors and canines, premolars, and molars. The segmentation of the anterior teeth achieved a DSC up to 98%, a JSC of 97%, and an MSD of 0.11 mm compared with manual segmentation. For the premolars, the average values of DSC, JSC, and MSD were 98%, 96%, and 0.12 mm, respectively. The proposed method yielded a DSC of 95%, a JSC of 89%, and an MSD of 0.26 mm for molars. Aside from the interactive definition of label priors by the user, automatic tooth segmentation can be achieved in an average of 1.18 min. Conclusions: The proposed technique enables an efficient and reliable tooth segmentation from CBCT images. This study makes it clinically practical to segment teeth from CBCT images, thus facilitating pre- and interoperative uses of dental morphologies in maxillofacial and orthodontic treatments.« less

A perspective on tritium versus carbon-14: ensuring optimal label selection in pharmaceutical research and development.

PubMed

Krauser, Joel A

2013-01-01

Tritium ((3) H) and carbon-14 ((14) C) labels applied in pharmaceutical research and development each offer their own distinctive advantages and disadvantages coupled with benefits and risks. The advantages of (3) H have a higher specific activity, shorter half-life that allows more manageable waste remediation, lower material costs, and often more direct synthetic routes. The advantages of (14) C offer certain analytical benefits and less potential for label loss. Although (3) H labels offer several advantages, they might be overlooked as a viable option because of the concerns about its drawbacks. A main drawback often challenged is metabolic liability. These drawbacks, in some cases, might be overstated leading to underutilization of a perfectly viable option. As a consequence, label selection may automatically default to (14) C, which is a more conservative approach. To challenge this '(14) C-by-default' approach, pharmaceutical agents with strategically selected (3) H-labeling positions based on non-labeled metabolism data have been successfully implemented and evaluated for (3) H loss. From in-house results, the long term success of projects clearly would benefit from a thorough, objective, and balanced assessment regarding label selection ((3) H or (14) C). This assessment should be based on available project information and scientific knowledge. Important considerations are project applicability (preclinical and clinical phases), synthetic feasibility, costs, and timelines. Copyright © 2013 John Wiley & Sons, Ltd.

CT-guided automated detection of lung tumors on PET images

NASA Astrophysics Data System (ADS)

Cui, Yunfeng; Zhao, Binsheng; Akhurst, Timothy J.; Yan, Jiayong; Schwartz, Lawrence H.

2008-03-01

The calculation of standardized uptake values (SUVs) in tumors on serial [ 18F]2-fluoro-2-deoxy-D-glucose ( 18F-FDG) positron emission tomography (PET) images is often used for the assessment of therapy response. We present a computerized method that automatically detects lung tumors on 18F-FDG PET/Computed Tomography (CT) images using both anatomic and metabolic information. First, on CT images, relevant organs, including lung, bone, liver and spleen, are automatically identified and segmented based on their locations and intensity distributions. Hot spots (SUV >= 1.5) on 18F-FDG PET images are then labeled using the connected component analysis. The resultant "hot objects" (geometrically connected hot spots in three dimensions) that fall into, reside at the edges or are in the vicinity of the lungs are considered as tumor candidates. To determine true lesions, further analyses are conducted, including reduction of tumor candidates by the masking out of hot objects within CT-determined normal organs, and analysis of candidate tumors' locations, intensity distributions and shapes on both CT and PET. The method was applied to 18F-FDG-PET/CT scans from 9 patients, on which 31 target lesions had been identified by a nuclear medicine radiologist during a Phase II lung cancer clinical trial. Out of 31 target lesions, 30 (97%) were detected by the computer method. However, sensitivity and specificity were not estimated because not all lesions had been marked up in the clinical trial. The method effectively excluded the hot spots caused by mediastinum, liver, spleen, skeletal muscle and bone metastasis.

A Vocal-Based Analytical Method for Goose Behaviour Recognition

PubMed Central

Steen, Kim Arild; Therkildsen, Ole Roland; Karstoft, Henrik; Green, Ole

2012-01-01

Since human-wildlife conflicts are increasing, the development of cost-effective methods for reducing damage or conflict levels is important in wildlife management. A wide range of devices to detect and deter animals causing conflict are used for this purpose, although their effectiveness is often highly variable, due to habituation to disruptive or disturbing stimuli. Automated recognition of behaviours could form a critical component of a system capable of altering the disruptive stimuli to avoid this. In this paper we present a novel method to automatically recognise goose behaviour based on vocalisations from flocks of free-living barnacle geese (Branta leucopsis). The geese were observed and recorded in a natural environment, using a shielded shotgun microphone. The classification used Support Vector Machines (SVMs), which had been trained with labeled data. Greenwood Function Cepstral Coefficients (GFCC) were used as features for the pattern recognition algorithm, as they can be adjusted to the hearing capabilities of different species. Three behaviours are classified based in this approach, and the method achieves a good recognition of foraging behaviour (86–97% sensitivity, 89–98% precision) and a reasonable recognition of flushing (79–86%, 66–80%) and landing behaviour(73–91%, 79–92%). The Support Vector Machine has proven to be a robust classifier for this kind of classification, as generality and non-linear capabilities are important. We conclude that vocalisations can be used to automatically detect behaviour of conflict wildlife species, and as such, may be used as an integrated part of a wildlife management system. PMID:22737037

Quality Evaluation of Land-Cover Classification Using Convolutional Neural Network

NASA Astrophysics Data System (ADS)

Dang, Y.; Zhang, J.; Zhao, Y.; Luo, F.; Ma, W.; Yu, F.

2018-04-01

Land-cover classification is one of the most important products of earth observation, which focuses mainly on profiling the physical characters of the land surface with temporal and distribution attributes and contains the information of both natural and man-made coverage elements, such as vegetation, soil, glaciers, rivers, lakes, marsh wetlands and various man-made structures. In recent years, the amount of high-resolution remote sensing data has increased sharply. Accordingly, the volume of land-cover classification products increases, as well as the need to evaluate such frequently updated products that is a big challenge. Conventionally, the automatic quality evaluation of land-cover classification is made through pixel-based classifying algorithms, which lead to a much trickier task and consequently hard to keep peace with the required updating frequency. In this paper, we propose a novel quality evaluation approach for evaluating the land-cover classification by a scene classification method Convolutional Neural Network (CNN) model. By learning from remote sensing data, those randomly generated kernels that serve as filter matrixes evolved to some operators that has similar functions to man-crafted operators, like Sobel operator or Canny operator, and there are other kernels learned by the CNN model that are much more complex and can't be understood as existing filters. The method using CNN approach as the core algorithm serves quality-evaluation tasks well since it calculates a bunch of outputs which directly represent the image's membership grade to certain classes. An automatic quality evaluation approach for the land-cover DLG-DOM coupling data (DLG for Digital Line Graphic, DOM for Digital Orthophoto Map) will be introduced in this paper. The CNN model as an robustness method for image evaluation, then brought out the idea of an automatic quality evaluation approach for land-cover classification. Based on this experiment, new ideas of quality evaluation of DLG-DOM coupling land-cover classification or other kinds of labelled remote sensing data can be further studied.

Automatic limb identification and sleeping parameters assessment for pressure ulcer prevention.

PubMed

Baran Pouyan, Maziyar; Birjandtalab, Javad; Nourani, Mehrdad; Matthew Pompeo, M D

2016-08-01

Pressure ulcers (PUs) are common among vulnerable patients such as elderly, bedridden and diabetic. PUs are very painful for patients and costly for hospitals and nursing homes. Assessment of sleeping parameters on at-risk limbs is critical for ulcer prevention. An effective assessment depends on automatic identification and tracking of at-risk limbs. An accurate limb identification can be used to analyze the pressure distribution and assess risk for each limb. In this paper, we propose a graph-based clustering approach to extract the body limbs from the pressure data collected by a commercial pressure map system. A robust signature-based technique is employed to automatically label each limb. Finally, an assessment technique is applied to evaluate the experienced stress by each limb over time. The experimental results indicate high performance and more than 94% average accuracy of the proposed approach. Copyright © 2016 Elsevier Ltd. All rights reserved.

Towards Autonomous Agriculture: Automatic Ground Detection Using Trinocular Stereovision

PubMed Central

Reina, Giulio; Milella, Annalisa

2012-01-01

Autonomous driving is a challenging problem, particularly when the domain is unstructured, as in an outdoor agricultural setting. Thus, advanced perception systems are primarily required to sense and understand the surrounding environment recognizing artificial and natural structures, topology, vegetation and paths. In this paper, a self-learning framework is proposed to automatically train a ground classifier for scene interpretation and autonomous navigation based on multi-baseline stereovision. The use of rich 3D data is emphasized where the sensor output includes range and color information of the surrounding environment. Two distinct classifiers are presented, one based on geometric data that can detect the broad class of ground and one based on color data that can further segment ground into subclasses. The geometry-based classifier features two main stages: an adaptive training stage and a classification stage. During the training stage, the system automatically learns to associate geometric appearance of 3D stereo-generated data with class labels. Then, it makes predictions based on past observations. It serves as well to provide training labels to the color-based classifier. Once trained, the color-based classifier is able to recognize similar terrain classes in stereo imagery. The system is continuously updated online using the latest stereo readings, thus making it feasible for long range and long duration navigation, over changing environments. Experimental results, obtained with a tractor test platform operating in a rural environment, are presented to validate this approach, showing an average classification precision and recall of 91.0% and 77.3%, respectively.

Nonlocal Intracranial Cavity Extraction

PubMed Central

Manjón, José V.; Eskildsen, Simon F.; Coupé, Pierrick; Romero, José E.; Collins, D. Louis; Robles, Montserrat

2014-01-01

Automatic and accurate methods to estimate normalized regional brain volumes from MRI data are valuable tools which may help to obtain an objective diagnosis and followup of many neurological diseases. To estimate such regional brain volumes, the intracranial cavity volume (ICV) is often used for normalization. However, the high variability of brain shape and size due to normal intersubject variability, normal changes occurring over the lifespan, and abnormal changes due to disease makes the ICV estimation problem challenging. In this paper, we present a new approach to perform ICV extraction based on the use of a library of prelabeled brain images to capture the large variability of brain shapes. To this end, an improved nonlocal label fusion scheme based on BEaST technique is proposed to increase the accuracy of the ICV estimation. The proposed method is compared with recent state-of-the-art methods and the results demonstrate an improved performance both in terms of accuracy and reproducibility while maintaining a reduced computational burden. PMID:25328511

Urban Area Detection in Very High Resolution Remote Sensing Images Using Deep Convolutional Neural Networks.

PubMed

Tian, Tian; Li, Chang; Xu, Jinkang; Ma, Jiayi

2018-03-18

Detecting urban areas from very high resolution (VHR) remote sensing images plays an important role in the field of Earth observation. The recently-developed deep convolutional neural networks (DCNNs), which can extract rich features from training data automatically, have achieved outstanding performance on many image classification databases. Motivated by this fact, we propose a new urban area detection method based on DCNNs in this paper. The proposed method mainly includes three steps: (i) a visual dictionary is obtained based on the deep features extracted by pre-trained DCNNs; (ii) urban words are learned from labeled images; (iii) the urban regions are detected in a new image based on the nearest dictionary word criterion. The qualitative and quantitative experiments on different datasets demonstrate that the proposed method can obtain a remarkable overall accuracy (OA) and kappa coefficient. Moreover, it can also strike a good balance between the true positive rate (TPR) and false positive rate (FPR).

Automatic identification of bird targets with radar via patterns produced by wing flapping.

PubMed

Zaugg, Serge; Saporta, Gilbert; van Loon, Emiel; Schmaljohann, Heiko; Liechti, Felix

2008-09-06

Bird identification with radar is important for bird migration research, environmental impact assessments (e.g. wind farms), aircraft security and radar meteorology. In a study on bird migration, radar signals from birds, insects and ground clutter were recorded. Signals from birds show a typical pattern due to wing flapping. The data were labelled by experts into the four classes BIRD, INSECT, CLUTTER and UFO (unidentifiable signals). We present a classification algorithm aimed at automatic recognition of bird targets. Variables related to signal intensity and wing flapping pattern were extracted (via continuous wavelet transform). We used support vector classifiers to build predictive models. We estimated classification performance via cross validation on four datasets. When data from the same dataset were used for training and testing the classifier, the classification performance was extremely to moderately high. When data from one dataset were used for training and the three remaining datasets were used as test sets, the performance was lower but still extremely to moderately high. This shows that the method generalizes well across different locations or times. Our method provides a substantial gain of time when birds must be identified in large collections of radar signals and it represents the first substantial step in developing a real time bird identification radar system. We provide some guidelines and ideas for future research.

SonoNet: Real-Time Detection and Localisation of Fetal Standard Scan Planes in Freehand Ultrasound.

PubMed

Baumgartner, Christian F; Kamnitsas, Konstantinos; Matthew, Jacqueline; Fletcher, Tara P; Smith, Sandra; Koch, Lisa M; Kainz, Bernhard; Rueckert, Daniel

2017-11-01

Identifying and interpreting fetal standard scan planes during 2-D ultrasound mid-pregnancy examinations are highly complex tasks, which require years of training. Apart from guiding the probe to the correct location, it can be equally difficult for a non-expert to identify relevant structures within the image. Automatic image processing can provide tools to help experienced as well as inexperienced operators with these tasks. In this paper, we propose a novel method based on convolutional neural networks, which can automatically detect 13 fetal standard views in freehand 2-D ultrasound data as well as provide a localization of the fetal structures via a bounding box. An important contribution is that the network learns to localize the target anatomy using weak supervision based on image-level labels only. The network architecture is designed to operate in real-time while providing optimal output for the localization task. We present results for real-time annotation, retrospective frame retrieval from saved videos, and localization on a very large and challenging dataset consisting of images and video recordings of full clinical anomaly screenings. We found that the proposed method achieved an average F1-score of 0.798 in a realistic classification experiment modeling real-time detection, and obtained a 90.09% accuracy for retrospective frame retrieval. Moreover, an accuracy of 77.8% was achieved on the localization task.

Toward real-time quantification of fluorescence molecular probes using target/background ratio for guiding biopsy and endoscopic therapy of esophageal neoplasia.

PubMed

Jiang, Yang; Gong, Yuanzheng; Rubenstein, Joel H; Wang, Thomas D; Seibel, Eric J

2017-04-01

Multimodal endoscopy using fluorescence molecular probes is a promising method of surveying the entire esophagus to detect cancer progression. Using the fluorescence ratio of a target compared to a surrounding background, a quantitative value is diagnostic for progression from Barrett's esophagus to high-grade dysplasia (HGD) and esophageal adenocarcinoma (EAC). However, current quantification of fluorescent images is done only after the endoscopic procedure. We developed a Chan-Vese-based algorithm to segment fluorescence targets, and subsequent morphological operations to generate background, thus calculating target/background (T/B) ratios, potentially to provide real-time guidance for biopsy and endoscopic therapy. With an initial processing speed of 2 fps and by calculating the T/B ratio for each frame, our method provides quasireal-time quantification of the molecular probe labeling to the endoscopist. Furthermore, an automatic computer-aided diagnosis algorithm can be applied to the recorded endoscopic video, and the overall T/B ratio is calculated for each patient. The receiver operating characteristic curve was employed to determine the threshold for classification of HGD/EAC using leave-one-out cross-validation. With 92% sensitivity and 75% specificity to classify HGD/EAC, our automatic algorithm shows promising results for a surveillance procedure to help manage esophageal cancer and other cancers inspected by endoscopy.

Automatic detection of axillary lymphadenopathy on CT scans of untreated chronic lymphocytic leukemia patients

NASA Astrophysics Data System (ADS)

Liu, Jiamin; Hua, Jeremy; Chellappa, Vivek; Petrick, Nicholas; Sahiner, Berkman; Farooqui, Mohammed; Marti, Gerald; Wiestner, Adrian; Summers, Ronald M.

2012-03-01

Patients with chronic lymphocytic leukemia (CLL) have an increased frequency of axillary lymphadenopathy. Pretreatment CT scans can be used to upstage patients at the time of presentation and post-treatment CT scans can reduce the number of complete responses. In the current clinical workflow, the detection and diagnosis of lymph nodes is usually performed manually by examining all slices of CT images, which can be time consuming and highly dependent on the observer's experience. A system for automatic lymph node detection and measurement is desired. We propose a computer aided detection (CAD) system for axillary lymph nodes on CT scans in CLL patients. The lung is first automatically segmented and the patient's body in lung region is extracted to set the search region for lymph nodes. Multi-scale Hessian based blob detection is then applied to detect potential lymph nodes within the search region. Next, the detected potential candidates are segmented by fast level set method. Finally, features are calculated from the segmented candidates and support vector machine (SVM) classification is utilized for false positive reduction. Two blobness features, Frangi's and Li's, are tested and their free-response receiver operating characteristic (FROC) curves are generated to assess system performance. We applied our detection system to 12 patients with 168 axillary lymph nodes measuring greater than 10 mm. All lymph nodes are manually labeled as ground truth. The system achieved sensitivities of 81% and 85% at 2 false positives per patient for Frangi's and Li's blobness, respectively.

Feature-based Morphometry

PubMed Central

Toews, Matthew; Wells, William M.; Collins, Louis; Arbel, Tal

2013-01-01

This paper presents feature-based morphometry (FBM), a new, fully data-driven technique for identifying group-related differences in volumetric imagery. In contrast to most morphometry methods which assume one-to-one correspondence between all subjects, FBM models images as a collage of distinct, localized image features which may not be present in all subjects. FBM thus explicitly accounts for the case where the same anatomical tissue cannot be reliably identified in all subjects due to disease or anatomical variability. A probabilistic model describes features in terms of their appearance, geometry, and relationship to sub-groups of a population, and is automatically learned from a set of subject images and group labels. Features identified indicate group-related anatomical structure that can potentially be used as disease biomarkers or as a basis for computer-aided diagnosis. Scale-invariant image features are used, which reflect generic, salient patterns in the image. Experiments validate FBM clinically in the analysis of normal (NC) and Alzheimer’s (AD) brain images using the freely available OASIS database. FBM automatically identifies known structural differences between NC and AD subjects in a fully data-driven fashion, and obtains an equal error classification rate of 0.78 on new subjects. PMID:20426102

Reticulocyte analysis using flow cytometry.

PubMed

Corberand, J X

1996-12-01

Automation of the reticulocyte count by means of flow cytometry has considerably improved the quality of this investigation. This article deals firstly with the reasons for the poor performance of the microscopic technique and with the physiological principles underlying identification and classification of reticulocytes using RNA labeling. It then outlines the automated methods currently on the market, which can be classified in three categories: a) "general-purpose" cytofluorometers, which in clinical laboratories usually deal with lymphocyte immunophenotyping; b) the only commercially available cytofluorometer dedicated to the reticulocyte count; this automat has the advantage of requiring no human intervention as it merely needs to be fed with samples; c) hematology analyzers with specific modules for automatic counting of reticulocytes previously incubated with a non-fluorescent dye. Of the various fluorescent markers available, thiazole orange, DEQTC iodide and auramine are most often used for this basic hematology test. The quality of the count, the availability of new reticulocyte indices (maturation index, percentage of young reticulocytes) and rapidity of the count give this test renewed value in the practical approach to the diagnosis of anemia, and also open new perspectives in the surveillance of aplastic anemia after chemotherapy or bone marrow grafting.

Automatic FDG-PET-based tumor and metastatic lymph node segmentation in cervical cancer

NASA Astrophysics Data System (ADS)

Arbonès, Dídac R.; Jensen, Henrik G.; Loft, Annika; Munck af Rosenschöld, Per; Hansen, Anders Elias; Igel, Christian; Darkner, Sune

2014-03-01

Treatment of cervical cancer, one of the three most commonly diagnosed cancers worldwide, often relies on delineations of the tumour and metastases based on PET imaging using the contrast agent 18F-Fluorodeoxyglucose (FDG). We present a robust automatic algorithm for segmenting the gross tumour volume (GTV) and metastatic lymph nodes in such images. As the cervix is located next to the bladder and FDG is washed out through the urine, the PET-positive GTV and the bladder cannot be easily separated. Our processing pipeline starts with a histogram-based region of interest detection followed by level set segmentation. After that, morphological image operations combined with clustering, region growing, and nearest neighbour labelling allow to remove the bladder and to identify the tumour and metastatic lymph nodes. The proposed method was applied to 125 patients and no failure could be detected by visual inspection. We compared our segmentations with results from manual delineations of corresponding MR and CT images, showing that the detected GTV lays at least 97.5% within the MR/CT delineations. We conclude that the algorithm has a very high potential for substituting the tedious manual delineation of PET positive areas.

Automatic detection of atrial fibrillation in cardiac vibration signals.

PubMed

Brueser, C; Diesel, J; Zink, M D H; Winter, S; Schauerte, P; Leonhardt, S

2013-01-01

We present a study on the feasibility of the automatic detection of atrial fibrillation (AF) from cardiac vibration signals (ballistocardiograms/BCGs) recorded by unobtrusive bedmounted sensors. The proposed system is intended as a screening and monitoring tool in home-healthcare applications and not as a replacement for ECG-based methods used in clinical environments. Based on BCG data recorded in a study with 10 AF patients, we evaluate and rank seven popular machine learning algorithms (naive Bayes, linear and quadratic discriminant analysis, support vector machines, random forests as well as bagged and boosted trees) for their performance in separating 30 s long BCG epochs into one of three classes: sinus rhythm, atrial fibrillation, and artifact. For each algorithm, feature subsets of a set of statistical time-frequency-domain and time-domain features were selected based on the mutual information between features and class labels as well as first- and second-order interactions among features. The classifiers were evaluated on a set of 856 epochs by means of 10-fold cross-validation. The best algorithm (random forests) achieved a Matthews correlation coefficient, mean sensitivity, and mean specificity of 0.921, 0.938, and 0.982, respectively.

Automatic segmentation of the left ventricle cavity and myocardium in MRI data.

PubMed

Lynch, M; Ghita, O; Whelan, P F

2006-04-01

A novel approach for the automatic segmentation has been developed to extract the epi-cardium and endo-cardium boundaries of the left ventricle (lv) of the heart. The developed segmentation scheme takes multi-slice and multi-phase magnetic resonance (MR) images of the heart, transversing the short-axis length from the base to the apex. Each image is taken at one instance in the heart's phase. The images are segmented using a diffusion-based filter followed by an unsupervised clustering technique and the resulting labels are checked to locate the (lv) cavity. From cardiac anatomy, the closest pool of blood to the lv cavity is the right ventricle cavity. The wall between these two blood-pools (interventricular septum) is measured to give an approximate thickness for the myocardium. This value is used when a radial search is performed on a gradient image to find appropriate robust segments of the epi-cardium boundary. The robust edge segments are then joined using a normal spline curve. Experimental results are presented with very encouraging qualitative and quantitative results and a comparison is made against the state-of-the art level-sets method.

High-resolution in vivo Wistar rodent brain atlas based on T1 weighted image

NASA Astrophysics Data System (ADS)

Huang, Su; Lu, Zhongkang; Huang, Weimin; Seramani, Sankar; Ramasamy, Boominathan; Sekar, Sakthivel; Guan, Cuntai; Bhakoo, Kishore

2016-03-01

Image based atlases for rats brain have a significant impact on pre-clinical research. In this project we acquired T1-weighted images from Wistar rodent brains with fine 59μm isotropical resolution for generation of the atlas template image. By applying post-process procedures using a semi-automatic brain extraction method, we delineated the brain tissues from source data. Furthermore, we applied a symmetric group-wise normalization method to generate an optimized template of T1 image of rodent brain, then aligned our template to the Waxholm Space. In addition, we defined several simple and explicit landmarks to corresponding our template with the well known Paxinos stereotaxic reference system. Anchoring at the origin of the Waxholm Space, we applied piece-wise linear transformation method to map the voxels of the template into the coordinates system in Paxinos' stereotoxic coordinates to facilitate the labelling task. We also cross-referenced our data with both published rodent brain atlas and image atlases available online, methodologically labelling the template to produce a Wistar brain atlas identifying more than 130 structures. Particular attention was paid to the cortex and cerebellum, as these areas encompass the most researched aspects of brain functions. Moreover, we adopted the structure hierarchy and naming nomenclature common to various atlases, so that the names and hierarchy structure presented in the atlas are readily recognised for easy use. It is believed the atlas will present a useful tool in rodent brain functional and pharmaceutical studies.

Improving image quality for digital breast tomosynthesis: an automated detection and diffusion-based method for metal artifact reduction

NASA Astrophysics Data System (ADS)

Lu, Yao; Chan, Heang-Ping; Wei, Jun; Hadjiiski, Lubomir M.; Samala, Ravi K.

2017-10-01

In digital breast tomosynthesis (DBT), the high-attenuation metallic clips marking a previous biopsy site in the breast cause errors in the estimation of attenuation along the ray paths intersecting the markers during reconstruction, which result in interplane and inplane artifacts obscuring the visibility of subtle lesions. We proposed a new metal artifact reduction (MAR) method to improve image quality. Our method uses automatic detection and segmentation to generate a marker location map for each projection (PV). A voting technique based on the geometric correlation among different PVs is designed to reduce false positives (FPs) and to label the pixels on the PVs and the voxels in the imaged volume that represent the location and shape of the markers. An iterative diffusion method replaces the labeled pixels on the PVs with estimated tissue intensity from the neighboring regions while preserving the original pixel values in the neighboring regions. The inpainted PVs are then used for DBT reconstruction. The markers are repainted on the reconstructed DBT slices for radiologists’ information. The MAR method is independent of reconstruction techniques or acquisition geometry. For the training set, the method achieved 100% success rate with one FP in 19 views. For the test set, the success rate by view was 97.2% for core biopsy microclips and 66.7% for clusters of large post-lumpectomy markers with a total of 10 FPs in 58 views. All FPs were large dense benign calcifications that also generated artifacts if they were not corrected by MAR. For the views with successful detection, the metal artifacts were reduced to a level that was not visually apparent in the reconstructed slices. The visibility of breast lesions obscured by the reconstruction artifacts from the metallic markers was restored.

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.

Automated Glioblastoma Segmentation Based on a Multiparametric Structured Unsupervised Classification

PubMed Central

Juan-Albarracín, Javier; Fuster-Garcia, Elies; Manjón, José V.; Robles, Montserrat; Aparici, F.; Martí-Bonmatí, L.; García-Gómez, Juan M.

2015-01-01

Automatic brain tumour segmentation has become a key component for the future of brain tumour treatment. Currently, most of brain tumour segmentation approaches arise from the supervised learning standpoint, which requires a labelled training dataset from which to infer the models of the classes. The performance of these models is directly determined by the size and quality of the training corpus, whose retrieval becomes a tedious and time-consuming task. On the other hand, unsupervised approaches avoid these limitations but often do not reach comparable results than the supervised methods. In this sense, we propose an automated unsupervised method for brain tumour segmentation based on anatomical Magnetic Resonance (MR) images. Four unsupervised classification algorithms, grouped by their structured or non-structured condition, were evaluated within our pipeline. Considering the non-structured algorithms, we evaluated K-means, Fuzzy K-means and Gaussian Mixture Model (GMM), whereas as structured classification algorithms we evaluated Gaussian Hidden Markov Random Field (GHMRF). An automated postprocess based on a statistical approach supported by tissue probability maps is proposed to automatically identify the tumour classes after the segmentations. We evaluated our brain tumour segmentation method with the public BRAin Tumor Segmentation (BRATS) 2013 Test and Leaderboard datasets. Our approach based on the GMM model improves the results obtained by most of the supervised methods evaluated with the Leaderboard set and reaches the second position in the ranking. Our variant based on the GHMRF achieves the first position in the Test ranking of the unsupervised approaches and the seventh position in the general Test ranking, which confirms the method as a viable alternative for brain tumour segmentation. PMID:25978453

Comparison of automatic and visual methods used for image segmentation in Endodontics: a microCT study.

PubMed

Queiroz, Polyane Mazucatto; Rovaris, Karla; Santaella, Gustavo Machado; Haiter-Neto, Francisco; Freitas, Deborah Queiroz

2017-01-01

To calculate root canal volume and surface area in microCT images, an image segmentation by selecting threshold values is required, which can be determined by visual or automatic methods. Visual determination is influenced by the operator's visual acuity, while the automatic method is done entirely by computer algorithms. To compare between visual and automatic segmentation, and to determine the influence of the operator's visual acuity on the reproducibility of root canal volume and area measurements. Images from 31 extracted human anterior teeth were scanned with a μCT scanner. Three experienced examiners performed visual image segmentation, and threshold values were recorded. Automatic segmentation was done using the "Automatic Threshold Tool" available in the dedicated software provided by the scanner's manufacturer. Volume and area measurements were performed using the threshold values determined both visually and automatically. The paired Student's t-test showed no significant difference between visual and automatic segmentation methods regarding root canal volume measurements (p=0.93) and root canal surface (p=0.79). Although visual and automatic segmentation methods can be used to determine the threshold and calculate root canal volume and surface, the automatic method may be the most suitable for ensuring the reproducibility of threshold determination.

Automatic detection of mycobacterium tuberculosis using artificial intelligence

PubMed Central

Xiong, Yan; Ba, Xiaojun; Hou, Ao; Zhang, Kaiwen; Chen, Longsen

2018-01-01

Background Tuberculosis (TB) is a global issue that seriously endangers public health. Pathology is one of the most important means for diagnosing TB in clinical practice. To confirm TB as the diagnosis, finding specially stained TB bacilli under a microscope is critical. Because of the very small size and number of bacilli, it is a time-consuming and strenuous work even for experienced pathologists, and this strenuosity often leads to low detection rate and false diagnoses. We investigated the clinical efficacy of an artificial intelligence (AI)-assisted detection method for acid-fast stained TB bacillus. Methods We built a convolutional neural networks (CNN) model, named tuberculosis AI (TB-AI), specifically to recognize TB bacillus. The training set contains 45 samples, including 30 positive cases and 15 negative cases, where bacilli are labeled by human pathologists. Upon training the neural network model, 201 samples (108 positive cases and 93 negative cases) were collected as test set and used to examine TB-AI. We compared the diagnosis of TB-AI to the ground truth result provided by human pathologists, analyzed inconsistencies between AI and human, and adjusted the protocol accordingly. Trained TB-AI were run on the test data twice. Results Examined against the double confirmed diagnosis by pathologists both via microscopes and digital slides, TB-AI achieved 97.94% sensitivity and 83.65% specificity. Conclusions TB-AI can be a promising support system to detect stained TB bacilli and help make clinical decisions. It holds the potential to relieve the heavy workload of pathologists and decrease chances of missed diagnosis. Samples labeled as positive by TB-AI must be confirmed by pathologists, and those labeled as negative should be reviewed to make sure that the digital slides are qualified. PMID:29707349

Inter-labeler and intra-labeler variability of condition severity classification models using active and passive learning methods.

PubMed

Nissim, Nir; Shahar, Yuval; Elovici, Yuval; Hripcsak, George; Moskovitch, Robert

2017-09-01

Labeling instances by domain experts for classification is often time consuming and expensive. To reduce such labeling efforts, we had proposed the application of active learning (AL) methods, introduced our CAESAR-ALE framework for classifying the severity of clinical conditions, and shown its significant reduction of labeling efforts. The use of any of three AL methods (one well known [SVM-Margin], and two that we introduced [Exploitation and Combination_XA]) significantly reduced (by 48% to 64%) condition labeling efforts, compared to standard passive (random instance-selection) SVM learning. Furthermore, our new AL methods achieved maximal accuracy using 12% fewer labeled cases than the SVM-Margin AL method. However, because labelers have varying levels of expertise, a major issue associated with learning methods, and AL methods in particular, is how to best to use the labeling provided by a committee of labelers. First, we wanted to know, based on the labelers' learning curves, whether using AL methods (versus standard passive learning methods) has an effect on the Intra-labeler variability (within the learning curve of each labeler) and inter-labeler variability (among the learning curves of different labelers). Then, we wanted to examine the effect of learning (either passively or actively) from the labels created by the majority consensus of a group of labelers. We used our CAESAR-ALE framework for classifying the severity of clinical conditions, the three AL methods and the passive learning method, as mentioned above, to induce the classifications models. We used a dataset of 516 clinical conditions and their severity labeling, represented by features aggregated from the medical records of 1.9 million patients treated at Columbia University Medical Center. We analyzed the variance of the classification performance within (intra-labeler), and especially among (inter-labeler) the classification models that were induced by using the labels provided by seven labelers. We also compared the performance of the passive and active learning models when using the consensus label. The AL methods: produced, for the models induced from each labeler, smoother Intra-labeler learning curves during the training phase, compared to the models produced when using the passive learning method. The mean standard deviation of the learning curves of the three AL methods over all labelers (mean: 0.0379; range: [0.0182 to 0.0496]), was significantly lower (p=0.049) than the Intra-labeler standard deviation when using the passive learning method (mean: 0.0484; range: [0.0275-0.0724). Using the AL methods resulted in a lower mean Inter-labeler AUC standard deviation among the AUC values of the labelers' different models during the training phase, compared to the variance of the induced models' AUC values when using passive learning. The Inter-labeler AUC standard deviation, using the passive learning method (0.039), was almost twice as high as the Inter-labeler standard deviation using our two new AL methods (0.02 and 0.019, respectively). The SVM-Margin AL method resulted in an Inter-labeler standard deviation (0.029) that was higher by almost 50% than that of our two AL methods The difference in the inter-labeler standard deviation between the passive learning method and the SVM-Margin learning method was significant (p=0.042). The difference between the SVM-Margin and Exploitation method was insignificant (p=0.29), as was the difference between the Combination_XA and Exploitation methods (p=0.67). Finally, using the consensus label led to a learning curve that had a higher mean intra-labeler variance, but resulted eventually in an AUC that was at least as high as the AUC achieved using the gold standard label and that was always higher than the expected mean AUC of a randomly selected labeler, regardless of the choice of learning method (including a passive learning method). Using a paired t-test, the difference between the intra-labeler AUC standard deviation when using the consensus label, versus that value when using the other two labeling strategies, was significant only when using the passive learning method (p=0.014), but not when using any of the three AL methods. The use of AL methods, (a) reduces intra-labeler variability in the performance of the induced models during the training phase, and thus reduces the risk of halting the process at a local minimum that is significantly different in performance from the rest of the learned models; and (b) reduces Inter-labeler performance variance, and thus reduces the dependence on the use of a particular labeler. In addition, the use of a consensus label, agreed upon by a rather uneven group of labelers, might be at least as good as using the gold standard labeler, who might not be available, and certainly better than randomly selecting one of the group's individual labelers. Finally, using the AL methods: when provided by the consensus label reduced the intra-labeler AUC variance during the learning phase, compared to using passive learning. Copyright © 2017 Elsevier B.V. All rights reserved.

An Open-Source Label Atlas Correction Tool and Preliminary Results on Huntingtons Disease Whole-Brain MRI Atlases

PubMed Central

Forbes, Jessica L.; Kim, Regina E. Y.; Paulsen, Jane S.; Johnson, Hans J.

2016-01-01

The creation of high-quality medical imaging reference atlas datasets with consistent dense anatomical region labels is a challenging task. Reference atlases have many uses in medical image applications and are essential components of atlas-based segmentation tools commonly used for producing personalized anatomical measurements for individual subjects. The process of manual identification of anatomical regions by experts is regarded as a so-called gold standard; however, it is usually impractical because of the labor-intensive costs. Further, as the number of regions of interest increases, these manually created atlases often contain many small inconsistently labeled or disconnected regions that need to be identified and corrected. This project proposes an efficient process to drastically reduce the time necessary for manual revision in order to improve atlas label quality. We introduce the LabelAtlasEditor tool, a SimpleITK-based open-source label atlas correction tool distributed within the image visualization software 3D Slicer. LabelAtlasEditor incorporates several 3D Slicer widgets into one consistent interface and provides label-specific correction tools, allowing for rapid identification, navigation, and modification of the small, disconnected erroneous labels within an atlas. The technical details for the implementation and performance of LabelAtlasEditor are demonstrated using an application of improving a set of 20 Huntingtons Disease-specific multi-modal brain atlases. Additionally, we present the advantages and limitations of automatic atlas correction. After the correction of atlas inconsistencies and small, disconnected regions, the number of unidentified voxels for each dataset was reduced on average by 68.48%. PMID:27536233

An Open-Source Label Atlas Correction Tool and Preliminary Results on Huntingtons Disease Whole-Brain MRI Atlases.

PubMed

Forbes, Jessica L; Kim, Regina E Y; Paulsen, Jane S; Johnson, Hans J

2016-01-01

The creation of high-quality medical imaging reference atlas datasets with consistent dense anatomical region labels is a challenging task. Reference atlases have many uses in medical image applications and are essential components of atlas-based segmentation tools commonly used for producing personalized anatomical measurements for individual subjects. The process of manual identification of anatomical regions by experts is regarded as a so-called gold standard; however, it is usually impractical because of the labor-intensive costs. Further, as the number of regions of interest increases, these manually created atlases often contain many small inconsistently labeled or disconnected regions that need to be identified and corrected. This project proposes an efficient process to drastically reduce the time necessary for manual revision in order to improve atlas label quality. We introduce the LabelAtlasEditor tool, a SimpleITK-based open-source label atlas correction tool distributed within the image visualization software 3D Slicer. LabelAtlasEditor incorporates several 3D Slicer widgets into one consistent interface and provides label-specific correction tools, allowing for rapid identification, navigation, and modification of the small, disconnected erroneous labels within an atlas. The technical details for the implementation and performance of LabelAtlasEditor are demonstrated using an application of improving a set of 20 Huntingtons Disease-specific multi-modal brain atlases. Additionally, we present the advantages and limitations of automatic atlas correction. After the correction of atlas inconsistencies and small, disconnected regions, the number of unidentified voxels for each dataset was reduced on average by 68.48%.

Inter-Labeler and Intra-Labeler Variability of Condition Severity Classification Models Using Active and Passive Learning Methods

PubMed Central

Nissim, Nir; Shahar, Yuval; Boland, Mary Regina; Tatonetti, Nicholas P; Elovici, Yuval; Hripcsak, George; Moskovitch, Robert

2018-01-01

Background and Objectives Labeling instances by domain experts for classification is often time consuming and expensive. To reduce such labeling efforts, we had proposed the application of active learning (AL) methods, introduced our CAESAR-ALE framework for classifying the severity of clinical conditions, and shown its significant reduction of labeling efforts. The use of any of three AL methods (one well known [SVM-Margin], and two that we introduced [Exploitation and Combination_XA]) significantly reduced (by 48% to 64%) condition labeling efforts, compared to standard passive (random instance-selection) SVM learning. Furthermore, our new AL methods achieved maximal accuracy using 12% fewer labeled cases than the SVM-Margin AL method. However, because labelers have varying levels of expertise, a major issue associated with learning methods, and AL methods in particular, is how to best to use the labeling provided by a committee of labelers. First, we wanted to know, based on the labelers’ learning curves, whether using AL methods (versus standard passive learning methods) has an effect on the Intra-labeler variability (within the learning curve of each labeler) and inter-labeler variability (among the learning curves of different labelers). Then, we wanted to examine the effect of learning (either passively or actively) from the labels created by the majority consensus of a group of labelers. Methods We used our CAESAR-ALE framework for classifying the severity of clinical conditions, the three AL methods and the passive learning method, as mentioned above, to induce the classifications models. We used a dataset of 516 clinical conditions and their severity labeling, represented by features aggregated from the medical records of 1.9 million patients treated at Columbia University Medical Center. We analyzed the variance of the classification performance within (intra-labeler), and especially among (inter-labeler) the classification models that were induced by using the labels provided by seven labelers. We also compared the performance of the passive and active learning models when using the consensus label. Results The AL methods produced, for the models induced from each labeler, smoother Intra-labeler learning curves during the training phase, compared to the models produced when using the passive learning method. The mean standard deviation of the learning curves of the three AL methods over all labelers (mean: 0.0379; range: [0.0182 to 0.0496]), was significantly lower (p = 0.049) than the Intra-labeler standard deviation when using the passive learning method (mean: 0.0484; range: [0.0275 to 0.0724). Using the AL methods resulted in a lower mean Inter-labeler AUC standard deviation among the AUC values of the labelers’ different models during the training phase, compared to the variance of the induced models’ AUC values when using passive learning. The Inter-labeler AUC standard deviation, using the passive learning method (0.039), was almost twice as high as the Inter-labeler standard deviation using our two new AL methods (0.02 and 0.019, respectively). The SVM-Margin AL method resulted in an Inter-labeler standard deviation (0.029) that was higher by almost 50% than that of our two AL methods. The difference in the inter-labeler standard deviation between the passive learning method and the SVM-Margin learning method was significant (p = 0.042). The difference between the SVM-Margin and Exploitation method was insignificant (p = 0.29), as was the difference between the Combination_XA and Exploitation methods (p = 0.67). Finally, using the consensus label led to a learning curve that had a higher mean intra-labeler variance, but resulted eventually in an AUC that was at least as high as the AUC achieved using the gold standard label and that was always higher than the expected mean AUC of a randomly selected labeler, regardless of the choice of learning method (including a passive learning method). Using a paired t-test, the difference between the intra-labeler AUC standard deviation when using the consensus label, versus that value when using the other two labeling strategies, was significant only when using the passive learning method (p = 0.014), but not when using any of the three AL methods. Conclusions The use of AL methods, (a) reduces intra-labeler variability in the performance of the induced models during the training phase, and thus reduces the risk of halting the process at a local minimum that is significantly different in performance from the rest of the learned models; and (b) reduces Inter-labeler performance variance, and thus reduces the dependence on the use of a particular labeler. In addition, the use of a consensus label, agreed upon by a rather uneven group of labelers, might be at least as good as using the gold standard labeler, who might not be available, and certainly better than randomly selecting one of the group’s individual labelers. Finally, using the AL methods when provided by the consensus label reduced the intra-labeler AUC variance during the learning phase, compared to using passive learning. PMID:28456512

Homography-based multiple-camera person-tracking

NASA Astrophysics Data System (ADS)

Turk, Matthew R.

2009-01-01

Multiple video cameras are cheaply installed overlooking an area of interest. While computerized single-camera tracking is well-developed, multiple-camera tracking is a relatively new problem. The main multi-camera problem is to give the same tracking label to all projections of a real-world target. This is called the consistent labelling problem. Khan and Shah (2003) introduced a method to use field of view lines to perform multiple-camera tracking. The method creates inter-camera meta-target associations when objects enter at the scene edges. They also said that a plane-induced homography could be used for tracking, but this method was not well described. Their homography-based system would not work if targets use only one side of a camera to enter the scene. This paper overcomes this limitation and fully describes a practical homography-based tracker. A new method to find the feet feature is introduced. The method works especially well if the camera is tilted, when using the bottom centre of the target's bounding-box would produce inaccurate results. The new method is more accurate than the bounding-box method even when the camera is not tilted. Next, a method is presented that uses a series of corresponding point pairs "dropped" by oblivious, live human targets to find a plane-induced homography. The point pairs are created by tracking the feet locations of moving targets that were associated using the field of view line method. Finally, a homography-based multiple-camera tracking algorithm is introduced. Rules governing when to create the homography are specified. The algorithm ensures that homography-based tracking only starts after a non-degenerate homography is found. The method works when not all four field of view lines are discoverable; only one line needs to be found to use the algorithm. To initialize the system, the operator must specify pairs of overlapping cameras. Aside from that, the algorithm is fully automatic and uses the natural movement of live targets for training. No calibration is required. Testing shows that the algorithm performs very well in real-world sequences. The consistent labelling problem is solved, even for targets that appear via in-scene entrances. Full occlusions are handled. Although implemented in Matlab, the multiple-camera tracking system runs at eight frames per second. A faster implementation would be suitable for real-world use at typical video frame rates.

3D exemplar-based random walks for tooth segmentation from cone-beam computed tomography images.

PubMed

Pei, Yuru; Ai, Xingsheng; Zha, Hongbin; Xu, Tianmin; Ma, Gengyu

2016-09-01

Tooth segmentation is an essential step in acquiring patient-specific dental geometries from cone-beam computed tomography (CBCT) images. Tooth segmentation from CBCT images is still a challenging task considering the comparatively low image quality caused by the limited radiation dose, as well as structural ambiguities from intercuspation and nearby alveolar bones. The goal of this paper is to present and discuss the latest accomplishments in semisupervised tooth segmentation with adaptive 3D shape constraints. The authors propose a 3D exemplar-based random walk method of tooth segmentation from CBCT images. The proposed method integrates semisupervised label propagation and regularization by 3D exemplar registration. To begin with, the pure random walk method is to get an initial segmentation of the teeth, which tends to be erroneous because of the structural ambiguity of CBCT images. And then, as an iterative refinement, the authors conduct a regularization by using 3D exemplar registration, as well as label propagation by random walks with soft constraints, to improve the tooth segmentation. In the first stage of the iteration, 3D exemplars with well-defined topologies are adapted to fit the tooth contours, which are obtained from the random walks based segmentation. The soft constraints on voxel labeling are defined by shape-based foreground dentine probability acquired by the exemplar registration, as well as the appearance-based probability from a support vector machine (SVM) classifier. In the second stage, the labels of the volume-of-interest (VOI) are updated by the random walks with soft constraints. The two stages are optimized iteratively. Instead of the one-shot label propagation in the VOI, an iterative refinement process can achieve a reliable tooth segmentation by virtue of exemplar-based random walks with adaptive soft constraints. The proposed method was applied for tooth segmentation of twenty clinically captured CBCT images. Three metrics, including the Dice similarity coefficient (DSC), the Jaccard similarity coefficient (JSC), and the mean surface deviation (MSD), were used to quantitatively analyze the segmentation of anterior teeth including incisors and canines, premolars, and molars. The segmentation of the anterior teeth achieved a DSC up to 98%, a JSC of 97%, and an MSD of 0.11 mm compared with manual segmentation. For the premolars, the average values of DSC, JSC, and MSD were 98%, 96%, and 0.12 mm, respectively. The proposed method yielded a DSC of 95%, a JSC of 89%, and an MSD of 0.26 mm for molars. Aside from the interactive definition of label priors by the user, automatic tooth segmentation can be achieved in an average of 1.18 min. The proposed technique enables an efficient and reliable tooth segmentation from CBCT images. This study makes it clinically practical to segment teeth from CBCT images, thus facilitating pre- and interoperative uses of dental morphologies in maxillofacial and orthodontic treatments.

Applying Machine Learning to Star Cluster Classification

NASA Astrophysics Data System (ADS)

Fedorenko, Kristina; Grasha, Kathryn; Calzetti, Daniela; Mahadevan, Sridhar

2016-01-01

Catalogs describing populations of star clusters are essential in investigating a range of important issues, from star formation to galaxy evolution. Star cluster catalogs are typically created in a two-step process: in the first step, a catalog of sources is automatically produced; in the second step, each of the extracted sources is visually inspected by 3-to-5 human classifiers and assigned a category. Classification by humans is labor-intensive and time consuming, thus it creates a bottleneck, and substantially slows down progress in star cluster research.We seek to automate the process of labeling star clusters (the second step) through applying supervised machine learning techniques. This will provide a fast, objective, and reproducible classification. Our data is HST (WFC3 and ACS) images of galaxies in the distance range of 3.5-12 Mpc, with a few thousand star clusters already classified by humans as a part of the LEGUS (Legacy ExtraGalactic UV Survey) project. The classification is based on 4 labels (Class 1 - symmetric, compact cluster; Class 2 - concentrated object with some degree of asymmetry; Class 3 - multiple peak system, diffuse; and Class 4 - spurious detection). We start by looking at basic machine learning methods such as decision trees. We then proceed to evaluate performance of more advanced techniques, focusing on convolutional neural networks and other Deep Learning methods. We analyze the results, and suggest several directions for further improvement.

Extracting PICO Sentences from Clinical Trial Reports using Supervised Distant Supervision

PubMed Central

Wallace, Byron C.; Kuiper, Joël; Sharma, Aakash; Zhu, Mingxi (Brian); Marshall, Iain J.

2016-01-01

Systematic reviews underpin Evidence Based Medicine (EBM) by addressing precise clinical questions via comprehensive synthesis of all relevant published evidence. Authors of systematic reviews typically define a Population/Problem, Intervention, Comparator, and Outcome (a PICO criteria) of interest, and then retrieve, appraise and synthesize results from all reports of clinical trials that meet these criteria. Identifying PICO elements in the full-texts of trial reports is thus a critical yet time-consuming step in the systematic review process. We seek to expedite evidence synthesis by developing machine learning models to automatically extract sentences from articles relevant to PICO elements. Collecting a large corpus of training data for this task would be prohibitively expensive. Therefore, we derive distant supervision (DS) with which to train models using previously conducted reviews. DS entails heuristically deriving ‘soft’ labels from an available structured resource. However, we have access only to unstructured, free-text summaries of PICO elements for corresponding articles; we must derive from these the desired sentence-level annotations. To this end, we propose a novel method – supervised distant supervision (SDS) – that uses a small amount of direct supervision to better exploit a large corpus of distantly labeled instances by learning to pseudo-annotate articles using the available DS. We show that this approach tends to outperform existing methods with respect to automated PICO extraction. PMID:27746703

Lesion Detection in CT Images Using Deep Learning Semantic Segmentation Technique

NASA Astrophysics Data System (ADS)

Kalinovsky, A.; Liauchuk, V.; Tarasau, A.

2017-05-01

In this paper, the problem of automatic detection of tuberculosis lesion on 3D lung CT images is considered as a benchmark for testing out algorithms based on a modern concept of Deep Learning. For training and testing of the algorithms a domestic dataset of 338 3D CT scans of tuberculosis patients with manually labelled lesions was used. The algorithms which are based on using Deep Convolutional Networks were implemented and applied in three different ways including slice-wise lesion detection in 2D images using semantic segmentation, slice-wise lesion detection in 2D images using sliding window technique as well as straightforward detection of lesions via semantic segmentation in whole 3D CT scans. The algorithms demonstrate superior performance compared to algorithms based on conventional image analysis methods.

Metric Learning for Hyperspectral Image Segmentation

NASA Technical Reports Server (NTRS)

Bue, Brian D.; Thompson, David R.; Gilmore, Martha S.; Castano, Rebecca

2011-01-01

We present a metric learning approach to improve the performance of unsupervised hyperspectral image segmentation. Unsupervised spatial segmentation can assist both user visualization and automatic recognition of surface features. Analysts can use spatially-continuous segments to decrease noise levels and/or localize feature boundaries. However, existing segmentation methods use tasks-agnostic measures of similarity. Here we learn task-specific similarity measures from training data, improving segment fidelity to classes of interest. Multiclass Linear Discriminate Analysis produces a linear transform that optimally separates a labeled set of training classes. The defines a distance metric that generalized to a new scenes, enabling graph-based segmentation that emphasizes key spectral features. We describe tests based on data from the Compact Reconnaissance Imaging Spectrometer (CRISM) in which learned metrics improve segment homogeneity with respect to mineralogical classes.

An Approach to Extract Moving Objects from Mls Data Using a Volumetric Background Representation

NASA Astrophysics Data System (ADS)

Gehrung, J.; Hebel, M.; Arens, M.; Stilla, U.

2017-05-01

Data recorded by mobile LiDAR systems (MLS) can be used for the generation and refinement of city models or for the automatic detection of long-term changes in the public road space. Since for this task only static structures are of interest, all mobile objects need to be removed. This work presents a straightforward but powerful approach to remove the subclass of moving objects. A probabilistic volumetric representation is utilized to separate MLS measurements recorded by a Velodyne HDL-64E into mobile objects and static background. The method was subjected to a quantitative and a qualitative examination using multiple datasets recorded by a mobile mapping platform. The results show that depending on the chosen octree resolution 87-95% of the measurements are labeled correctly.

Variability and trends in area, location, cloudiness and cloud top temperature of the ITCZ in the east to central Pacific over the past 30 years

NASA Astrophysics Data System (ADS)

Magnusdottir, G.; Bain, C.; Smyth, P.; Stern, H.; Knapp, K.

2010-12-01

A team of multidisciplinary scientists at the University of California Irvine has developed a novel spatial-temporal statistical model to detect the presence/absence of the ITCZ in high-resolution instantaneous satellite data. The Markov random field (MRF) statistical model is briefly introduced and compared to other automatic methods such as thresholding. The statistical model emulates human identification of the ITCZ as an envelope of convective activity (as seen in different fields) plus produces the same results given the same data, which may not be the case for human analysis. The MRF statistical model uses satellite data at a given location as well as information from its neighboring points (in time and space) to decide whether the given point is classified as ITCZ or non-ITCZ. Two different labels of ITCZ occurrence are produced. IR-only labels result from running the model with 3-hourly infrared data available for a 30 yr period, 1980--2009. Data-all labels result from running the model with additional satellite data (visible and total precipitable water), available from 1995--2008. IR-only labels detect less area of ITCZ than Data-all labels, especially where the ITCZ is shallower. Yet, qualitatively, the results for the two sets of labels are similar. Here, we focus on results from the IR-only labels over the east Pacific for the past 30 summer half-years (May to October). The IR data are from the HURSAT Basin data of NOAA’s National Climatic Data Center, which are derived from ISCCP B1 data. The data were collected from radiometers on different geostationary satellites. The IR channel data were recalibrated to reduce inter-satellite differences. The seasonal distribution of the ITCZ through the summer half year is presented, showing typical location and extent. The ITCZ is mostly confined to the eastern Pacific in May, and becomes more zonally distributed towards September and October each year. Northward and westward shifts in the location of the ITCZ occur in line with the seasonal cycle and warm sea surface temperatures. The ITCZ is quite variable on interannual time scales and highly correlated with ENSO variability. When we removed the ENSO signal from labels, interannual variability remained high. The resulting IR-only labels, showed no evidence of a trend in location, nor evidence of a trend in area for the 30 yr period. However, a trend in cloudiness within labels is observed and will be discussed.

Labeling Defects in CT Images of Hardwood Logs with Species-Dependent and Species-Independent Classifiers

Treesearch

Pei Li; Jing He; A. Lynn Abbott; Daniel L. Schmoldt

1996-01-01

This paper analyses computed tomography (CT) images of hardwood logs, with the goal of locating internal defects. The ability to detect and identify defects automatically is a critical component of efficiency improvements for future sawmills and veneer mills. This paper describes an approach in which 1) histogram equalization is used during preprocessing to normalize...

Impact of Machine-Translated Text on Entity and Relationship Extraction

DTIC Science & Technology

2014-12-01

20 1 1. Introduction Using social network analysis tools is an important asset in...semantic modeling software to automatically build detailed network models from unstructured text. Contour imports unstructured text and then maps the text...onto an existing ontology of frames at the sentence level, using FrameNet, a structured language model, and through Semantic Role Labeling ( SRL

A New Approach to Automated Labeling of Internal Features of Hardwood Logs Using CT Images

Treesearch

Daniel L. Schmoldt; Pei Li; A. Lynn Abbott

1996-01-01

The feasibility of automatically identifying internal features of hardwood logs using CT imagery has been established previously. Features of primary interest are bark, knots, voids, decay, and clear wood. Our previous approach: filtered original CT images, applied histogram segmentation, grew volumes to extract 3-d regions, and applied a rule base, with Dempster-...

Automated 3D Phenotype Analysis Using Data Mining

PubMed Central

Plyusnin, Ilya; Evans, Alistair R.; Karme, Aleksis; Gionis, Aristides; Jernvall, Jukka

2008-01-01

The ability to analyze and classify three-dimensional (3D) biological morphology has lagged behind the analysis of other biological data types such as gene sequences. Here, we introduce the techniques of data mining to the study of 3D biological shapes to bring the analyses of phenomes closer to the efficiency of studying genomes. We compiled five training sets of highly variable morphologies of mammalian teeth from the MorphoBrowser database. Samples were labeled either by dietary class or by conventional dental types (e.g. carnassial, selenodont). We automatically extracted a multitude of topological attributes using Geographic Information Systems (GIS)-like procedures that were then used in several combinations of feature selection schemes and probabilistic classification models to build and optimize classifiers for predicting the labels of the training sets. In terms of classification accuracy, computational time and size of the feature sets used, non-repeated best-first search combined with 1-nearest neighbor classifier was the best approach. However, several other classification models combined with the same searching scheme proved practical. The current study represents a first step in the automatic analysis of 3D phenotypes, which will be increasingly valuable with the future increase in 3D morphology and phenomics databases. PMID:18320060

Game-powered machine learning

PubMed Central

Barrington, Luke; Turnbull, Douglas; Lanckriet, Gert

2012-01-01

Searching for relevant content in a massive amount of multimedia information is facilitated by accurately annotating each image, video, or song with a large number of relevant semantic keywords, or tags. We introduce game-powered machine learning, an integrated approach to annotating multimedia content that combines the effectiveness of human computation, through online games, with the scalability of machine learning. We investigate this framework for labeling music. First, a socially-oriented music annotation game called Herd It collects reliable music annotations based on the “wisdom of the crowds.” Second, these annotated examples are used to train a supervised machine learning system. Third, the machine learning system actively directs the annotation games to collect new data that will most benefit future model iterations. Once trained, the system can automatically annotate a corpus of music much larger than what could be labeled using human computation alone. Automatically annotated songs can be retrieved based on their semantic relevance to text-based queries (e.g., “funky jazz with saxophone,” “spooky electronica,” etc.). Based on the results presented in this paper, we find that actively coupling annotation games with machine learning provides a reliable and scalable approach to making searchable massive amounts of multimedia data. PMID:22460786

Game-powered machine learning.

PubMed

Barrington, Luke; Turnbull, Douglas; Lanckriet, Gert

2012-04-24

Searching for relevant content in a massive amount of multimedia information is facilitated by accurately annotating each image, video, or song with a large number of relevant semantic keywords, or tags. We introduce game-powered machine learning, an integrated approach to annotating multimedia content that combines the effectiveness of human computation, through online games, with the scalability of machine learning. We investigate this framework for labeling music. First, a socially-oriented music annotation game called Herd It collects reliable music annotations based on the "wisdom of the crowds." Second, these annotated examples are used to train a supervised machine learning system. Third, the machine learning system actively directs the annotation games to collect new data that will most benefit future model iterations. Once trained, the system can automatically annotate a corpus of music much larger than what could be labeled using human computation alone. Automatically annotated songs can be retrieved based on their semantic relevance to text-based queries (e.g., "funky jazz with saxophone," "spooky electronica," etc.). Based on the results presented in this paper, we find that actively coupling annotation games with machine learning provides a reliable and scalable approach to making searchable massive amounts of multimedia data.

Application of Classification Methods for Forecasting Mid-Term Power Load Patterns

NASA Astrophysics Data System (ADS)

Piao, Minghao; Lee, Heon Gyu; Park, Jin Hyoung; Ryu, Keun Ho

Currently an automated methodology based on data mining techniques is presented for the prediction of customer load patterns in long duration load profiles. The proposed approach in this paper consists of three stages: (i) data preprocessing: noise or outlier is removed and the continuous attribute-valued features are transformed to discrete values, (ii) cluster analysis: k-means clustering is used to create load pattern classes and the representative load profiles for each class and (iii) classification: we evaluated several supervised learning methods in order to select a suitable prediction method. According to the proposed methodology, power load measured from AMR (automatic meter reading) system, as well as customer indexes, were used as inputs for clustering. The output of clustering was the classification of representative load profiles (or classes). In order to evaluate the result of forecasting load patterns, the several classification methods were applied on a set of high voltage customers of the Korea power system and derived class labels from clustering and other features are used as input to produce classifiers. Lastly, the result of our experiments was presented.

Coupled dimensionality reduction and classification for supervised and semi-supervised multilabel learning

PubMed Central

Gönen, Mehmet

2014-01-01

Coupled training of dimensionality reduction and classification is proposed previously to improve the prediction performance for single-label problems. Following this line of research, in this paper, we first introduce a novel Bayesian method that combines linear dimensionality reduction with linear binary classification for supervised multilabel learning and present a deterministic variational approximation algorithm to learn the proposed probabilistic model. We then extend the proposed method to find intrinsic dimensionality of the projected subspace using automatic relevance determination and to handle semi-supervised learning using a low-density assumption. We perform supervised learning experiments on four benchmark multilabel learning data sets by comparing our method with baseline linear dimensionality reduction algorithms. These experiments show that the proposed approach achieves good performance values in terms of hamming loss, average AUC, macro F1, and micro F1 on held-out test data. The low-dimensional embeddings obtained by our method are also very useful for exploratory data analysis. We also show the effectiveness of our approach in finding intrinsic subspace dimensionality and semi-supervised learning tasks. PMID:24532862

Coupled dimensionality reduction and classification for supervised and semi-supervised multilabel learning.

PubMed

Gönen, Mehmet

2014-03-01

Coupled training of dimensionality reduction and classification is proposed previously to improve the prediction performance for single-label problems. Following this line of research, in this paper, we first introduce a novel Bayesian method that combines linear dimensionality reduction with linear binary classification for supervised multilabel learning and present a deterministic variational approximation algorithm to learn the proposed probabilistic model. We then extend the proposed method to find intrinsic dimensionality of the projected subspace using automatic relevance determination and to handle semi-supervised learning using a low-density assumption. We perform supervised learning experiments on four benchmark multilabel learning data sets by comparing our method with baseline linear dimensionality reduction algorithms. These experiments show that the proposed approach achieves good performance values in terms of hamming loss, average AUC, macro F 1 , and micro F 1 on held-out test data. The low-dimensional embeddings obtained by our method are also very useful for exploratory data analysis. We also show the effectiveness of our approach in finding intrinsic subspace dimensionality and semi-supervised learning tasks.

Reliability of Three Dimentional Pseudo-continuous Arterial Spin Labeling: A Volumetric Cerebral Perfusion Imaging with Different Post-labeling Time and Functional State in Health Adults.

PubMed

Liu, Meng-Qi; Chen, Zhi-Ye; Ma, Lin

2018-03-30

Objective To evaluate the reliability of three dimensional spiral fast spin echo pseudo-continuous arterial spin labeling (3D pc-ASL) in measuring cerebral blood flow (CBF) with different post-labeling delay time (PLD) in the resting state and the right finger taping state. Methods 3D pc-ASL and three dimensional T1-weighted fast spoiled gradient recalled echo (3D T1-FSPGR) sequence were applied to eight healthy subjects twice at the same time each day for one week interval. ASL data acquisition was performed with post-labeling delay time (PLD) 1.5 seconds and 2.0 seconds in the resting state and the right finger taping state respectively. CBF mapping was calculated and CBF value of both the gray matter (GM) and white matter (WM) was automatically extracted. The reliability was evaluated using the intraclass correlation coefficient (ICC) and Bland and Altman plot. Results ICC of the GM (0.84) and WM (0.92) was lower at PLD 1.5 seconds than that (GM, 0.88; WM, 0.94) at PLD 2.0 seconds in the resting state, and ICC of GM (0.88) was higher in the right finger taping state than that in the resting state at PLD 1.5 seconds. ICC of the GM and WM was 0.71 and 0.78 for PLD 1.5 seconds and PLD 2.0 seconds in the resting state at the first scan, and ICC of the GM and WM was 0.83 and 0.79 at the second scan, respectively. Conclusion This work demonstrated that 3D pc-ASL might be a reliable imaging technique to measure CBF over the whole brain at different PLD in the resting state or controlled state.

Discovering motion primitives for unsupervised grouping and one-shot learning of human actions, gestures, and expressions.

PubMed

Yang, Yang; Saleemi, Imran; Shah, Mubarak

2013-07-01

This paper proposes a novel representation of articulated human actions and gestures and facial expressions. The main goals of the proposed approach are: 1) to enable recognition using very few examples, i.e., one or k-shot learning, and 2) meaningful organization of unlabeled datasets by unsupervised clustering. Our proposed representation is obtained by automatically discovering high-level subactions or motion primitives, by hierarchical clustering of observed optical flow in four-dimensional, spatial, and motion flow space. The completely unsupervised proposed method, in contrast to state-of-the-art representations like bag of video words, provides a meaningful representation conducive to visual interpretation and textual labeling. Each primitive action depicts an atomic subaction, like directional motion of limb or torso, and is represented by a mixture of four-dimensional Gaussian distributions. For one--shot and k-shot learning, the sequence of primitive labels discovered in a test video are labeled using KL divergence, and can then be represented as a string and matched against similar strings of training videos. The same sequence can also be collapsed into a histogram of primitives or be used to learn a Hidden Markov model to represent classes. We have performed extensive experiments on recognition by one and k-shot learning as well as unsupervised action clustering on six human actions and gesture datasets, a composite dataset, and a database of facial expressions. These experiments confirm the validity and discriminative nature of the proposed representation.

[Application of automatic photography in Schistosoma japonicum miracidium hatching experiments].

PubMed

Ming-Li, Zhou; Ai-Ling, Cai; Xue-Feng, Wang

2016-05-20

To explore the value of automatic photography in the observation of results of Schistosoma japonicum miracidium hatching experiments. Some fresh S. japonicum eggs were added into cow feces, and the samples of feces were divided into a low infested experimental group and a high infested group (40 samples each group). In addition, there was a negative control group with 40 samples of cow feces without S. japonicum eggs. The conventional nylon bag S. japonicum miracidium hatching experiments were performed. The process was observed with the method of flashlight and magnifying glass combined with automatic video (automatic photography method), and, at the same time, with the naked eye observation method. The results were compared. In the low infested group, the miracidium positive detection rates were 57.5% and 85.0% by the naked eye observation method and automatic photography method, respectively ( χ 2 = 11.723, P < 0.05). In the high infested group, the positive detection rates were 97.5% and 100% by the naked eye observation method and automatic photography method, respectively ( χ 2 = 1.253, P > 0.05). In the two infested groups, the average positive detection rates were 77.5% and 92.5% by the naked eye observation method and automatic photography method, respectively ( χ 2 = 6.894, P < 0.05). The automatic photography can effectively improve the positive detection rate in the S. japonicum miracidium hatching experiments.

Automated regional analysis of B-mode ultrasound images of skeletal muscle movement

PubMed Central

Darby, John; Costen, Nicholas; Loram, Ian D.

2012-01-01

To understand the functional significance of skeletal muscle anatomy, a method of quantifying local shape changes in different tissue structures during dynamic tasks is required. Taking advantage of the good spatial and temporal resolution of B-mode ultrasound imaging, we describe a method of automatically segmenting images into fascicle and aponeurosis regions and tracking movement of features, independently, in localized portions of each tissue. Ultrasound images (25 Hz) of the medial gastrocnemius muscle were collected from eight participants during ankle joint rotation (2° and 20°), isometric contractions (1, 5, and 50 Nm), and deep knee bends. A Kanade-Lucas-Tomasi feature tracker was used to identify and track any distinctive and persistent features within the image sequences. A velocity field representation of local movement was then found and subdivided between fascicle and aponeurosis regions using segmentations from a multiresolution active shape model (ASM). Movement in each region was quantified by interpolating the effect of the fields on a set of probes. ASM segmentation results were compared with hand-labeled data, while aponeurosis and fascicle movement were compared with results from a previously documented cross-correlation approach. ASM provided good image segmentations (<1 mm average error), with fully automatic initialization possible in sequences from seven participants. Feature tracking provided similar length change results to the cross-correlation approach for small movements, while outperforming it in larger movements. The proposed method provides the potential to distinguish between active and passive changes in muscle shape and model strain distributions during different movements/conditions and quantify nonhomogeneous strain along aponeuroses. PMID:22033532

Optimization of automated large-scale production of [(18)F]fluoroethylcholine for PET prostate cancer imaging.

PubMed

Pascali, Giancarlo; D'Antonio, Luca; Bovone, Paola; Gerundini, Paolo; August, Thorsten

2009-07-01

PET tumor imaging is gaining importance in current clinical practice. FDG-PET is the most utilized approach but suffers from inflammation influences and is not utilizable in prostate cancer detection. Recently, (11)C-choline analogues have been employed successfully in this field of imaging, leading to a growing interest in the utilization of (18)F-labeled analogues: [(18)F]fluoroethylcholine (FEC) has been demonstrated to be promising, especially in prostate cancer imaging. In this work we report an automatic radiosynthesis of this tracer with high yields, short synthesis time and ease of performance, potentially utilizable in routine production sites. We used a Modular Lab system to automatically perform the two-step/one-pot synthesis. In the first step, we labeled ethyleneglycolditosylate obtaining [(18)F]fluoroethyltosylate; in the second step, we performed the coupling of the latter intermediate with neat dimethylethanolamine. The final mixture was purified by means of solid phase extraction; in particular, the product was trapped into a cation-exchange resin and eluted with isotonic saline. The optimized procedure resulted in a non decay corrected yield of 36% and produced a range of 30-45 GBq of product already in injectable form. The product was analyzed for quality control and resulted as pure and sterile; in addition, residual solvents were under the required threshold. In this work, we present an automatic FEC radiosynthesis that has been optimized for routine production. This findings should foster the interest for a wider utilization of this radiomolecule for imaging of prostate cancer with PET, a field for which no gold-standard tracer has yet been validated.

Automatic Semantic Segmentation of Brain Gliomas from MRI Images Using a Deep Cascaded Neural Network.

PubMed

Cui, Shaoguo; Mao, Lei; Jiang, Jingfeng; Liu, Chang; Xiong, Shuyu

2018-01-01

Brain tumors can appear anywhere in the brain and have vastly different sizes and morphology. Additionally, these tumors are often diffused and poorly contrasted. Consequently, the segmentation of brain tumor and intratumor subregions using magnetic resonance imaging (MRI) data with minimal human interventions remains a challenging task. In this paper, we present a novel fully automatic segmentation method from MRI data containing in vivo brain gliomas. This approach can not only localize the entire tumor region but can also accurately segment the intratumor structure. The proposed work was based on a cascaded deep learning convolutional neural network consisting of two subnetworks: (1) a tumor localization network (TLN) and (2) an intratumor classification network (ITCN). The TLN, a fully convolutional network (FCN) in conjunction with the transfer learning technology, was used to first process MRI data. The goal of the first subnetwork was to define the tumor region from an MRI slice. Then, the ITCN was used to label the defined tumor region into multiple subregions. Particularly, ITCN exploited a convolutional neural network (CNN) with deeper architecture and smaller kernel. The proposed approach was validated on multimodal brain tumor segmentation (BRATS 2015) datasets, which contain 220 high-grade glioma (HGG) and 54 low-grade glioma (LGG) cases. Dice similarity coefficient (DSC), positive predictive value (PPV), and sensitivity were used as evaluation metrics. Our experimental results indicated that our method could obtain the promising segmentation results and had a faster segmentation speed. More specifically, the proposed method obtained comparable and overall better DSC values (0.89, 0.77, and 0.80) on the combined (HGG + LGG) testing set, as compared to other methods reported in the literature. Additionally, the proposed approach was able to complete a segmentation task at a rate of 1.54 seconds per slice.

How to translate therapeutic recommendations in clinical practice guidelines into rules for critiquing physician prescriptions? Methods and application to five guidelines

PubMed Central

2010-01-01

Background Clinical practice guidelines give recommendations about what to do in various medical situations, including therapeutical recommendations for drug prescription. An effective way to computerize these recommendations is to design critiquing decision support systems, i.e. systems that criticize the physician's prescription when it does not conform to the guidelines. These systems are commonly based on a list of "if conditions then criticism" rules. However, writing these rules from the guidelines is not a trivial task. The objective of this article is to propose methods that (1) simplify the implementation of guidelines' therapeutical recommendations in critiquing systems by automatically translating structured therapeutical recommendations into a list of "if conditions then criticize" rules, and (2) can generate an appropriate textual label to explain to the physician why his/her prescription is not recommended. Methods We worked on the therapeutic recommendations in five clinical practice guidelines concerning chronic diseases related to the management of cardiovascular risk. We evaluated the system using a test base of more than 2000 cases. Results Algorithms for automatically translating therapeutical recommendations into "if conditions then criticize" rules are presented. Eight generic recommendations are also proposed; they are guideline-independent, and can be used as default behaviour for handling various situations that are usually implicit in the guidelines, such as decreasing the dose of a poorly tolerated drug. Finally, we provide models and methods for generating a human-readable textual critique. The system was successfully evaluated on the test base. Conclusion We show that it is possible to criticize physicians' prescriptions starting from a structured clinical guideline, and to provide clear explanations. We are now planning a randomized clinical trial to evaluate the impact of the system on practices. PMID:20509903

Brand Cigarillos: Low Price but High Particulate Matter Levels-Is Their Favorable Taxation in the European Union Justified?

PubMed

Wasel, Julia; Boll, Michael; Schulze, Michaela; Mueller, Daniel; Bundschuh, Matthias; Groneberg, David A; Gerber, Alexander

2015-08-06

Second hand smoke (ETS)-associated particulate matter (PM) contributes considerably to indoor air contamination and constitutes a health risk for passive smokers. Easy to measure, PM is a useful parameter to estimate the dosage of ETS that passive smokers are exposed to. Apart from its suitability as a surrogate parameter for ETS-exposure, PM itself affects human morbidity and mortality in a dose-dependent manner. We think that ETS-associated PM should be considered an independent hazard factor, separately from the many other known harmful compounds of ETS. We believe that brand-specific and tobacco-product-specific differences in the release of PM matter and that these differences are of public interest. To generate ETS of cigarettes and cigarillos as standardized and reproducible as possible, an automatic second hand smoke emitter (AETSE) was developed and placed in a glass chamber. L&M cigarettes ("without additives", "red label", "blue label"), L&M filtered cigarillos ("red") and 3R4F standard research cigarettes (as reference) were smoked automatically according to a self-developed, standardized protocol until the tobacco product was smoked down to 8 mm distance from the tipping paper of the filter. Mean concentration (Cmean) and area under the curve (AUC) in a plot of PM2.5 against time were measured, and compared. CmeanPM2.5 were found to be 518 μg/m(3) for 3R4F cigarettes, 576 μg/m(3) for L&M "without additives" ("red"), 448 μg/m(3) for L&M "blue label", 547 μg/m(3) for L&M "red label", and 755 μg/m(3) for L&M filtered cigarillos ("red"). AUCPM2.5-values were 208,214 μg/m(3)·s for 3R4F reference cigarettes, 204,629 μg/m(3)·s for L&M "without additives" ("red"), 152,718 μg/m(3)·s for L&M "blue label", 238,098 μg/m(3)·s for L&M "red label" and 796,909 μg/m(3)·s for L&M filtered cigarillos ("red"). Considering the large and significant differences in particulate matter emissions between cigarettes and cigarillos, we think that a favorable taxation of cigarillos is not justifiable.

CARBON-14 FIXATION IN POLLEN OF YELLOW LUPINE (LUPINUS LUTEUS LINN.)

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

Schwien, W.G.; Frazier, J.C.; Moser, H.C.

1962-10-31

Carbon-14 fixation studies were made on germinated pollen of yellow lupine to ascertain whether the chlorophyll reported to be in these grains was functional photosynthetically. Light and dark exposures to atmospheres containing 20 and 500 mu c of carbon-14 labeled carbon dioxide were made for 1.5 and 45 minutes, respectively. The exposed pollen was extracted in 80% ethanol, the resulting extract reduced in volume, and chromatographed two dimensionally. When the chromatograms were cut inio numbered small squares and their activity counted in an automatic sample counting system, a marked similarity was observed in the pattern of radioactivity from all exposures.more » Eluting and co- chromatographing this activity from the squares, with known standards, demonstrated labeling to be specific to certain intermediates of the Krebs cycle and their derived amine acids. The labeling in these intermediates and the absence of labeling in photosynthetic metabolites is strong evidence that only respiratory fixation of carbon-14 occurs in the germinated pollen of this variety of yellow lupine under the conditions of the experiment. (auth)« less

Real-time automatic registration in optical surgical navigation

NASA Astrophysics Data System (ADS)

Lin, Qinyong; Yang, Rongqian; Cai, Ken; Si, Xuan; Chen, Xiuwen; Wu, Xiaoming

2016-05-01

An image-guided surgical navigation system requires the improvement of the patient-to-image registration time to enhance the convenience of the registration procedure. A critical step in achieving this aim is performing a fully automatic patient-to-image registration. This study reports on a design of custom fiducial markers and the performance of a real-time automatic patient-to-image registration method using these markers on the basis of an optical tracking system for rigid anatomy. The custom fiducial markers are designed to be automatically localized in both patient and image spaces. An automatic localization method is performed by registering a point cloud sampled from the three dimensional (3D) pedestal model surface of a fiducial marker to each pedestal of fiducial markers searched in image space. A head phantom is constructed to estimate the performance of the real-time automatic registration method under four fiducial configurations. The head phantom experimental results demonstrate that the real-time automatic registration method is more convenient, rapid, and accurate than the manual method. The time required for each registration is approximately 0.1 s. The automatic localization method precisely localizes the fiducial markers in image space. The averaged target registration error for the four configurations is approximately 0.7 mm. The automatic registration performance is independent of the positions relative to the tracking system and the movement of the patient during the operation.

Unconstrained face detection and recognition based on RGB-D camera for the visually impaired

NASA Astrophysics Data System (ADS)

Zhao, Xiangdong; Wang, Kaiwei; Yang, Kailun; Hu, Weijian

2017-02-01

It is highly important for visually impaired people (VIP) to be aware of human beings around themselves, so correctly recognizing people in VIP assisting apparatus provide great convenience. However, in classical face recognition technology, faces used in training and prediction procedures are usually frontal, and the procedures of acquiring face images require subjects to get close to the camera so that frontal face and illumination guaranteed. Meanwhile, labels of faces are defined manually rather than automatically. Most of the time, labels belonging to different classes need to be input one by one. It prevents assisting application for VIP with these constraints in practice. In this article, a face recognition system under unconstrained environment is proposed. Specifically, it doesn't require frontal pose or uniform illumination as required by previous algorithms. The attributes of this work lie in three aspects. First, a real time frontal-face synthesizing enhancement is implemented, and frontal faces help to increase recognition rate, which is proved with experiment results. Secondly, RGB-D camera plays a significant role in our system, from which both color and depth information are utilized to achieve real time face tracking which not only raises the detection rate but also gives an access to label faces automatically. Finally, we propose to use neural networks to train a face recognition system, and Principal Component Analysis (PCA) is applied to pre-refine the input data. This system is expected to provide convenient help for VIP to get familiar with others, and make an access for them to recognize people when the system is trained enough.

Automatic segmentation of pulmonary fissures in x-ray CT images using anatomic guidance

NASA Astrophysics Data System (ADS)

Ukil, Soumik; Sonka, Milan; Reinhardt, Joseph M.

2006-03-01

The pulmonary lobes are the five distinct anatomic divisions of the human lungs. The physical boundaries between the lobes are called the lobar fissures. Detection of lobar fissure positions in pulmonary X-ray CT images is of increasing interest for the early detection of pathologies, and also for the regional functional analysis of the lungs. We have developed a two-step automatic method for the accurate segmentation of the three pulmonary fissures. In the first step, an approximation of the actual fissure locations is made using a 3-D watershed transform on the distance map of the segmented vasculature. Information from the anatomically labeled human airway tree is used to guide the watershed segmentation. These approximate fissure boundaries are then used to define the region of interest (ROI) for a more exact 3-D graph search to locate the fissures. Within the ROI the fissures are enhanced by computing a ridgeness measure, and this is used as the cost function for the graph search. The fissures are detected as the optimal surface within the graph defined by the cost function, which is computed by transforming the problem to the problem of finding a minimum s-t cut on a derived graph. The accuracy of the lobar borders is assessed by comparing the automatic results to manually traced lobe segments. The mean distance error between manually traced and computer detected left oblique, right oblique and right horizontal fissures is 2.3 +/- 0.8 mm, 2.3 +/- 0.7 mm and 1.0 +/- 0.1 mm, respectively.

filltex: Automatic queries to ADS and INSPIRE databases to fill LaTex bibliography

NASA Astrophysics Data System (ADS)

Gerosa, Davide; Vallisneri, Michele

2017-05-01

filltex is a simple tool to fill LaTex reference lists with records from the ADS and INSPIRE databases. ADS and INSPIRE are the most common databases used among the theoretical physics and astronomy scientific communities, respectively. filltex automatically looks for all citation labels present in a tex document and, by means of web-scraping, downloads all the required citation records from either of the two databases. filltex significantly speeds up the LaTex scientific writing workflow, as all required actions (compile the tex file, fill the bibliography, compile the bibliography, compile the tex file again) are automated in a single command. We also provide an integration of filltex for the macOS LaTex editor TexShop.

Classifying features in CT imagery: accuracy for some single- and multiple-species classifiers

Treesearch

Daniel L. Schmoldt; Jing He; A. Lynn Abbott

1998-01-01

Our current approach to automatically label features in CT images of hardwood logs classifies each pixel of an image individually. These feature classifiers use a back-propagation artificial neural network (ANN) and feature vectors that include a small, local neighborhood of pixels and the distance of the target pixel to the center of the log. Initially, this type of...

Automatic Railway Traffic Object Detection System Using Feature Fusion Refine Neural Network under Shunting Mode.

PubMed

Ye, Tao; Wang, Baocheng; Song, Ping; Li, Juan

2018-06-12

Many accidents happen under shunting mode when the speed of a train is below 45 km/h. In this mode, train attendants observe the railway condition ahead using the traditional manual method and tell the observation results to the driver in order to avoid danger. To address this problem, an automatic object detection system based on convolutional neural network (CNN) is proposed to detect objects ahead in shunting mode, which is called Feature Fusion Refine neural network (FR-Net). It consists of three connected modules, i.e., the depthwise-pointwise convolution, the coarse detection module, and the object detection module. Depth-wise-pointwise convolutions are used to improve the detection in real time. The coarse detection module coarsely refine the locations and sizes of prior anchors to provide better initialization for the subsequent module and also reduces search space for the classification, whereas the object detection module aims to regress accurate object locations and predict the class labels for the prior anchors. The experimental results on the railway traffic dataset show that FR-Net achieves 0.8953 mAP with 72.3 FPS performance on a machine with a GeForce GTX1080Ti with the input size of 320 × 320 pixels. The results imply that FR-Net takes a good tradeoff both on effectiveness and real time performance. The proposed method can meet the needs of practical application in shunting mode.

Towards the Real-Time Evaluation of Collaborative Activities: Integration of an Automatic Rater of Collaboration Quality in the Classroom from the Teacher's Perspective

ERIC Educational Resources Information Center

Chounta, Irene-Angelica; Avouris, Nikolaos

2016-01-01

This paper presents the integration of a real time evaluation method of collaboration quality in a monitoring application that supports teachers in class orchestration. The method is implemented as an automatic rater of collaboration quality and studied in a real time scenario of use. We argue that automatic and semi-automatic methods which…

Classification of visual signs in abdominal CT image figures in biomedical literature

NASA Astrophysics Data System (ADS)

Xue, Zhiyun; You, Daekeun; Antani, Sameer; Long, L. Rodney; Demner-Fushman, Dina; Thoma, George R.

2014-03-01

"Imaging signs" are a critical part of radiology's language. They not only are important for conveying diagnosis, but may also aid in indexing radiology literature and retrieving relevant cases and images. Here we report our work towards representing and categorizing imaging signs of abdominal abnormalities in figures in the radiology literature. Given a region-of-interest (ROI) from a figure, our goal was to assign a correct imaging sign label to that ROI from the following seven: accordion, comb, ring, sandwich, small bowel feces, target, or whirl. As training and test data, we created our own "gold standard" dataset of regions containing imaging signs. We computed 2997 feature attributes to represent imaging sign characteristics for each ROI in training and test sets. Following feature selection they were reduced to 70 attributes and were input to a Support Vector Machine classifier. We applied image-enhancement methods to compensate for variable quality of the images in radiology articles. In particular we developed a method for automatic detection and removal of pointers/markers (arrows, arrowheads, and asterisk symbols) on the images. These pointers/markers are valuable for approximately locating ROIs; however, they degrade the classification because they are often (partially) included in the training ROIs. On a test set of 283 ROIs, our method achieved an overall accuracy of 70% in labeling the seven signs, which we believe is a promising result for using imaging signs to search/retrieve radiology literature. This work is also potentially valuable for the creation of a visual ontology of biomedical imaging entities.

Automatic image enhancement based on multi-scale image decomposition

NASA Astrophysics Data System (ADS)

Feng, Lu; Wu, Zhuangzhi; Pei, Luo; Long, Xiong

2014-01-01

In image processing and computational photography, automatic image enhancement is one of the long-range objectives. Recently the automatic image enhancement methods not only take account of the globe semantics, like correct color hue and brightness imbalances, but also the local content of the image, such as human face and sky of landscape. In this paper we describe a new scheme for automatic image enhancement that considers both global semantics and local content of image. Our automatic image enhancement method employs the multi-scale edge-aware image decomposition approach to detect the underexposure regions and enhance the detail of the salient content. The experiment results demonstrate the effectiveness of our approach compared to existing automatic enhancement methods.

Label free cell-tracking and division detection based on 2D time-lapse images for lineage analysis of early embryo development.

PubMed

Cicconet, Marcelo; Gutwein, Michelle; Gunsalus, Kristin C; Geiger, Davi

2014-08-01

In this paper we report a database and a series of techniques related to the problem of tracking cells, and detecting their divisions, in time-lapse movies of mammalian embryos. Our contributions are (1) a method for counting embryos in a well, and cropping each individual embryo across frames, to create individual movies for cell tracking; (2) a semi-automated method for cell tracking that works up to the 8-cell stage, along with a software implementation available to the public (this software was used to build the reported database); (3) an algorithm for automatic tracking up to the 4-cell stage, based on histograms of mirror symmetry coefficients captured using wavelets; (4) a cell-tracking database containing 100 annotated examples of mammalian embryos up to the 8-cell stage; and (5) statistical analysis of various timing distributions obtained from those examples. Copyright © 2014 Elsevier Ltd. All rights reserved.

Age and gender classification in the wild with unsupervised feature learning

NASA Astrophysics Data System (ADS)

Wan, Lihong; Huo, Hong; Fang, Tao

2017-03-01

Inspired by unsupervised feature learning (UFL) within the self-taught learning framework, we propose a method based on UFL, convolution representation, and part-based dimensionality reduction to handle facial age and gender classification, which are two challenging problems under unconstrained circumstances. First, UFL is introduced to learn selective receptive fields (filters) automatically by applying whitening transformation and spherical k-means on random patches collected from unlabeled data. The learning process is fast and has no hyperparameters to tune. Then, the input image is convolved with these filters to obtain filtering responses on which local contrast normalization is applied. Average pooling and feature concatenation are then used to form global face representation. Finally, linear discriminant analysis with part-based strategy is presented to reduce the dimensions of the global representation and to improve classification performances further. Experiments on three challenging databases, namely, Labeled faces in the wild, Gallagher group photos, and Adience, demonstrate the effectiveness of the proposed method relative to that of state-of-the-art approaches.

Automatic Detection of Driver Fatigue Using Driving Operation Information for Transportation Safety

PubMed Central

Li, Zuojin; Chen, Liukui; Peng, Jun; Wu, Ying

2017-01-01

Fatigued driving is a major cause of road accidents. For this reason, the method in this paper is based on the steering wheel angles (SWA) and yaw angles (YA) information under real driving conditions to detect drivers’ fatigue levels. It analyzes the operation features of SWA and YA under different fatigue statuses, then calculates the approximate entropy (ApEn) features of a short sliding window on time series. Using the nonlinear feature construction theory of dynamic time series, with the fatigue features as input, designs a “2-6-6-3” multi-level back propagation (BP) Neural Networks classifier to realize the fatigue detection. An approximately 15-h experiment is carried out on a real road, and the data retrieved are segmented and labeled with three fatigue levels after expert evaluation, namely “awake”, “drowsy” and “very drowsy”. The average accuracy of 88.02% in fatigue identification was achieved in the experiment, endorsing the value of the proposed method for engineering applications. PMID:28587072

Automatic Detection of Driver Fatigue Using Driving Operation Information for Transportation Safety.

PubMed

Li, Zuojin; Chen, Liukui; Peng, Jun; Wu, Ying

2017-05-25

Fatigued driving is a major cause of road accidents. For this reason, the method in this paper is based on the steering wheel angles (SWA) and yaw angles (YA) information under real driving conditions to detect drivers' fatigue levels. It analyzes the operation features of SWA and YA under different fatigue statuses, then calculates the approximate entropy (ApEn) features of a short sliding window on time series. Using the nonlinear feature construction theory of dynamic time series, with the fatigue features as input, designs a "2-6-6-3" multi-level back propagation (BP) Neural Networks classifier to realize the fatigue detection. An approximately 15-h experiment is carried out on a real road, and the data retrieved are segmented and labeled with three fatigue levels after expert evaluation, namely "awake", "drowsy" and "very drowsy". The average accuracy of 88.02% in fatigue identification was achieved in the experiment, endorsing the value of the proposed method for engineering applications.

Desired and Undesired Effects of Energy Labels--An Eye-Tracking Study.

PubMed

Waechter, Signe; Sütterlin, Bernadette; Siegrist, Michael

2015-01-01

Saving energy is an important pillar for the mitigation of climate change. Electric devices (e.g., freezer and television) are an important player in the residential sector in the final demand for energy. Consumers' purchase decisions are therefore crucial to successfully reach the energy-efficiency goals. Putting energy labels on products is often considered an adequate way of empowering consumers to make informed purchase decisions. Consequently, this approach should contribute to reducing overall energy consumption. The effectiveness of its measurement depends on consumers' use and interpretation of the information provided. Despite advances in energy efficiency and a mandatory labeling policy, final energy consumption per capita is in many countries still increasing. This paper provides a systematic analysis of consumers' reactions to one of the most widely used eco-labels, the European Union (EU) energy label, by using eye-tracking methodology as an objective measurement. The study's results partially support the EU's mandatory policy, showing that the energy label triggers attention toward energy information in general. However, the energy label's effect on consumers' actual product choices seems to be rather low. The study's results show that the currently used presentation format on the label is insufficient. The findings suggest that it does not facilitate the integration of energy-related information. Furthermore, the current format can attract consumers to focus more on energy-efficiency information, leading them to disregard information about actual energy consumption. As a result, the final energy consumption may increase because excellent ratings on energy efficiency (e.g., A++) do not automatically imply little consumption. Finally, implications for policymakers and suggestions for further research are discussed.

10 CFR 431.134 - Uniform test methods for the measurement of energy consumption and water consumption of automatic...

Code of Federal Regulations, 2011 CFR

2011-01-01

... consumption and water consumption of automatic commercial ice makers. 431.134 Section 431.134 Energy... EQUIPMENT Automatic Commercial Ice Makers Test Procedures § 431.134 Uniform test methods for the measurement of energy consumption and water consumption of automatic commercial ice makers. (a) Scope. This...

Miniaturization of the Clonogenic Assay Using Confluence Measurement

PubMed Central

Mayr, Christian; Beyreis, Marlena; Dobias, Heidemarie; Gaisberger, Martin; Pichler, Martin; Ritter, Markus; Jakab, Martin; Neureiter, Daniel; Kiesslich, Tobias

2018-01-01

The clonogenic assay is a widely used method to study the ability of cells to ‘infinitely’ produce progeny and is, therefore, used as a tool in tumor biology to measure tumor-initiating capacity and stem cell status. However, the standard protocol of using 6-well plates has several disadvantages. By miniaturizing the assay to a 96-well microplate format, as well as by utilizing the confluence detection function of a multimode reader, we here describe a new and modified protocol that allows comprehensive experimental setups and a non-endpoint, label-free semi-automatic analysis. Comparison of bright field images with confluence images demonstrated robust and reproducible detection of clones by the confluence detection function. Moreover, time-resolved non-endpoint confluence measurement of the same well showed that semi-automatic analysis was suitable for determining the mean size and colony number. By treating cells with an inhibitor of clonogenic growth (PTC-209), we show that our modified protocol is suitable for comprehensive (broad concentration range, addition of technical replicates) concentration- and time-resolved analysis of the effect of substances or treatments on clonogenic growth. In summary, this protocol represents a time- and cost-effective alternative to the commonly used 6-well protocol (with endpoint staining) and also provides additional information about the kinetics of clonogenic growth. PMID:29510509

Automated region selection for analysis of dynamic cardiac SPECT data

NASA Astrophysics Data System (ADS)

Di Bella, E. V. R.; Gullberg, G. T.; Barclay, A. B.; Eisner, R. L.

1997-06-01

Dynamic cardiac SPECT using Tc-99m labeled teboroxime can provide kinetic parameters (washin, washout) indicative of myocardial blood flow. A time-consuming and subjective step of the data analysis is drawing regions of interest to delineate blood pool and myocardial tissue regions. The time-activity curves of the regions are then used to estimate local kinetic parameters. In this work, the appropriate regions are found automatically, in a manner similar to that used for calculating maximum count circumferential profiles in conventional static cardiac studies. The drawbacks to applying standard static circumferential profile methods are the high noise level and high liver uptake common in dynamic teboroxime studies. Searching along each ray for maxima to locate the myocardium does not typically provide useful information. Here we propose an iterative scheme in which constraints are imposed on the radii searched along each ray. The constraints are based on the shape of the time-activity curves of the circumferential profile members and on an assumption that the short axis slices are approximately circular. The constraints eliminate outliers and help to reduce the effects of noise and liver activity. Kinetic parameter estimates from the automatically generated regions were comparable to estimates from manually selected regions in dynamic canine teboroxime studies.

Automatic content-based analysis of georeferenced image data: Detection of Beggiatoa mats in seafloor video mosaics from the HÅkon Mosby Mud Volcano

NASA Astrophysics Data System (ADS)

Jerosch, K.; Lüdtke, A.; Schlüter, M.; Ioannidis, G. T.

2007-02-01

The combination of new underwater technology as remotely operating vehicles (ROVs), high-resolution video imagery, and software to compute georeferenced mosaics of the seafloor provides new opportunities for marine geological or biological studies and applications in offshore industry. Even during single surveys by ROVs or towed systems large amounts of images are compiled. While these underwater techniques are now well-engineered, there is still a lack of methods for the automatic analysis of the acquired image data. During ROV dives more than 4200 georeferenced video mosaics were compiled for the HÅkon Mosby Mud Volcano (HMMV). Mud volcanoes as HMMV are considered as significant source locations for methane characterised by unique chemoautotrophic communities as Beggiatoa mats. For the detection and quantification of the spatial distribution of Beggiatoa mats an automated image analysis technique was developed, which applies watershed transformation and relaxation-based labelling of pre-segmented regions. Comparison of the data derived by visual inspection of 2840 video images with the automated image analysis revealed similarities with a precision better than 90%. We consider this as a step towards a time-efficient and accurate analysis of seafloor images for computation of geochemical budgets and identification of habitats at the seafloor.

Real-time road detection in infrared imagery

NASA Astrophysics Data System (ADS)

Andre, Haritini E.; McCoy, Keith

1990-09-01

Automatic road detection is an important part in many scene recognition applications. The extraction of roads provides a means of navigation and position update for remotely piloted vehicles or autonomous vehicles. Roads supply strong contextual information which can be used to improve the performance of automatic target recognition (ATh) systems by directing the search for targets and adjusting target classification confidences. This paper will describe algorithmic techniques for labeling roads in high-resolution infrared imagery. In addition, realtime implementation of this structural approach using a processor array based on the Martin Marietta Geometric Arithmetic Parallel Processor (GAPPTh) chip will be addressed. The algorithm described is based on the hypothesis that a road consists of pairs of line segments separated by a distance "d" with opposite gradient directions (antiparallel). The general nature of the algorithm, in addition to its parallel implementation in a single instruction, multiple data (SIMD) machine, are improvements to existing work. The algorithm seeks to identify line segments meeting the road hypothesis in a manner that performs well, even when the side of the road is fragmented due to occlusion or intersections. The use of geometrical relationships between line segments is a powerful yet flexible method of road classification which is independent of orientation. In addition, this approach can be used to nominate other types of objects with minor parametric changes.

Automated segmentation of retinal blood vessels and identification of proliferative diabetic retinopathy

NASA Astrophysics Data System (ADS)

Jelinek, Herbert F.; Cree, Michael J.; Leandro, Jorge J. G.; Soares, João V. B.; Cesar, Roberto M.; Luckie, A.

2007-05-01

Proliferative diabetic retinopathy can lead to blindness. However, early recognition allows appropriate, timely intervention. Fluorescein-labeled retinal blood vessels of 27 digital images were automatically segmented using the Gabor wavelet transform and classified using traditional features such as area, perimeter, and an additional five morphological features based on the derivatives-of-Gaussian wavelet-derived data. Discriminant analysis indicated that traditional features do not detect early proliferative retinopathy. The best single feature for discrimination was the wavelet curvature with an area under the curve (AUC) of 0.76. Linear discriminant analysis with a selection of six features achieved an AUC of 0.90 (0.73-0.97, 95% confidence interval). The wavelet method was able to segment retinal blood vessels and classify the images according to the presence or absence of proliferative retinopathy.

Marker-Based Hierarchical Segmentation and Classification Approach for Hyperspectral Imagery

NASA Technical Reports Server (NTRS)

Tarabalka, Yuliya; Tilton, James C.; Benediktsson, Jon Atli; Chanussot, Jocelyn

2011-01-01

The Hierarchical SEGmentation (HSEG) algorithm, which is a combination of hierarchical step-wise optimization and spectral clustering, has given good performances for hyperspectral image analysis. This technique produces at its output a hierarchical set of image segmentations. The automated selection of a single segmentation level is often necessary. We propose and investigate the use of automatically selected markers for this purpose. In this paper, a novel Marker-based HSEG (M-HSEG) method for spectral-spatial classification of hyperspectral images is proposed. First, pixelwise classification is performed and the most reliably classified pixels are selected as markers, with the corresponding class labels. Then, a novel constrained marker-based HSEG algorithm is applied, resulting in a spectral-spatial classification map. The experimental results show that the proposed approach yields accurate segmentation and classification maps, and thus is attractive for hyperspectral image analysis.

Statistical modelling of subdiffusive dynamics in the cytoplasm of living cells: A FARIMA approach

NASA Astrophysics Data System (ADS)

Burnecki, K.; Muszkieta, M.; Sikora, G.; Weron, A.

2012-04-01

Golding and Cox (Phys. Rev. Lett., 96 (2006) 098102) tracked the motion of individual fluorescently labelled mRNA molecules inside live E. coli cells. They found that in the set of 23 trajectories from 3 different experiments, the automatically recognized motion is subdiffusive and published an intriguing microscopy video. Here, we extract the corresponding time series from this video by image segmentation method and present its detailed statistical analysis. We find that this trajectory was not included in the data set already studied and has different statistical properties. It is best fitted by a fractional autoregressive integrated moving average (FARIMA) process with the normal-inverse Gaussian (NIG) noise and the negative memory. In contrast to earlier studies, this shows that the fractional Brownian motion is not the best model for the dynamics documented in this video.

Imaging Fibrosis and Separating Collagens using Second Harmonic Generation and Phasor Approach to Fluorescence Lifetime Imaging

PubMed Central

Ranjit, Suman; Dvornikov, Alexander; Stakic, Milka; Hong, Suk-Hyun; Levi, Moshe; Evans, Ronald M.; Gratton, Enrico

2015-01-01

In this paper we have used second harmonic generation (SHG) and phasor approach to auto fluorescence lifetime imaging (FLIM) to obtain fingerprints of different collagens and then used these fingerprints to observe bone marrow fibrosis in the mouse femur. This is a label free approach towards fast automatable detection of fibrosis in tissue samples. FLIM has previously been used as a method of contrast in different tissues and in this paper phasor approach to FLIM is used to separate collagen I from collagen III, the markers of fibrosis, the largest groups of disorders that are often without any effective therapy. Often characterized by an increase in collagen content of the corresponding tissue, the samples are usually visualized by histochemical staining, which is pathologist dependent and cannot be automated. PMID:26293987

[Development of an automated processing method to detect coronary motion for coronary magnetic resonance angiography].

PubMed

Asou, Hiroya; Imada, N; Sato, T

2010-06-20

On coronary MR angiography (CMRA), cardiac motions worsen the image quality. To improve the image quality, detection of cardiac especially for individual coronary motion is very important. Usually, scan delay and duration were determined manually by the operator. We developed a new evaluation method to calculate static time of individual coronary artery. At first, coronary cine MRI was taken at the level of about 3 cm below the aortic valve (80 images/R-R). Chronological change of the signals were evaluated with Fourier transformation of each pixel of the images were done. Noise reduction with subtraction process and extraction process were done. To extract higher motion such as coronary arteries, morphological filter process and labeling process were added. Using these imaging processes, individual coronary motion was extracted and individual coronary static time was calculated automatically. We compared the images with ordinary manual method and new automated method in 10 healthy volunteers. Coronary static times were calculated with our method. Calculated coronary static time was shorter than that of ordinary manual method. And scan time became about 10% longer than that of ordinary method. Image qualities were improved in our method. Our automated detection method for coronary static time with chronological Fourier transformation has a potential to improve the image quality of CMRA and easy processing.

Towards an Automatic Framework for Urban Settlement Mapping from Satellite Images: Applications of Geo-referenced Social Media and One Class Classification

NASA Astrophysics Data System (ADS)

Miao, Zelang

2017-04-01

Currently, urban dwellers comprise more than half of the world's population and this percentage is still dramatically increasing. The explosive urban growth over the next two decades poses long-term profound impact on people as well as the environment. Accurate and up-to-date delineation of urban settlements plays a fundamental role in defining planning strategies and in supporting sustainable development of urban settlements. In order to provide adequate data about urban extents and land covers, classifying satellite data has become a common practice, usually with accurate enough results. Indeed, a number of supervised learning methods have proven effective in urban area classification, but they usually depend on a large amount of training samples, whose collection is a time and labor expensive task. This issue becomes particularly serious when classifying large areas at the regional/global level. As an alternative to manual ground truth collection, in this work we use geo-referenced social media data. Cities and densely populated areas are an extremely fertile land for the production of individual geo-referenced data (such as GPS and social network data). Training samples derived from geo-referenced social media have several advantages: they are easy to collect, usually they are freely exploitable; and, finally, data from social media are spatially available in many locations, and with no doubt in most urban areas around the world. Despite these advantages, the selection of training samples from social media meets two challenges: 1) there are many duplicated points; 2) method is required to automatically label them as "urban/non-urban". The objective of this research is to validate automatic sample selection from geo-referenced social media and its applicability in one class classification for urban extent mapping from satellite images. The findings in this study shed new light on social media applications in the field of remote sensing.

Compositional mining of multiple object API protocols through state abstraction.

PubMed

Dai, Ziying; Mao, Xiaoguang; Lei, Yan; Qi, Yuhua; Wang, Rui; Gu, Bin

2013-01-01

API protocols specify correct sequences of method invocations. Despite their usefulness, API protocols are often unavailable in practice because writing them is cumbersome and error prone. Multiple object API protocols are more expressive than single object API protocols. However, the huge number of objects of typical object-oriented programs poses a major challenge to the automatic mining of multiple object API protocols: besides maintaining scalability, it is important to capture various object interactions. Current approaches utilize various heuristics to focus on small sets of methods. In this paper, we present a general, scalable, multiple object API protocols mining approach that can capture all object interactions. Our approach uses abstract field values to label object states during the mining process. We first mine single object typestates as finite state automata whose transitions are annotated with states of interacting objects before and after the execution of the corresponding method and then construct multiple object API protocols by composing these annotated single object typestates. We implement our approach for Java and evaluate it through a series of experiments.

Compositional Mining of Multiple Object API Protocols through State Abstraction

PubMed Central

Mao, Xiaoguang; Qi, Yuhua; Wang, Rui; Gu, Bin

2013-01-01

API protocols specify correct sequences of method invocations. Despite their usefulness, API protocols are often unavailable in practice because writing them is cumbersome and error prone. Multiple object API protocols are more expressive than single object API protocols. However, the huge number of objects of typical object-oriented programs poses a major challenge to the automatic mining of multiple object API protocols: besides maintaining scalability, it is important to capture various object interactions. Current approaches utilize various heuristics to focus on small sets of methods. In this paper, we present a general, scalable, multiple object API protocols mining approach that can capture all object interactions. Our approach uses abstract field values to label object states during the mining process. We first mine single object typestates as finite state automata whose transitions are annotated with states of interacting objects before and after the execution of the corresponding method and then construct multiple object API protocols by composing these annotated single object typestates. We implement our approach for Java and evaluate it through a series of experiments. PMID:23844378

CNNdel: Calling Structural Variations on Low Coverage Data Based on Convolutional Neural Networks

PubMed Central

2017-01-01

Many structural variations (SVs) detection methods have been proposed due to the popularization of next-generation sequencing (NGS). These SV calling methods use different SV-property-dependent features; however, they all suffer from poor accuracy when running on low coverage sequences. The union of results from these tools achieves fairly high sensitivity but still produces low accuracy on low coverage sequence data. That is, these methods contain many false positives. In this paper, we present CNNdel, an approach for calling deletions from paired-end reads. CNNdel gathers SV candidates reported by multiple tools and then extracts features from aligned BAM files at the positions of candidates. With labeled feature-expressed candidates as a training set, CNNdel trains convolutional neural networks (CNNs) to distinguish true unlabeled candidates from false ones. Results show that CNNdel works well with NGS reads from 26 low coverage genomes of the 1000 Genomes Project. The paper demonstrates that convolutional neural networks can automatically assign the priority of SV features and reduce the false positives efficaciously. PMID:28630866

Semi-automated contour recognition using DICOMautomaton

NASA Astrophysics Data System (ADS)

Clark, H.; Wu, J.; Moiseenko, V.; Lee, R.; Gill, B.; Duzenli, C.; Thomas, S.

2014-03-01

Purpose: A system has been developed which recognizes and classifies Digital Imaging and Communication in Medicine contour data with minimal human intervention. It allows researchers to overcome obstacles which tax analysis and mining systems, including inconsistent naming conventions and differences in data age or resolution. Methods: Lexicographic and geometric analysis is used for recognition. Well-known lexicographic methods implemented include Levenshtein-Damerau, bag-of-characters, Double Metaphone, Soundex, and (word and character)-N-grams. Geometrical implementations include 3D Fourier Descriptors, probability spheres, boolean overlap, simple feature comparison (e.g. eccentricity, volume) and rule-based techniques. Both analyses implement custom, domain-specific modules (e.g. emphasis differentiating left/right organ variants). Contour labels from 60 head and neck patients are used for cross-validation. Results: Mixed-lexicographical methods show an effective improvement in more than 10% of recognition attempts compared with a pure Levenshtein-Damerau approach when withholding 70% of the lexicon. Domain-specific and geometrical techniques further boost performance. Conclusions: DICOMautomaton allows users to recognize contours semi-automatically. As usage increases and the lexicon is filled with additional structures, performance improves, increasing the overall utility of the system.

Identification of ghost artifact using texture analysis in pediatric spinal cord diffusion tensor images.

PubMed

Alizadeh, Mahdi; Conklin, Chris J; Middleton, Devon M; Shah, Pallav; Saksena, Sona; Krisa, Laura; Finsterbusch, Jürgen; Faro, Scott H; Mulcahey, M J; Mohamed, Feroze B

2018-04-01

Ghost artifacts are a major contributor to degradation of spinal cord diffusion tensor images. A multi-stage post-processing pipeline was designed, implemented and validated to automatically remove ghost artifacts arising from reduced field of view diffusion tensor imaging (DTI) of the pediatric spinal cord. A total of 12 pediatric subjects including 7 healthy subjects (mean age=11.34years) with no evidence of spinal cord injury or pathology and 5 patients (mean age=10.96years) with cervical spinal cord injury were studied. Ghost/true cords, labeled as region of interests (ROIs), in non-diffusion weighted b0 images were segmented automatically using mathematical morphological processing. Initially, 21 texture features were extracted from each segmented ROI including 5 first-order features based on the histogram of the image (mean, variance, skewness, kurtosis and entropy) and 16s-order feature vector elements, incorporating four statistical measures (contrast, correlation, homogeneity and energy) calculated from co-occurrence matrices in directions of 0°, 45°, 90° and 135°. Next, ten features with a high value of mutual information (MI) relative to the pre-defined target class and within the features were selected as final features which were input to a trained classifier (adaptive neuro-fuzzy interface system) to separate the true cord from the ghost cord. The implemented pipeline was successfully able to separate the ghost artifacts from true cord structures. The results obtained from the classifier showed a sensitivity of 91%, specificity of 79%, and accuracy of 84% in separating the true cord from ghost artifacts. The results show that the proposed method is promising for the automatic detection of ghost cords present in DTI images of the spinal cord. This step is crucial towards development of accurate, automatic DTI spinal cord post processing pipelines. Copyright © 2017 Elsevier Inc. All rights reserved.

Comparison of liver volumetry on contrast-enhanced CT images: one semiautomatic and two automatic approaches.

PubMed

Cai, Wei; He, Baochun; Fan, Yingfang; Fang, Chihua; Jia, Fucang

2016-11-08

This study was to evaluate the accuracy, consistency, and efficiency of three liver volumetry methods- one interactive method, an in-house-developed 3D medical Image Analysis (3DMIA) system, one automatic active shape model (ASM)-based segmentation, and one automatic probabilistic atlas (PA)-guided segmentation method on clinical contrast-enhanced CT images. Forty-two datasets, including 27 normal liver and 15 space-occupying liver lesion patients, were retrospectively included in this study. The three methods - one semiautomatic 3DMIA, one automatic ASM-based, and one automatic PA-based liver volumetry - achieved an accuracy with VD (volume difference) of -1.69%, -2.75%, and 3.06% in the normal group, respectively, and with VD of -3.20%, -3.35%, and 4.14% in the space-occupying lesion group, respectively. However, the three methods achieved an efficiency of 27.63 mins, 1.26 mins, 1.18 mins on average, respectively, compared with the manual volumetry, which took 43.98 mins. The high intraclass correlation coefficient between the three methods and the manual method indicated an excel-lent agreement on liver volumetry. Significant differences in segmentation time were observed between the three methods (3DMIA, ASM, and PA) and the manual volumetry (p < 0.001), as well as between the automatic volumetries (ASM and PA) and the semiautomatic volumetry (3DMIA) (p < 0.001). The semiautomatic interactive 3DMIA, automatic ASM-based, and automatic PA-based liver volum-etry agreed well with manual gold standard in both the normal liver group and the space-occupying lesion group. The ASM- and PA-based automatic segmentation have better efficiency in clinical use. © 2016 The Authors.

Reference standard space hippocampus labels according to the European Alzheimer's Disease Consortium-Alzheimer's Disease Neuroimaging Initiative harmonized protocol: Utility in automated volumetry.

PubMed

Wolf, Dominik; Bocchetta, Martina; Preboske, Gregory M; Boccardi, Marina; Grothe, Michel J

2017-08-01

A harmonized protocol (HarP) for manual hippocampal segmentation on magnetic resonance imaging (MRI) has recently been developed by an international European Alzheimer's Disease Consortium-Alzheimer's Disease Neuroimaging Initiative project. We aimed at providing consensual certified HarP hippocampal labels in Montreal Neurological Institute (MNI) standard space to serve as reference in automated image analyses. Manual HarP tracings on the high-resolution MNI152 standard space template of four expert certified HarP tracers were combined to obtain consensual bilateral hippocampus labels. Utility and validity of these reference labels is demonstrated in a simple atlas-based morphometry approach for automated calculation of HarP-compliant hippocampal volumes within SPM software. Individual tracings showed very high agreement among the four expert tracers (pairwise Jaccard indices 0.82-0.87). Automatically calculated hippocampal volumes were highly correlated (r L/R  = 0.89/0.91) with gold standard volumes in the HarP benchmark data set (N = 135 MRIs), with a mean volume difference of 9% (standard deviation 7%). The consensual HarP hippocampus labels in the MNI152 template can serve as a reference standard for automated image analyses involving MNI standard space normalization. Copyright © 2017 the Alzheimer's Association. Published by Elsevier Inc. All rights reserved.

Dynamic generation of a table of contents with consumer-friendly labels.

PubMed

Miller, Trudi; Leroy, Gondy; Wood, Elizabeth

2006-01-01

Consumers increasingly look to the Internet for health information, but available resources are too difficult for the majority to understand. Interactive tables of contents (TOC) can help consumers access health information by providing an easy to understand structure. Using natural language processing and the Unified Medical Language System (UMLS), we have automatically generated TOCs for consumer health information. The TOC are categorized according to consumer-friendly labels for the UMLS semantic types and semantic groups. Categorizing phrases by semantic types is significantly more correct and relevant. Greater correctness and relevance was achieved with documents that are difficult to read than those at an easier reading level. Pruning TOCs to use categories that consumers favor further increases relevancy and correctness while reducing structural complexity.

10 CFR 431.134 - Uniform test methods for the measurement of energy and water consumption of automatic commercial...

Code of Federal Regulations, 2013 CFR

2013-01-01

... water consumption of automatic commercial ice makers. 431.134 Section 431.134 Energy DEPARTMENT OF... Automatic Commercial Ice Makers Test Procedures § 431.134 Uniform test methods for the measurement of energy and water consumption of automatic commercial ice makers. (a) Scope. This section provides the test...

10 CFR 431.134 - Uniform test methods for the measurement of energy and water consumption of automatic commercial...

Code of Federal Regulations, 2014 CFR

2014-01-01

... water consumption of automatic commercial ice makers. 431.134 Section 431.134 Energy DEPARTMENT OF... Automatic Commercial Ice Makers Test Procedures § 431.134 Uniform test methods for the measurement of energy and water consumption of automatic commercial ice makers. (a) Scope. This section provides the test...

A Hopfield neural network for image change detection.

PubMed

Pajares, Gonzalo

2006-09-01

This paper outlines an optimization relaxation approach based on the analog Hopfield neural network (HNN) for solving the image change detection problem between two images. A difference image is obtained by subtracting pixel by pixel both images. The network topology is built so that each pixel in the difference image is a node in the network. Each node is characterized by its state, which determines if a pixel has changed. An energy function is derived, so that the network converges to stable states. The analog Hopfield's model allows each node to take on analog state values. Unlike most widely used approaches, where binary labels (changed/unchanged) are assigned to each pixel, the analog property provides the strength of the change. The main contribution of this paper is reflected in the customization of the analog Hopfield neural network to derive an automatic image change detection approach. When a pixel is being processed, some existing image change detection procedures consider only interpixel relations on its neighborhood. The main drawback of such approaches is the labeling of this pixel as changed or unchanged according to the information supplied by its neighbors, where its own information is ignored. The Hopfield model overcomes this drawback and for each pixel allows a tradeoff between the influence of its neighborhood and its own criterion. This is mapped under the energy function to be minimized. The performance of the proposed method is illustrated by comparative analysis against some existing image change detection methods.

Short non-coding RNAs as bacteria species identifiers detected by surface plasmon resonance enhanced common path interferometry

NASA Astrophysics Data System (ADS)

Greef, Charles; Petropavlovskikh, Viatcheslav; Nilsen, Oyvind; Khattatov, Boris; Plam, Mikhail; Gardner, Patrick; Hall, John

2008-04-01

Small non-coding RNA sequences have recently been discovered as unique identifiers of certain bacterial species, raising the possibility that they can be used as highly specific Biowarfare Agent detection markers in automated field deployable integrated detection systems. Because they are present in high abundance they could allow genomic based bacterial species identification without the need for pre-assay amplification. Further, a direct detection method would obviate the need for chemical labeling, enabling a rapid, efficient, high sensitivity mechanism for bacterial detection. Surface Plasmon Resonance enhanced Common Path Interferometry (SPR-CPI) is a potentially market disruptive, high sensitivity dual technology that allows real-time direct multiplex measurement of biomolecule interactions, including small molecules, nucleic acids, proteins, and microbes. SPR-CPI measures differences in phase shift of reflected S and P polarized light under Total Internal Reflection (TIR) conditions at a surface, caused by changes in refractive index induced by biomolecular interactions within the evanescent field at the TIR interface. The measurement is performed on a microarray of discrete 2-dimensional areas functionalized with biomolecule capture reagents, allowing simultaneous measurement of up to 100 separate analytes. The optical beam encompasses the entire microarray, allowing a solid state detector system with no scanning requirement. Output consists of simultaneous voltage measurements proportional to the phase differences resulting from the refractive index changes from each microarray feature, and is automatically processed and displayed graphically or delivered to a decision making algorithm, enabling a fully automatic detection system capable of rapid detection and quantification of small nucleic acids at extremely sensitive levels. Proof-of-concept experiments on model systems and cell culture samples have demonstrated utility of the system, and efforts are in progress for full development and deployment of the device. The technology has broad applicability as a universal detection platform for BWA detection, medical diagnostics, and drug discovery research, and represents a new class of instrumentation as a rapid, high sensitivity, label-free methodology.

Invisible data matrix detection with smart phone using geometric correction and Hough transform

NASA Astrophysics Data System (ADS)

Sun, Halit; Uysalturk, Mahir C.; Karakaya, Mahmut

2016-04-01

Two-dimensional data matrices are used in many different areas that provide quick and automatic data entry to the computer system. Their most common usage is to automatically read labeled products (books, medicines, food, etc.) and recognize them. In Turkey, alcohol beverages and tobacco products are labeled and tracked with the invisible data matrices for public safety and tax purposes. In this application, since data matrixes are printed on a special paper with a pigmented ink, it cannot be seen under daylight. When red LEDs are utilized for illumination and reflected light is filtered, invisible data matrices become visible and decoded by special barcode readers. Owing to their physical dimensions, price and requirement of special training to use; cheap, small sized and easily carried domestic mobile invisible data matrix reader systems are required to be delivered to every inspector in the law enforcement units. In this paper, we first developed an apparatus attached to the smartphone including a red LED light and a high pass filter. Then, we promoted an algorithm to process captured images by smartphones and to decode all information stored in the invisible data matrix images. The proposed algorithm mainly involves four stages. In the first step, data matrix code is processed by Hough transform processing to find "L" shaped pattern. In the second step, borders of the data matrix are found by using the convex hull and corner detection methods. Afterwards, distortion of invisible data matrix corrected by geometric correction technique and the size of every module is fixed in rectangular shape. Finally, the invisible data matrix is scanned line by line in the horizontal axis to decode it. Based on the results obtained from the real test images of invisible data matrix captured with a smartphone, the proposed algorithm indicates high accuracy and low error rate.

Automatic and Controlled Semantic Retrieval: TMS Reveals Distinct Contributions of Posterior Middle Temporal Gyrus and Angular Gyrus

PubMed Central

Davey, James; Cornelissen, Piers L.; Thompson, Hannah E.; Sonkusare, Saurabh; Hallam, Glyn; Smallwood, Jonathan

2015-01-01

Semantic retrieval involves both (1) automatic spreading activation between highly related concepts and (2) executive control processes that tailor this activation to suit the current context or goals. Two structures in left temporoparietal cortex, angular gyrus (AG) and posterior middle temporal gyrus (pMTG), are thought to be crucial to semantic retrieval and are often recruited together during semantic tasks; however, they show strikingly different patterns of functional connectivity at rest (coupling with the “default mode network” and “frontoparietal control system,” respectively). Here, transcranial magnetic stimulation (TMS) was used to establish a causal yet dissociable role for these sites in semantic cognition in human volunteers. TMS to AG disrupted thematic judgments particularly when the link between probe and target was strong (e.g., a picture of an Alsatian with a bone), and impaired the identification of objects at a specific but not a superordinate level (for the verbal label “Alsatian” not “animal”). In contrast, TMS to pMTG disrupted thematic judgments for weak but not strong associations (e.g., a picture of an Alsatian with razor wire), and impaired identity matching for both superordinate and specific-level labels. Thus, stimulation to AG interfered with the automatic retrieval of specific concepts from the semantic store while stimulation of pMTG impaired semantic cognition when there was a requirement to flexibly shape conceptual activation in line with the task requirements. These results demonstrate that AG and pMTG make a dissociable contribution to automatic and controlled aspects of semantic retrieval. SIGNIFICANCE STATEMENT We demonstrate a novel functional dissociation between the angular gyrus (AG) and posterior middle temporal gyrus (pMTG) in conceptual processing. These sites are often coactivated during neuroimaging studies using semantic tasks, but their individual contributions are unclear. Using transcranial magnetic stimulation and tasks designed to assess different aspects of semantics (item identity and thematic matching), we tested two alternative theoretical accounts. Neither site showed the pattern expected for a “thematic hub” (i.e., a site storing associations between concepts) since stimulation disrupted both tasks. Instead, the data indicated that pMTG contributes to the controlled retrieval of conceptual knowledge, while AG is critical for the efficient automatic retrieval of specific semantic information. PMID:26586812

Using Anatomic Magnetic Resonance Image Information to Enhance Visualization and Interpretation of Functional Images: A Comparison of Methods Applied to Clinical Arterial Spin Labeling Images

PubMed Central

Dai, Weiying; Soman, Salil; Hackney, David B.; Wong, Eric T.; Robson, Philip M.; Alsop, David C.

2017-01-01

Functional imaging provides hemodynamic and metabolic information and is increasingly being incorporated into clinical diagnostic and research studies. Typically functional images have reduced signal-to-noise ratio and spatial resolution compared to other non-functional cross sectional images obtained as part of a routine clinical protocol. We hypothesized that enhancing visualization and interpretation of functional images with anatomic information could provide preferable quality and superior diagnostic value. In this work, we implemented five methods (frequency addition, frequency multiplication, wavelet transform, non-subsampled contourlet transform and intensity-hue-saturation) and a newly proposed ShArpening by Local Similarity with Anatomic images (SALSA) method to enhance the visualization of functional images, while preserving the original functional contrast and quantitative signal intensity characteristics over larger spatial scales. Arterial spin labeling blood flow MR images of the brain were visualization enhanced using anatomic images with multiple contrasts. The algorithms were validated on a numerical phantom and their performance on images of brain tumor patients were assessed by quantitative metrics and neuroradiologist subjective ratings. The frequency multiplication method had the lowest residual error for preserving the original functional image contrast at larger spatial scales (55%–98% of the other methods with simulated data and 64%–86% with experimental data). It was also significantly more highly graded by the radiologists (p<0.005 for clear brain anatomy around the tumor). Compared to other methods, the SALSA provided 11%–133% higher similarity with ground truth images in the simulation and showed just slightly lower neuroradiologist grading score. Most of these monochrome methods do not require any prior knowledge about the functional and anatomic image characteristics, except the acquired resolution. Hence, automatic implementation on clinical images should be readily feasible. PMID:27723582

Multi-atlas segmentation for abdominal organs with Gaussian mixture models

NASA Astrophysics Data System (ADS)

Burke, Ryan P.; Xu, Zhoubing; Lee, Christopher P.; Baucom, Rebeccah B.; Poulose, Benjamin K.; Abramson, Richard G.; Landman, Bennett A.

2015-03-01

Abdominal organ segmentation with clinically acquired computed tomography (CT) is drawing increasing interest in the medical imaging community. Gaussian mixture models (GMM) have been extensively used through medical segmentation, most notably in the brain for cerebrospinal fluid / gray matter / white matter differentiation. Because abdominal CT exhibit strong localized intensity characteristics, GMM have recently been incorporated in multi-stage abdominal segmentation algorithms. In the context of variable abdominal anatomy and rich algorithms, it is difficult to assess the marginal contribution of GMM. Herein, we characterize the efficacy of an a posteriori framework that integrates GMM of organ-wise intensity likelihood with spatial priors from multiple target-specific registered labels. In our study, we first manually labeled 100 CT images. Then, we assigned 40 images to use as training data for constructing target-specific spatial priors and intensity likelihoods. The remaining 60 images were evaluated as test targets for segmenting 12 abdominal organs. The overlap between the true and the automatic segmentations was measured by Dice similarity coefficient (DSC). A median improvement of 145% was achieved by integrating the GMM intensity likelihood against the specific spatial prior. The proposed framework opens the opportunities for abdominal organ segmentation by efficiently using both the spatial and appearance information from the atlases, and creates a benchmark for large-scale automatic abdominal segmentation.

FacetGist: Collective Extraction of Document Facets in Large Technical Corpora.

PubMed

Siddiqui, Tarique; Ren, Xiang; Parameswaran, Aditya; Han, Jiawei

2016-10-01

Given the large volume of technical documents available, it is crucial to automatically organize and categorize these documents to be able to understand and extract value from them. Towards this end, we introduce a new research problem called Facet Extraction. Given a collection of technical documents, the goal of Facet Extraction is to automatically label each document with a set of concepts for the key facets ( e.g. , application, technique, evaluation metrics, and dataset) that people may be interested in. Facet Extraction has numerous applications, including document summarization, literature search, patent search and business intelligence. The major challenge in performing Facet Extraction arises from multiple sources: concept extraction, concept to facet matching, and facet disambiguation. To tackle these challenges, we develop FacetGist, a framework for facet extraction. Facet Extraction involves constructing a graph-based heterogeneous network to capture information available across multiple local sentence-level features, as well as global context features. We then formulate a joint optimization problem, and propose an efficient algorithm for graph-based label propagation to estimate the facet of each concept mention. Experimental results on technical corpora from two domains demonstrate that Facet Extraction can lead to an improvement of over 25% in both precision and recall over competing schemes.

FacetGist: Collective Extraction of Document Facets in Large Technical Corpora

PubMed Central

Siddiqui, Tarique; Ren, Xiang; Parameswaran, Aditya; Han, Jiawei

2017-01-01

Given the large volume of technical documents available, it is crucial to automatically organize and categorize these documents to be able to understand and extract value from them. Towards this end, we introduce a new research problem called Facet Extraction. Given a collection of technical documents, the goal of Facet Extraction is to automatically label each document with a set of concepts for the key facets (e.g., application, technique, evaluation metrics, and dataset) that people may be interested in. Facet Extraction has numerous applications, including document summarization, literature search, patent search and business intelligence. The major challenge in performing Facet Extraction arises from multiple sources: concept extraction, concept to facet matching, and facet disambiguation. To tackle these challenges, we develop FacetGist, a framework for facet extraction. Facet Extraction involves constructing a graph-based heterogeneous network to capture information available across multiple local sentence-level features, as well as global context features. We then formulate a joint optimization problem, and propose an efficient algorithm for graph-based label propagation to estimate the facet of each concept mention. Experimental results on technical corpora from two domains demonstrate that Facet Extraction can lead to an improvement of over 25% in both precision and recall over competing schemes. PMID:28210517

RobotReviewer: evaluation of a system for automatically assessing bias in clinical trials.

PubMed

Marshall, Iain J; Kuiper, Joël; Wallace, Byron C

2016-01-01

To develop and evaluate RobotReviewer, a machine learning (ML) system that automatically assesses bias in clinical trials. From a (PDF-formatted) trial report, the system should determine risks of bias for the domains defined by the Cochrane Risk of Bias (RoB) tool, and extract supporting text for these judgments. We algorithmically annotated 12,808 trial PDFs using data from the Cochrane Database of Systematic Reviews (CDSR). Trials were labeled as being at low or high/unclear risk of bias for each domain, and sentences were labeled as being informative or not. This dataset was used to train a multi-task ML model. We estimated the accuracy of ML judgments versus humans by comparing trials with two or more independent RoB assessments in the CDSR. Twenty blinded experienced reviewers rated the relevance of supporting text, comparing ML output with equivalent (human-extracted) text from the CDSR. By retrieving the top 3 candidate sentences per document (top3 recall), the best ML text was rated more relevant than text from the CDSR, but not significantly (60.4% ML text rated 'highly relevant' v 56.5% of text from reviews; difference +3.9%, [-3.2% to +10.9%]). Model RoB judgments were less accurate than those from published reviews, though the difference was <10% (overall accuracy 71.0% with ML v 78.3% with CDSR). Risk of bias assessment may be automated with reasonable accuracy. Automatically identified text supporting bias assessment is of equal quality to the manually identified text in the CDSR. This technology could substantially reduce reviewer workload and expedite evidence syntheses. © The Author 2015. Published by Oxford University Press on behalf of the American Medical Informatics Association.

The CHEMDNER corpus of chemicals and drugs and its annotation principles.

PubMed

Krallinger, Martin; Rabal, Obdulia; Leitner, Florian; Vazquez, Miguel; Salgado, David; Lu, Zhiyong; Leaman, Robert; Lu, Yanan; Ji, Donghong; Lowe, Daniel M; Sayle, Roger A; Batista-Navarro, Riza Theresa; Rak, Rafal; Huber, Torsten; Rocktäschel, Tim; Matos, Sérgio; Campos, David; Tang, Buzhou; Xu, Hua; Munkhdalai, Tsendsuren; Ryu, Keun Ho; Ramanan, S V; Nathan, Senthil; Žitnik, Slavko; Bajec, Marko; Weber, Lutz; Irmer, Matthias; Akhondi, Saber A; Kors, Jan A; Xu, Shuo; An, Xin; Sikdar, Utpal Kumar; Ekbal, Asif; Yoshioka, Masaharu; Dieb, Thaer M; Choi, Miji; Verspoor, Karin; Khabsa, Madian; Giles, C Lee; Liu, Hongfang; Ravikumar, Komandur Elayavilli; Lamurias, Andre; Couto, Francisco M; Dai, Hong-Jie; Tsai, Richard Tzong-Han; Ata, Caglar; Can, Tolga; Usié, Anabel; Alves, Rui; Segura-Bedmar, Isabel; Martínez, Paloma; Oyarzabal, Julen; Valencia, Alfonso

2015-01-01

The automatic extraction of chemical information from text requires the recognition of chemical entity mentions as one of its key steps. When developing supervised named entity recognition (NER) systems, the availability of a large, manually annotated text corpus is desirable. Furthermore, large corpora permit the robust evaluation and comparison of different approaches that detect chemicals in documents. We present the CHEMDNER corpus, a collection of 10,000 PubMed abstracts that contain a total of 84,355 chemical entity mentions labeled manually by expert chemistry literature curators, following annotation guidelines specifically defined for this task. The abstracts of the CHEMDNER corpus were selected to be representative for all major chemical disciplines. Each of the chemical entity mentions was manually labeled according to its structure-associated chemical entity mention (SACEM) class: abbreviation, family, formula, identifier, multiple, systematic and trivial. The difficulty and consistency of tagging chemicals in text was measured using an agreement study between annotators, obtaining a percentage agreement of 91. For a subset of the CHEMDNER corpus (the test set of 3,000 abstracts) we provide not only the Gold Standard manual annotations, but also mentions automatically detected by the 26 teams that participated in the BioCreative IV CHEMDNER chemical mention recognition task. In addition, we release the CHEMDNER silver standard corpus of automatically extracted mentions from 17,000 randomly selected PubMed abstracts. A version of the CHEMDNER corpus in the BioC format has been generated as well. We propose a standard for required minimum information about entity annotations for the construction of domain specific corpora on chemical and drug entities. The CHEMDNER corpus and annotation guidelines are available at: http://www.biocreative.org/resources/biocreative-iv/chemdner-corpus/.

Toward high-throughput genotyping: dynamic and automatic software for manipulating large-scale genotype data using fluorescently labeled dinucleotide markers.

PubMed

Li, J L; Deng, H; Lai, D B; Xu, F; Chen, J; Gao, G; Recker, R R; Deng, H W

2001-07-01

To efficiently manipulate large amounts of genotype data generated with fluorescently labeled dinucleotide markers, we developed a Microsoft database management system, named. offers several advantages. First, it accommodates the dynamic nature of the accumulations of genotype data during the genotyping process; some data need to be confirmed or replaced by repeat lab procedures. By using, the raw genotype data can be imported easily and continuously and incorporated into the database during the genotyping process that may continue over an extended period of time in large projects. Second, almost all of the procedures are automatic, including autocomparison of the raw data read by different technicians from the same gel, autoadjustment among the allele fragment-size data from cross-runs or cross-platforms, autobinning of alleles, and autocompilation of genotype data for suitable programs to perform inheritance check in pedigrees. Third, provides functions to track electrophoresis gel files to locate gel or sample sources for any resultant genotype data, which is extremely helpful for double-checking consistency of raw and final data and for directing repeat experiments. In addition, the user-friendly graphic interface of renders processing of large amounts of data much less labor-intensive. Furthermore, has built-in mechanisms to detect some genotyping errors and to assess the quality of genotype data that then are summarized in the statistic reports automatically generated by. The can easily handle >500,000 genotype data entries, a number more than sufficient for typical whole-genome linkage studies. The modules and programs we developed for the can be extended to other database platforms, such as Microsoft SQL server, if the capability to handle still greater quantities of genotype data simultaneously is desired.

The CHEMDNER corpus of chemicals and drugs and its annotation principles

PubMed Central

2015-01-01

The automatic extraction of chemical information from text requires the recognition of chemical entity mentions as one of its key steps. When developing supervised named entity recognition (NER) systems, the availability of a large, manually annotated text corpus is desirable. Furthermore, large corpora permit the robust evaluation and comparison of different approaches that detect chemicals in documents. We present the CHEMDNER corpus, a collection of 10,000 PubMed abstracts that contain a total of 84,355 chemical entity mentions labeled manually by expert chemistry literature curators, following annotation guidelines specifically defined for this task. The abstracts of the CHEMDNER corpus were selected to be representative for all major chemical disciplines. Each of the chemical entity mentions was manually labeled according to its structure-associated chemical entity mention (SACEM) class: abbreviation, family, formula, identifier, multiple, systematic and trivial. The difficulty and consistency of tagging chemicals in text was measured using an agreement study between annotators, obtaining a percentage agreement of 91. For a subset of the CHEMDNER corpus (the test set of 3,000 abstracts) we provide not only the Gold Standard manual annotations, but also mentions automatically detected by the 26 teams that participated in the BioCreative IV CHEMDNER chemical mention recognition task. In addition, we release the CHEMDNER silver standard corpus of automatically extracted mentions from 17,000 randomly selected PubMed abstracts. A version of the CHEMDNER corpus in the BioC format has been generated as well. We propose a standard for required minimum information about entity annotations for the construction of domain specific corpora on chemical and drug entities. The CHEMDNER corpus and annotation guidelines are available at: http://www.biocreative.org/resources/biocreative-iv/chemdner-corpus/ PMID:25810773

Systematic Comparison of Label-Free, Metabolic Labeling, and Isobaric Chemical Labeling for Quantitative Proteomics on LTQ Orbitrap Velos

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

Li, Zhou; Adams, Rachel M; Chourey, Karuna

2012-01-01

A variety of quantitative proteomics methods have been developed, including label-free, metabolic labeling, and isobaric chemical labeling using iTRAQ or TMT. Here, these methods were compared in terms of the depth of proteome coverage, quantification accuracy, precision, and reproducibility using a high-performance hybrid mass spectrometer, LTQ Orbitrap Velos. Our results show that (1) the spectral counting method provides the deepest proteome coverage for identification, but its quantification performance is worse than labeling-based approaches, especially the quantification reproducibility; (2) metabolic labeling and isobaric chemical labeling are capable of accurate, precise, and reproducible quantification and provide deep proteome coverage for quantification. Isobaricmore » chemical labeling surpasses metabolic labeling in terms of quantification precision and reproducibility; (3) iTRAQ and TMT perform similarly in all aspects compared in the current study using a CID-HCD dual scan configuration. Based on the unique advantages of each method, we provide guidance for selection of the appropriate method for a quantitative proteomics study.« less

Comparison of liver volumetry on contrast‐enhanced CT images: one semiautomatic and two automatic approaches

PubMed Central

Cai, Wei; He, Baochun; Fang, Chihua

2016-01-01

This study was to evaluate the accuracy, consistency, and efficiency of three liver volumetry methods— one interactive method, an in‐house‐developed 3D medical Image Analysis (3DMIA) system, one automatic active shape model (ASM)‐based segmentation, and one automatic probabilistic atlas (PA)‐guided segmentation method on clinical contrast‐enhanced CT images. Forty‐two datasets, including 27 normal liver and 15 space‐occupying liver lesion patients, were retrospectively included in this study. The three methods — one semiautomatic 3DMIA, one automatic ASM‐based, and one automatic PA‐based liver volumetry — achieved an accuracy with VD (volume difference) of −1.69%,−2.75%, and 3.06% in the normal group, respectively, and with VD of −3.20%,−3.35%, and 4.14% in the space‐occupying lesion group, respectively. However, the three methods achieved an efficiency of 27.63 mins, 1.26 mins, 1.18 mins on average, respectively, compared with the manual volumetry, which took 43.98 mins. The high intraclass correlation coefficient between the three methods and the manual method indicated an excellent agreement on liver volumetry. Significant differences in segmentation time were observed between the three methods (3DMIA, ASM, and PA) and the manual volumetry (p<0.001), as well as between the automatic volumetries (ASM and PA) and the semiautomatic volumetry (3DMIA) (p<0.001). The semiautomatic interactive 3DMIA, automatic ASM‐based, and automatic PA‐based liver volumetry agreed well with manual gold standard in both the normal liver group and the space‐occupying lesion group. The ASM‐ and PA‐based automatic segmentation have better efficiency in clinical use. PACS number(s): 87.55.‐x PMID:27929487

Automatic tissue segmentation of breast biopsies imaged by QPI

NASA Astrophysics Data System (ADS)

Majeed, Hassaan; Nguyen, Tan; Kandel, Mikhail; Marcias, Virgilia; Do, Minh; Tangella, Krishnarao; Balla, Andre; Popescu, Gabriel

2016-03-01

The current tissue evaluation method for breast cancer would greatly benefit from higher throughput and less inter-observer variation. Since quantitative phase imaging (QPI) measures physical parameters of tissue, it can be used to find quantitative markers, eliminating observer subjectivity. Furthermore, since the pixel values in QPI remain the same regardless of the instrument used, classifiers can be built to segment various tissue components without need for color calibration. In this work we use a texton-based approach to segment QPI images of breast tissue into various tissue components (epithelium, stroma or lumen). A tissue microarray comprising of 900 unstained cores from 400 different patients was imaged using Spatial Light Interference Microscopy. The training data were generated by manually segmenting the images for 36 cores and labelling each pixel (epithelium, stroma or lumen.). For each pixel in the data, a response vector was generated by the Leung-Malik (LM) filter bank and these responses were clustered using the k-means algorithm to find the centers (called textons). A random forest classifier was then trained to find the relationship between a pixel's label and the histogram of these textons in that pixel's neighborhood. The segmentation was carried out on the validation set by calculating the texton histogram in a pixel's neighborhood and generating a label based on the model learnt during training. Segmentation of the tissue into various components is an important step toward efficiently computing parameters that are markers of disease. Automated segmentation, followed by diagnosis, can improve the accuracy and speed of analysis leading to better health outcomes.

Bayesian network classifiers for categorizing cortical GABAergic interneurons.

PubMed

Mihaljević, Bojan; Benavides-Piccione, Ruth; Bielza, Concha; DeFelipe, Javier; Larrañaga, Pedro

2015-04-01

An accepted classification of GABAergic interneurons of the cerebral cortex is a major goal in neuroscience. A recently proposed taxonomy based on patterns of axonal arborization promises to be a pragmatic method for achieving this goal. It involves characterizing interneurons according to five axonal arborization features, called F1-F5, and classifying them into a set of predefined types, most of which are established in the literature. Unfortunately, there is little consensus among expert neuroscientists regarding the morphological definitions of some of the proposed types. While supervised classifiers were able to categorize the interneurons in accordance with experts' assignments, their accuracy was limited because they were trained with disputed labels. Thus, here we automatically classify interneuron subsets with different label reliability thresholds (i.e., such that every cell's label is backed by at least a certain (threshold) number of experts). We quantify the cells with parameters of axonal and dendritic morphologies and, in order to predict the type, also with axonal features F1-F4 provided by the experts. Using Bayesian network classifiers, we accurately characterize and classify the interneurons and identify useful predictor variables. In particular, we discriminate among reliable examples of common basket, horse-tail, large basket, and Martinotti cells with up to 89.52% accuracy, and single out the number of branches at 180 μm from the soma, the convex hull 2D area, and the axonal features F1-F4 as especially useful predictors for distinguishing among these types. These results open up new possibilities for an objective and pragmatic classification of interneurons.

Cellular image segmentation using n-agent cooperative game theory

NASA Astrophysics Data System (ADS)

Dimock, Ian B.; Wan, Justin W. L.

2016-03-01

Image segmentation is an important problem in computer vision and has significant applications in the segmentation of cellular images. Many different imaging techniques exist and produce a variety of image properties which pose difficulties to image segmentation routines. Bright-field images are particularly challenging because of the non-uniform shape of the cells, the low contrast between cells and background, and imaging artifacts such as halos and broken edges. Classical segmentation techniques often produce poor results on these challenging images. Previous attempts at bright-field imaging are often limited in scope to the images that they segment. In this paper, we introduce a new algorithm for automatically segmenting cellular images. The algorithm incorporates two game theoretic models which allow each pixel to act as an independent agent with the goal of selecting their best labelling strategy. In the non-cooperative model, the pixels choose strategies greedily based only on local information. In the cooperative model, the pixels can form coalitions, which select labelling strategies that benefit the entire group. Combining these two models produces a method which allows the pixels to balance both local and global information when selecting their label. With the addition of k-means and active contour techniques for initialization and post-processing purposes, we achieve a robust segmentation routine. The algorithm is applied to several cell image datasets including bright-field images, fluorescent images and simulated images. Experiments show that the algorithm produces good segmentation results across the variety of datasets which differ in cell density, cell shape, contrast, and noise levels.

Nonparametric, Coupled ,Bayesian ,Dictionary ,and Classifier Learning for Hyperspectral Classification.

PubMed

Akhtar, Naveed; Mian, Ajmal

2017-10-03

We present a principled approach to learn a discriminative dictionary along a linear classifier for hyperspectral classification. Our approach places Gaussian Process priors over the dictionary to account for the relative smoothness of the natural spectra, whereas the classifier parameters are sampled from multivariate Gaussians. We employ two Beta-Bernoulli processes to jointly infer the dictionary and the classifier. These processes are coupled under the same sets of Bernoulli distributions. In our approach, these distributions signify the frequency of the dictionary atom usage in representing class-specific training spectra, which also makes the dictionary discriminative. Due to the coupling between the dictionary and the classifier, the popularity of the atoms for representing different classes gets encoded into the classifier. This helps in predicting the class labels of test spectra that are first represented over the dictionary by solving a simultaneous sparse optimization problem. The labels of the spectra are predicted by feeding the resulting representations to the classifier. Our approach exploits the nonparametric Bayesian framework to automatically infer the dictionary size--the key parameter in discriminative dictionary learning. Moreover, it also has the desirable property of adaptively learning the association between the dictionary atoms and the class labels by itself. We use Gibbs sampling to infer the posterior probability distributions over the dictionary and the classifier under the proposed model, for which, we derive analytical expressions. To establish the effectiveness of our approach, we test it on benchmark hyperspectral images. The classification performance is compared with the state-of-the-art dictionary learning-based classification methods.

Discovering cell types in flow cytometry data with random matrix theory

NASA Astrophysics Data System (ADS)

Shen, Yang; Nussenblatt, Robert; Losert, Wolfgang

Flow cytometry is a widely used experimental technique in immunology research. During the experiments, peripheral blood mononuclear cells (PBMC) from a single patient, labeled with multiple fluorescent stains that bind to different proteins, are illuminated by a laser. The intensity of each stain on a single cell is recorded and reflects the amount of protein expressed by that cell. The data analysis focuses on identifying specific cell types related to a disease. Different cell types can be identified by the type and amount of protein they express. To date, this has most often been done manually by labelling a protein as expressed or not while ignoring the amount of expression. Using a cross correlation matrix of stain intensities, which contains both information on the proteins expressed and their amount, has been largely ignored by researchers as it suffers from measurement noise. Here we present an algorithm to identify cell types in flow cytometry data which uses random matrix theory (RMT) to reduce noise in a cross correlation matrix. We demonstrate our method using a published flow cytometry data set. Compared with previous analysis techniques, we were able to rediscover relevant cell types in an automatic way. Department of Physics, University of Maryland, College Park, MD 20742.

PSNet: prostate segmentation on MRI based on a convolutional neural network.

PubMed

Tian, Zhiqiang; Liu, Lizhi; Zhang, Zhenfeng; Fei, Baowei

2018-04-01

Automatic segmentation of the prostate on magnetic resonance images (MRI) has many applications in prostate cancer diagnosis and therapy. We proposed a deep fully convolutional neural network (CNN) to segment the prostate automatically. Our deep CNN model is trained end-to-end in a single learning stage, which uses prostate MRI and the corresponding ground truths as inputs. The learned CNN model can be used to make an inference for pixel-wise segmentation. Experiments were performed on three data sets, which contain prostate MRI of 140 patients. The proposed CNN model of prostate segmentation (PSNet) obtained a mean Dice similarity coefficient of [Formula: see text] as compared to the manually labeled ground truth. Experimental results show that the proposed model could yield satisfactory segmentation of the prostate on MRI.

Multi-atlas label fusion using hybrid of discriminative and generative classifiers for segmentation of cardiac MR images.

PubMed

Sedai, Suman; Garnavi, Rahil; Roy, Pallab; Xi Liang

2015-08-01

Multi-atlas segmentation first registers each atlas image to the target image and transfers the label of atlas image to the coordinate system of the target image. The transferred labels are then combined, using a label fusion algorithm. In this paper, we propose a novel label fusion method which aggregates discriminative learning and generative modeling for segmentation of cardiac MR images. First, a probabilistic Random Forest classifier is trained as a discriminative model to obtain the prior probability of a label at the given voxel of the target image. Then, a probability distribution of image patches is modeled using Gaussian Mixture Model for each label, providing the likelihood of the voxel belonging to the label. The final label posterior is obtained by combining the classification score and the likelihood score under Bayesian rule. Comparative study performed on MICCAI 2013 SATA Segmentation Challenge demonstrates that our proposed hybrid label fusion algorithm is accurate than other five state-of-the-art label fusion methods. The proposed method obtains dice similarity coefficient of 0.94 and 0.92 in segmenting epicardium and endocardium respectively. Moreover, our label fusion method achieves more accurate segmentation results compared to four other label fusion methods.

An evaluation of automatic coronary artery calcium scoring methods with cardiac CT using the orCaScore framework.

PubMed

Wolterink, Jelmer M; Leiner, Tim; de Vos, Bob D; Coatrieux, Jean-Louis; Kelm, B Michael; Kondo, Satoshi; Salgado, Rodrigo A; Shahzad, Rahil; Shu, Huazhong; Snoeren, Miranda; Takx, Richard A P; van Vliet, Lucas J; van Walsum, Theo; Willems, Tineke P; Yang, Guanyu; Zheng, Yefeng; Viergever, Max A; Išgum, Ivana

2016-05-01

The amount of coronary artery calcification (CAC) is a strong and independent predictor of cardiovascular disease (CVD) events. In clinical practice, CAC is manually identified and automatically quantified in cardiac CT using commercially available software. This is a tedious and time-consuming process in large-scale studies. Therefore, a number of automatic methods that require no interaction and semiautomatic methods that require very limited interaction for the identification of CAC in cardiac CT have been proposed. Thus far, a comparison of their performance has been lacking. The objective of this study was to perform an independent evaluation of (semi)automatic methods for CAC scoring in cardiac CT using a publicly available standardized framework. Cardiac CT exams of 72 patients distributed over four CVD risk categories were provided for (semi)automatic CAC scoring. Each exam consisted of a noncontrast-enhanced calcium scoring CT (CSCT) and a corresponding coronary CT angiography (CCTA) scan. The exams were acquired in four different hospitals using state-of-the-art equipment from four major CT scanner vendors. The data were divided into 32 training exams and 40 test exams. A reference standard for CAC in CSCT was defined by consensus of two experts following a clinical protocol. The framework organizers evaluated the performance of (semi)automatic methods on test CSCT scans, per lesion, artery, and patient. Five (semi)automatic methods were evaluated. Four methods used both CSCT and CCTA to identify CAC, and one method used only CSCT. The evaluated methods correctly detected between 52% and 94% of CAC lesions with positive predictive values between 65% and 96%. Lesions in distal coronary arteries were most commonly missed and aortic calcifications close to the coronary ostia were the most common false positive errors. The majority (between 88% and 98%) of correctly identified CAC lesions were assigned to the correct artery. Linearly weighted Cohen's kappa for patient CVD risk categorization by the evaluated methods ranged from 0.80 to 1.00. A publicly available standardized framework for the evaluation of (semi)automatic methods for CAC identification in cardiac CT is described. An evaluation of five (semi)automatic methods within this framework shows that automatic per patient CVD risk categorization is feasible. CAC lesions at ambiguous locations such as the coronary ostia remain challenging, but their detection had limited impact on CVD risk determination.

An empirical evaluation of supervised learning approaches in assigning diagnosis codes to electronic medical records

PubMed Central

Kavuluru, Ramakanth; Rios, Anthony; Lu, Yuan

2015-01-01

Background Diagnosis codes are assigned to medical records in healthcare facilities by trained coders by reviewing all physician authored documents associated with a patient's visit. This is a necessary and complex task involving coders adhering to coding guidelines and coding all assignable codes. With the popularity of electronic medical records (EMRs), computational approaches to code assignment have been proposed in the recent years. However, most efforts have focused on single and often short clinical narratives, while realistic scenarios warrant full EMR level analysis for code assignment. Objective We evaluate supervised learning approaches to automatically assign international classification of diseases (ninth revision) - clinical modification (ICD-9-CM) codes to EMRs by experimenting with a large realistic EMR dataset. The overall goal is to identify methods that offer superior performance in this task when considering such datasets. Methods We use a dataset of 71,463 EMRs corresponding to in-patient visits with discharge date falling in a two year period (2011–2012) from the University of Kentucky (UKY) Medical Center. We curate a smaller subset of this dataset and also use a third gold standard dataset of radiology reports. We conduct experiments using different problem transformation approaches with feature and data selection components and employing suitable label calibration and ranking methods with novel features involving code co-occurrence frequencies and latent code associations. Results Over all codes with at least 50 training examples we obtain a micro F-score of 0.48. On the set of codes that occur at least in 1% of the two year dataset, we achieve a micro F-score of 0.54. For the smaller radiology report dataset, the classifier chaining approach yields best results. For the smaller subset of the UKY dataset, feature selection, data selection, and label calibration offer best performance. Conclusions We show that datasets at different scale (size of the EMRs, number of distinct codes) and with different characteristics warrant different learning approaches. For shorter narratives pertaining to a particular medical subdomain (e.g., radiology, pathology), classifier chaining is ideal given the codes are highly related with each other. For realistic in-patient full EMRs, feature and data selection methods offer high performance for smaller datasets. However, for large EMR datasets, we observe that the binary relevance approach with learning-to-rank based code reranking offers the best performance. Regardless of the training dataset size, for general EMRs, label calibration to select the optimal number of labels is an indispensable final step. PMID:26054428

Active learning of neuron morphology for accurate automated tracing of neurites

PubMed Central

Gala, Rohan; Chapeton, Julio; Jitesh, Jayant; Bhavsar, Chintan; Stepanyants, Armen

2014-01-01

Automating the process of neurite tracing from light microscopy stacks of images is essential for large-scale or high-throughput quantitative studies of neural circuits. While the general layout of labeled neurites can be captured by many automated tracing algorithms, it is often not possible to differentiate reliably between the processes belonging to different cells. The reason is that some neurites in the stack may appear broken due to imperfect labeling, while others may appear fused due to the limited resolution of optical microscopy. Trained neuroanatomists routinely resolve such topological ambiguities during manual tracing tasks by combining information about distances between branches, branch orientations, intensities, calibers, tortuosities, colors, as well as the presence of spines or boutons. Likewise, to evaluate different topological scenarios automatically, we developed a machine learning approach that combines many of the above mentioned features. A specifically designed confidence measure was used to actively train the algorithm during user-assisted tracing procedure. Active learning significantly reduces the training time and makes it possible to obtain less than 1% generalization error rates by providing few training examples. To evaluate the overall performance of the algorithm a number of image stacks were reconstructed automatically, as well as manually by several trained users, making it possible to compare the automated traces to the baseline inter-user variability. Several geometrical and topological features of the traces were selected for the comparisons. These features include the total trace length, the total numbers of branch and terminal points, the affinity of corresponding traces, and the distances between corresponding branch and terminal points. Our results show that when the density of labeled neurites is sufficiently low, automated traces are not significantly different from manual reconstructions obtained by trained users. PMID:24904306

A label distance maximum-based classifier for multi-label learning.

PubMed

Liu, Xiaoli; Bao, Hang; Zhao, Dazhe; Cao, Peng

2015-01-01

Multi-label classification is useful in many bioinformatics tasks such as gene function prediction and protein site localization. This paper presents an improved neural network algorithm, Max Label Distance Back Propagation Algorithm for Multi-Label Classification. The method was formulated by modifying the total error function of the standard BP by adding a penalty term, which was realized by maximizing the distance between the positive and negative labels. Extensive experiments were conducted to compare this method against state-of-the-art multi-label methods on three popular bioinformatic benchmark datasets. The results illustrated that this proposed method is more effective for bioinformatic multi-label classification compared to commonly used techniques.

Hippocampus Segmentation Based on Local Linear Mapping

PubMed Central

Pang, Shumao; Jiang, Jun; Lu, Zhentai; Li, Xueli; Yang, Wei; Huang, Meiyan; Zhang, Yu; Feng, Yanqiu; Huang, Wenhua; Feng, Qianjin

2017-01-01

We propose local linear mapping (LLM), a novel fusion framework for distance field (DF) to perform automatic hippocampus segmentation. A k-means cluster method is propose for constructing magnetic resonance (MR) and DF dictionaries. In LLM, we assume that the MR and DF samples are located on two nonlinear manifolds and the mapping from the MR manifold to the DF manifold is differentiable and locally linear. We combine the MR dictionary using local linear representation to present the test sample, and combine the DF dictionary using the corresponding coefficients derived from local linear representation procedure to predict the DF of the test sample. We then merge the overlapped predicted DF patch to obtain the DF value of each point in the test image via a confidence-based weighted average method. This approach enabled us to estimate the label of the test image according to the predicted DF. The proposed method was evaluated on brain images of 35 subjects obtained from SATA dataset. Results indicate the effectiveness of the proposed method, which yields mean Dice similarity coefficients of 0.8697, 0.8770 and 0.8734 for the left, right and bi-lateral hippocampus, respectively. PMID:28368016

Hippocampus Segmentation Based on Local Linear Mapping.

PubMed

Pang, Shumao; Jiang, Jun; Lu, Zhentai; Li, Xueli; Yang, Wei; Huang, Meiyan; Zhang, Yu; Feng, Yanqiu; Huang, Wenhua; Feng, Qianjin

2017-04-03

We propose local linear mapping (LLM), a novel fusion framework for distance field (DF) to perform automatic hippocampus segmentation. A k-means cluster method is propose for constructing magnetic resonance (MR) and DF dictionaries. In LLM, we assume that the MR and DF samples are located on two nonlinear manifolds and the mapping from the MR manifold to the DF manifold is differentiable and locally linear. We combine the MR dictionary using local linear representation to present the test sample, and combine the DF dictionary using the corresponding coefficients derived from local linear representation procedure to predict the DF of the test sample. We then merge the overlapped predicted DF patch to obtain the DF value of each point in the test image via a confidence-based weighted average method. This approach enabled us to estimate the label of the test image according to the predicted DF. The proposed method was evaluated on brain images of 35 subjects obtained from SATA dataset. Results indicate the effectiveness of the proposed method, which yields mean Dice similarity coefficients of 0.8697, 0.8770 and 0.8734 for the left, right and bi-lateral hippocampus, respectively.

Hippocampus Segmentation Based on Local Linear Mapping

NASA Astrophysics Data System (ADS)

Pang, Shumao; Jiang, Jun; Lu, Zhentai; Li, Xueli; Yang, Wei; Huang, Meiyan; Zhang, Yu; Feng, Yanqiu; Huang, Wenhua; Feng, Qianjin

2017-04-01

We propose local linear mapping (LLM), a novel fusion framework for distance field (DF) to perform automatic hippocampus segmentation. A k-means cluster method is propose for constructing magnetic resonance (MR) and DF dictionaries. In LLM, we assume that the MR and DF samples are located on two nonlinear manifolds and the mapping from the MR manifold to the DF manifold is differentiable and locally linear. We combine the MR dictionary using local linear representation to present the test sample, and combine the DF dictionary using the corresponding coefficients derived from local linear representation procedure to predict the DF of the test sample. We then merge the overlapped predicted DF patch to obtain the DF value of each point in the test image via a confidence-based weighted average method. This approach enabled us to estimate the label of the test image according to the predicted DF. The proposed method was evaluated on brain images of 35 subjects obtained from SATA dataset. Results indicate the effectiveness of the proposed method, which yields mean Dice similarity coefficients of 0.8697, 0.8770 and 0.8734 for the left, right and bi-lateral hippocampus, respectively.

Holographic deep learning for rapid optical screening of anthrax spores

PubMed Central

Jo, YoungJu; Park, Sangjin; Jung, JaeHwang; Yoon, Jonghee; Joo, Hosung; Kim, Min-hyeok; Kang, Suk-Jo; Choi, Myung Chul; Lee, Sang Yup; Park, YongKeun

2017-01-01

Establishing early warning systems for anthrax attacks is crucial in biodefense. Despite numerous studies for decades, the limited sensitivity of conventional biochemical methods essentially requires preprocessing steps and thus has limitations to be used in realistic settings of biological warfare. We present an optical method for rapid and label-free screening of Bacillus anthracis spores through the synergistic application of holographic microscopy and deep learning. A deep convolutional neural network is designed to classify holographic images of unlabeled living cells. After training, the network outperforms previous techniques in all accuracy measures, achieving single-spore sensitivity and subgenus specificity. The unique “representation learning” capability of deep learning enables direct training from raw images instead of manually extracted features. The method automatically recognizes key biological traits encoded in the images and exploits them as fingerprints. This remarkable learning ability makes the proposed method readily applicable to classifying various single cells in addition to B. anthracis, as demonstrated for the diagnosis of Listeria monocytogenes, without any modification. We believe that our strategy will make holographic microscopy more accessible to medical doctors and biomedical scientists for easy, rapid, and accurate point-of-care diagnosis of pathogens. PMID:28798957

Feature Selection based on Machine Learning in MRIs for Hippocampal Segmentation

NASA Astrophysics Data System (ADS)

Tangaro, Sabina; Amoroso, Nicola; Brescia, Massimo; Cavuoti, Stefano; Chincarini, Andrea; Errico, Rosangela; Paolo, Inglese; Longo, Giuseppe; Maglietta, Rosalia; Tateo, Andrea; Riccio, Giuseppe; Bellotti, Roberto

2015-01-01

Neurodegenerative diseases are frequently associated with structural changes in the brain. Magnetic resonance imaging (MRI) scans can show these variations and therefore can be used as a supportive feature for a number of neurodegenerative diseases. The hippocampus has been known to be a biomarker for Alzheimer disease and other neurological and psychiatric diseases. However, it requires accurate, robust, and reproducible delineation of hippocampal structures. Fully automatic methods are usually the voxel based approach; for each voxel a number of local features were calculated. In this paper, we compared four different techniques for feature selection from a set of 315 features extracted for each voxel: (i) filter method based on the Kolmogorov-Smirnov test; two wrapper methods, respectively, (ii) sequential forward selection and (iii) sequential backward elimination; and (iv) embedded method based on the Random Forest Classifier on a set of 10 T1-weighted brain MRIs and tested on an independent set of 25 subjects. The resulting segmentations were compared with manual reference labelling. By using only 23 feature for each voxel (sequential backward elimination) we obtained comparable state-of-the-art performances with respect to the standard tool FreeSurfer.

FIB/SEM technology and high-throughput 3D reconstruction of dendritic spines and synapses in GFP-labeled adult-generated neurons.

PubMed

Bosch, Carles; Martínez, Albert; Masachs, Nuria; Teixeira, Cátia M; Fernaud, Isabel; Ulloa, Fausto; Pérez-Martínez, Esther; Lois, Carlos; Comella, Joan X; DeFelipe, Javier; Merchán-Pérez, Angel; Soriano, Eduardo

2015-01-01

The fine analysis of synaptic contacts is usually performed using transmission electron microscopy (TEM) and its combination with neuronal labeling techniques. However, the complex 3D architecture of neuronal samples calls for their reconstruction from serial sections. Here we show that focused ion beam/scanning electron microscopy (FIB/SEM) allows efficient, complete, and automatic 3D reconstruction of identified dendrites, including their spines and synapses, from GFP/DAB-labeled neurons, with a resolution comparable to that of TEM. We applied this technology to analyze the synaptogenesis of labeled adult-generated granule cells (GCs) in mice. 3D reconstruction of dendritic spines in GCs aged 3-4 and 8-9 weeks revealed two different stages of dendritic spine development and unexpected features of synapse formation, including vacant and branched dendritic spines and presynaptic terminals establishing synapses with up to 10 dendritic spines. Given the reliability, efficiency, and high resolution of FIB/SEM technology and the wide use of DAB in conventional EM, we consider FIB/SEM fundamental for the detailed characterization of identified synaptic contacts in neurons in a high-throughput manner.

FIB/SEM technology and high-throughput 3D reconstruction of dendritic spines and synapses in GFP-labeled adult-generated neurons

PubMed Central

Bosch, Carles; Martínez, Albert; Masachs, Nuria; Teixeira, Cátia M.; Fernaud, Isabel; Ulloa, Fausto; Pérez-Martínez, Esther; Lois, Carlos; Comella, Joan X.; DeFelipe, Javier; Merchán-Pérez, Angel; Soriano, Eduardo

2015-01-01

The fine analysis of synaptic contacts is usually performed using transmission electron microscopy (TEM) and its combination with neuronal labeling techniques. However, the complex 3D architecture of neuronal samples calls for their reconstruction from serial sections. Here we show that focused ion beam/scanning electron microscopy (FIB/SEM) allows efficient, complete, and automatic 3D reconstruction of identified dendrites, including their spines and synapses, from GFP/DAB-labeled neurons, with a resolution comparable to that of TEM. We applied this technology to analyze the synaptogenesis of labeled adult-generated granule cells (GCs) in mice. 3D reconstruction of dendritic spines in GCs aged 3–4 and 8–9 weeks revealed two different stages of dendritic spine development and unexpected features of synapse formation, including vacant and branched dendritic spines and presynaptic terminals establishing synapses with up to 10 dendritic spines. Given the reliability, efficiency, and high resolution of FIB/SEM technology and the wide use of DAB in conventional EM, we consider FIB/SEM fundamental for the detailed characterization of identified synaptic contacts in neurons in a high-throughput manner. PMID:26052271

Effect of task demands on dual coding of pictorial stimuli.

PubMed

Babbitt, B C

1982-01-01

Recent studies have suggested that verbal labeling of a picture does not occur automatically. Although several experiments using paired-associate tasks produced little evidence indicating the use of a verbal code with picture stimuli, the tasks were probably not sensitive to whether the codes were activated initially. It is possible that verbal labels were activated at input, but not used later in performing the tasks. The present experiment used a color-naming interference task in order to assess, with a more sensitive measure, the amount of verbal coding occurring in response to word or picture input. Subjects named the color of ink in which words were printed following either word or picture input. If verbal labeling of the input occurs, then latency of color naming should increase when the input item and color-naming word are related. The results provided substantial evidence of such verbal activation when the input items were words. However, the presence of verbal activation with picture input was a function of task demands. Activation occurred when a recall memory test was used, but not when a recognition memory test was used. The results support the conclusion that name information (labels) need not be activated during presentation of visual stimuli.

Emotion Recognition of Weblog Sentences Based on an Ensemble Algorithm of Multi-label Classification and Word Emotions

NASA Astrophysics Data System (ADS)

Li, Ji; Ren, Fuji

Weblogs have greatly changed the communication ways of mankind. Affective analysis of blog posts is found valuable for many applications such as text-to-speech synthesis or computer-assisted recommendation. Traditional emotion recognition in text based on single-label classification can not satisfy higher requirements of affective computing. In this paper, the automatic identification of sentence emotion in weblogs is modeled as a multi-label text categorization task. Experiments are carried out on 12273 blog sentences from the Chinese emotion corpus Ren_CECps with 8-dimension emotion annotation. An ensemble algorithm RAKEL is used to recognize dominant emotions from the writer's perspective. Our emotion feature using detailed intensity representation for word emotions outperforms the other main features such as the word frequency feature and the traditional lexicon-based feature. In order to deal with relatively complex sentences, we integrate grammatical characteristics of punctuations, disjunctive connectives, modification relations and negation into features. It achieves 13.51% and 12.49% increases for Micro-averaged F1 and Macro-averaged F1 respectively compared to the traditional lexicon-based feature. Result shows that multiple-dimension emotion representation with grammatical features can efficiently classify sentence emotion in a multi-label problem.

Implicit associations and compensatory health beliefs in smokers: exploring their role for behaviour and their change through warning labels.

PubMed

Glock, Sabine; Müller, Barbara C N; Krolak-Schwerdt, Sabine

2013-11-01

Smokers might think that the negative effects of smoking can be compensated for by other behaviours, such as doing exercise or eating healthily. This phenomenon is known as compensatory health beliefs (CHBs). Graphic warning labels on cigarette packets emphasize the negative effects of smoking, which may impact CHBs. Research so far has assessed CHBs explicitly only via questionnaires, although implicit cognition might be an important factor in continuing to smoke. This study investigated the impact of graphic warning labels on CHBs, by testing CHBs both implicitly and explicitly. The study had a three-group experimental design. ANOVAs and multiple regression analyses were run on the results. We assessed explicit CHBs among non-smokers, smokers, and smokers confronted with graphic warning labels (N = 107; 47 females, 23.89 years old, 78 daily smokers). Implicit associations between smoking and CHB-specific behaviours (e.g., eating healthy food) were measured using a Single-Target Implicit Association Test. After the experiment, participants were able to choose between a healthy and unhealthy food reward. Non-smokers and smokers differed in explicit CHBs but not in implicit cognitions. Warning labels influenced implicit associations among smokers but did not affect explicit CHBs. Most interestingly, implicit associations and explicit CHBs predicted food choice and smoking among smokers not confronted with warning labels. Graphic warning labels could be used in interventions to inhibit automatic associations between smoking and healthy behaviours. Unlearning implicit cognitions might in turn affect explicit CHBs, thus decreasing their role in reducing the negative feelings caused by smoking. © 2013 The British Psychological Society.

PCR-Free Detection of Genetically Modified Organisms Using Magnetic Capture Technology and Fluorescence Cross-Correlation Spectroscopy

PubMed Central

Zhou, Xiaoming; Xing, Da; Tang, Yonghong; Chen, Wei R.

2009-01-01

The safety of genetically modified organisms (GMOs) has attracted much attention recently. Polymerase chain reaction (PCR) amplification is a common method used in the identification of GMOs. However, a major disadvantage of PCR is the potential amplification of non-target DNA, causing false-positive identification. Thus, there remains a need for a simple, reliable and ultrasensitive method to identify and quantify GMO in crops. This report is to introduce a magnetic bead-based PCR-free method for rapid detection of GMOs using dual-color fluorescence cross-correlation spectroscopy (FCCS). The cauliflower mosaic virus 35S (CaMV35S) promoter commonly used in transgenic products was targeted. CaMV35S target was captured by a biotin-labeled nucleic acid probe and then purified using streptavidin-coated magnetic beads through biotin-streptavidin linkage. The purified target DNA fragment was hybridized with two nucleic acid probes labeled respectively by Rhodamine Green and Cy5 dyes. Finally, FCCS was used to detect and quantify the target DNA fragment through simultaneously detecting the fluorescence emissions from the two dyes. In our study, GMOs in genetically engineered soybeans and tomatoes were detected, using the magnetic bead-based PCR-free FCCS method. A detection limit of 50 pM GMOs target was achieved and PCR-free detection of GMOs from 5 µg genomic DNA with magnetic capture technology was accomplished. Also, the accuracy of GMO determination by the FCCS method is verified by spectrophotometry at 260 nm using PCR amplified target DNA fragment from GM tomato. The new method is rapid and effective as demonstrated in our experiments and can be easily extended to high-throughput and automatic screening format. We believe that the new magnetic bead-assisted FCCS detection technique will be a useful tool for PCR-free GMOs identification and other specific nucleic acids. PMID:19956680

Automatic Query Formulations in Information Retrieval.

ERIC Educational Resources Information Center

Salton, G.; And Others

1983-01-01

Introduces methods designed to reduce role of search intermediaries by generating Boolean search formulations automatically using term frequency considerations from natural language statements provided by system patrons. Experimental results are supplied and methods are described for applying automatic query formulation process in practice.…

Automatic detection of anatomical regions in frontal x-ray images: comparing convolutional neural networks to random forest

NASA Astrophysics Data System (ADS)

Olory Agomma, R.; Vázquez, C.; Cresson, T.; De Guise, J.

2018-02-01

Most algorithms to detect and identify anatomical structures in medical images require either to be initialized close to the target structure, or to know that the structure is present in the image, or to be trained on a homogeneous database (e.g. all full body or all lower limbs). Detecting these structures when there is no guarantee that the structure is present in the image, or when the image database is heterogeneous (mixed configurations), is a challenge for automatic algorithms. In this work we compared two state-of-the-art machine learning techniques in order to determine which one is the most appropriate for predicting targets locations based on image patches. By knowing the position of thirteen landmarks points, labelled by an expert in EOS frontal radiography, we learn the displacement between salient points detected in the image and these thirteen landmarks. The learning step is carried out with a machine learning approach by exploring two methods: Convolutional Neural Network (CNN) and Random Forest (RF). The automatic detection of the thirteen landmarks points in a new image is then obtained by averaging the positions of each one of these thirteen landmarks estimated from all the salient points in the new image. We respectively obtain for CNN and RF, an average prediction error (both mean and standard deviation in mm) of 29 +/-18 and 30 +/- 21 for the thirteen landmarks points, indicating the approximate location of anatomical regions. On the other hand, the learning time is 9 days for CNN versus 80 minutes for RF. We provide a comparison of the results between the two machine learning approaches.

The Potential of Automatic Word Comparison for Historical Linguistics.

PubMed

List, Johann-Mattis; Greenhill, Simon J; Gray, Russell D

2017-01-01

The amount of data from languages spoken all over the world is rapidly increasing. Traditional manual methods in historical linguistics need to face the challenges brought by this influx of data. Automatic approaches to word comparison could provide invaluable help to pre-analyze data which can be later enhanced by experts. In this way, computational approaches can take care of the repetitive and schematic tasks leaving experts to concentrate on answering interesting questions. Here we test the potential of automatic methods to detect etymologically related words (cognates) in cross-linguistic data. Using a newly compiled database of expert cognate judgments across five different language families, we compare how well different automatic approaches distinguish related from unrelated words. Our results show that automatic methods can identify cognates with a very high degree of accuracy, reaching 89% for the best-performing method Infomap. We identify the specific strengths and weaknesses of these different methods and point to major challenges for future approaches. Current automatic approaches for cognate detection-although not perfect-could become an important component of future research in historical linguistics.

The Potential of Automatic Word Comparison for Historical Linguistics

PubMed Central

Greenhill, Simon J.; Gray, Russell D.

2017-01-01

The amount of data from languages spoken all over the world is rapidly increasing. Traditional manual methods in historical linguistics need to face the challenges brought by this influx of data. Automatic approaches to word comparison could provide invaluable help to pre-analyze data which can be later enhanced by experts. In this way, computational approaches can take care of the repetitive and schematic tasks leaving experts to concentrate on answering interesting questions. Here we test the potential of automatic methods to detect etymologically related words (cognates) in cross-linguistic data. Using a newly compiled database of expert cognate judgments across five different language families, we compare how well different automatic approaches distinguish related from unrelated words. Our results show that automatic methods can identify cognates with a very high degree of accuracy, reaching 89% for the best-performing method Infomap. We identify the specific strengths and weaknesses of these different methods and point to major challenges for future approaches. Current automatic approaches for cognate detection—although not perfect—could become an important component of future research in historical linguistics. PMID:28129337