A light and faster regional convolutional neural network for object detection in optical remote sensing images

NASA Astrophysics Data System (ADS)

Ding, Peng; Zhang, Ye; Deng, Wei-Jian; Jia, Ping; Kuijper, Arjan

2018-07-01

Detection of objects from satellite optical remote sensing images is very important for many commercial and governmental applications. With the development of deep convolutional neural networks (deep CNNs), the field of object detection has seen tremendous advances. Currently, objects in satellite remote sensing images can be detected using deep CNNs. In general, optical remote sensing images contain many dense and small objects, and the use of the original Faster Regional CNN framework does not yield a suitably high precision. Therefore, after careful analysis we adopt dense convoluted networks, a multi-scale representation and various combinations of improvement schemes to enhance the structure of the base VGG16-Net for improving the precision. We propose an approach to reduce the test-time (detection time) and memory requirements. To validate the effectiveness of our approach, we perform experiments using satellite remote sensing image datasets of aircraft and automobiles. The results show that the improved network structure can detect objects in satellite optical remote sensing images more accurately and efficiently.

Alcoholism Detection by Data Augmentation and Convolutional Neural Network with Stochastic Pooling.

PubMed

Wang, Shui-Hua; Lv, Yi-Ding; Sui, Yuxiu; Liu, Shuai; Wang, Su-Jing; Zhang, Yu-Dong

2017-11-17

Alcohol use disorder (AUD) is an important brain disease. It alters the brain structure. Recently, scholars tend to use computer vision based techniques to detect AUD. We collected 235 subjects, 114 alcoholic and 121 non-alcoholic. Among the 235 image, 100 images were used as training set, and data augmentation method was used. The rest 135 images were used as test set. Further, we chose the latest powerful technique-convolutional neural network (CNN) based on convolutional layer, rectified linear unit layer, pooling layer, fully connected layer, and softmax layer. We also compared three different pooling techniques: max pooling, average pooling, and stochastic pooling. The results showed that our method achieved a sensitivity of 96.88%, a specificity of 97.18%, and an accuracy of 97.04%. Our method was better than three state-of-the-art approaches. Besides, stochastic pooling performed better than other max pooling and average pooling. We validated CNN with five convolution layers and two fully connected layers performed the best. The GPU yielded a 149× acceleration in training and a 166× acceleration in test, compared to CPU.

Fully automatic detection and segmentation of abdominal aortic thrombus in post-operative CTA images using Deep Convolutional Neural Networks.

PubMed

López-Linares, Karen; Aranjuelo, Nerea; Kabongo, Luis; Maclair, Gregory; Lete, Nerea; Ceresa, Mario; García-Familiar, Ainhoa; Macía, Iván; González Ballester, Miguel A

2018-05-01

Computerized Tomography Angiography (CTA) based follow-up of Abdominal Aortic Aneurysms (AAA) treated with Endovascular Aneurysm Repair (EVAR) is essential to evaluate the progress of the patient and detect complications. In this context, accurate quantification of post-operative thrombus volume is required. However, a proper evaluation is hindered by the lack of automatic, robust and reproducible thrombus segmentation algorithms. We propose a new fully automatic approach based on Deep Convolutional Neural Networks (DCNN) for robust and reproducible thrombus region of interest detection and subsequent fine thrombus segmentation. The DetecNet detection network is adapted to perform region of interest extraction from a complete CTA and a new segmentation network architecture, based on Fully Convolutional Networks and a Holistically-Nested Edge Detection Network, is presented. These networks are trained, validated and tested in 13 post-operative CTA volumes of different patients using a 4-fold cross-validation approach to provide more robustness to the results. Our pipeline achieves a Dice score of more than 82% for post-operative thrombus segmentation and provides a mean relative volume difference between ground truth and automatic segmentation that lays within the experienced human observer variance without the need of human intervention in most common cases. Copyright © 2018 Elsevier B.V. All rights reserved.

Estimating Isometric Tension of Finger Muscle Using Needle EMG Signals and the Twitch Contraction Model

NASA Astrophysics Data System (ADS)

Tachibana, Hideyuki; Suzuki, Takafumi; Mabuchi, Kunihiko

We address an estimation method of isometric muscle tension of fingers, as fundamental research for a neural signal-based prosthesis of fingers. We utilize needle electromyogram (EMG) signals, which have approximately equivalent information to peripheral neural signals. The estimating algorithm comprised two convolution operations. The first convolution is between normal distribution and a spike array, which is detected by needle EMG signals. The convolution estimates the probability density of spike-invoking time in the muscle. In this convolution, we hypothesize that each motor unit in a muscle activates spikes independently based on a same probability density function. The second convolution is between the result of the previous convolution and isometric twitch, viz., the impulse response of the motor unit. The result of the calculation is the sum of all estimated tensions of whole muscle fibers, i.e., muscle tension. We confirmed that there is good correlation between the estimated tension of the muscle and the actual tension, with >0.9 correlation coefficients at 59%, and >0.8 at 89% of all trials.

Convolutional neural network features based change detection in satellite images

NASA Astrophysics Data System (ADS)

Mohammed El Amin, Arabi; Liu, Qingjie; Wang, Yunhong

2016-07-01

With the popular use of high resolution remote sensing (HRRS) satellite images, a huge research efforts have been placed on change detection (CD) problem. An effective feature selection method can significantly boost the final result. While hand-designed features have proven difficulties to design features that effectively capture high and mid-level representations, the recent developments in machine learning (Deep Learning) omit this problem by learning hierarchical representation in an unsupervised manner directly from data without human intervention. In this letter, we propose approaching the change detection problem from a feature learning perspective. A novel deep Convolutional Neural Networks (CNN) features based HR satellite images change detection method is proposed. The main guideline is to produce a change detection map directly from two images using a pretrained CNN. This method can omit the limited performance of hand-crafted features. Firstly, CNN features are extracted through different convolutional layers. Then, a concatenation step is evaluated after an normalization step, resulting in a unique higher dimensional feature map. Finally, a change map was computed using pixel-wise Euclidean distance. Our method has been validated on real bitemporal HRRS satellite images according to qualitative and quantitative analyses. The results obtained confirm the interest of the proposed method.

ID card number detection algorithm based on convolutional neural network

NASA Astrophysics Data System (ADS)

Zhu, Jian; Ma, Hanjie; Feng, Jie; Dai, Leiyan

2018-04-01

In this paper, a new detection algorithm based on Convolutional Neural Network is presented in order to realize the fast and convenient ID information extraction in multiple scenarios. The algorithm uses the mobile device equipped with Android operating system to locate and extract the ID number; Use the special color distribution of the ID card, select the appropriate channel component; Use the image threshold segmentation, noise processing and morphological processing to take the binary processing for image; At the same time, the image rotation and projection method are used for horizontal correction when image was tilting; Finally, the single character is extracted by the projection method, and recognized by using Convolutional Neural Network. Through test shows that, A single ID number image from the extraction to the identification time is about 80ms, the accuracy rate is about 99%, It can be applied to the actual production and living environment.

Deep feature representation with stacked sparse auto-encoder and convolutional neural network for hyperspectral imaging-based detection of cucumber defects

USDA-ARS?s Scientific Manuscript database

It is challenging to achieve rapid and accurate processing of large amounts of hyperspectral image data. This research was aimed to develop a novel classification method by employing deep feature representation with the stacked sparse auto-encoder (SSAE) and the SSAE combined with convolutional neur...

Ship detection in optical remote sensing images based on deep convolutional neural networks

NASA Astrophysics Data System (ADS)

Yao, Yuan; Jiang, Zhiguo; Zhang, Haopeng; Zhao, Danpei; Cai, Bowen

2017-10-01

Automatic ship detection in optical remote sensing images has attracted wide attention for its broad applications. Major challenges for this task include the interference of cloud, wave, wake, and the high computational expenses. We propose a fast and robust ship detection algorithm to solve these issues. The framework for ship detection is designed based on deep convolutional neural networks (CNNs), which provide the accurate locations of ship targets in an efficient way. First, the deep CNN is designed to extract features. Then, a region proposal network (RPN) is applied to discriminate ship targets and regress the detection bounding boxes, in which the anchors are designed by intrinsic shape of ship targets. Experimental results on numerous panchromatic images demonstrate that, in comparison with other state-of-the-art ship detection methods, our method is more efficient and achieves higher detection accuracy and more precise bounding boxes in different complex backgrounds.

Convolutional Neural Network-Based Shadow Detection in Images Using Visible Light Camera Sensor.

PubMed

Kim, Dong Seop; Arsalan, Muhammad; Park, Kang Ryoung

2018-03-23

Recent developments in intelligence surveillance camera systems have enabled more research on the detection, tracking, and recognition of humans. Such systems typically use visible light cameras and images, in which shadows make it difficult to detect and recognize the exact human area. Near-infrared (NIR) light cameras and thermal cameras are used to mitigate this problem. However, such instruments require a separate NIR illuminator, or are prohibitively expensive. Existing research on shadow detection in images captured by visible light cameras have utilized object and shadow color features for detection. Unfortunately, various environmental factors such as illumination change and brightness of background cause detection to be a difficult task. To overcome this problem, we propose a convolutional neural network-based shadow detection method. Experimental results with a database built from various outdoor surveillance camera environments, and from the context-aware vision using image-based active recognition (CAVIAR) open database, show that our method outperforms previous works.

Convolutional Neural Network-Based Shadow Detection in Images Using Visible Light Camera Sensor

PubMed Central

Kim, Dong Seop; Arsalan, Muhammad; Park, Kang Ryoung

2018-01-01

Recent developments in intelligence surveillance camera systems have enabled more research on the detection, tracking, and recognition of humans. Such systems typically use visible light cameras and images, in which shadows make it difficult to detect and recognize the exact human area. Near-infrared (NIR) light cameras and thermal cameras are used to mitigate this problem. However, such instruments require a separate NIR illuminator, or are prohibitively expensive. Existing research on shadow detection in images captured by visible light cameras have utilized object and shadow color features for detection. Unfortunately, various environmental factors such as illumination change and brightness of background cause detection to be a difficult task. To overcome this problem, we propose a convolutional neural network-based shadow detection method. Experimental results with a database built from various outdoor surveillance camera environments, and from the context-aware vision using image-based active recognition (CAVIAR) open database, show that our method outperforms previous works. PMID:29570690

CONEDEP: COnvolutional Neural network based Earthquake DEtection and Phase Picking

NASA Astrophysics Data System (ADS)

Zhou, Y.; Huang, Y.; Yue, H.; Zhou, S.; An, S.; Yun, N.

2017-12-01

We developed an automatic local earthquake detection and phase picking algorithm based on Fully Convolutional Neural network (FCN). The FCN algorithm detects and segments certain features (phases) in 3 component seismograms to realize efficient picking. We use STA/LTA algorithm and template matching algorithm to construct the training set from seismograms recorded 1 month before and after the Wenchuan earthquake. Precise P and S phases are identified and labeled to construct the training set. Noise data are produced by combining back-ground noise and artificial synthetic noise to form the equivalent scale of noise set as the signal set. Training is performed on GPUs to achieve efficient convergence. Our algorithm has significantly improved performance in terms of the detection rate and precision in comparison with STA/LTA and template matching algorithms.

IRIS family of IRCCD thermal imagers integrating long-life cryogenic coolers, sophisticated algorithms for image enhancement, and hot points detection

NASA Astrophysics Data System (ADS)

Dupuy, Pascal; Harter, Jean

1995-09-01

Iris is a modular infrared thermal image developed by SAGEM since 1988, based on a 288 by 4 IRCCD detector. The first section of the presentation gives a description of the different modules of the IRIS thermal imager and their evolution in recent years. The second section covers the description of the major evolution, namely the integrated detector cooler assembly (IDCA), using a SOFRADIR 288 by 4 detector and a SAGEM microcooler, now integrated in the IRIS thermal imagers. The third section gives the description of two functions integrated in the IRIS thermal imager: (1) image enhancement, using a digital convolution filter, and (2) automatic hot points detection and tracking, offering an assistance to surveillance and automatic detection. The last section presents several programs for navy, air forces, and land applications for which IRIS has already been selected and achieved.

Salient regions detection using convolutional neural networks and color volume

NASA Astrophysics Data System (ADS)

Liu, Guang-Hai; Hou, Yingkun

2018-03-01

Convolutional neural network is an important technique in machine learning, pattern recognition and image processing. In order to reduce the computational burden and extend the classical LeNet-5 model to the field of saliency detection, we propose a simple and novel computing model based on LeNet-5 network. In the proposed model, hue, saturation and intensity are utilized to extract depth cues, and then we integrate depth cues and color volume to saliency detection following the basic structure of the feature integration theory. Experimental results show that the proposed computing model outperforms some existing state-of-the-art methods on MSRA1000 and ECSSD datasets.

Development and application of deep convolutional neural network in target detection

NASA Astrophysics Data System (ADS)

Jiang, Xiaowei; Wang, Chunping; Fu, Qiang

2018-04-01

With the development of big data and algorithms, deep convolution neural networks with more hidden layers have more powerful feature learning and feature expression ability than traditional machine learning methods, making artificial intelligence surpass human level in many fields. This paper first reviews the development and application of deep convolutional neural networks in the field of object detection in recent years, then briefly summarizes and ponders some existing problems in the current research, and the future development of deep convolutional neural network is prospected.

Accelerated Time-Domain Modeling of Electromagnetic Pulse Excitation of Finite-Length Dissipative Conductors over a Ground Plane via Function Fitting and Recursive Convolution

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

Campione, Salvatore; Warne, Larry K.; Sainath, Kamalesh

In this report we overview the fundamental concepts for a pair of techniques which together greatly hasten computational predictions of electromagnetic pulse (EMP) excitation of finite-length dissipative conductors over a ground plane. In a time- domain, transmission line (TL) model implementation, predictions are computationally bottlenecked time-wise, either for late-time predictions (about 100ns-10000ns range) or predictions concerning EMP excitation of long TLs (order of kilometers or more ). This is because the method requires a temporal convolution to account for the losses in the ground. Addressing this to facilitate practical simulation of EMP excitation of TLs, we first apply a techniquemore » to extract an (approximate) complex exponential function basis-fit to the ground/Earth's impedance function, followed by incorporating this into a recursion-based convolution acceleration technique. Because the recursion-based method only requires the evaluation of the most recent voltage history data (versus the entire history in a "brute-force" convolution evaluation), we achieve necessary time speed- ups across a variety of TL/Earth geometry/material scenarios. Intentionally Left Blank« less

Accurate segmentation of lung fields on chest radiographs using deep convolutional networks

NASA Astrophysics Data System (ADS)

Arbabshirani, Mohammad R.; Dallal, Ahmed H.; Agarwal, Chirag; Patel, Aalpan; Moore, Gregory

2017-02-01

Accurate segmentation of lung fields on chest radiographs is the primary step for computer-aided detection of various conditions such as lung cancer and tuberculosis. The size, shape and texture of lung fields are key parameters for chest X-ray (CXR) based lung disease diagnosis in which the lung field segmentation is a significant primary step. Although many methods have been proposed for this problem, lung field segmentation remains as a challenge. In recent years, deep learning has shown state of the art performance in many visual tasks such as object detection, image classification and semantic image segmentation. In this study, we propose a deep convolutional neural network (CNN) framework for segmentation of lung fields. The algorithm was developed and tested on 167 clinical posterior-anterior (PA) CXR images collected retrospectively from picture archiving and communication system (PACS) of Geisinger Health System. The proposed multi-scale network is composed of five convolutional and two fully connected layers. The framework achieved IOU (intersection over union) of 0.96 on the testing dataset as compared to manual segmentation. The suggested framework outperforms state of the art registration-based segmentation by a significant margin. To our knowledge, this is the first deep learning based study of lung field segmentation on CXR images developed on a heterogeneous clinical dataset. The results suggest that convolutional neural networks could be employed reliably for lung field segmentation.

Automated detection of geological landforms on Mars using Convolutional Neural Networks

NASA Astrophysics Data System (ADS)

Palafox, Leon F.; Hamilton, Christopher W.; Scheidt, Stephen P.; Alvarez, Alexander M.

2017-04-01

The large volume of high-resolution images acquired by the Mars Reconnaissance Orbiter has opened a new frontier for developing automated approaches to detecting landforms on the surface of Mars. However, most landform classifiers focus on crater detection, which represents only one of many geological landforms of scientific interest. In this work, we use Convolutional Neural Networks (ConvNets) to detect both volcanic rootless cones and transverse aeolian ridges. Our system, named MarsNet, consists of five networks, each of which is trained to detect landforms of different sizes. We compare our detection algorithm with a widely used method for image recognition, Support Vector Machines (SVMs) using Histogram of Oriented Gradients (HOG) features. We show that ConvNets can detect a wide range of landforms and has better accuracy and recall in testing data than traditional classifiers based on SVMs.

Automated detection of geological landforms on Mars using Convolutional Neural Networks.

PubMed

Palafox, Leon F; Hamilton, Christopher W; Scheidt, Stephen P; Alvarez, Alexander M

2017-04-01

The large volume of high-resolution images acquired by the Mars Reconnaissance Orbiter has opened a new frontier for developing automated approaches to detecting landforms on the surface of Mars. However, most landform classifiers focus on crater detection, which represents only one of many geological landforms of scientific interest. In this work, we use Convolutional Neural Networks (ConvNets) to detect both volcanic rootless cones and transverse aeolian ridges. Our system, named MarsNet, consists of five networks, each of which is trained to detect landforms of different sizes. We compare our detection algorithm with a widely used method for image recognition, Support Vector Machines (SVMs) using Histogram of Oriented Gradients (HOG) features. We show that ConvNets can detect a wide range of landforms and has better accuracy and recall in testing data than traditional classifiers based on SVMs.

Subject independent facial expression recognition with robust face detection using a convolutional neural network.

PubMed

Matsugu, Masakazu; Mori, Katsuhiko; Mitari, Yusuke; Kaneda, Yuji

2003-01-01

Reliable detection of ordinary facial expressions (e.g. smile) despite the variability among individuals as well as face appearance is an important step toward the realization of perceptual user interface with autonomous perception of persons. We describe a rule-based algorithm for robust facial expression recognition combined with robust face detection using a convolutional neural network. In this study, we address the problem of subject independence as well as translation, rotation, and scale invariance in the recognition of facial expression. The result shows reliable detection of smiles with recognition rate of 97.6% for 5600 still images of more than 10 subjects. The proposed algorithm demonstrated the ability to discriminate smiling from talking based on the saliency score obtained from voting visual cues. To the best of our knowledge, it is the first facial expression recognition model with the property of subject independence combined with robustness to variability in facial appearance.

Coding/modulation trade-offs for Shuttle wideband data links

NASA Technical Reports Server (NTRS)

Batson, B. H.; Huth, G. K.; Trumpis, B. D.

1974-01-01

This paper describes various modulation and coding schemes which are potentially applicable to the Shuttle wideband data relay communications link. This link will be capable of accommodating up to 50 Mbps of scientific data and will be subject to a power constraint which forces the use of channel coding. Although convolutionally encoded coherent binary PSK is the tentative signal design choice for the wideband data relay link, FM techniques are of interest because of the associated hardware simplicity and because an FM system is already planned to be available for transmission of television via relay satellite to the ground. Binary and M-ary FSK are considered as candidate modulation techniques, and both coherent and noncoherent ground station detection schemes are examined. The potential use of convolutional coding is considered in conjunction with each of the candidate modulation techniques.

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).

A convolutional neural network-based screening tool for X-ray serial crystallography

PubMed Central

Ke, Tsung-Wei; Brewster, Aaron S.; Yu, Stella X.; Ushizima, Daniela; Yang, Chao; Sauter, Nicholas K.

2018-01-01

A new tool is introduced for screening macromolecular X-ray crystallography diffraction images produced at an X-ray free-electron laser light source. Based on a data-driven deep learning approach, the proposed tool executes a convolutional neural network to detect Bragg spots. Automatic image processing algorithms described can enable the classification of large data sets, acquired under realistic conditions consisting of noisy data with experimental artifacts. Outcomes are compared for different data regimes, including samples from multiple instruments and differing amounts of training data for neural network optimization. PMID:29714177

A convolutional neural network-based screening tool for X-ray serial crystallography.

PubMed

Ke, Tsung Wei; Brewster, Aaron S; Yu, Stella X; Ushizima, Daniela; Yang, Chao; Sauter, Nicholas K

2018-05-01

A new tool is introduced for screening macromolecular X-ray crystallography diffraction images produced at an X-ray free-electron laser light source. Based on a data-driven deep learning approach, the proposed tool executes a convolutional neural network to detect Bragg spots. Automatic image processing algorithms described can enable the classification of large data sets, acquired under realistic conditions consisting of noisy data with experimental artifacts. Outcomes are compared for different data regimes, including samples from multiple instruments and differing amounts of training data for neural network optimization. open access.

A convolutional neural network-based screening tool for X-ray serial crystallography

DOE PAGES

Ke, Tsung-Wei; Brewster, Aaron S.; Yu, Stella X.; ...

2018-04-24

A new tool is introduced for screening macromolecular X-ray crystallography diffraction images produced at an X-ray free-electron laser light source. Based on a data-driven deep learning approach, the proposed tool executes a convolutional neural network to detect Bragg spots. Automatic image processing algorithms described can enable the classification of large data sets, acquired under realistic conditions consisting of noisy data with experimental artifacts. Outcomes are compared for different data regimes, including samples from multiple instruments and differing amounts of training data for neural network optimization.

A convolutional neural network-based screening tool for X-ray serial crystallography

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

Ke, Tsung-Wei; Brewster, Aaron S.; Yu, Stella X.

A new tool is introduced for screening macromolecular X-ray crystallography diffraction images produced at an X-ray free-electron laser light source. Based on a data-driven deep learning approach, the proposed tool executes a convolutional neural network to detect Bragg spots. Automatic image processing algorithms described can enable the classification of large data sets, acquired under realistic conditions consisting of noisy data with experimental artifacts. Outcomes are compared for different data regimes, including samples from multiple instruments and differing amounts of training data for neural network optimization.

Signal Detection and Frame Synchronization of Multiple Wireless Networking Waveforms

DTIC Science & Technology

2007-09-01

punctured to obtain coding rates of 2 3 and 3 4 . Convolutional forward error correction coding is used to detect and correct bit...likely to be isolated and be correctable by the convolutional decoder. 44 Data rate (Mbps) Modulation Coding Rate Coded bits per subcarrier...binary convolutional code . A shortened Reed-Solomon technique is employed first. The code is shortened depending upon the data

Defect detection and classification of galvanized stamping parts based on fully convolution neural network

NASA Astrophysics Data System (ADS)

Xiao, Zhitao; Leng, Yanyi; Geng, Lei; Xi, Jiangtao

2018-04-01

In this paper, a new convolution neural network method is proposed for the inspection and classification of galvanized stamping parts. Firstly, all workpieces are divided into normal and defective by image processing, and then the defective workpieces extracted from the region of interest (ROI) area are input to the trained fully convolutional networks (FCN). The network utilizes an end-to-end and pixel-to-pixel training convolution network that is currently the most advanced technology in semantic segmentation, predicts result of each pixel. Secondly, we mark the different pixel values of the workpiece, defect and background for the training image, and use the pixel value and the number of pixels to realize the recognition of the defects of the output picture. Finally, the defect area's threshold depended on the needs of the project is set to achieve the specific classification of the workpiece. The experiment results show that the proposed method can successfully achieve defect detection and classification of galvanized stamping parts under ordinary camera and illumination conditions, and its accuracy can reach 99.6%. Moreover, it overcomes the problem of complex image preprocessing and difficult feature extraction and performs better adaptability.

Tweaked residual convolutional network for face alignment

NASA Astrophysics Data System (ADS)

Du, Wenchao; Li, Ke; Zhao, Qijun; Zhang, Yi; Chen, Hu

2017-08-01

We propose a novel Tweaked Residual Convolutional Network approach for face alignment with two-level convolutional networks architecture. Specifically, the first-level Tweaked Convolutional Network (TCN) module predicts the landmark quickly but accurately enough as a preliminary, by taking low-resolution version of the detected face holistically as the input. The following Residual Convolutional Networks (RCN) module progressively refines the landmark by taking as input the local patch extracted around the predicted landmark, particularly, which allows the Convolutional Neural Network (CNN) to extract local shape-indexed features to fine tune landmark position. Extensive evaluations show that the proposed Tweaked Residual Convolutional Network approach outperforms existing methods.

Airplane detection in remote sensing images using convolutional neural networks

NASA Astrophysics Data System (ADS)

Ouyang, Chao; Chen, Zhong; Zhang, Feng; Zhang, Yifei

2018-03-01

Airplane detection in remote sensing images remains a challenging problem and has also been taking a great interest to researchers. In this paper we propose an effective method to detect airplanes in remote sensing images using convolutional neural networks. Deep learning methods show greater advantages than the traditional methods with the rise of deep neural networks in target detection, and we give an explanation why this happens. To improve the performance on detection of airplane, we combine a region proposal algorithm with convolutional neural networks. And in the training phase, we divide the background into multi classes rather than one class, which can reduce false alarms. Our experimental results show that the proposed method is effective and robust in detecting airplane.

Using YOLO based deep learning network for real time detection and localization of lung nodules from low dose CT scans

NASA Astrophysics Data System (ADS)

Ramachandran S., Sindhu; George, Jose; Skaria, Shibon; V. V., Varun

2018-02-01

Lung cancer is the leading cause of cancer related deaths in the world. The survival rate can be improved if the presence of lung nodules are detected early. This has also led to more focus being given to computer aided detection (CAD) and diagnosis of lung nodules. The arbitrariness of shape, size and texture of lung nodules is a challenge to be faced when developing these detection systems. In the proposed work we use convolutional neural networks to learn the features for nodule detection, replacing the traditional method of handcrafting features like geometric shape or texture. Our network uses the DetectNet architecture based on YOLO (You Only Look Once) to detect the nodules in CT scans of lung. In this architecture, object detection is treated as a regression problem with a single convolutional network simultaneously predicting multiple bounding boxes and class probabilities for those boxes. By performing training using chest CT scans from Lung Image Database Consortium (LIDC), NVIDIA DIGITS and Caffe deep learning framework, we show that nodule detection using this single neural network can result in reasonably low false positive rates with high sensitivity and precision.

Real-time vibration-based structural damage detection using one-dimensional convolutional neural networks

NASA Astrophysics Data System (ADS)

Abdeljaber, Osama; Avci, Onur; Kiranyaz, Serkan; Gabbouj, Moncef; Inman, Daniel J.

2017-02-01

Structural health monitoring (SHM) and vibration-based structural damage detection have been a continuous interest for civil, mechanical and aerospace engineers over the decades. Early and meticulous damage detection has always been one of the principal objectives of SHM applications. The performance of a classical damage detection system predominantly depends on the choice of the features and the classifier. While the fixed and hand-crafted features may either be a sub-optimal choice for a particular structure or fail to achieve the same level of performance on another structure, they usually require a large computation power which may hinder their usage for real-time structural damage detection. This paper presents a novel, fast and accurate structural damage detection system using 1D Convolutional Neural Networks (CNNs) that has an inherent adaptive design to fuse both feature extraction and classification blocks into a single and compact learning body. The proposed method performs vibration-based damage detection and localization of the damage in real-time. The advantage of this approach is its ability to extract optimal damage-sensitive features automatically from the raw acceleration signals. Large-scale experiments conducted on a grandstand simulator revealed an outstanding performance and verified the computational efficiency of the proposed real-time damage detection method.

Multi-class geospatial object detection based on a position-sensitive balancing framework for high spatial resolution remote sensing imagery

NASA Astrophysics Data System (ADS)

Zhong, Yanfei; Han, Xiaobing; Zhang, Liangpei

2018-04-01

Multi-class geospatial object detection from high spatial resolution (HSR) remote sensing imagery is attracting increasing attention in a wide range of object-related civil and engineering applications. However, the distribution of objects in HSR remote sensing imagery is location-variable and complicated, and how to accurately detect the objects in HSR remote sensing imagery is a critical problem. Due to the powerful feature extraction and representation capability of deep learning, the deep learning based region proposal generation and object detection integrated framework has greatly promoted the performance of multi-class geospatial object detection for HSR remote sensing imagery. However, due to the translation caused by the convolution operation in the convolutional neural network (CNN), although the performance of the classification stage is seldom influenced, the localization accuracies of the predicted bounding boxes in the detection stage are easily influenced. The dilemma between translation-invariance in the classification stage and translation-variance in the object detection stage has not been addressed for HSR remote sensing imagery, and causes position accuracy problems for multi-class geospatial object detection with region proposal generation and object detection. In order to further improve the performance of the region proposal generation and object detection integrated framework for HSR remote sensing imagery object detection, a position-sensitive balancing (PSB) framework is proposed in this paper for multi-class geospatial object detection from HSR remote sensing imagery. The proposed PSB framework takes full advantage of the fully convolutional network (FCN), on the basis of a residual network, and adopts the PSB framework to solve the dilemma between translation-invariance in the classification stage and translation-variance in the object detection stage. In addition, a pre-training mechanism is utilized to accelerate the training procedure and increase the robustness of the proposed algorithm. The proposed algorithm is validated with a publicly available 10-class object detection dataset.

Vehicle Detection in Aerial Images Based on Region Convolutional Neural Networks and Hard Negative Example Mining.

PubMed

Tang, Tianyu; Zhou, Shilin; Deng, Zhipeng; Zou, Huanxin; Lei, Lin

2017-02-10

Detecting vehicles in aerial imagery plays an important role in a wide range of applications. The current vehicle detection methods are mostly based on sliding-window search and handcrafted or shallow-learning-based features, having limited description capability and heavy computational costs. Recently, due to the powerful feature representations, region convolutional neural networks (CNN) based detection methods have achieved state-of-the-art performance in computer vision, especially Faster R-CNN. However, directly using it for vehicle detection in aerial images has many limitations: (1) region proposal network (RPN) in Faster R-CNN has poor performance for accurately locating small-sized vehicles, due to the relatively coarse feature maps; and (2) the classifier after RPN cannot distinguish vehicles and complex backgrounds well. In this study, an improved detection method based on Faster R-CNN is proposed in order to accomplish the two challenges mentioned above. Firstly, to improve the recall, we employ a hyper region proposal network (HRPN) to extract vehicle-like targets with a combination of hierarchical feature maps. Then, we replace the classifier after RPN by a cascade of boosted classifiers to verify the candidate regions, aiming at reducing false detection by negative example mining. We evaluate our method on the Munich vehicle dataset and the collected vehicle dataset, with improvements in accuracy and robustness compared to existing methods.

Convolution neural networks for real-time needle detection and localization in 2D ultrasound.

PubMed

Mwikirize, Cosmas; Nosher, John L; Hacihaliloglu, Ilker

2018-05-01

We propose a framework for automatic and accurate detection of steeply inserted needles in 2D ultrasound data using convolution neural networks. We demonstrate its application in needle trajectory estimation and tip localization. Our approach consists of a unified network, comprising a fully convolutional network (FCN) and a fast region-based convolutional neural network (R-CNN). The FCN proposes candidate regions, which are then fed to a fast R-CNN for finer needle detection. We leverage a transfer learning paradigm, where the network weights are initialized by training with non-medical images, and fine-tuned with ex vivo ultrasound scans collected during insertion of a 17G epidural needle into freshly excised porcine and bovine tissue at depth settings up to 9 cm and [Formula: see text]-[Formula: see text] insertion angles. Needle detection results are used to accurately estimate needle trajectory from intensity invariant needle features and perform needle tip localization from an intensity search along the needle trajectory. Our needle detection model was trained and validated on 2500 ex vivo ultrasound scans. The detection system has a frame rate of 25 fps on a GPU and achieves 99.6% precision, 99.78% recall rate and an [Formula: see text] score of 0.99. Validation for needle localization was performed on 400 scans collected using a different imaging platform, over a bovine/porcine lumbosacral spine phantom. Shaft localization error of [Formula: see text], tip localization error of [Formula: see text] mm, and a total processing time of 0.58 s were achieved. The proposed method is fully automatic and provides robust needle localization results in challenging scanning conditions. The accurate and robust results coupled with real-time detection and sub-second total processing make the proposed method promising in applications for needle detection and localization during challenging minimally invasive ultrasound-guided procedures.

Potential fault region detection in TFDS images based on convolutional neural network

NASA Astrophysics Data System (ADS)

Sun, Junhua; Xiao, Zhongwen

2016-10-01

In recent years, more than 300 sets of Trouble of Running Freight Train Detection System (TFDS) have been installed on railway to monitor the safety of running freight trains in China. However, TFDS is simply responsible for capturing, transmitting, and storing images, and fails to recognize faults automatically due to some difficulties such as such as the diversity and complexity of faults and some low quality images. To improve the performance of automatic fault recognition, it is of great importance to locate the potential fault areas. In this paper, we first introduce a convolutional neural network (CNN) model to TFDS and propose a potential fault region detection system (PFRDS) for simultaneously detecting four typical types of potential fault regions (PFRs). The experimental results show that this system has a higher performance of image detection to PFRs in TFDS. An average detection recall of 98.95% and precision of 100% are obtained, demonstrating the high detection ability and robustness against various poor imaging situations.

Mass detection in digital breast tomosynthesis: Deep convolutional neural network with transfer learning from mammography.

PubMed

Samala, Ravi K; Chan, Heang-Ping; Hadjiiski, Lubomir; Helvie, Mark A; Wei, Jun; Cha, Kenny

2016-12-01

Develop a computer-aided detection (CAD) system for masses in digital breast tomosynthesis (DBT) volume using a deep convolutional neural network (DCNN) with transfer learning from mammograms. A data set containing 2282 digitized film and digital mammograms and 324 DBT volumes were collected with IRB approval. The mass of interest on the images was marked by an experienced breast radiologist as reference standard. The data set was partitioned into a training set (2282 mammograms with 2461 masses and 230 DBT views with 228 masses) and an independent test set (94 DBT views with 89 masses). For DCNN training, the region of interest (ROI) containing the mass (true positive) was extracted from each image. False positive (FP) ROIs were identified at prescreening by their previously developed CAD systems. After data augmentation, a total of 45 072 mammographic ROIs and 37 450 DBT ROIs were obtained. Data normalization and reduction of non-uniformity in the ROIs across heterogeneous data was achieved using a background correction method applied to each ROI. A DCNN with four convolutional layers and three fully connected (FC) layers was first trained on the mammography data. Jittering and dropout techniques were used to reduce overfitting. After training with the mammographic ROIs, all weights in the first three convolutional layers were frozen, and only the last convolution layer and the FC layers were randomly initialized again and trained using the DBT training ROIs. The authors compared the performances of two CAD systems for mass detection in DBT: one used the DCNN-based approach and the other used their previously developed feature-based approach for FP reduction. The prescreening stage was identical in both systems, passing the same set of mass candidates to the FP reduction stage. For the feature-based CAD system, 3D clustering and active contour method was used for segmentation; morphological, gray level, and texture features were extracted and merged with a linear discriminant classifier to score the detected masses. For the DCNN-based CAD system, ROIs from five consecutive slices centered at each candidate were passed through the trained DCNN and a mass likelihood score was generated. The performances of the CAD systems were evaluated using free-response ROC curves and the performance difference was analyzed using a non-parametric method. Before transfer learning, the DCNN trained only on mammograms with an AUC of 0.99 classified DBT masses with an AUC of 0.81 in the DBT training set. After transfer learning with DBT, the AUC improved to 0.90. For breast-based CAD detection in the test set, the sensitivity for the feature-based and the DCNN-based CAD systems was 83% and 91%, respectively, at 1 FP/DBT volume. The difference between the performances for the two systems was statistically significant (p-value < 0.05). The image patterns learned from the mammograms were transferred to the mass detection on DBT slices through the DCNN. This study demonstrated that large data sets collected from mammography are useful for developing new CAD systems for DBT, alleviating the problem and effort of collecting entirely new large data sets for the new modality.

Convolutional neural networks for event-related potential detection: impact of the architecture.

PubMed

Cecotti, H

2017-07-01

The detection of brain responses at the single-trial level in the electroencephalogram (EEG) such as event-related potentials (ERPs) is a difficult problem that requires different processing steps to extract relevant discriminant features. While most of the signal and classification techniques for the detection of brain responses are based on linear algebra, different pattern recognition techniques such as convolutional neural network (CNN), as a type of deep learning technique, have shown some interests as they are able to process the signal after limited pre-processing. In this study, we propose to investigate the performance of CNNs in relation of their architecture and in relation to how they are evaluated: a single system for each subject, or a system for all the subjects. More particularly, we want to address the change of performance that can be observed between specifying a neural network to a subject, or by considering a neural network for a group of subjects, taking advantage of a larger number of trials from different subjects. The results support the conclusion that a convolutional neural network trained on different subjects can lead to an AUC above 0.9 by using an appropriate architecture using spatial filtering and shift invariant layers.

Vanishing points detection using combination of fast Hough transform and deep learning

NASA Astrophysics Data System (ADS)

Sheshkus, Alexander; Ingacheva, Anastasia; Nikolaev, Dmitry

2018-04-01

In this paper we propose a novel method for vanishing points detection based on convolutional neural network (CNN) approach and fast Hough transform algorithm. We show how to determine fast Hough transform neural network layer and how to use it in order to increase usability of the neural network approach to the vanishing point detection task. Our algorithm includes CNN with consequence of convolutional and fast Hough transform layers. We are building estimator for distribution of possible vanishing points in the image. This distribution can be used to find candidates of vanishing point. We provide experimental results from tests of suggested method using images collected from videos of road trips. Our approach shows stable result on test images with different projective distortions and noise. Described approach can be effectively implemented for mobile GPU and CPU.

Convolutional neural network-based malaria diagnosis from focus stack of blood smear images acquired using custom-built slide scanner.

PubMed

Gopakumar, Gopalakrishna Pillai; Swetha, Murali; Sai Siva, Gorthi; Sai Subrahmanyam, Gorthi R K

2018-03-01

The present paper introduces a focus stacking-based approach for automated quantitative detection of Plasmodium falciparum malaria from blood smear. For the detection, a custom designed convolutional neural network (CNN) operating on focus stack of images is used. The cell counting problem is addressed as the segmentation problem and we propose a 2-level segmentation strategy. Use of CNN operating on focus stack for the detection of malaria is first of its kind, and it not only improved the detection accuracy (both in terms of sensitivity [97.06%] and specificity [98.50%]) but also favored the processing on cell patches and avoided the need for hand-engineered features. The slide images are acquired with a custom-built portable slide scanner made from low-cost, off-the-shelf components and is suitable for point-of-care diagnostics. The proposed approach of employing sophisticated algorithmic processing together with inexpensive instrumentation can potentially benefit clinicians to enable malaria diagnosis. © 2017 WILEY-VCH Verlag GmbH & Co. KGaA, Weinheim.

Knowledge-guided golf course detection using a convolutional neural network fine-tuned on temporally augmented data

NASA Astrophysics Data System (ADS)

Chen, Jingbo; Wang, Chengyi; Yue, Anzhi; Chen, Jiansheng; He, Dongxu; Zhang, Xiuyan

2017-10-01

The tremendous success of deep learning models such as convolutional neural networks (CNNs) in computer vision provides a method for similar problems in the field of remote sensing. Although research on repurposing pretrained CNN to remote sensing tasks is emerging, the scarcity of labeled samples and the complexity of remote sensing imagery still pose challenges. We developed a knowledge-guided golf course detection approach using a CNN fine-tuned on temporally augmented data. The proposed approach is a combination of knowledge-driven region proposal, data-driven detection based on CNN, and knowledge-driven postprocessing. To confront data complexity, knowledge-derived cooccurrence, composition, and area-based rules are applied sequentially to propose candidate golf regions. To confront sample scarcity, we employed data augmentation in the temporal domain, which extracts samples from multitemporal images. The augmented samples were then used to fine-tune a pretrained CNN for golf detection. Finally, commission error was further suppressed by postprocessing. Experiments conducted on GF-1 imagery prove the effectiveness of the proposed approach.

Deep learning based hand gesture recognition in complex scenes

NASA Astrophysics Data System (ADS)

Ni, Zihan; Sang, Nong; Tan, Cheng

2018-03-01

Recently, region-based convolutional neural networks(R-CNNs) have achieved significant success in the field of object detection, but their accuracy is not too high for small objects and similar objects, such as the gestures. To solve this problem, we present an online hard example testing(OHET) technology to evaluate the confidence of the R-CNNs' outputs, and regard those outputs with low confidence as hard examples. In this paper, we proposed a cascaded networks to recognize the gestures. Firstly, we use the region-based fully convolutional neural network(R-FCN), which is capable of the detection for small object, to detect the gestures, and then use the OHET to select the hard examples. To enhance the accuracy of the gesture recognition, we re-classify the hard examples through VGG-19 classification network to obtain the final output of the gesture recognition system. Through the contrast experiments with other methods, we can see that the cascaded networks combined with the OHET reached to the state-of-the-art results of 99.3% mAP on small and similar gestures in complex scenes.

Automated Detection of Obstructive Sleep Apnea Events from a Single-Lead Electrocardiogram Using a Convolutional Neural Network.

PubMed

Urtnasan, Erdenebayar; Park, Jong-Uk; Joo, Eun-Yeon; Lee, Kyoung-Joung

2018-04-23

In this study, we propose a method for the automated detection of obstructive sleep apnea (OSA) from a single-lead electrocardiogram (ECG) using a convolutional neural network (CNN). A CNN model was designed with six optimized convolution layers including activation, pooling, and dropout layers. One-dimensional (1D) convolution, rectified linear units (ReLU), and max pooling were applied to the convolution, activation, and pooling layers, respectively. For training and evaluation of the CNN model, a single-lead ECG dataset was collected from 82 subjects with OSA and was divided into training (including data from 63 patients with 34,281 events) and testing (including data from 19 patients with 8571 events) datasets. Using this CNN model, a precision of 0.99%, a recall of 0.99%, and an F 1 -score of 0.99% were attained with the training dataset; these values were all 0.96% when the CNN was applied to the testing dataset. These results show that the proposed CNN model can be used to detect OSA accurately on the basis of a single-lead ECG. Ultimately, this CNN model may be used as a screening tool for those suspected to suffer from OSA.

Convolutional neural network based deep-learning architecture for prostate cancer detection on multiparametric magnetic resonance images

NASA Astrophysics Data System (ADS)

Tsehay, Yohannes K.; Lay, Nathan S.; Roth, Holger R.; Wang, Xiaosong; Kwak, Jin Tae; Turkbey, Baris I.; Pinto, Peter A.; Wood, Brad J.; Summers, Ronald M.

2017-03-01

Prostate cancer (PCa) is the second most common cause of cancer related deaths in men. Multiparametric MRI (mpMRI) is the most accurate imaging method for PCa detection; however, it requires the expertise of experienced radiologists leading to inconsistency across readers of varying experience. To increase inter-reader agreement and sensitivity, we developed a computer-aided detection (CAD) system that can automatically detect lesions on mpMRI that readers can use as a reference. We investigated a convolutional neural network based deep-learing (DCNN) architecture to find an improved solution for PCa detection on mpMRI. We adopted a network architecture from a state-of-the-art edge detector that takes an image as an input and produces an image probability map. Two-fold cross validation along with a receiver operating characteristic (ROC) analysis and free-response ROC (FROC) were used to determine our deep-learning based prostate-CAD's (CADDL) performance. The efficacy was compared to an existing prostate CAD system that is based on hand-crafted features, which was evaluated on the same test-set. CADDL had an 86% detection rate at 20% false-positive rate while the top-down learning CAD had 80% detection rate at the same false-positive rate, which translated to 94% and 85% detection rate at 10 false-positives per patient on the FROC. A CNN based CAD is able to detect cancerous lesions on mpMRI of the prostate with results comparable to an existing prostate-CAD showing potential for further development.

Object Detection and Classification by Decision-Level Fusion for Intelligent Vehicle Systems.

PubMed

Oh, Sang-Il; Kang, Hang-Bong

2017-01-22

To understand driving environments effectively, it is important to achieve accurate detection and classification of objects detected by sensor-based intelligent vehicle systems, which are significantly important tasks. Object detection is performed for the localization of objects, whereas object classification recognizes object classes from detected object regions. For accurate object detection and classification, fusing multiple sensor information into a key component of the representation and perception processes is necessary. In this paper, we propose a new object-detection and classification method using decision-level fusion. We fuse the classification outputs from independent unary classifiers, such as 3D point clouds and image data using a convolutional neural network (CNN). The unary classifiers for the two sensors are the CNN with five layers, which use more than two pre-trained convolutional layers to consider local to global features as data representation. To represent data using convolutional layers, we apply region of interest (ROI) pooling to the outputs of each layer on the object candidate regions generated using object proposal generation to realize color flattening and semantic grouping for charge-coupled device and Light Detection And Ranging (LiDAR) sensors. We evaluate our proposed method on a KITTI benchmark dataset to detect and classify three object classes: cars, pedestrians and cyclists. The evaluation results show that the proposed method achieves better performance than the previous methods. Our proposed method extracted approximately 500 proposals on a 1226 × 370 image, whereas the original selective search method extracted approximately 10 6 × n proposals. We obtained classification performance with 77.72% mean average precision over the entirety of the classes in the moderate detection level of the KITTI benchmark dataset.

Object Detection and Classification by Decision-Level Fusion for Intelligent Vehicle Systems

PubMed Central

Oh, Sang-Il; Kang, Hang-Bong

2017-01-01

To understand driving environments effectively, it is important to achieve accurate detection and classification of objects detected by sensor-based intelligent vehicle systems, which are significantly important tasks. Object detection is performed for the localization of objects, whereas object classification recognizes object classes from detected object regions. For accurate object detection and classification, fusing multiple sensor information into a key component of the representation and perception processes is necessary. In this paper, we propose a new object-detection and classification method using decision-level fusion. We fuse the classification outputs from independent unary classifiers, such as 3D point clouds and image data using a convolutional neural network (CNN). The unary classifiers for the two sensors are the CNN with five layers, which use more than two pre-trained convolutional layers to consider local to global features as data representation. To represent data using convolutional layers, we apply region of interest (ROI) pooling to the outputs of each layer on the object candidate regions generated using object proposal generation to realize color flattening and semantic grouping for charge-coupled device and Light Detection And Ranging (LiDAR) sensors. We evaluate our proposed method on a KITTI benchmark dataset to detect and classify three object classes: cars, pedestrians and cyclists. The evaluation results show that the proposed method achieves better performance than the previous methods. Our proposed method extracted approximately 500 proposals on a 1226×370 image, whereas the original selective search method extracted approximately 106×n proposals. We obtained classification performance with 77.72% mean average precision over the entirety of the classes in the moderate detection level of the KITTI benchmark dataset. PMID:28117742

Automatic QRS complex detection using two-level convolutional neural network.

PubMed

Xiang, Yande; Lin, Zhitao; Meng, Jianyi

2018-01-29

The QRS complex is the most noticeable feature in the electrocardiogram (ECG) signal, therefore, its detection is critical for ECG signal analysis. The existing detection methods largely depend on hand-crafted manual features and parameters, which may introduce significant computational complexity, especially in the transform domains. In addition, fixed features and parameters are not suitable for detecting various kinds of QRS complexes under different circumstances. In this study, based on 1-D convolutional neural network (CNN), an accurate method for QRS complex detection is proposed. The CNN consists of object-level and part-level CNNs for extracting different grained ECG morphological features automatically. All the extracted morphological features are used by multi-layer perceptron (MLP) for QRS complex detection. Additionally, a simple ECG signal preprocessing technique which only contains difference operation in temporal domain is adopted. Based on the MIT-BIH arrhythmia (MIT-BIH-AR) database, the proposed detection method achieves overall sensitivity Sen = 99.77%, positive predictivity rate PPR = 99.91%, and detection error rate DER = 0.32%. In addition, the performance variation is performed according to different signal-to-noise ratio (SNR) values. An automatic QRS detection method using two-level 1-D CNN and simple signal preprocessing technique is proposed for QRS complex detection. Compared with the state-of-the-art QRS complex detection approaches, experimental results show that the proposed method acquires comparable accuracy.

Surface potential extraction from electrostatic and Kelvin-probe force microscopy images

NASA Astrophysics Data System (ADS)

Xu, Jie; Chen, Deyuan; Li, Wei; Xu, Jun

2018-05-01

A comprehensive comparison study of electrostatic force microscopy (EFM) and Kelvin probe force microscopy (KPFM) is conducted in this manuscript. First, it is theoretically demonstrated that for metallic or semiconductor samples, both the EFM and KPFM signals are a convolution of the sample surface potential with their respective transfer functions. Then, an equivalent point-mass model describing cantilever deflection under distributed loads is developed to reevaluate the cantilever influence on detection signals, and it is shown that the cantilever has no influence on the EFM signal, while it will affect the KPFM signal intensity but not change the resolution. Finally, EFM and KPFM experiments are carried out, and the surface potential is extracted from the EFM and KPFM images by deconvolution processing, respectively. The extracted potential intensity is well consistent with each other and the detection resolution also complies with the theoretical analysis. Our work is helpful to perform a quantitative analysis of EFM and KPFM signals, and the developed point-mass model can also be used for other cantilever beam deflection problems.

Mass detection in digital breast tomosynthesis: Deep convolutional neural network with transfer learning from mammography

PubMed Central

Chan, Heang-Ping; Hadjiiski, Lubomir; Helvie, Mark A.; Wei, Jun; Cha, Kenny

2016-01-01

Purpose: Develop a computer-aided detection (CAD) system for masses in digital breast tomosynthesis (DBT) volume using a deep convolutional neural network (DCNN) with transfer learning from mammograms. Methods: A data set containing 2282 digitized film and digital mammograms and 324 DBT volumes were collected with IRB approval. The mass of interest on the images was marked by an experienced breast radiologist as reference standard. The data set was partitioned into a training set (2282 mammograms with 2461 masses and 230 DBT views with 228 masses) and an independent test set (94 DBT views with 89 masses). For DCNN training, the region of interest (ROI) containing the mass (true positive) was extracted from each image. False positive (FP) ROIs were identified at prescreening by their previously developed CAD systems. After data augmentation, a total of 45 072 mammographic ROIs and 37 450 DBT ROIs were obtained. Data normalization and reduction of non-uniformity in the ROIs across heterogeneous data was achieved using a background correction method applied to each ROI. A DCNN with four convolutional layers and three fully connected (FC) layers was first trained on the mammography data. Jittering and dropout techniques were used to reduce overfitting. After training with the mammographic ROIs, all weights in the first three convolutional layers were frozen, and only the last convolution layer and the FC layers were randomly initialized again and trained using the DBT training ROIs. The authors compared the performances of two CAD systems for mass detection in DBT: one used the DCNN-based approach and the other used their previously developed feature-based approach for FP reduction. The prescreening stage was identical in both systems, passing the same set of mass candidates to the FP reduction stage. For the feature-based CAD system, 3D clustering and active contour method was used for segmentation; morphological, gray level, and texture features were extracted and merged with a linear discriminant classifier to score the detected masses. For the DCNN-based CAD system, ROIs from five consecutive slices centered at each candidate were passed through the trained DCNN and a mass likelihood score was generated. The performances of the CAD systems were evaluated using free-response ROC curves and the performance difference was analyzed using a non-parametric method. Results: Before transfer learning, the DCNN trained only on mammograms with an AUC of 0.99 classified DBT masses with an AUC of 0.81 in the DBT training set. After transfer learning with DBT, the AUC improved to 0.90. For breast-based CAD detection in the test set, the sensitivity for the feature-based and the DCNN-based CAD systems was 83% and 91%, respectively, at 1 FP/DBT volume. The difference between the performances for the two systems was statistically significant (p-value < 0.05). Conclusions: The image patterns learned from the mammograms were transferred to the mass detection on DBT slices through the DCNN. This study demonstrated that large data sets collected from mammography are useful for developing new CAD systems for DBT, alleviating the problem and effort of collecting entirely new large data sets for the new modality. PMID:27908154

Effective Vehicle-Based Kangaroo Detection for Collision Warning Systems Using Region-Based Convolutional Networks.

PubMed

Saleh, Khaled; Hossny, Mohammed; Nahavandi, Saeid

2018-06-12

Traffic collisions between kangaroos and motorists are on the rise on Australian roads. According to a recent report, it was estimated that there were more than 20,000 kangaroo vehicle collisions that occurred only during the year 2015 in Australia. In this work, we are proposing a vehicle-based framework for kangaroo detection in urban and highway traffic environment that could be used for collision warning systems. Our proposed framework is based on region-based convolutional neural networks (RCNN). Given the scarcity of labeled data of kangaroos in traffic environments, we utilized our state-of-the-art data generation pipeline to generate 17,000 synthetic depth images of traffic scenes with kangaroo instances annotated in them. We trained our proposed RCNN-based framework on a subset of the generated synthetic depth images dataset. The proposed framework achieved a higher average precision (AP) score of 92% over all the testing synthetic depth image datasets. We compared our proposed framework against other baseline approaches and we outperformed it with more than 37% in AP score over all the testing datasets. Additionally, we evaluated the generalization performance of the proposed framework on real live data and we achieved a resilient detection accuracy without any further fine-tuning of our proposed RCNN-based framework.

Simultaneous detection and classification of breast masses in digital mammograms via a deep learning YOLO-based CAD system.

PubMed

Al-Masni, Mohammed A; Al-Antari, Mugahed A; Park, Jeong-Min; Gi, Geon; Kim, Tae-Yeon; Rivera, Patricio; Valarezo, Edwin; Choi, Mun-Taek; Han, Seung-Moo; Kim, Tae-Seong

2018-04-01

Automatic detection and classification of the masses in mammograms are still a big challenge and play a crucial role to assist radiologists for accurate diagnosis. In this paper, we propose a novel Computer-Aided Diagnosis (CAD) system based on one of the regional deep learning techniques, a ROI-based Convolutional Neural Network (CNN) which is called You Only Look Once (YOLO). Although most previous studies only deal with classification of masses, our proposed YOLO-based CAD system can handle detection and classification simultaneously in one framework. The proposed CAD system contains four main stages: preprocessing of mammograms, feature extraction utilizing deep convolutional networks, mass detection with confidence, and finally mass classification using Fully Connected Neural Networks (FC-NNs). In this study, we utilized original 600 mammograms from Digital Database for Screening Mammography (DDSM) and their augmented mammograms of 2,400 with the information of the masses and their types in training and testing our CAD. The trained YOLO-based CAD system detects the masses and then classifies their types into benign or malignant. Our results with five-fold cross validation tests show that the proposed CAD system detects the mass location with an overall accuracy of 99.7%. The system also distinguishes between benign and malignant lesions with an overall accuracy of 97%. Our proposed system even works on some challenging breast cancer cases where the masses exist over the pectoral muscles or dense regions. Copyright © 2018 Elsevier B.V. All rights reserved.

Detection and diagnosis of colitis on computed tomography using deep convolutional neural networks.

PubMed

Liu, Jiamin; Wang, David; Lu, Le; Wei, Zhuoshi; Kim, Lauren; Turkbey, Evrim B; Sahiner, Berkman; Petrick, Nicholas A; Summers, Ronald M

2017-09-01

Colitis refers to inflammation of the inner lining of the colon that is frequently associated with infection and allergic reactions. In this paper, we propose deep convolutional neural networks methods for lesion-level colitis detection and a support vector machine (SVM) classifier for patient-level colitis diagnosis on routine abdominal CT scans. The recently developed Faster Region-based Convolutional Neural Network (Faster RCNN) is utilized for lesion-level colitis detection. For each 2D slice, rectangular region proposals are generated by region proposal networks (RPN). Then, each region proposal is jointly classified and refined by a softmax classifier and bounding-box regressor. Two convolutional neural networks, eight layers of ZF net and 16 layers of VGG net are compared for colitis detection. Finally, for each patient, the detections on all 2D slices are collected and a SVM classifier is applied to develop a patient-level diagnosis. We trained and evaluated our method with 80 colitis patients and 80 normal cases using 4 × 4-fold cross validation. For lesion-level colitis detection, with ZF net, the mean of average precisions (mAP) were 48.7% and 50.9% for RCNN and Faster RCNN, respectively. The detection system achieved sensitivities of 51.4% and 54.0% at two false positives per patient for RCNN and Faster RCNN, respectively. With VGG net, Faster RCNN increased the mAP to 56.9% and increased the sensitivity to 58.4% at two false positive per patient. For patient-level colitis diagnosis, with ZF net, the average areas under the ROC curve (AUC) were 0.978 ± 0.009 and 0.984 ± 0.008 for RCNN and Faster RCNN method, respectively. The difference was not statistically significant with P = 0.18. At the optimal operating point, the RCNN method correctly identified 90.4% (72.3/80) of the colitis patients and 94.0% (75.2/80) of normal cases. The sensitivity improved to 91.6% (73.3/80) and the specificity improved to 95.0% (76.0/80) for the Faster RCNN method. With VGG net, Faster RCNN increased the AUC to 0.986 ± 0.007 and increased the diagnosis sensitivity to 93.7% (75.0/80) and specificity was unchanged at 95.0% (76.0/80). Colitis detection and diagnosis by deep convolutional neural networks is accurate and promising for future clinical application. Published 2017. This article is a U.S. Government work and is in the public domain in the USA.

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

PubMed

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

2017-12-01

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

Nonlinear damage identification of breathing cracks in Truss system

NASA Astrophysics Data System (ADS)

Zhao, Jie; DeSmidt, Hans

2014-03-01

The breathing cracks in truss system are detected by Frequency Response Function (FRF) based damage identification method. This method utilizes damage-induced changes of frequency response functions to estimate the severity and location of structural damage. This approach enables the possibility of arbitrary interrogation frequency and multiple inputs/outputs which greatly enrich the dataset for damage identification. The dynamical model of truss system is built using the finite element method and the crack model is based on fracture mechanics. Since the crack is driven by tensional and compressive forces of truss member, only one damage parameter is needed to represent the stiffness reduction of each truss member. Assuming that the crack constantly breathes with the exciting frequency, the linear damage detection algorithm is developed in frequency/time domain using Least Square and Newton Raphson methods. Then, the dynamic response of the truss system with breathing cracks is simulated in the time domain and meanwhile the crack breathing status for each member is determined by the feedback from real-time displacements of member's nodes. Harmonic Fourier Coefficients (HFCs) of dynamical response are computed by processing the data through convolution and moving average filters. Finally, the results show the effectiveness of linear damage detection algorithm in identifying the nonlinear breathing cracks using different combinations of HFCs and sensors.

Ship Detection in Gaofen-3 SAR Images Based on Sea Clutter Distribution Analysis and Deep Convolutional Neural Network

PubMed Central

You, Hongjian

2018-01-01

Target detection is one of the important applications in the field of remote sensing. The Gaofen-3 (GF-3) Synthetic Aperture Radar (SAR) satellite launched by China is a powerful tool for maritime monitoring. This work aims at detecting ships in GF-3 SAR images using a new land masking strategy, the appropriate model for sea clutter and a neural network as the discrimination scheme. Firstly, the fully convolutional network (FCN) is applied to separate the sea from the land. Then, by analyzing the sea clutter distribution in GF-3 SAR images, we choose the probability distribution model of Constant False Alarm Rate (CFAR) detector from K-distribution, Gamma distribution and Rayleigh distribution based on a tradeoff between the sea clutter modeling accuracy and the computational complexity. Furthermore, in order to better implement CFAR detection, we also use truncated statistic (TS) as a preprocessing scheme and iterative censoring scheme (ICS) for boosting the performance of detector. Finally, we employ a neural network to re-examine the results as the discrimination stage. Experiment results on three GF-3 SAR images verify the effectiveness and efficiency of this approach. PMID:29364194

Ship Detection in Gaofen-3 SAR Images Based on Sea Clutter Distribution Analysis and Deep Convolutional Neural Network.

PubMed

An, Quanzhi; Pan, Zongxu; You, Hongjian

2018-01-24

Target detection is one of the important applications in the field of remote sensing. The Gaofen-3 (GF-3) Synthetic Aperture Radar (SAR) satellite launched by China is a powerful tool for maritime monitoring. This work aims at detecting ships in GF-3 SAR images using a new land masking strategy, the appropriate model for sea clutter and a neural network as the discrimination scheme. Firstly, the fully convolutional network (FCN) is applied to separate the sea from the land. Then, by analyzing the sea clutter distribution in GF-3 SAR images, we choose the probability distribution model of Constant False Alarm Rate (CFAR) detector from K-distribution, Gamma distribution and Rayleigh distribution based on a tradeoff between the sea clutter modeling accuracy and the computational complexity. Furthermore, in order to better implement CFAR detection, we also use truncated statistic (TS) as a preprocessing scheme and iterative censoring scheme (ICS) for boosting the performance of detector. Finally, we employ a neural network to re-examine the results as the discrimination stage. Experiment results on three GF-3 SAR images verify the effectiveness and efficiency of this approach.

Scene text detection via extremal region based double threshold convolutional network classification

PubMed Central

Zhu, Wei; Lou, Jing; Chen, Longtao; Xia, Qingyuan

2017-01-01

In this paper, we present a robust text detection approach in natural images which is based on region proposal mechanism. A powerful low-level detector named saliency enhanced-MSER extended from the widely-used MSER is proposed by incorporating saliency detection methods, which ensures a high recall rate. Given a natural image, character candidates are extracted from three channels in a perception-based illumination invariant color space by saliency-enhanced MSER algorithm. A discriminative convolutional neural network (CNN) is jointly trained with multi-level information including pixel-level and character-level information as character candidate classifier. Each image patch is classified as strong text, weak text and non-text by double threshold filtering instead of conventional one-step classification, leveraging confident scores obtained via CNN. To further prune non-text regions, we develop a recursive neighborhood search algorithm to track credible texts from weak text set. Finally, characters are grouped into text lines using heuristic features such as spatial location, size, color, and stroke width. We compare our approach with several state-of-the-art methods, and experiments show that our method achieves competitive performance on public datasets ICDAR 2011 and ICDAR 2013. PMID:28820891

Comparison of hand-craft feature based SVM and CNN based deep learning framework for automatic polyp classification.

PubMed

Younghak Shin; Balasingham, Ilangko

2017-07-01

Colonoscopy is a standard method for screening polyps by highly trained physicians. Miss-detected polyps in colonoscopy are potential risk factor for colorectal cancer. In this study, we investigate an automatic polyp classification framework. We aim to compare two different approaches named hand-craft feature method and convolutional neural network (CNN) based deep learning method. Combined shape and color features are used for hand craft feature extraction and support vector machine (SVM) method is adopted for classification. For CNN approach, three convolution and pooling based deep learning framework is used for classification purpose. The proposed framework is evaluated using three public polyp databases. From the experimental results, we have shown that the CNN based deep learning framework shows better classification performance than the hand-craft feature based methods. It achieves over 90% of classification accuracy, sensitivity, specificity and precision.

High-throughput adaptive sampling for whole-slide histopathology image analysis (HASHI) via convolutional neural networks: Application to invasive breast cancer detection.

PubMed

Cruz-Roa, Angel; Gilmore, Hannah; Basavanhally, Ajay; Feldman, Michael; Ganesan, Shridar; Shih, Natalie; Tomaszewski, John; Madabhushi, Anant; González, Fabio

2018-01-01

Precise detection of invasive cancer on whole-slide images (WSI) is a critical first step in digital pathology tasks of diagnosis and grading. Convolutional neural network (CNN) is the most popular representation learning method for computer vision tasks, which have been successfully applied in digital pathology, including tumor and mitosis detection. However, CNNs are typically only tenable with relatively small image sizes (200 × 200 pixels). Only recently, Fully convolutional networks (FCN) are able to deal with larger image sizes (500 × 500 pixels) for semantic segmentation. Hence, the direct application of CNNs to WSI is not computationally feasible because for a WSI, a CNN would require billions or trillions of parameters. To alleviate this issue, this paper presents a novel method, High-throughput Adaptive Sampling for whole-slide Histopathology Image analysis (HASHI), which involves: i) a new efficient adaptive sampling method based on probability gradient and quasi-Monte Carlo sampling, and, ii) a powerful representation learning classifier based on CNNs. We applied HASHI to automated detection of invasive breast cancer on WSI. HASHI was trained and validated using three different data cohorts involving near 500 cases and then independently tested on 195 studies from The Cancer Genome Atlas. The results show that (1) the adaptive sampling method is an effective strategy to deal with WSI without compromising prediction accuracy by obtaining comparative results of a dense sampling (∼6 million of samples in 24 hours) with far fewer samples (∼2,000 samples in 1 minute), and (2) on an independent test dataset, HASHI is effective and robust to data from multiple sites, scanners, and platforms, achieving an average Dice coefficient of 76%.

High-throughput adaptive sampling for whole-slide histopathology image analysis (HASHI) via convolutional neural networks: Application to invasive breast cancer detection

PubMed Central

Gilmore, Hannah; Basavanhally, Ajay; Feldman, Michael; Ganesan, Shridar; Shih, Natalie; Tomaszewski, John; Madabhushi, Anant; González, Fabio

2018-01-01

Precise detection of invasive cancer on whole-slide images (WSI) is a critical first step in digital pathology tasks of diagnosis and grading. Convolutional neural network (CNN) is the most popular representation learning method for computer vision tasks, which have been successfully applied in digital pathology, including tumor and mitosis detection. However, CNNs are typically only tenable with relatively small image sizes (200 × 200 pixels). Only recently, Fully convolutional networks (FCN) are able to deal with larger image sizes (500 × 500 pixels) for semantic segmentation. Hence, the direct application of CNNs to WSI is not computationally feasible because for a WSI, a CNN would require billions or trillions of parameters. To alleviate this issue, this paper presents a novel method, High-throughput Adaptive Sampling for whole-slide Histopathology Image analysis (HASHI), which involves: i) a new efficient adaptive sampling method based on probability gradient and quasi-Monte Carlo sampling, and, ii) a powerful representation learning classifier based on CNNs. We applied HASHI to automated detection of invasive breast cancer on WSI. HASHI was trained and validated using three different data cohorts involving near 500 cases and then independently tested on 195 studies from The Cancer Genome Atlas. The results show that (1) the adaptive sampling method is an effective strategy to deal with WSI without compromising prediction accuracy by obtaining comparative results of a dense sampling (∼6 million of samples in 24 hours) with far fewer samples (∼2,000 samples in 1 minute), and (2) on an independent test dataset, HASHI is effective and robust to data from multiple sites, scanners, and platforms, achieving an average Dice coefficient of 76%. PMID:29795581

A fully automatic microcalcification detection approach based on deep convolution neural network

NASA Astrophysics Data System (ADS)

Cai, Guanxiong; Guo, Yanhui; Zhang, Yaqin; Qin, Genggeng; Zhou, Yuanpin; Lu, Yao

2018-02-01

Breast cancer is one of the most common cancers and has high morbidity and mortality worldwide, posing a serious threat to the health of human beings. The emergence of microcalcifications (MCs) is an important signal of early breast cancer. However, it is still challenging and time consuming for radiologists to identify some tiny and subtle individual MCs in mammograms. This study proposed a novel computer-aided MC detection algorithm on the full field digital mammograms (FFDMs) using deep convolution neural network (DCNN). Firstly, a MC candidate detection system was used to obtain potential MC candidates. Then a DCNN was trained using a novel adaptive learning strategy, neutrosophic reinforcement sample learning (NRSL) strategy to speed up the learning process. The trained DCNN served to recognize true MCs. After been classified by DCNN, a density-based regional clustering method was imposed to form MC clusters. The accuracy of the DCNN with our proposed NRSL strategy converges faster and goes higher than the traditional DCNN at same epochs, and the obtained an accuracy of 99.87% on training set, 95.12% on validation set, and 93.68% on testing set at epoch 40. For cluster-based MC cluster detection evaluation, a sensitivity of 90% was achieved at 0.13 false positives (FPs) per image. The obtained results demonstrate that the designed DCNN plays a significant role in the MC detection after being prior trained.

Cephalometric landmark detection in dental x-ray images using convolutional neural networks

NASA Astrophysics Data System (ADS)

Lee, Hansang; Park, Minseok; Kim, Junmo

2017-03-01

In dental X-ray images, an accurate detection of cephalometric landmarks plays an important role in clinical diagnosis, treatment and surgical decisions for dental problems. In this work, we propose an end-to-end deep learning system for cephalometric landmark detection in dental X-ray images, using convolutional neural networks (CNN). For detecting 19 cephalometric landmarks in dental X-ray images, we develop a detection system using CNN-based coordinate-wise regression systems. By viewing x- and y-coordinates of all landmarks as 38 independent variables, multiple CNN-based regression systems are constructed to predict the coordinate variables from input X-ray images. First, each coordinate variable is normalized by the length of either height or width of an image. For each normalized coordinate variable, a CNN-based regression system is trained on training images and corresponding coordinate variable, which is a variable to be regressed. We train 38 regression systems with the same CNN structure on coordinate variables, respectively. Finally, we compute 38 coordinate variables with these trained systems from unseen images and extract 19 landmarks by pairing the regressed coordinates. In experiments, the public database from the Grand Challenges in Dental X-ray Image Analysis in ISBI 2015 was used and the proposed system showed promising performance by successfully locating the cephalometric landmarks within considerable margins from the ground truths.

Pedestrian Detection Based on Adaptive Selection of Visible Light or Far-Infrared Light Camera Image by Fuzzy Inference System and Convolutional Neural Network-Based Verification.

PubMed

Kang, Jin Kyu; Hong, Hyung Gil; Park, Kang Ryoung

2017-07-08

A number of studies have been conducted to enhance the pedestrian detection accuracy of intelligent surveillance systems. However, detecting pedestrians under outdoor conditions is a challenging problem due to the varying lighting, shadows, and occlusions. In recent times, a growing number of studies have been performed on visible light camera-based pedestrian detection systems using a convolutional neural network (CNN) in order to make the pedestrian detection process more resilient to such conditions. However, visible light cameras still cannot detect pedestrians during nighttime, and are easily affected by shadows and lighting. There are many studies on CNN-based pedestrian detection through the use of far-infrared (FIR) light cameras (i.e., thermal cameras) to address such difficulties. However, when the solar radiation increases and the background temperature reaches the same level as the body temperature, it remains difficult for the FIR light camera to detect pedestrians due to the insignificant difference between the pedestrian and non-pedestrian features within the images. Researchers have been trying to solve this issue by inputting both the visible light and the FIR camera images into the CNN as the input. This, however, takes a longer time to process, and makes the system structure more complex as the CNN needs to process both camera images. This research adaptively selects a more appropriate candidate between two pedestrian images from visible light and FIR cameras based on a fuzzy inference system (FIS), and the selected candidate is verified with a CNN. Three types of databases were tested, taking into account various environmental factors using visible light and FIR cameras. The results showed that the proposed method performs better than the previously reported methods.

Breast mass detection in mammography and tomosynthesis via fully convolutional network-based heatmap regression

NASA Astrophysics Data System (ADS)

Zhang, Jun; Cain, Elizabeth Hope; Saha, Ashirbani; Zhu, Zhe; Mazurowski, Maciej A.

2018-02-01

Breast mass detection in mammography and digital breast tomosynthesis (DBT) is an essential step in computerized breast cancer analysis. Deep learning-based methods incorporate feature extraction and model learning into a unified framework and have achieved impressive performance in various medical applications (e.g., disease diagnosis, tumor detection, and landmark detection). However, these methods require large-scale accurately annotated data. Unfortunately, it is challenging to get precise annotations of breast masses. To address this issue, we propose a fully convolutional network (FCN) based heatmap regression method for breast mass detection, using only weakly annotated mass regions in mammography images. Specifically, we first generate heat maps of masses based on human-annotated rough regions for breast masses. We then develop an FCN model for end-to-end heatmap regression with an F-score loss function, where the mammography images are regarded as the input and heatmaps for breast masses are used as the output. Finally, the probability map of mass locations can be estimated with the trained model. Experimental results on a mammography dataset with 439 subjects demonstrate the effectiveness of our method. Furthermore, we evaluate whether we can use mammography data to improve detection models for DBT, since mammography shares similar structure with tomosynthesis. We propose a transfer learning strategy by fine-tuning the learned FCN model from mammography images. We test this approach on a small tomosynthesis dataset with only 40 subjects, and we show an improvement in the detection performance as compared to training the model from scratch.

Detection of soft tissue densities from digital breast tomosynthesis: comparison of conventional and deep learning approaches

NASA Astrophysics Data System (ADS)

Fotin, Sergei V.; Yin, Yin; Haldankar, Hrishikesh; Hoffmeister, Jeffrey W.; Periaswamy, Senthil

2016-03-01

Computer-aided detection (CAD) has been used in screening mammography for many years and is likely to be utilized for digital breast tomosynthesis (DBT). Higher detection performance is desirable as it may have an impact on radiologist's decisions and clinical outcomes. Recently the algorithms based on deep convolutional architectures have been shown to achieve state of the art performance in object classification and detection. Similarly, we trained a deep convolutional neural network directly on patches sampled from two-dimensional mammography and reconstructed DBT volumes and compared its performance to a conventional CAD algorithm that is based on computation and classification of hand-engineered features. The detection performance was evaluated on the independent test set of 344 DBT reconstructions (GE SenoClaire 3D, iterative reconstruction algorithm) containing 328 suspicious and 115 malignant soft tissue densities including masses and architectural distortions. Detection sensitivity was measured on a region of interest (ROI) basis at the rate of five detection marks per volume. Moving from conventional to deep learning approach resulted in increase of ROI sensitivity from 0:832 +/- 0:040 to 0:893 +/- 0:033 for suspicious ROIs; and from 0:852 +/- 0:065 to 0:930 +/- 0:046 for malignant ROIs. These results indicate the high utility of deep feature learning in the analysis of DBT data and high potential of the method for broader medical image analysis tasks.

Image denoising based on noise detection

NASA Astrophysics Data System (ADS)

Jiang, Yuanxiang; Yuan, Rui; Sun, Yuqiu; Tian, Jinwen

2018-03-01

Because of the noise points in the images, any operation of denoising would change the original information of non-noise pixel. A noise detection algorithm based on fractional calculus was proposed to denoise in this paper. Convolution of the image was made to gain direction gradient masks firstly. Then, the mean gray was calculated to obtain the gradient detection maps. Logical product was made to acquire noise position image next. Comparisons in the visual effect and evaluation parameters after processing, the results of experiment showed that the denoising algorithms based on noise were better than that of traditional methods in both subjective and objective aspects.

Using deep convolutional neural networks to identify and classify tumor-associated stroma in diagnostic breast biopsies.

PubMed

Ehteshami Bejnordi, Babak; Mullooly, Maeve; Pfeiffer, Ruth M; Fan, Shaoqi; Vacek, Pamela M; Weaver, Donald L; Herschorn, Sally; Brinton, Louise A; van Ginneken, Bram; Karssemeijer, Nico; Beck, Andrew H; Gierach, Gretchen L; van der Laak, Jeroen A W M; Sherman, Mark E

2018-06-13

The breast stromal microenvironment is a pivotal factor in breast cancer development, growth and metastases. Although pathologists often detect morphologic changes in stroma by light microscopy, visual classification of such changes is subjective and non-quantitative, limiting its diagnostic utility. To gain insights into stromal changes associated with breast cancer, we applied automated machine learning techniques to digital images of 2387 hematoxylin and eosin stained tissue sections of benign and malignant image-guided breast biopsies performed to investigate mammographic abnormalities among 882 patients, ages 40-65 years, that were enrolled in the Breast Radiology Evaluation and Study of Tissues (BREAST) Stamp Project. Using deep convolutional neural networks, we trained an algorithm to discriminate between stroma surrounding invasive cancer and stroma from benign biopsies. In test sets (928 whole-slide images from 330 patients), this algorithm could distinguish biopsies diagnosed as invasive cancer from benign biopsies solely based on the stromal characteristics (area under the receiver operator characteristics curve = 0.962). Furthermore, without being trained specifically using ductal carcinoma in situ as an outcome, the algorithm detected tumor-associated stroma in greater amounts and at larger distances from grade 3 versus grade 1 ductal carcinoma in situ. Collectively, these results suggest that algorithms based on deep convolutional neural networks that evaluate only stroma may prove useful to classify breast biopsies and aid in understanding and evaluating the biology of breast lesions.

Learning the ideal observer for SKE detection tasks by use of convolutional neural networks (Cum Laude Poster Award)

NASA Astrophysics Data System (ADS)

Zhou, Weimin; Anastasio, Mark A.

2018-03-01

It has been advocated that task-based measures of image quality (IQ) should be employed to evaluate and optimize imaging systems. Task-based measures of IQ quantify the performance of an observer on a medically relevant task. The Bayesian Ideal Observer (IO), which employs complete statistical information of the object and noise, achieves the upper limit of the performance for a binary signal classification task. However, computing the IO performance is generally analytically intractable and can be computationally burdensome when Markov-chain Monte Carlo (MCMC) techniques are employed. In this paper, supervised learning with convolutional neural networks (CNNs) is employed to approximate the IO test statistics for a signal-known-exactly and background-known-exactly (SKE/BKE) binary detection task. The receiver operating characteristic (ROC) curve and the area under the ROC curve (AUC) are compared to those produced by the analytically computed IO. The advantages of the proposed supervised learning approach for approximating the IO are demonstrated.

Yarn-dyed fabric defect classification based on convolutional neural network

NASA Astrophysics Data System (ADS)

Jing, Junfeng; Dong, Amei; Li, Pengfei

2017-07-01

Considering that the manual inspection of the yarn-dyed fabric can be time consuming and less efficient, a convolutional neural network (CNN) solution based on the modified AlexNet structure for the classification of the yarn-dyed fabric defect is proposed. CNN has powerful ability of feature extraction and feature fusion which can simulate the learning mechanism of the human brain. In order to enhance computational efficiency and detection accuracy, the local response normalization (LRN) layers in AlexNet are replaced by the batch normalization (BN) layers. In the process of the network training, through several convolution operations, the characteristics of the image are extracted step by step, and the essential features of the image can be obtained from the edge features. And the max pooling layers, the dropout layers, the fully connected layers are also employed in the classification model to reduce the computation cost and acquire more precise features of fabric defect. Finally, the results of the defect classification are predicted by the softmax function. The experimental results show the capability of defect classification via the modified Alexnet model and indicate its robustness.

Convolutional neural networks applied to neutrino events in a liquid argon time projection chamber

NASA Astrophysics Data System (ADS)

Acciarri, R.; Adams, C.; An, R.; Asaadi, J.; Auger, M.; Bagby, L.; Baller, B.; Barr, G.; Bass, M.; Bay, F.; Bishai, M.; Blake, A.; Bolton, T.; Bugel, L.; Camilleri, L.; Caratelli, D.; Carls, B.; Castillo Fernandez, R.; Cavanna, F.; Chen, H.; Church, E.; Cianci, D.; Collin, G. H.; Conrad, J. M.; Convery, M.; Crespo-Anadón, J. I.; Del Tutto, M.; Devitt, D.; Dytman, S.; Eberly, B.; Ereditato, A.; Escudero Sanchez, L.; Esquivel, J.; Fleming, B. T.; Foreman, W.; Furmanski, A. P.; Garvey, G. T.; Genty, V.; Goeldi, D.; Gollapinni, S.; Graf, N.; Gramellini, E.; Greenlee, H.; Grosso, R.; Guenette, R.; Hackenburg, A.; Hamilton, P.; Hen, O.; Hewes, J.; Hill, C.; Ho, J.; Horton-Smith, G.; James, C.; de Vries, J. Jan; Jen, C.-M.; Jiang, L.; Johnson, R. A.; Jones, B. J. P.; Joshi, J.; Jostlein, H.; Kaleko, D.; Karagiorgi, G.; Ketchum, W.; Kirby, B.; Kirby, M.; Kobilarcik, T.; Kreslo, I.; Laube, A.; Li, Y.; Lister, A.; Littlejohn, B. R.; Lockwitz, S.; Lorca, D.; Louis, W. C.; Luethi, M.; Lundberg, B.; Luo, X.; Marchionni, A.; Mariani, C.; Marshall, J.; Martinez Caicedo, D. A.; Meddage, V.; Miceli, T.; Mills, G. B.; Moon, J.; Mooney, M.; Moore, C. D.; Mousseau, J.; Murrells, R.; Naples, D.; Nienaber, P.; Nowak, J.; Palamara, O.; Paolone, V.; Papavassiliou, V.; Pate, S. F.; Pavlovic, Z.; Porzio, D.; Pulliam, G.; Qian, X.; Raaf, J. L.; Rafique, A.; Rochester, L.; von Rohr, C. Rudolf; Russell, B.; Schmitz, D. W.; Schukraft, A.; Seligman, W.; Shaevitz, M. H.; Sinclair, J.; Snider, E. L.; Soderberg, M.; Söldner-Rembold, S.; Soleti, S. R.; Spentzouris, P.; Spitz, J.; St. John, J.; Strauss, T.; Szelc, A. M.; Tagg, N.; Terao, K.; Thomson, M.; Toups, M.; Tsai, Y.-T.; Tufanli, S.; Usher, T.; Van de Water, R. G.; Viren, B.; Weber, M.; Weston, J.; Wickremasinghe, D. A.; Wolbers, S.; Wongjirad, T.; Woodruff, K.; Yang, T.; Zeller, G. P.; Zennamo, J.; Zhang, C.

2017-03-01

We present several studies of convolutional neural networks applied to data coming from the MicroBooNE detector, a liquid argon time projection chamber (LArTPC). The algorithms studied include the classification of single particle images, the localization of single particle and neutrino interactions in an image, and the detection of a simulated neutrino event overlaid with cosmic ray backgrounds taken from real detector data. These studies demonstrate the potential of convolutional neural networks for particle identification or event detection on simulated neutrino interactions. We also address technical issues that arise when applying this technique to data from a large LArTPC at or near ground level.

Fully convolutional neural networks for polyp segmentation in colonoscopy

NASA Astrophysics Data System (ADS)

Brandao, Patrick; Mazomenos, Evangelos; Ciuti, Gastone; Caliò, Renato; Bianchi, Federico; Menciassi, Arianna; Dario, Paolo; Koulaouzidis, Anastasios; Arezzo, Alberto; Stoyanov, Danail

2017-03-01

Colorectal cancer (CRC) is one of the most common and deadliest forms of cancer, accounting for nearly 10% of all forms of cancer in the world. Even though colonoscopy is considered the most effective method for screening and diagnosis, the success of the procedure is highly dependent on the operator skills and level of hand-eye coordination. In this work, we propose to adapt fully convolution neural networks (FCN), to identify and segment polyps in colonoscopy images. We converted three established networks into a fully convolution architecture and fine-tuned their learned representations to the polyp segmentation task. We validate our framework on the 2015 MICCAI polyp detection challenge dataset, surpassing the state-of-the-art in automated polyp detection. Our method obtained high segmentation accuracy and a detection precision and recall of 73.61% and 86.31%, respectively.

Simulation study of amplitude-modulated (AM) harmonic motion imaging (HMI) for stiffness contrast quantification with experimental validation.

PubMed

Maleke, Caroline; Luo, Jianwen; Gamarnik, Viktor; Lu, Xin L; Konofagou, Elisa E

2010-07-01

The objective of this study is to show that Harmonic Motion Imaging (HMI) can be used as a reliable tumor-mapping technique based on the tumor's distinct stiffness at the early onset of disease. HMI is a radiation-force-based imaging method that generates a localized vibration deep inside the tissue to estimate the relative tissue stiffness based on the resulting displacement amplitude. In this paper, a finite-element model (FEM) study is presented, followed by an experimental validation in tissue-mimicking polyacrylamide gels and excised human breast tumors ex vivo. This study compares the resulting tissue motion in simulations and experiments at four different gel stiffnesses and three distinct spherical inclusion diameters. The elastic moduli of the gels were separately measured using mechanical testing. Identical transducer parameters were used in both the FEM and experimental studies, i.e., a 4.5-MHz single-element focused ultrasound (FUS) and a 7.5-MHz diagnostic (pulse-echo) transducer. In the simulation, an acoustic pressure field was used as the input stimulus to generate a localized vibration inside the target. Radiofrequency (rf) signals were then simulated using a 2D convolution model. A one-dimensional cross-correlation technique was performed on the simulated and experimental rf signals to estimate the axial displacement resulting from the harmonic radiation force. In order to measure the reliability of the displacement profiles in estimating the tissue stiffness distribution, the contrast-transfer efficiency (CTE) was calculated. For tumor mapping ex vivo, a harmonic radiation force was applied using a 2D raster-scan technique. The 2D HMI images of the breast tumor ex vivo could detect a malignant tumor (20 x 10 mm2) surrounded by glandular and fat tissues. The FEM and experimental results from both gels and breast tumors ex vivo demonstrated that HMI was capable of detecting and mapping the tumor or stiff inclusion with various diameters or stiffnesses. HMI may thus constitute a promising technique in tumor detection (>3 mm in diameter) and mapping based on its distinct stiffness.

DeepSite: protein-binding site predictor using 3D-convolutional neural networks.

PubMed

Jiménez, J; Doerr, S; Martínez-Rosell, G; Rose, A S; De Fabritiis, G

2017-10-01

An important step in structure-based drug design consists in the prediction of druggable binding sites. Several algorithms for detecting binding cavities, those likely to bind to a small drug compound, have been developed over the years by clever exploitation of geometric, chemical and evolutionary features of the protein. Here we present a novel knowledge-based approach that uses state-of-the-art convolutional neural networks, where the algorithm is learned by examples. In total, 7622 proteins from the scPDB database of binding sites have been evaluated using both a distance and a volumetric overlap approach. Our machine-learning based method demonstrates superior performance to two other competitive algorithmic strategies. DeepSite is freely available at www.playmolecule.org. Users can submit either a PDB ID or PDB file for pocket detection to our NVIDIA GPU-equipped servers through a WebGL graphical interface. gianni.defabritiis@upf.edu. Supplementary data are available at Bioinformatics online. © The Author (2017). Published by Oxford University Press. All rights reserved. For Permissions, please email: journals.permissions@oup.com

Region Based CNN for Foreign Object Debris Detection on Airfield Pavement

PubMed Central

Cao, Xiaoguang; Wang, Peng; Meng, Cai; Gong, Guoping; Liu, Miaoming; Qi, Jun

2018-01-01

In this paper, a novel algorithm based on convolutional neural network (CNN) is proposed to detect foreign object debris (FOD) based on optical imaging sensors. It contains two modules, the improved region proposal network (RPN) and spatial transformer network (STN) based CNN classifier. In the improved RPN, some extra select rules are designed and deployed to generate high quality candidates with fewer numbers. Moreover, the efficiency of CNN detector is significantly improved by introducing STN layer. Compared to faster R-CNN and single shot multiBox detector (SSD), the proposed algorithm achieves better result for FOD detection on airfield pavement in the experiment. PMID:29494524

Region Based CNN for Foreign Object Debris Detection on Airfield Pavement.

PubMed

Cao, Xiaoguang; Wang, Peng; Meng, Cai; Bai, Xiangzhi; Gong, Guoping; Liu, Miaoming; Qi, Jun

2018-03-01

In this paper, a novel algorithm based on convolutional neural network (CNN) is proposed to detect foreign object debris (FOD) based on optical imaging sensors. It contains two modules, the improved region proposal network (RPN) and spatial transformer network (STN) based CNN classifier. In the improved RPN, some extra select rules are designed and deployed to generate high quality candidates with fewer numbers. Moreover, the efficiency of CNN detector is significantly improved by introducing STN layer. Compared to faster R-CNN and single shot multiBox detector (SSD), the proposed algorithm achieves better result for FOD detection on airfield pavement in the experiment.

Microaneurysm detection using fully convolutional neural networks.

PubMed

Chudzik, Piotr; Majumdar, Somshubra; Calivá, Francesco; Al-Diri, Bashir; Hunter, Andrew

2018-05-01

Diabetic retinopathy is a microvascular complication of diabetes that can lead to sight loss if treated not early enough. Microaneurysms are the earliest clinical signs of diabetic retinopathy. This paper presents an automatic method for detecting microaneurysms in fundus photographies. A novel patch-based fully convolutional neural network with batch normalization layers and Dice loss function is proposed. Compared to other methods that require up to five processing stages, it requires only three. Furthermore, to the best of the authors' knowledge, this is the first paper that shows how to successfully transfer knowledge between datasets in the microaneurysm detection domain. The proposed method was evaluated using three publicly available and widely used datasets: E-Ophtha, DIARETDB1, and ROC. It achieved better results than state-of-the-art methods using the FROC metric. The proposed algorithm accomplished highest sensitivities for low false positive rates, which is particularly important for screening purposes. Performance, simplicity, and robustness of the proposed method demonstrates its suitability for diabetic retinopathy screening applications. Copyright © 2018 Elsevier B.V. All rights reserved.

Hazardous gas detection for FTIR-based hyperspectral imaging system using DNN and CNN

NASA Astrophysics Data System (ADS)

Kim, Yong Chan; Yu, Hyeong-Geun; Lee, Jae-Hoon; Park, Dong-Jo; Nam, Hyun-Woo

2017-10-01

Recently, a hyperspectral imaging system (HIS) with a Fourier Transform InfraRed (FTIR) spectrometer has been widely used due to its strengths in detecting gaseous fumes. Even though numerous algorithms for detecting gaseous fumes have already been studied, it is still difficult to detect target gases properly because of atmospheric interference substances and unclear characteristics of low concentration gases. In this paper, we propose detection algorithms for classifying hazardous gases using a deep neural network (DNN) and a convolutional neural network (CNN). In both the DNN and CNN, spectral signal preprocessing, e.g., offset, noise, and baseline removal, are carried out. In the DNN algorithm, the preprocessed spectral signals are used as feature maps of the DNN with five layers, and it is trained by a stochastic gradient descent (SGD) algorithm (50 batch size) and dropout regularization (0.7 ratio). In the CNN algorithm, preprocessed spectral signals are trained with 1 × 3 convolution layers and 1 × 2 max-pooling layers. As a result, the proposed algorithms improve the classification accuracy rate by 1.5% over the existing support vector machine (SVM) algorithm for detecting and classifying hazardous gases.

Enhanced line integral convolution with flow feature detection

DOT National Transportation Integrated Search

1995-01-01

Prepared ca. 1995. The Line Integral Convolution (LIC) method, which blurs white noise textures along a vector field, is an effective way to visualize overall flow patterns in a 2D domain [Cabral & Leedom '93]. The method produces a flow texture imag...

A deep learning method for early screening of lung cancer

NASA Astrophysics Data System (ADS)

Zhang, Kunpeng; Jiang, Huiqin; Ma, Ling; Gao, Jianbo; Yang, Xiaopeng

2018-04-01

Lung cancer is the leading cause of cancer-related deaths among men. In this paper, we propose a pulmonary nodule detection method for early screening of lung cancer based on the improved AlexNet model. In order to maintain the same image quality as the existing B/S architecture PACS system, we convert the original CT image into JPEG format image by analyzing the DICOM file firstly. Secondly, in view of the large size and complex background of CT chest images, we design the convolution neural network on basis of AlexNet model and sparse convolution structure. At last we train our models on the software named DIGITS which is provided by NVIDIA. The main contribution of this paper is to apply the convolutional neural network for the early screening of lung cancer and improve the screening accuracy by combining the AlexNet model with the sparse convolution structure. We make a series of experiments on the chest CT images using the proposed method, of which the sensitivity and specificity indicates that the method presented in this paper can effectively improve the accuracy of early screening of lung cancer and it has certain clinical significance at the same time.

Mass detection in digital breast tomosynthesis data using convolutional neural networks and multiple instance learning.

PubMed

Yousefi, Mina; Krzyżak, Adam; Suen, Ching Y

2018-05-01

Digital breast tomosynthesis (DBT) was developed in the field of breast cancer screening as a new tomographic technique to minimize the limitations of conventional digital mammography breast screening methods. A computer-aided detection (CAD) framework for mass detection in DBT has been developed and is described in this paper. The proposed framework operates on a set of two-dimensional (2D) slices. With plane-to-plane analysis on corresponding 2D slices from each DBT, it automatically learns complex patterns of 2D slices through a deep convolutional neural network (DCNN). It then applies multiple instance learning (MIL) with a randomized trees approach to classify DBT images based on extracted information from 2D slices. This CAD framework was developed and evaluated using 5040 2D image slices derived from 87 DBT volumes. The empirical results demonstrate that this proposed CAD framework achieves much better performance than CAD systems that use hand-crafted features and deep cardinality-restricted Bolzmann machines to detect masses in DBTs. Copyright © 2018 Elsevier Ltd. All rights reserved.

Cerebral microbleed detection in traumatic brain injury patients using 3D convolutional neural networks

NASA Astrophysics Data System (ADS)

Standvoss, K.; Crijns, T.; Goerke, L.; Janssen, D.; Kern, S.; van Niedek, T.; van Vugt, J.; Alfonso Burgos, N.; Gerritse, E. J.; Mol, J.; van de Vooren, D.; Ghafoorian, M.; van den Heuvel, T. L. A.; Manniesing, R.

2018-02-01

The number and location of cerebral microbleeds (CMBs) in patients with traumatic brain injury (TBI) is important to determine the severity of trauma and may hold prognostic value for patient outcome. However, manual assessment is subjective and time-consuming due to the resemblance of CMBs to blood vessels, the possible presence of imaging artifacts, and the typical heterogeneity of trauma imaging data. In this work, we present a computer aided detection system based on 3D convolutional neural networks for detecting CMBs in 3D susceptibility weighted images. Network architectures with varying depth were evaluated. Data augmentation techniques were employed to improve the networks' generalization ability and selective sampling was implemented to handle class imbalance. The predictions of the models were clustered using a connected component analysis. The system was trained on ten annotated scans and evaluated on an independent test set of eight scans. Despite this limited data set, the system reached a sensitivity of 0.87 at 16.75 false positives per scan (2.5 false positives per CMB), outperforming related work on CMB detection in TBI patients.

The unitary convolution approximation for heavy ions

NASA Astrophysics Data System (ADS)

Grande, P. L.; Schiwietz, G.

2002-10-01

The convolution approximation for the impact-parameter dependent energy loss is reviewed with emphasis on the determination of the stopping force for heavy projectiles. In this method, the energy loss in different impact-parameter regions is well determined and interpolated smoothly. The physical inputs of the model are the projectile-screening function (in the case of dressed ions), the electron density and oscillators strengths of the target atoms. Moreover, the convolution approximation, in the perturbative mode (called PCA), yields remarkable agreement with full semi-classical-approximation (SCA) results for bare as well as for screened ions at all impact parameters. In the unitary mode (called UCA), the method contains some higher-order effects (yielding in some cases rather good agreement with full coupled-channel calculations) and approaches the classical regime similar as the Bohr model for large perturbations ( Z/ v≫1). The results are then used to compare with experimental values of the non-equilibrium stopping force as a function of the projectile charge as well as with the equilibrium energy loss under non-aligned and channeling conditions.

Convolutional neural networks applied to neutrino events in a liquid argon time projection chamber

DOE PAGES

Acciarri, R.; Adams, C.; An, R.; ...

2017-03-14

Here, we present several studies of convolutional neural networks applied to data coming from the MicroBooNE detector, a liquid argon time projection chamber (LArTPC). The algorithms studied include the classification of single particle images, the localization of single particle and neutrino interactions in an image, and the detection of a simulated neutrino event overlaid with cosmic ray backgrounds taken from real detector data. These studies demonstrate the potential of convolutional neural networks for particle identification or event detection on simulated neutrino interactions. Lastly, we also address technical issues that arise when applying this technique to data from a large LArTPCmore » at or near ground level.« less

Pneumothorax detection in chest radiographs using convolutional neural networks

NASA Astrophysics Data System (ADS)

Blumenfeld, Aviel; Konen, Eli; Greenspan, Hayit

2018-02-01

This study presents a computer assisted diagnosis system for the detection of pneumothorax (PTX) in chest radiographs based on a convolutional neural network (CNN) for pixel classification. Using a pixel classification approach allows utilization of the texture information in the local environment of each pixel while training a CNN model on millions of training patches extracted from a relatively small dataset. The proposed system uses a pre-processing step of lung field segmentation to overcome the large variability in the input images coming from a variety of imaging sources and protocols. Using a CNN classification, suspected pixel candidates are extracted within each lung segment. A postprocessing step follows to remove non-physiological suspected regions and noisy connected components. The overall percentage of suspected PTX area was used as a robust global decision for the presence of PTX in each lung. The system was trained on a set of 117 chest x-ray images with ground truth segmentations of the PTX regions. The system was tested on a set of 86 images and reached diagnosis accuracy of AUC=0.95. Overall preliminary results are promising and indicate the growing ability of CAD based systems to detect findings in medical imaging on a clinical level accuracy.

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.

Development of a morphological convolution operator for bearing fault detection

NASA Astrophysics Data System (ADS)

Li, Yifan; Liang, Xihui; Liu, Weiwei; Wang, Yan

2018-05-01

This paper presents a novel signal processing scheme, namely morphological convolution operator (MCO) lifted morphological undecimated wavelet (MUDW), for rolling element bearing fault detection. In this scheme, a MCO is first designed to fully utilize the advantage of the closing & opening gradient operator and the closing-opening & opening-closing gradient operator for feature extraction as well as the merit of excellent denoising characteristics of the convolution operator. The MCO is then introduced into MUDW for the purpose of improving the fault detection ability of the reported MUDWs. Experimental vibration signals collected from a train wheelset test rig and the bearing data center of Case Western Reserve University are employed to evaluate the effectiveness of the proposed MCO lifted MUDW on fault detection of rolling element bearings. The results show that the proposed approach has a superior performance in extracting fault features of defective rolling element bearings. In addition, comparisons are performed between two reported MUDWs and the proposed MCO lifted MUDW. The MCO lifted MUDW outperforms both of them in detection of outer race faults and inner race faults of rolling element bearings.

S-CNN: Subcategory-aware convolutional networks for object detection.

PubMed

Chen, Tao; Lu, Shijian; Fan, Jiayuan

2017-09-26

The marriage between the deep convolutional neural network (CNN) and region proposals has made breakthroughs for object detection in recent years. While the discriminative object features are learned via a deep CNN for classification, the large intra-class variation and deformation still limit the performance of the CNN based object detection. We propose a subcategory-aware CNN (S-CNN) to solve the object intra-class variation problem. In the proposed technique, the training samples are first grouped into multiple subcategories automatically through a novel instance sharing maximum margin clustering process. A multi-component Aggregated Channel Feature (ACF) detector is then trained to produce more latent training samples, where each ACF component corresponds to one clustered subcategory. The produced latent samples together with their subcategory labels are further fed into a CNN classifier to filter out false proposals for object detection. An iterative learning algorithm is designed for the joint optimization of image subcategorization, multi-component ACF detector, and subcategory-aware CNN classifier. Experiments on INRIA Person dataset, Pascal VOC 2007 dataset and MS COCO dataset show that the proposed technique clearly outperforms the state-of-the-art methods for generic object detection.

Automatic detection and segmentation of brain metastases on multimodal MR images with a deep convolutional neural network.

PubMed

Charron, Odelin; Lallement, Alex; Jarnet, Delphine; Noblet, Vincent; Clavier, Jean-Baptiste; Meyer, Philippe

2018-04-01

Stereotactic treatments are today the reference techniques for the irradiation of brain metastases in radiotherapy. The dose per fraction is very high, and delivered in small volumes (diameter <1 cm). As part of these treatments, effective detection and precise segmentation of lesions are imperative. Many methods based on deep-learning approaches have been developed for the automatic segmentation of gliomas, but very little for that of brain metastases. We adapted an existing 3D convolutional neural network (DeepMedic) to detect and segment brain metastases on MRI. At first, we sought to adapt the network parameters to brain metastases. We then explored the single or combined use of different MRI modalities, by evaluating network performance in terms of detection and segmentation. We also studied the interest of increasing the database with virtual patients or of using an additional database in which the active parts of the metastases are separated from the necrotic parts. Our results indicated that a deep network approach is promising for the detection and the segmentation of brain metastases on multimodal MRI. Copyright © 2018 Elsevier Ltd. All rights reserved.

Convolutional neural network guided blue crab knuckle detection for autonomous crab meat picking machine

NASA Astrophysics Data System (ADS)

Wang, Dongyi; Vinson, Robert; Holmes, Maxwell; Seibel, Gary; Tao, Yang

2018-04-01

The Atlantic blue crab is among the highest-valued seafood found in the American Eastern Seaboard. Currently, the crab processing industry is highly dependent on manual labor. However, there is great potential for vision-guided intelligent machines to automate the meat picking process. Studies show that the back-fin knuckles are robust features containing information about a crab's size, orientation, and the position of the crab's meat compartments. Our studies also make it clear that detecting the knuckles reliably in images is challenging due to the knuckle's small size, anomalous shape, and similarity to joints in the legs and claws. An accurate and reliable computer vision algorithm was proposed to detect the crab's back-fin knuckles in digital images. Convolutional neural networks (CNNs) can localize rough knuckle positions with 97.67% accuracy, transforming a global detection problem into a local detection problem. Compared to the rough localization based on human experience or other machine learning classification methods, the CNN shows the best localization results. In the rough knuckle position, a k-means clustering method is able to further extract the exact knuckle positions based on the back-fin knuckle color features. The exact knuckle position can help us to generate a crab cutline in XY plane using a template matching method. This is a pioneering research project in crab image analysis and offers advanced machine intelligence for automated crab processing.

Convolution neural-network-based detection of lung structures

NASA Astrophysics Data System (ADS)

Hasegawa, Akira; Lo, Shih-Chung B.; Freedman, Matthew T.; Mun, Seong K.

1994-05-01

Chest radiography is one of the most primary and widely used techniques in diagnostic imaging. Nowadays with the advent of digital radiology, the digital medical image processing techniques for digital chest radiographs have attracted considerable attention, and several studies on the computer-aided diagnosis (CADx) as well as on the conventional image processing techniques for chest radiographs have been reported. In the automatic diagnostic process for chest radiographs, it is important to outline the areas of the lungs, the heart, and the diaphragm. This is because the original chest radiograph is composed of important anatomic structures and, without knowing exact positions of the organs, the automatic diagnosis may result in unexpected detections. The automatic extraction of an anatomical structure from digital chest radiographs can be a useful tool for (1) the evaluation of heart size, (2) automatic detection of interstitial lung diseases, (3) automatic detection of lung nodules, and (4) data compression, etc. Based on the clearly defined boundaries of heart area, rib spaces, rib positions, and rib cage extracted, one should be able to use this information to facilitate the tasks of the CADx on chest radiographs. In this paper, we present an automatic scheme for the detection of lung field from chest radiographs by using a shift-invariant convolution neural network. A novel algorithm for smoothing boundaries of lungs is also presented.

Convolutional Neural Network-Based Classification of Driver's Emotion during Aggressive and Smooth Driving Using Multi-Modal Camera Sensors.

PubMed

Lee, Kwan Woo; Yoon, Hyo Sik; Song, Jong Min; Park, Kang Ryoung

2018-03-23

Because aggressive driving often causes large-scale loss of life and property, techniques for advance detection of adverse driver emotional states have become important for the prevention of aggressive driving behaviors. Previous studies have primarily focused on systems for detecting aggressive driver emotion via smart-phone accelerometers and gyro-sensors, or they focused on methods of detecting physiological signals using electroencephalography (EEG) or electrocardiogram (ECG) sensors. Because EEG and ECG sensors cause discomfort to drivers and can be detached from the driver's body, it becomes difficult to focus on bio-signals to determine their emotional state. Gyro-sensors and accelerometers depend on the performance of GPS receivers and cannot be used in areas where GPS signals are blocked. Moreover, if driving on a mountain road with many quick turns, a driver's emotional state can easily be misrecognized as that of an aggressive driver. To resolve these problems, we propose a convolutional neural network (CNN)-based method of detecting emotion to identify aggressive driving using input images of the driver's face, obtained using near-infrared (NIR) light and thermal camera sensors. In this research, we conducted an experiment using our own database, which provides a high classification accuracy for detecting driver emotion leading to either aggressive or smooth (i.e., relaxed) driving. Our proposed method demonstrates better performance than existing methods.

A Data-Driven Response Virtual Sensor Technique with Partial Vibration Measurements Using Convolutional Neural Network.

PubMed

Sun, Shan-Bin; He, Yuan-Yuan; Zhou, Si-Da; Yue, Zhen-Jiang

2017-12-12

Measurement of dynamic responses plays an important role in structural health monitoring, damage detection and other fields of research. However, in aerospace engineering, the physical sensors are limited in the operational conditions of spacecraft, due to the severe environment in outer space. This paper proposes a virtual sensor model with partial vibration measurements using a convolutional neural network. The transmissibility function is employed as prior knowledge. A four-layer neural network with two convolutional layers, one fully connected layer, and an output layer is proposed as the predicting model. Numerical examples of two different structural dynamic systems demonstrate the performance of the proposed approach. The excellence of the novel technique is further indicated using a simply supported beam experiment comparing to a modal-model-based virtual sensor, which uses modal parameters, such as mode shapes, for estimating the responses of the faulty sensors. The results show that the presented data-driven response virtual sensor technique can predict structural response with high accuracy.

A Data-Driven Response Virtual Sensor Technique with Partial Vibration Measurements Using Convolutional Neural Network

PubMed Central

Sun, Shan-Bin; He, Yuan-Yuan; Zhou, Si-Da; Yue, Zhen-Jiang

2017-01-01

Measurement of dynamic responses plays an important role in structural health monitoring, damage detection and other fields of research. However, in aerospace engineering, the physical sensors are limited in the operational conditions of spacecraft, due to the severe environment in outer space. This paper proposes a virtual sensor model with partial vibration measurements using a convolutional neural network. The transmissibility function is employed as prior knowledge. A four-layer neural network with two convolutional layers, one fully connected layer, and an output layer is proposed as the predicting model. Numerical examples of two different structural dynamic systems demonstrate the performance of the proposed approach. The excellence of the novel technique is further indicated using a simply supported beam experiment comparing to a modal-model-based virtual sensor, which uses modal parameters, such as mode shapes, for estimating the responses of the faulty sensors. The results show that the presented data-driven response virtual sensor technique can predict structural response with high accuracy. PMID:29231868

Convolutional Neural Network-Based Finger-Vein Recognition Using NIR Image Sensors

PubMed Central

Hong, Hyung Gil; Lee, Min Beom; Park, Kang Ryoung

2017-01-01

Conventional finger-vein recognition systems perform recognition based on the finger-vein lines extracted from the input images or image enhancement, and texture feature extraction from the finger-vein images. In these cases, however, the inaccurate detection of finger-vein lines lowers the recognition accuracy. In the case of texture feature extraction, the developer must experimentally decide on a form of the optimal filter for extraction considering the characteristics of the image database. To address this problem, this research proposes a finger-vein recognition method that is robust to various database types and environmental changes based on the convolutional neural network (CNN). In the experiments using the two finger-vein databases constructed in this research and the SDUMLA-HMT finger-vein database, which is an open database, the method proposed in this research showed a better performance compared to the conventional methods. PMID:28587269

Convolutional Neural Network-Based Finger-Vein Recognition Using NIR Image Sensors.

PubMed

Hong, Hyung Gil; Lee, Min Beom; Park, Kang Ryoung

2017-06-06

Conventional finger-vein recognition systems perform recognition based on the finger-vein lines extracted from the input images or image enhancement, and texture feature extraction from the finger-vein images. In these cases, however, the inaccurate detection of finger-vein lines lowers the recognition accuracy. In the case of texture feature extraction, the developer must experimentally decide on a form of the optimal filter for extraction considering the characteristics of the image database. To address this problem, this research proposes a finger-vein recognition method that is robust to various database types and environmental changes based on the convolutional neural network (CNN). In the experiments using the two finger-vein databases constructed in this research and the SDUMLA-HMT finger-vein database, which is an open database, the method proposed in this research showed a better performance compared to the conventional methods.

Pelvic artery calcification detection on CT scans using convolutional neural networks

NASA Astrophysics Data System (ADS)

Liu, Jiamin; Lu, Le; Yao, Jianhua; Bagheri, Mohammadhadi; Summers, Ronald M.

2017-03-01

Artery calcification is observed commonly in elderly patients, especially in patients with chronic kidney disease, and may affect coronary, carotid and peripheral arteries. Vascular calcification has been associated with many clinical outcomes. Manual identification of calcification in CT scans requires substantial expert interaction, which makes it time-consuming and infeasible for large-scale studies. Many works have been proposed for coronary artery calcification detection in cardiac CT scans. In these works, coronary artery extraction is commonly required for calcification detection. However, there are few works about abdominal or pelvic artery calcification detection. In this work, we present a method for automatic pelvic artery calcification detection on CT scan. This method uses the recent advanced faster region-based convolutional neural network (R-CNN) to directly identify artery calcification without a need for artery extraction since pelvic artery extraction itself is challenging. Our method first generates category-independent region proposals for each slice of the input CT scan using region proposal networks (RPN). Then, each region proposal is jointly classified and refined by softmax classifier and bounding box regressor. We applied the detection method to 500 images from 20 CT scans of patients for evaluation. The detection system achieved a 77.4% average precision and a 85% sensitivity at 1 false positive per image.

Anomaly Detection in Nanofibrous Materials by CNN-Based Self-Similarity.

PubMed

Napoletano, Paolo; Piccoli, Flavio; Schettini, Raimondo

2018-01-12

Automatic detection and localization of anomalies in nanofibrous materials help to reduce the cost of the production process and the time of the post-production visual inspection process. Amongst all the monitoring methods, those exploiting Scanning Electron Microscope (SEM) imaging are the most effective. In this paper, we propose a region-based method for the detection and localization of anomalies in SEM images, based on Convolutional Neural Networks (CNNs) and self-similarity. The method evaluates the degree of abnormality of each subregion of an image under consideration by computing a CNN-based visual similarity with respect to a dictionary of anomaly-free subregions belonging to a training set. The proposed method outperforms the state of the art.

Change detection in multitemporal synthetic aperture radar images using dual-channel convolutional neural network

NASA Astrophysics Data System (ADS)

Liu, Tao; Li, Ying; Cao, Ying; Shen, Qiang

2017-10-01

This paper proposes a model of dual-channel convolutional neural network (CNN) that is designed for change detection in SAR images, in an effort to acquire higher detection accuracy and lower misclassification rate. This network model contains two parallel CNN channels, which can extract deep features from two multitemporal SAR images. For comparison and validation, the proposed method is tested along with other change detection algorithms on both simulated SAR images and real-world SAR images captured by different sensors. The experimental results demonstrate that the presented method outperforms the state-of-the-art techniques by a considerable margin.

ConvNetQuake: Convolutional Neural Network for Earthquake Detection and Location

NASA Astrophysics Data System (ADS)

Denolle, M.; Perol, T.; Gharbi, M.

2017-12-01

Over the last decades, the volume of seismic data has increased exponentially, creating a need for efficient algorithms to reliably detect and locate earthquakes. Today's most elaborate methods scan through the plethora of continuous seismic records, searching for repeating seismic signals. In this work, we leverage the recent advances in artificial intelligence and present ConvNetQuake, a highly scalable convolutional neural network for probabilistic earthquake detection and location from single stations. We apply our technique to study two years of induced seismicity in Oklahoma (USA). We detect 20 times more earthquakes than previously cataloged by the Oklahoma Geological Survey. Our algorithm detection performances are at least one order of magnitude faster than other established methods.

Learned filters for object detection in multi-object visual tracking

NASA Astrophysics Data System (ADS)

Stamatescu, Victor; Wong, Sebastien; McDonnell, Mark D.; Kearney, David

2016-05-01

We investigate the application of learned convolutional filters in multi-object visual tracking. The filters were learned in both a supervised and unsupervised manner from image data using artificial neural networks. This work follows recent results in the field of machine learning that demonstrate the use learned filters for enhanced object detection and classification. Here we employ a track-before-detect approach to multi-object tracking, where tracking guides the detection process. The object detection provides a probabilistic input image calculated by selecting from features obtained using banks of generative or discriminative learned filters. We present a systematic evaluation of these convolutional filters using a real-world data set that examines their performance as generic object detectors.

Convolutional Neural Network-Based Human Detection in Nighttime Images Using Visible Light Camera Sensors.

PubMed

Kim, Jong Hyun; Hong, Hyung Gil; Park, Kang Ryoung

2017-05-08

Because intelligent surveillance systems have recently undergone rapid growth, research on accurately detecting humans in videos captured at a long distance is growing in importance. The existing research using visible light cameras has mainly focused on methods of human detection for daytime hours when there is outside light, but human detection during nighttime hours when there is no outside light is difficult. Thus, methods that employ additional near-infrared (NIR) illuminators and NIR cameras or thermal cameras have been used. However, in the case of NIR illuminators, there are limitations in terms of the illumination angle and distance. There are also difficulties because the illuminator power must be adaptively adjusted depending on whether the object is close or far away. In the case of thermal cameras, their cost is still high, which makes it difficult to install and use them in a variety of places. Because of this, research has been conducted on nighttime human detection using visible light cameras, but this has focused on objects at a short distance in an indoor environment or the use of video-based methods to capture multiple images and process them, which causes problems related to the increase in the processing time. To resolve these problems, this paper presents a method that uses a single image captured at night on a visible light camera to detect humans in a variety of environments based on a convolutional neural network. Experimental results using a self-constructed Dongguk night-time human detection database (DNHD-DB1) and two open databases (Korea advanced institute of science and technology (KAIST) and computer vision center (CVC) databases), as well as high-accuracy human detection in a variety of environments, show that the method has excellent performance compared to existing methods.

Convolutional virtual electric field for image segmentation using active contours.

PubMed

Wang, Yuanquan; Zhu, Ce; Zhang, Jiawan; Jian, Yuden

2014-01-01

Gradient vector flow (GVF) is an effective external force for active contours; however, it suffers from heavy computation load. The virtual electric field (VEF) model, which can be implemented in real time using fast Fourier transform (FFT), has been proposed later as a remedy for the GVF model. In this work, we present an extension of the VEF model, which is referred to as CONvolutional Virtual Electric Field, CONVEF for short. This proposed CONVEF model takes the VEF model as a convolution operation and employs a modified distance in the convolution kernel. The CONVEF model is also closely related to the vector field convolution (VFC) model. Compared with the GVF, VEF and VFC models, the CONVEF model possesses not only some desirable properties of these models, such as enlarged capture range, u-shape concavity convergence, subject contour convergence and initialization insensitivity, but also some other interesting properties such as G-shape concavity convergence, neighboring objects separation, and noise suppression and simultaneously weak edge preserving. Meanwhile, the CONVEF model can also be implemented in real-time by using FFT. Experimental results illustrate these advantages of the CONVEF model on both synthetic and natural images.

Myocardial scar segmentation from magnetic resonance images using convolutional neural network

NASA Astrophysics Data System (ADS)

Zabihollahy, Fatemeh; White, James A.; Ukwatta, Eranga

2018-02-01

Accurate segmentation of the myocardial fibrosis or scar may provide important advancements for the prediction and management of malignant ventricular arrhythmias in patients with cardiovascular disease. In this paper, we propose a semi-automated method for segmentation of myocardial scar from late gadolinium enhancement magnetic resonance image (LGE-MRI) using a convolutional neural network (CNN). In contrast to image intensitybased methods, CNN-based algorithms have the potential to improve the accuracy of scar segmentation through the creation of high-level features from a combination of convolutional, detection and pooling layers. Our developed algorithm was trained using 2,336,703 image patches extracted from 420 slices of five 3D LGE-MR datasets, then validated on 2,204,178 patches from a testing dataset of seven 3D LGE-MR images including 624 slices, all obtained from patients with chronic myocardial infarction. For evaluation of the algorithm, we compared the algorithmgenerated segmentations to manual delineations by experts. Our CNN-based method reported an average Dice similarity coefficient (DSC), precision, and recall of 94.50 +/- 3.62%, 96.08 +/- 3.10%, and 93.96 +/- 3.75% as the accuracy of segmentation, respectively. As compared to several intensity threshold-based methods for scar segmentation, the results of our developed method have a greater agreement with manual expert segmentation.

Splenomegaly Segmentation using Global Convolutional Kernels and Conditional Generative Adversarial Networks

PubMed Central

Huo, Yuankai; Xu, Zhoubing; Bao, Shunxing; Bermudez, Camilo; Plassard, Andrew J.; Liu, Jiaqi; Yao, Yuang; Assad, Albert; Abramson, Richard G.; Landman, Bennett A.

2018-01-01

Spleen volume estimation using automated image segmentation technique may be used to detect splenomegaly (abnormally enlarged spleen) on Magnetic Resonance Imaging (MRI) scans. In recent years, Deep Convolutional Neural Networks (DCNN) segmentation methods have demonstrated advantages for abdominal organ segmentation. However, variations in both size and shape of the spleen on MRI images may result in large false positive and false negative labeling when deploying DCNN based methods. In this paper, we propose the Splenomegaly Segmentation Network (SSNet) to address spatial variations when segmenting extraordinarily large spleens. SSNet was designed based on the framework of image-to-image conditional generative adversarial networks (cGAN). Specifically, the Global Convolutional Network (GCN) was used as the generator to reduce false negatives, while the Markovian discriminator (PatchGAN) was used to alleviate false positives. A cohort of clinically acquired 3D MRI scans (both T1 weighted and T2 weighted) from patients with splenomegaly were used to train and test the networks. The experimental results demonstrated that a mean Dice coefficient of 0.9260 and a median Dice coefficient of 0.9262 using SSNet on independently tested MRI volumes of patients with splenomegaly.

A novel microaneurysms detection approach based on convolutional neural networks with reinforcement sample learning algorithm.

PubMed

Budak, Umit; Şengür, Abdulkadir; Guo, Yanhui; Akbulut, Yaman

2017-12-01

Microaneurysms (MAs) are known as early signs of diabetic-retinopathy which are called red lesions in color fundus images. Detection of MAs in fundus images needs highly skilled physicians or eye angiography. Eye angiography is an invasive and expensive procedure. Therefore, an automatic detection system to identify the MAs locations in fundus images is in demand. In this paper, we proposed a system to detect the MAs in colored fundus images. The proposed method composed of three stages. In the first stage, a series of pre-processing steps are used to make the input images more convenient for MAs detection. To this end, green channel decomposition, Gaussian filtering, median filtering, back ground determination, and subtraction operations are applied to input colored fundus images. After pre-processing, a candidate MAs extraction procedure is applied to detect potential regions. A five-stepped procedure is adopted to get the potential MA locations. Finally, deep convolutional neural network (DCNN) with reinforcement sample learning strategy is used to train the proposed system. The DCNN is trained with color image patches which are collected from ground-truth MA locations and non-MA locations. We conducted extensive experiments on ROC dataset to evaluate of our proposal. The results are encouraging.

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.

Deep Learning Nuclei Detection in Digitized Histology Images by Superpixels.

PubMed

Sornapudi, Sudhir; Stanley, Ronald Joe; Stoecker, William V; Almubarak, Haidar; Long, Rodney; Antani, Sameer; Thoma, George; Zuna, Rosemary; Frazier, Shelliane R

2018-01-01

Advances in image analysis and computational techniques have facilitated automatic detection of critical features in histopathology images. Detection of nuclei is critical for squamous epithelium cervical intraepithelial neoplasia (CIN) classification into normal, CIN1, CIN2, and CIN3 grades. In this study, a deep learning (DL)-based nuclei segmentation approach is investigated based on gathering localized information through the generation of superpixels using a simple linear iterative clustering algorithm and training with a convolutional neural network. The proposed approach was evaluated on a dataset of 133 digitized histology images and achieved an overall nuclei detection (object-based) accuracy of 95.97%, with demonstrated improvement over imaging-based and clustering-based benchmark techniques. The proposed DL-based nuclei segmentation Method with superpixel analysis has shown improved segmentation results in comparison to state-of-the-art methods.

A robust sub-pixel edge detection method of infrared image based on tremor-based retinal receptive field model

NASA Astrophysics Data System (ADS)

Gao, Kun; Yang, Hu; Chen, Xiaomei; Ni, Guoqiang

2008-03-01

Because of complex thermal objects in an infrared image, the prevalent image edge detection operators are often suitable for a certain scene and extract too wide edges sometimes. From a biological point of view, the image edge detection operators work reliably when assuming a convolution-based receptive field architecture. A DoG (Difference-of- Gaussians) model filter based on ON-center retinal ganglion cell receptive field architecture with artificial eye tremors introduced is proposed for the image contour detection. Aiming at the blurred edges of an infrared image, the subsequent orthogonal polynomial interpolation and sub-pixel level edge detection in rough edge pixel neighborhood is adopted to locate the foregoing rough edges in sub-pixel level. Numerical simulations show that this method can locate the target edge accurately and robustly.

Experimental study of current loss and plasma formation in the Z machine post-hole convolute

NASA Astrophysics Data System (ADS)

Gomez, M. R.; Gilgenbach, R. M.; Cuneo, M. E.; Jennings, C. A.; McBride, R. D.; Waisman, E. M.; Hutsel, B. T.; Stygar, W. A.; Rose, D. V.; Maron, Y.

2017-01-01

The Z pulsed-power generator at Sandia National Laboratories drives high energy density physics experiments with load currents of up to 26 MA. Z utilizes a double post-hole convolute to combine the current from four parallel magnetically insulated transmission lines into a single transmission line just upstream of the load. Current loss is observed in most experiments and is traditionally attributed to inefficient convolute performance. The apparent loss current varies substantially for z-pinch loads with different inductance histories; however, a similar convolute impedance history is observed for all load types. This paper details direct spectroscopic measurements of plasma density, temperature, and apparent and actual plasma closure velocities within the convolute. Spectral measurements indicate a correlation between impedance collapse and plasma formation in the convolute. Absorption features in the spectra show the convolute plasma consists primarily of hydrogen, which likely forms from desorbed electrode contaminant species such as H2O , H2 , and hydrocarbons. Plasma densities increase from 1 ×1016 cm-3 (level of detectability) just before peak current to over 1 ×1017 cm-3 at stagnation (tens of ns later). The density seems to be highest near the cathode surface, with an apparent cathode to anode plasma velocity in the range of 35 - 50 cm /μ s . Similar plasma conditions and convolute impedance histories are observed in experiments with high and low losses, suggesting that losses are driven largely by load dynamics, which determine the voltage on the convolute.

Melon yield prediction using small unmanned aerial vehicles

NASA Astrophysics Data System (ADS)

Zhao, Tiebiao; Wang, Zhongdao; Yang, Qi; Chen, YangQuan

2017-05-01

Thanks to the development of camera technologies, small unmanned aerial systems (sUAS), it is possible to collect aerial images of field with more flexible visit, higher resolution and much lower cost. Furthermore, the performance of objection detection based on deeply trained convolutional neural networks (CNNs) has been improved significantly. In this study, we applied these technologies in the melon production, where high-resolution aerial images were used to count melons in the field and predict the yield. CNN-based object detection framework-Faster R-CNN is applied in the melon classification. Our results showed that sUAS plus CNNs were able to detect melons accurately in the late harvest season.

Enhanced Line Integral Convolution with Flow Feature Detection

NASA Technical Reports Server (NTRS)

Lane, David; Okada, Arthur

1996-01-01

The Line Integral Convolution (LIC) method, which blurs white noise textures along a vector field, is an effective way to visualize overall flow patterns in a 2D domain. The method produces a flow texture image based on the input velocity field defined in the domain. Because of the nature of the algorithm, the texture image tends to be blurry. This sometimes makes it difficult to identify boundaries where flow separation and reattachments occur. We present techniques to enhance LIC texture images and use colored texture images to highlight flow separation and reattachment boundaries. Our techniques have been applied to several flow fields defined in 3D curvilinear multi-block grids and scientists have found the results to be very useful.

A systematic FPGA acceleration design for applications based on convolutional neural networks

NASA Astrophysics Data System (ADS)

Dong, Hao; Jiang, Li; Li, Tianjian; Liang, Xiaoyao

2018-04-01

Most FPGA accelerators for convolutional neural network are designed to optimize the inner acceleration and are ignored of the optimization for the data path between the inner accelerator and the outer system. This could lead to poor performance in applications like real time video object detection. We propose a brand new systematic FPFA acceleration design to solve this problem. This design takes the data path optimization between the inner accelerator and the outer system into consideration and optimizes the data path using techniques like hardware format transformation, frame compression. It also takes fixed-point, new pipeline technique to optimize the inner accelerator. All these make the final system's performance very good, reaching about 10 times the performance comparing with the original system.

World of intelligence defense object detection-machine learning (artificial intelligence)

NASA Astrophysics Data System (ADS)

Gupta, Anitya; Kumar, Akhilesh; Bhushan, Vinayak

2018-04-01

This paper proposes a Quick Locale based Convolutional System strategy (Quick R-CNN) for question recognition. Quick R-CNN expands on past work to effectively characterize ob-ject recommendations utilizing profound convolutional systems. Com-pared to past work, Quick R-CNN utilizes a few in-novations to enhance preparing and testing speed while likewise expanding identification precision. Quick R-CNN trains the profound VGG16 arrange 9 quicker than R-CNN, is 213 speedier at test-time, and accomplishes a higher Guide on PASCAL VOC 2012. Contrasted with SPPnet, Quick R-CNN trains VGG16 3 quicker, tests 10 speedier, and is more exact. Quick R-CNN is actualized in Python and C++ (utilizing Caffe) and is accessible under the open-source MIT Permit.

Anomaly Detection in Nanofibrous Materials by CNN-Based Self-Similarity

PubMed Central

Schettini, Raimondo

2018-01-01

Automatic detection and localization of anomalies in nanofibrous materials help to reduce the cost of the production process and the time of the post-production visual inspection process. Amongst all the monitoring methods, those exploiting Scanning Electron Microscope (SEM) imaging are the most effective. In this paper, we propose a region-based method for the detection and localization of anomalies in SEM images, based on Convolutional Neural Networks (CNNs) and self-similarity. The method evaluates the degree of abnormality of each subregion of an image under consideration by computing a CNN-based visual similarity with respect to a dictionary of anomaly-free subregions belonging to a training set. The proposed method outperforms the state of the art. PMID:29329268

Application of artificial intelligence using a convolutional neural network for detecting gastric cancer in endoscopic images.

PubMed

Hirasawa, Toshiaki; Aoyama, Kazuharu; Tanimoto, Tetsuya; Ishihara, Soichiro; Shichijo, Satoki; Ozawa, Tsuyoshi; Ohnishi, Tatsuya; Fujishiro, Mitsuhiro; Matsuo, Keigo; Fujisaki, Junko; Tada, Tomohiro

2018-07-01

Image recognition using artificial intelligence with deep learning through convolutional neural networks (CNNs) has dramatically improved and been increasingly applied to medical fields for diagnostic imaging. We developed a CNN that can automatically detect gastric cancer in endoscopic images. A CNN-based diagnostic system was constructed based on Single Shot MultiBox Detector architecture and trained using 13,584 endoscopic images of gastric cancer. To evaluate the diagnostic accuracy, an independent test set of 2296 stomach images collected from 69 consecutive patients with 77 gastric cancer lesions was applied to the constructed CNN. The CNN required 47 s to analyze 2296 test images. The CNN correctly diagnosed 71 of 77 gastric cancer lesions with an overall sensitivity of 92.2%, and 161 non-cancerous lesions were detected as gastric cancer, resulting in a positive predictive value of 30.6%. Seventy of the 71 lesions (98.6%) with a diameter of 6 mm or more as well as all invasive cancers were correctly detected. All missed lesions were superficially depressed and differentiated-type intramucosal cancers that were difficult to distinguish from gastritis even for experienced endoscopists. Nearly half of the false-positive lesions were gastritis with changes in color tone or an irregular mucosal surface. The constructed CNN system for detecting gastric cancer could process numerous stored endoscopic images in a very short time with a clinically relevant diagnostic ability. It may be well applicable to daily clinical practice to reduce the burden of endoscopists.

Handwritten dynamics assessment through convolutional neural networks: An application to Parkinson's disease identification.

PubMed

Pereira, Clayton R; Pereira, Danilo R; Rosa, Gustavo H; Albuquerque, Victor H C; Weber, Silke A T; Hook, Christian; Papa, João P

2018-05-01

Parkinson's disease (PD) is considered a degenerative disorder that affects the motor system, which may cause tremors, micrography, and the freezing of gait. Although PD is related to the lack of dopamine, the triggering process of its development is not fully understood yet. In this work, we introduce convolutional neural networks to learn features from images produced by handwritten dynamics, which capture different information during the individual's assessment. Additionally, we make available a dataset composed of images and signal-based data to foster the research related to computer-aided PD diagnosis. The proposed approach was compared against raw data and texture-based descriptors, showing suitable results, mainly in the context of early stage detection, with results nearly to 95%. The analysis of handwritten dynamics using deep learning techniques showed to be useful for automatic Parkinson's disease identification, as well as it can outperform handcrafted features. Copyright © 2018 Elsevier B.V. All rights reserved.

Crowd density estimation based on convolutional neural networks with mixed pooling

NASA Astrophysics Data System (ADS)

Zhang, Li; Zheng, Hong; Zhang, Ying; Zhang, Dongming

2017-09-01

Crowd density estimation is an important topic in the fields of machine learning and video surveillance. Existing methods do not provide satisfactory classification accuracy; moreover, they have difficulty in adapting to complex scenes. Therefore, we propose a method based on convolutional neural networks (CNNs). The proposed method improves performance of crowd density estimation in two key ways. First, we propose a feature pooling method named mixed pooling to regularize the CNNs. It replaces deterministic pooling operations with a parameter that, by studying the algorithm, could combine the conventional max pooling with average pooling methods. Second, we present a classification strategy, in which an image is divided into two cells and respectively categorized. The proposed approach was evaluated on three datasets: two ground truth image sequences and the University of California, San Diego, anomaly detection dataset. The results demonstrate that the proposed approach performs more effectively and easily than other methods.

Automated detection of masses on whole breast volume ultrasound scanner: false positive reduction using deep convolutional neural network

NASA Astrophysics Data System (ADS)

Hiramatsu, Yuya; Muramatsu, Chisako; Kobayashi, Hironobu; Hara, Takeshi; Fujita, Hiroshi

2017-03-01

Breast cancer screening with mammography and ultrasonography is expected to improve sensitivity compared with mammography alone, especially for women with dense breast. An automated breast volume scanner (ABVS) provides the operator-independent whole breast data which facilitate double reading and comparison with past exams, contralateral breast, and multimodality images. However, large volumetric data in screening practice increase radiologists' workload. Therefore, our goal is to develop a computer-aided detection scheme of breast masses in ABVS data for assisting radiologists' diagnosis and comparison with mammographic findings. In this study, false positive (FP) reduction scheme using deep convolutional neural network (DCNN) was investigated. For training DCNN, true positive and FP samples were obtained from the result of our initial mass detection scheme using the vector convergence filter. Regions of interest including the detected regions were extracted from the multiplanar reconstraction slices. We investigated methods to select effective FP samples for training the DCNN. Based on the free response receiver operating characteristic analysis, simple random sampling from the entire candidates was most effective in this study. Using DCNN, the number of FPs could be reduced by 60%, while retaining 90% of true masses. The result indicates the potential usefulness of DCNN for FP reduction in automated mass detection on ABVS images.

Acral melanoma detection using a convolutional neural network for dermoscopy images.

PubMed

Yu, Chanki; Yang, Sejung; Kim, Wonoh; Jung, Jinwoong; Chung, Kee-Yang; Lee, Sang Wook; Oh, Byungho

2018-01-01

Acral melanoma is the most common type of melanoma in Asians, and usually results in a poor prognosis due to late diagnosis. We applied a convolutional neural network to dermoscopy images of acral melanoma and benign nevi on the hands and feet and evaluated its usefulness for the early diagnosis of these conditions. A total of 724 dermoscopy images comprising acral melanoma (350 images from 81 patients) and benign nevi (374 images from 194 patients), and confirmed by histopathological examination, were analyzed in this study. To perform the 2-fold cross validation, we split them into two mutually exclusive subsets: half of the total image dataset was selected for training and the rest for testing, and we calculated the accuracy of diagnosis comparing it with the dermatologist's and non-expert's evaluation. The accuracy (percentage of true positive and true negative from all images) of the convolutional neural network was 83.51% and 80.23%, which was higher than the non-expert's evaluation (67.84%, 62.71%) and close to that of the expert (81.08%, 81.64%). Moreover, the convolutional neural network showed area-under-the-curve values like 0.8, 0.84 and Youden's index like 0.6795, 0.6073, which were similar score with the expert. Although further data analysis is necessary to improve their accuracy, convolutional neural networks would be helpful to detect acral melanoma from dermoscopy images of the hands and feet.

Fully automatic acute ischemic lesion segmentation in DWI using convolutional neural networks.

PubMed

Chen, Liang; Bentley, Paul; Rueckert, Daniel

2017-01-01

Stroke is an acute cerebral vascular disease, which is likely to cause long-term disabilities and death. Acute ischemic lesions occur in most stroke patients. These lesions are treatable under accurate diagnosis and treatments. Although diffusion-weighted MR imaging (DWI) is sensitive to these lesions, localizing and quantifying them manually is costly and challenging for clinicians. In this paper, we propose a novel framework to automatically segment stroke lesions in DWI. Our framework consists of two convolutional neural networks (CNNs): one is an ensemble of two DeconvNets (Noh et al., 2015), which is the EDD Net; the second CNN is the multi-scale convolutional label evaluation net (MUSCLE Net), which aims to evaluate the lesions detected by the EDD Net in order to remove potential false positives. To the best of our knowledge, it is the first attempt to solve this problem and using both CNNs achieves very good results. Furthermore, we study the network architectures and key configurations in detail to ensure the best performance. It is validated on a large dataset comprising clinical acquired DW images from 741 subjects. A mean accuracy of Dice coefficient obtained is 0.67 in total. The mean Dice scores based on subjects with only small and large lesions are 0.61 and 0.83, respectively. The lesion detection rate achieved is 0.94.

On-line bolt-loosening detection method of key components of running trains using binocular vision

NASA Astrophysics Data System (ADS)

Xie, Yanxia; Sun, Junhua

2017-11-01

Bolt loosening, as one of hidden faults, affects the running quality of trains and even causes serious safety accidents. However, the developed fault detection approaches based on two-dimensional images cannot detect bolt-loosening due to lack of depth information. Therefore, we propose a novel online bolt-loosening detection method using binocular vision. Firstly, the target detection model based on convolutional neural network (CNN) is used to locate the target regions. And then, stereo matching and three-dimensional reconstruction are performed to detect bolt-loosening faults. The experimental results show that the looseness of multiple bolts can be characterized by the method simultaneously. The measurement repeatability and precision are less than 0.03mm, 0.09mm respectively, and its relative error is controlled within 1.09%.

Dynamic analysis of nonlinear rotor-housing systems

NASA Technical Reports Server (NTRS)

Noah, Sherif T.

1988-01-01

Nonlinear analysis methods are developed which will enable the reliable prediction of the dynamic behavior of the space shuttle main engine (SSME) turbopumps in the presence of bearing clearances and other local nonlinearities. A computationally efficient convolution method, based on discretized Duhamel and transition matrix integral formulations, is developed for the transient analysis. In the formulation, the coupling forces due to the nonlinearities are treated as external forces acting on the coupled subsystems. Iteration is utilized to determine their magnitudes at each time increment. The method is applied to a nonlinear generic model of the high pressure oxygen turbopump (HPOTP). As compared to the fourth order Runge-Kutta numerical integration methods, the convolution approach proved to be more accurate and more highly efficient. For determining the nonlinear, steady-state periodic responses, an incremental harmonic balance method was also developed. The method was successfully used to determine dominantly harmonic and subharmonic responses fo the HPOTP generic model with bearing clearances. A reduction method similar to the impedance formulation utilized with linear systems is used to reduce the housing-rotor models to their coordinates at the bearing clearances. Recommendations are included for further development of the method, for extending the analysis to aperiodic and chaotic regimes and for conducting critical parameteric studies of the nonlinear response of the current SSME turbopumps.

Dusty Pair Plasma—Wave Propagation and Diffusive Transition of Oscillations

NASA Astrophysics Data System (ADS)

Atamaniuk, Barbara; Turski, Andrzej J.

2011-11-01

The crucial point of the paper is the relation between equilibrium distributions of plasma species and the type of propagation or diffusive transition of plasma response to a disturbance. The paper contains a unified treatment of disturbance propagation (transport) in the linearized Vlasov electron-positron and fullerene pair plasmas containing charged dust impurities, based on the space-time convolution integral equations. Electron-positron-dust/ion (e-p-d/i) plasmas are rather widespread in nature. Space-time responses of multi-component linearized Vlasov plasmas on the basis of multiple integral equations are invoked. An initial-value problem for Vlasov-Poisson/Ampère equations is reduced to the one multiple integral equation and the solution is expressed in terms of forcing function and its space-time convolution with the resolvent kernel. The forcing function is responsible for the initial disturbance and the resolvent is responsible for the equilibrium velocity distributions of plasma species. By use of resolvent equations, time-reversibility, space-reflexivity and the other symmetries are revealed. The symmetries carry on physical properties of Vlasov pair plasmas, e.g., conservation laws. Properly choosing equilibrium distributions for dusty pair plasmas, we can reduce the resolvent equation to: (i) the undamped dispersive wave equations, (ii) and diffusive transport equations of oscillations.

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

Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks.

PubMed

Ren, Shaoqing; He, Kaiming; Girshick, Ross; Sun, Jian

2017-06-01

State-of-the-art object detection networks depend on region proposal algorithms to hypothesize object locations. Advances like SPPnet [1] and Fast R-CNN [2] have reduced the running time of these detection networks, exposing region proposal computation as a bottleneck. In this work, we introduce a Region Proposal Network (RPN) that shares full-image convolutional features with the detection network, thus enabling nearly cost-free region proposals. An RPN is a fully convolutional network that simultaneously predicts object bounds and objectness scores at each position. The RPN is trained end-to-end to generate high-quality region proposals, which are used by Fast R-CNN for detection. We further merge RPN and Fast R-CNN into a single network by sharing their convolutional features-using the recently popular terminology of neural networks with 'attention' mechanisms, the RPN component tells the unified network where to look. For the very deep VGG-16 model [3] , our detection system has a frame rate of 5 fps (including all steps) on a GPU, while achieving state-of-the-art object detection accuracy on PASCAL VOC 2007, 2012, and MS COCO datasets with only 300 proposals per image. In ILSVRC and COCO 2015 competitions, Faster R-CNN and RPN are the foundations of the 1st-place winning entries in several tracks. Code has been made publicly available.

Deep Learning Nuclei Detection in Digitized Histology Images by Superpixels

PubMed Central

Sornapudi, Sudhir; Stanley, Ronald Joe; Stoecker, William V.; Almubarak, Haidar; Long, Rodney; Antani, Sameer; Thoma, George; Zuna, Rosemary; Frazier, Shelliane R.

2018-01-01

Background: Advances in image analysis and computational techniques have facilitated automatic detection of critical features in histopathology images. Detection of nuclei is critical for squamous epithelium cervical intraepithelial neoplasia (CIN) classification into normal, CIN1, CIN2, and CIN3 grades. Methods: In this study, a deep learning (DL)-based nuclei segmentation approach is investigated based on gathering localized information through the generation of superpixels using a simple linear iterative clustering algorithm and training with a convolutional neural network. Results: The proposed approach was evaluated on a dataset of 133 digitized histology images and achieved an overall nuclei detection (object-based) accuracy of 95.97%, with demonstrated improvement over imaging-based and clustering-based benchmark techniques. Conclusions: The proposed DL-based nuclei segmentation Method with superpixel analysis has shown improved segmentation results in comparison to state-of-the-art methods. PMID:29619277

Scalable Track Detection in SAR CCD Images

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

Chow, James G; Quach, Tu-Thach

Existing methods to detect vehicle tracks in coherent change detection images, a product of combining two synthetic aperture radar images ta ken at different times of the same scene, rely on simple, fast models to label track pixels. These models, however, are often too simple to capture natural track features such as continuity and parallelism. We present a simple convolutional network architecture consisting of a series of 3-by-3 convolutions to detect tracks. The network is trained end-to-end to learn natural track features entirely from data. The network is computationally efficient and improves the F-score on a standard dataset to 0.988,more » up fr om 0.907 obtained by the current state-of-the-art method.« less

Deep convolutional neural network for the automated detection and diagnosis of seizure using EEG signals.

PubMed

Acharya, U Rajendra; Oh, Shu Lih; Hagiwara, Yuki; Tan, Jen Hong; Adeli, Hojjat

2017-09-27

An encephalogram (EEG) is a commonly used ancillary test to aide in the diagnosis of epilepsy. The EEG signal contains information about the electrical activity of the brain. Traditionally, neurologists employ direct visual inspection to identify epileptiform abnormalities. This technique can be time-consuming, limited by technical artifact, provides variable results secondary to reader expertise level, and is limited in identifying abnormalities. Therefore, it is essential to develop a computer-aided diagnosis (CAD) system to automatically distinguish the class of these EEG signals using machine learning techniques. This is the first study to employ the convolutional neural network (CNN) for analysis of EEG signals. In this work, a 13-layer deep convolutional neural network (CNN) algorithm is implemented to detect normal, preictal, and seizure classes. The proposed technique achieved an accuracy, specificity, and sensitivity of 88.67%, 90.00% and 95.00%, respectively. Copyright © 2017 Elsevier Ltd. All rights reserved.

Molecular graph convolutions: moving beyond fingerprints

NASA Astrophysics Data System (ADS)

Kearnes, Steven; McCloskey, Kevin; Berndl, Marc; Pande, Vijay; Riley, Patrick

2016-08-01

Molecular "fingerprints" encoding structural information are the workhorse of cheminformatics and machine learning in drug discovery applications. However, fingerprint representations necessarily emphasize particular aspects of the molecular structure while ignoring others, rather than allowing the model to make data-driven decisions. We describe molecular graph convolutions, a machine learning architecture for learning from undirected graphs, specifically small molecules. Graph convolutions use a simple encoding of the molecular graph—atoms, bonds, distances, etc.—which allows the model to take greater advantage of information in the graph structure. Although graph convolutions do not outperform all fingerprint-based methods, they (along with other graph-based methods) represent a new paradigm in ligand-based virtual screening with exciting opportunities for future improvement.

Molecular graph convolutions: moving beyond fingerprints.

PubMed

Kearnes, Steven; McCloskey, Kevin; Berndl, Marc; Pande, Vijay; Riley, Patrick

2016-08-01

Molecular "fingerprints" encoding structural information are the workhorse of cheminformatics and machine learning in drug discovery applications. However, fingerprint representations necessarily emphasize particular aspects of the molecular structure while ignoring others, rather than allowing the model to make data-driven decisions. We describe molecular graph convolutions, a machine learning architecture for learning from undirected graphs, specifically small molecules. Graph convolutions use a simple encoding of the molecular graph-atoms, bonds, distances, etc.-which allows the model to take greater advantage of information in the graph structure. Although graph convolutions do not outperform all fingerprint-based methods, they (along with other graph-based methods) represent a new paradigm in ligand-based virtual screening with exciting opportunities for future improvement.

Robust visual tracking based on deep convolutional neural networks and kernelized correlation filters

NASA Astrophysics Data System (ADS)

Yang, Hua; Zhong, Donghong; Liu, Chenyi; Song, Kaiyou; Yin, Zhouping

2018-03-01

Object tracking is still a challenging problem in computer vision, as it entails learning an effective model to account for appearance changes caused by occlusion, out of view, plane rotation, scale change, and background clutter. This paper proposes a robust visual tracking algorithm called deep convolutional neural network (DCNNCT) to simultaneously address these challenges. The proposed DCNNCT algorithm utilizes a DCNN to extract the image feature of a tracked target, and the full range of information regarding each convolutional layer is used to express the image feature. Subsequently, the kernelized correlation filters (CF) in each convolutional layer are adaptively learned, the correlation response maps of that are combined to estimate the location of the tracked target. To avoid the case of tracking failure, an online random ferns classifier is employed to redetect the tracked target, and a dual-threshold scheme is used to obtain the final target location by comparing the tracking result with the detection result. Finally, the change in scale of the target is determined by building scale pyramids and training a CF. Extensive experiments demonstrate that the proposed algorithm is effective at tracking, especially when evaluated using an index called the overlap rate. The DCNNCT algorithm is also highly competitive in terms of robustness with respect to state-of-the-art trackers in various challenging scenarios.

Deep Learning @15 Petaflops/second: Semi-supervised pattern detection for 15 Terabytes of climate data

NASA Astrophysics Data System (ADS)

Collins, W. D.; Wehner, M. F.; Prabhat, M.; Kurth, T.; Satish, N.; Mitliagkas, I.; Zhang, J.; Racah, E.; Patwary, M.; Sundaram, N.; Dubey, P.

2017-12-01

Anthropogenically-forced climate changes in the number and character of extreme storms have the potential to significantly impact human and natural systems. Current high-performance computing enables multidecadal simulations with global climate models at resolutions of 25km or finer. Such high-resolution simulations are demonstrably superior in simulating extreme storms such as tropical cyclones than the coarser simulations available in the Coupled Model Intercomparison Project (CMIP5) and provide the capability to more credibly project future changes in extreme storm statistics and properties. The identification and tracking of storms in the voluminous model output is very challenging as it is impractical to manually identify storms due to the enormous size of the datasets, and therefore automated procedures are used. Traditionally, these procedures are based on a multi-variate set of physical conditions based on known properties of the class of storms in question. In recent years, we have successfully demonstrated that Deep Learning produces state of the art results for pattern detection in climate data. We have developed supervised and semi-supervised convolutional architectures for detecting and localizing tropical cyclones, extra-tropical cyclones and atmospheric rivers in simulation data. One of the primary challenges in the applicability of Deep Learning to climate data is in the expensive training phase. Typical networks may take days to converge on 10GB-sized datasets, while the climate science community has ready access to O(10 TB)-O(PB) sized datasets. In this work, we present the most scalable implementation of Deep Learning to date. We successfully scale a unified, semi-supervised convolutional architecture on all of the Cori Phase II supercomputer at NERSC. We use IntelCaffe, MKL and MLSL libraries. We have optimized single node MKL libraries to obtain 1-4 TF on single KNL nodes. We have developed a novel hybrid parameter update strategy to improve scaling to 9600 KNL nodes (600,000 cores). We obtain 15PF performance over the course of the training run; setting a new watermark for the HPC and Deep Learning communities. This talk will share insights on how to obtain this extreme level of performance, current gaps/challenges and implications for the climate science community.

Using deep learning in image hyper spectral segmentation, classification, and detection

NASA Astrophysics Data System (ADS)

Zhao, Xiuying; Su, Zhenyu

2018-02-01

Recent years have shown that deep learning neural networks are a valuable tool in the field of computer vision. Deep learning method can be used in applications like remote sensing such as Land cover Classification, Detection of Vehicle in Satellite Images, Hyper spectral Image classification. This paper addresses the use of the deep learning artificial neural network in Satellite image segmentation. Image segmentation plays an important role in image processing. The hue of the remote sensing image often has a large hue difference, which will result in the poor display of the images in the VR environment. Image segmentation is a pre processing technique applied to the original images and splits the image into many parts which have different hue to unify the color. Several computational models based on supervised, unsupervised, parametric, probabilistic region based image segmentation techniques have been proposed. Recently, one of the machine learning technique known as, deep learning with convolution neural network has been widely used for development of efficient and automatic image segmentation models. In this paper, we focus on study of deep neural convolution network and its variants for automatic image segmentation rather than traditional image segmentation strategies.

Lumen-based detection of prostate cancer via convolutional neural networks

NASA Astrophysics Data System (ADS)

Kwak, Jin Tae; Hewitt, Stephen M.

2017-03-01

We present a deep learning approach for detecting prostate cancers. The approach consists of two steps. In the first step, we perform tissue segmentation that identifies lumens within digitized prostate tissue specimen images. Intensity- and texture-based image features are computed at five different scales, and a multiview boosting method is adopted to cooperatively combine the image features from differing scales and to identify lumens. In the second step, we utilize convolutional neural networks (CNN) to automatically extract high-level image features of lumens and to predict cancers. The segmented lumens are rescaled to reduce computational complexity and data augmentation by scaling, rotating, and flipping the rescaled image is applied to avoid overfitting. We evaluate the proposed method using two tissue microarrays (TMA) - TMA1 includes 162 tissue specimens (73 Benign and 89 Cancer) and TMA2 comprises 185 tissue specimens (70 Benign and 115 Cancer). In cross-validation on TMA1, the proposed method achieved an AUC of 0.95 (CI: 0.93-0.98). Trained on TMA1 and tested on TMA2, CNN obtained an AUC of 0.95 (CI: 0.92-0.98). This demonstrates that the proposed method can potentially improve prostate cancer pathology.

An Adaptive Multi-Sensor Data Fusion Method Based on Deep Convolutional Neural Networks for Fault Diagnosis of Planetary Gearbox

PubMed Central

Jing, Luyang; Wang, Taiyong; Zhao, Ming; Wang, Peng

2017-01-01

A fault diagnosis approach based on multi-sensor data fusion is a promising tool to deal with complicated damage detection problems of mechanical systems. Nevertheless, this approach suffers from two challenges, which are (1) the feature extraction from various types of sensory data and (2) the selection of a suitable fusion level. It is usually difficult to choose an optimal feature or fusion level for a specific fault diagnosis task, and extensive domain expertise and human labor are also highly required during these selections. To address these two challenges, we propose an adaptive multi-sensor data fusion method based on deep convolutional neural networks (DCNN) for fault diagnosis. The proposed method can learn features from raw data and optimize a combination of different fusion levels adaptively to satisfy the requirements of any fault diagnosis task. The proposed method is tested through a planetary gearbox test rig. Handcraft features, manual-selected fusion levels, single sensory data, and two traditional intelligent models, back-propagation neural networks (BPNN) and a support vector machine (SVM), are used as comparisons in the experiment. The results demonstrate that the proposed method is able to detect the conditions of the planetary gearbox effectively with the best diagnosis accuracy among all comparative methods in the experiment. PMID:28230767

Collaborative identification method for sea battlefield target based on deep convolutional neural networks

NASA Astrophysics Data System (ADS)

Zheng, Guangdi; Pan, Mingbo; Liu, Wei; Wu, Xuetong

2018-03-01

The target identification of the sea battlefield is the prerequisite for the judgment of the enemy in the modern naval battle. In this paper, a collaborative identification method based on convolution neural network is proposed to identify the typical targets of sea battlefields. Different from the traditional single-input/single-output identification method, the proposed method constructs a multi-input/single-output co-identification architecture based on optimized convolution neural network and weighted D-S evidence theory. The simulation results show that

Molecular graph convolutions: moving beyond fingerprints

PubMed Central

Kearnes, Steven; McCloskey, Kevin; Berndl, Marc; Pande, Vijay; Riley, Patrick

2016-01-01

Molecular “fingerprints” encoding structural information are the workhorse of cheminformatics and machine learning in drug discovery applications. However, fingerprint representations necessarily emphasize particular aspects of the molecular structure while ignoring others, rather than allowing the model to make data-driven decisions. We describe molecular graph convolutions, a machine learning architecture for learning from undirected graphs, specifically small molecules. Graph convolutions use a simple encoding of the molecular graph—atoms, bonds, distances, etc.—which allows the model to take greater advantage of information in the graph structure. Although graph convolutions do not outperform all fingerprint-based methods, they (along with other graph-based methods) represent a new paradigm in ligand-based virtual screening with exciting opportunities for future improvement. PMID:27558503

Microvessel prediction in H&E Stained Pathology Images using fully convolutional neural networks.

PubMed

Yi, Faliu; Yang, Lin; Wang, Shidan; Guo, Lei; Huang, Chenglong; Xie, Yang; Xiao, Guanghua

2018-02-27

Pathological angiogenesis has been identified in many malignancies as a potential prognostic factor and target for therapy. In most cases, angiogenic analysis is based on the measurement of microvessel density (MVD) detected by immunostaining of CD31 or CD34. However, most retrievable public data is generally composed of Hematoxylin and Eosin (H&E)-stained pathology images, for which is difficult to get the corresponding immunohistochemistry images. The role of microvessels in H&E stained images has not been widely studied due to their complexity and heterogeneity. Furthermore, identifying microvessels manually for study is a labor-intensive task for pathologists, with high inter- and intra-observer variation. Therefore, it is important to develop automated microvessel-detection algorithms in H&E stained pathology images for clinical association analysis. In this paper, we propose a microvessel prediction method using fully convolutional neural networks. The feasibility of our proposed algorithm is demonstrated through experimental results on H&E stained images. Furthermore, the identified microvessel features were significantly associated with the patient clinical outcomes. This is the first study to develop an algorithm for automated microvessel detection in H&E stained pathology images.

Deep 3D convolution neural network for CT brain hemorrhage classification

NASA Astrophysics Data System (ADS)

Jnawali, Kamal; Arbabshirani, Mohammad R.; Rao, Navalgund; Patel, Alpen A.

2018-02-01

Intracranial hemorrhage is a critical conditional with the high mortality rate that is typically diagnosed based on head computer tomography (CT) images. Deep learning algorithms, in particular, convolution neural networks (CNN), are becoming the methodology of choice in medical image analysis for a variety of applications such as computer-aided diagnosis, and segmentation. In this study, we propose a fully automated deep learning framework which learns to detect brain hemorrhage based on cross sectional CT images. The dataset for this work consists of 40,367 3D head CT studies (over 1.5 million 2D images) acquired retrospectively over a decade from multiple radiology facilities at Geisinger Health System. The proposed algorithm first extracts features using 3D CNN and then detects brain hemorrhage using the logistic function as the last layer of the network. Finally, we created an ensemble of three different 3D CNN architectures to improve the classification accuracy. The area under the curve (AUC) of the receiver operator characteristic (ROC) curve of the ensemble of three architectures was 0.87. Their results are very promising considering the fact that the head CT studies were not controlled for slice thickness, scanner type, study protocol or any other settings. Moreover, the proposed algorithm reliably detected various types of hemorrhage within the skull. This work is one of the first applications of 3D CNN trained on a large dataset of cross sectional medical images for detection of a critical radiological condition

Enhanced online convolutional neural networks for object tracking

NASA Astrophysics Data System (ADS)

Zhang, Dengzhuo; Gao, Yun; Zhou, Hao; Li, Tianwen

2018-04-01

In recent several years, object tracking based on convolution neural network has gained more and more attention. The initialization and update of convolution filters can directly affect the precision of object tracking effective. In this paper, a novel object tracking via an enhanced online convolution neural network without offline training is proposed, which initializes the convolution filters by a k-means++ algorithm and updates the filters by an error back-propagation. The comparative experiments of 7 trackers on 15 challenging sequences showed that our tracker can perform better than other trackers in terms of AUC and precision.

Convolutional neural network for earthquake detection and location

PubMed Central

Perol, Thibaut; Gharbi, Michaël; Denolle, Marine

2018-01-01

The recent evolution of induced seismicity in Central United States calls for exhaustive catalogs to improve seismic hazard assessment. Over the last decades, the volume of seismic data has increased exponentially, creating a need for efficient algorithms to reliably detect and locate earthquakes. Today’s most elaborate methods scan through the plethora of continuous seismic records, searching for repeating seismic signals. We leverage the recent advances in artificial intelligence and present ConvNetQuake, a highly scalable convolutional neural network for earthquake detection and location from a single waveform. We apply our technique to study the induced seismicity in Oklahoma, USA. We detect more than 17 times more earthquakes than previously cataloged by the Oklahoma Geological Survey. Our algorithm is orders of magnitude faster than established methods. PMID:29487899

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

PubMed Central

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

2017-01-01

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

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

PubMed

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

2017-01-01

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

Detection of prostate cancer on multiparametric MRI

NASA Astrophysics Data System (ADS)

Seah, Jarrel C. Y.; Tang, Jennifer S. N.; Kitchen, Andy

2017-03-01

In this manuscript, we describe our approach and methods to the ProstateX challenge, which achieved an overall AUC of 0.84 and the runner-up position. We train a deep convolutional neural network to classify lesions marked on multiparametric MRI of the prostate as clinically significant or not. We implement a novel addition to the standard convolutional architecture described as auto-windowing which is clinically inspired and designed to overcome some of the difficulties faced in MRI interpretation, where high dynamic ranges and low contrast edges may cause difficulty for traditional convolutional neural networks trained on high contrast natural imagery. We demonstrate that this system can be trained end to end and outperforms a similar architecture without such additions. Although a relatively small training set was provided, we use extensive data augmentation to prevent overfitting and transfer learning to improve convergence speed, showing that deep convolutional neural networks can be feasibly trained on small datasets.

Automated Detection of Craters in Martian Satellite Imagery Using Convolutional Neural Networks

NASA Astrophysics Data System (ADS)

Norman, C. J.; Paxman, J.; Benedix, G. K.; Tan, T.; Bland, P. A.; Towner, M.

2018-04-01

Crater counting is used in determining surface age of planets. We propose improvements to martian Crater Detection Algorithms by implementing an end-to-end detection approach with the possibility of scaling the algorithm planet-wide.

The analysis of convolutional codes via the extended Smith algorithm

NASA Technical Reports Server (NTRS)

Mceliece, R. J.; Onyszchuk, I.

1993-01-01

Convolutional codes have been the central part of most error-control systems in deep-space communication for many years. Almost all such applications, however, have used the restricted class of (n,1), also known as 'rate 1/n,' convolutional codes. The more general class of (n,k) convolutional codes contains many potentially useful codes, but their algebraic theory is difficult and has proved to be a stumbling block in the evolution of convolutional coding systems. In this article, the situation is improved by describing a set of practical algorithms for computing certain basic things about a convolutional code (among them the degree, the Forney indices, a minimal generator matrix, and a parity-check matrix), which are usually needed before a system using the code can be built. The approach is based on the classic Forney theory for convolutional codes, together with the extended Smith algorithm for polynomial matrices, which is introduced in this article.

Pedestrian detection in video surveillance using fully convolutional YOLO neural network

NASA Astrophysics Data System (ADS)

Molchanov, V. V.; Vishnyakov, B. V.; Vizilter, Y. V.; Vishnyakova, O. V.; Knyaz, V. A.

2017-06-01

More than 80% of video surveillance systems are used for monitoring people. Old human detection algorithms, based on background and foreground modelling, could not even deal with a group of people, to say nothing of a crowd. Recent robust and highly effective pedestrian detection algorithms are a new milestone of video surveillance systems. Based on modern approaches in deep learning, these algorithms produce very discriminative features that can be used for getting robust inference in real visual scenes. They deal with such tasks as distinguishing different persons in a group, overcome problem with sufficient enclosures of human bodies by the foreground, detect various poses of people. In our work we use a new approach which enables to combine detection and classification tasks into one challenge using convolution neural networks. As a start point we choose YOLO CNN, whose authors propose a very efficient way of combining mentioned above tasks by learning a single neural network. This approach showed competitive results with state-of-the-art models such as FAST R-CNN, significantly overcoming them in speed, which allows us to apply it in real time video surveillance and other video monitoring systems. Despite all advantages it suffers from some known drawbacks, related to the fully-connected layers that obstruct applying the CNN to images with different resolution. Also it limits the ability to distinguish small close human figures in groups which is crucial for our tasks since we work with rather low quality images which often include dense small groups of people. In this work we gradually change network architecture to overcome mentioned above problems, train it on a complex pedestrian dataset and finally get the CNN detecting small pedestrians in real scenes.

Multiple-Symbol Noncoherent Decoding of Uncoded and Convolutionally Codes Continous Phase Modulation

NASA Technical Reports Server (NTRS)

Divsalar, D.; Raphaeli, D.

2000-01-01

Recently, a method for combined noncoherent detection and decoding of trellis-codes (noncoherent coded modulation) has been proposed, which can practically approach the performance of coherent detection.

Convolution Operation of Optical Information via Quantum Storage

NASA Astrophysics Data System (ADS)

Li, Zhixiang; Liu, Jianji; Fan, Hongming; Zhang, Guoquan

2017-06-01

We proposed a novel method to achieve optical convolution of two input images via quantum storage based on electromagnetically induced transparency (EIT) effect. By placing an EIT media in the confocal Fourier plane of the 4f-imaging system, the optical convolution of the two input images can be achieved in the image plane.

High Performance Implementation of 3D Convolutional Neural Networks on a GPU.

PubMed

Lan, Qiang; Wang, Zelong; Wen, Mei; Zhang, Chunyuan; Wang, Yijie

2017-01-01

Convolutional neural networks have proven to be highly successful in applications such as image classification, object tracking, and many other tasks based on 2D inputs. Recently, researchers have started to apply convolutional neural networks to video classification, which constitutes a 3D input and requires far larger amounts of memory and much more computation. FFT based methods can reduce the amount of computation, but this generally comes at the cost of an increased memory requirement. On the other hand, the Winograd Minimal Filtering Algorithm (WMFA) can reduce the number of operations required and thus can speed up the computation, without increasing the required memory. This strategy was shown to be successful for 2D neural networks. We implement the algorithm for 3D convolutional neural networks and apply it to a popular 3D convolutional neural network which is used to classify videos and compare it to cuDNN. For our highly optimized implementation of the algorithm, we observe a twofold speedup for most of the 3D convolution layers of our test network compared to the cuDNN version.

High Performance Implementation of 3D Convolutional Neural Networks on a GPU

PubMed Central

Wang, Zelong; Wen, Mei; Zhang, Chunyuan; Wang, Yijie

2017-01-01

Convolutional neural networks have proven to be highly successful in applications such as image classification, object tracking, and many other tasks based on 2D inputs. Recently, researchers have started to apply convolutional neural networks to video classification, which constitutes a 3D input and requires far larger amounts of memory and much more computation. FFT based methods can reduce the amount of computation, but this generally comes at the cost of an increased memory requirement. On the other hand, the Winograd Minimal Filtering Algorithm (WMFA) can reduce the number of operations required and thus can speed up the computation, without increasing the required memory. This strategy was shown to be successful for 2D neural networks. We implement the algorithm for 3D convolutional neural networks and apply it to a popular 3D convolutional neural network which is used to classify videos and compare it to cuDNN. For our highly optimized implementation of the algorithm, we observe a twofold speedup for most of the 3D convolution layers of our test network compared to the cuDNN version. PMID:29250109

Squeeze-SegNet: a new fast deep convolutional neural network for semantic segmentation

NASA Astrophysics Data System (ADS)

Nanfack, Geraldin; Elhassouny, Azeddine; Oulad Haj Thami, Rachid

2018-04-01

The recent researches in Deep Convolutional Neural Network have focused their attention on improving accuracy that provide significant advances. However, if they were limited to classification tasks, nowadays with contributions from Scientific Communities who are embarking in this field, they have become very useful in higher level tasks such as object detection and pixel-wise semantic segmentation. Thus, brilliant ideas in the field of semantic segmentation with deep learning have completed the state of the art of accuracy, however this architectures become very difficult to apply in embedded systems as is the case for autonomous driving. We present a new Deep fully Convolutional Neural Network for pixel-wise semantic segmentation which we call Squeeze-SegNet. The architecture is based on Encoder-Decoder style. We use a SqueezeNet-like encoder and a decoder formed by our proposed squeeze-decoder module and upsample layer using downsample indices like in SegNet and we add a deconvolution layer to provide final multi-channel feature map. On datasets like Camvid or City-states, our net gets SegNet-level accuracy with less than 10 times fewer parameters than SegNet.

Thermalnet: a Deep Convolutional Network for Synthetic Thermal Image Generation

NASA Astrophysics Data System (ADS)

Kniaz, V. V.; Gorbatsevich, V. S.; Mizginov, V. A.

2017-05-01

Deep convolutional neural networks have dramatically changed the landscape of the modern computer vision. Nowadays methods based on deep neural networks show the best performance among image recognition and object detection algorithms. While polishing of network architectures received a lot of scholar attention, from the practical point of view the preparation of a large image dataset for a successful training of a neural network became one of major challenges. This challenge is particularly profound for image recognition in wavelengths lying outside the visible spectrum. For example no infrared or radar image datasets large enough for successful training of a deep neural network are available to date in public domain. Recent advances of deep neural networks prove that they are also capable to do arbitrary image transformations such as super-resolution image generation, grayscale image colorisation and imitation of style of a given artist. Thus a natural question arise: how could be deep neural networks used for augmentation of existing large image datasets? This paper is focused on the development of the Thermalnet deep convolutional neural network for augmentation of existing large visible image datasets with synthetic thermal images. The Thermalnet network architecture is inspired by colorisation deep neural networks.

Automated and real-time segmentation of suspicious breast masses using convolutional neural network

PubMed Central

Gregory, Adriana; Denis, Max; Meixner, Duane D.; Bayat, Mahdi; Whaley, Dana H.; Fatemi, Mostafa; Alizad, Azra

2018-01-01

In this work, a computer-aided tool for detection was developed to segment breast masses from clinical ultrasound (US) scans. The underlying Multi U-net algorithm is based on convolutional neural networks. Under the Mayo Clinic Institutional Review Board protocol, a prospective study of the automatic segmentation of suspicious breast masses was performed. The cohort consisted of 258 female patients who were clinically identified with suspicious breast masses and underwent clinical US scan and breast biopsy. The computer-aided detection tool effectively segmented the breast masses, achieving a mean Dice coefficient of 0.82, a true positive fraction (TPF) of 0.84, and a false positive fraction (FPF) of 0.01. By avoiding positioning of an initial seed, the algorithm is able to segment images in real time (13–55 ms per image), and can have potential clinical applications. The algorithm is at par with a conventional seeded algorithm, which had a mean Dice coefficient of 0.84 and performs significantly better (P< 0.0001) than the original U-net algorithm. PMID:29768415

Computer aided detection of ureteral stones in thin slice computed tomography volumes using Convolutional Neural Networks.

PubMed

Längkvist, Martin; Jendeberg, Johan; Thunberg, Per; Loutfi, Amy; Lidén, Mats

2018-06-01

Computed tomography (CT) is the method of choice for diagnosing ureteral stones - kidney stones that obstruct the ureter. The purpose of this study is to develop a computer aided detection (CAD) algorithm for identifying a ureteral stone in thin slice CT volumes. The challenge in CAD for urinary stones lies in the similarity in shape and intensity of stones with non-stone structures and how to efficiently deal with large high-resolution CT volumes. We address these challenges by using a Convolutional Neural Network (CNN) that works directly on the high resolution CT volumes. The method is evaluated on a large data base of 465 clinically acquired high-resolution CT volumes of the urinary tract with labeling of ureteral stones performed by a radiologist. The best model using 2.5D input data and anatomical information achieved a sensitivity of 100% and an average of 2.68 false-positives per patient on a test set of 88 scans. Copyright © 2018 The Authors. Published by Elsevier Ltd.. All rights reserved.

Neonatal Seizure Detection Using Deep Convolutional Neural Networks.

PubMed

Ansari, Amir H; Cherian, Perumpillichira J; Caicedo, Alexander; Naulaers, Gunnar; De Vos, Maarten; Van Huffel, Sabine

2018-04-02

Identifying a core set of features is one of the most important steps in the development of an automated seizure detector. In most of the published studies describing features and seizure classifiers, the features were hand-engineered, which may not be optimal. The main goal of the present paper is using deep convolutional neural networks (CNNs) and random forest to automatically optimize feature selection and classification. The input of the proposed classifier is raw multi-channel EEG and the output is the class label: seizure/nonseizure. By training this network, the required features are optimized, while fitting a nonlinear classifier on the features. After training the network with EEG recordings of 26 neonates, five end layers performing the classification were replaced with a random forest classifier in order to improve the performance. This resulted in a false alarm rate of 0.9 per hour and seizure detection rate of 77% using a test set of EEG recordings of 22 neonates that also included dubious seizures. The newly proposed CNN classifier outperformed three data-driven feature-based approaches and performed similar to a previously developed heuristic method.

Regioselective electrochemical reduction of 2,4-dichlorobiphenyl - Distinct standard reduction potentials for carbon-chlorine bonds using convolution potential sweep voltammetry

NASA Astrophysics Data System (ADS)

Muthukrishnan, A.; Sangaranarayanan, M. V.; Boyarskiy, V. P.; Boyarskaya, I. A.

2010-04-01

The reductive cleavage of carbon-chlorine bonds in 2,4-dichlorobiphenyl (PCB-7) is investigated using the convolution potential sweep voltammetry and quantum chemical calculations. The potential dependence of the logarithmic rate constant is non-linear which indicates the validity of Marcus-Hush theory of quadratic activation-driving force relationship. The ortho-chlorine of the 2,4-dichlorobiphenyl gets reduced first as inferred from the quantum chemical calculations and bulk electrolysis. The standard reduction potentials pertaining to the ortho-chlorine of 2,4-dichlorobiphenyl and that corresponding to para chlorine of the 4-chlorobiphenyl have been estimated.

Detection of bars in galaxies using a deep convolutional neural network

NASA Astrophysics Data System (ADS)

Abraham, Sheelu; Aniyan, A. K.; Kembhavi, Ajit K.; Philip, N. S.; Vaghmare, Kaustubh

2018-06-01

We present an automated method for the detection of bar structure in optical images of galaxies using a deep convolutional neural network that is easy to use and provides good accuracy. In our study, we use a sample of 9346 galaxies in the redshift range of 0.009-0.2 from the Sloan Digital Sky Survey (SDSS), which has 3864 barred galaxies, the rest being unbarred. We reach a top precision of 94 per cent in identifying bars in galaxies using the trained network. This accuracy matches the accuracy reached by human experts on the same data without additional information about the images. Since deep convolutional neural networks can be scaled to handle large volumes of data, the method is expected to have great relevance in an era where astronomy data is rapidly increasing in terms of volume, variety, volatility, and velocity along with other V's that characterize big data. With the trained model, we have constructed a catalogue of barred galaxies from SDSS and made it available online.

Convolutional networks for vehicle track segmentation

NASA Astrophysics Data System (ADS)

Quach, Tu-Thach

2017-10-01

Existing methods to detect vehicle tracks in coherent change detection images, a product of combining two synthetic aperture radar images taken at different times of the same scene, rely on simple and fast models to label track pixels. These models, however, are unable to capture natural track features, such as continuity and parallelism. More powerful but computationally expensive models can be used in offline settings. We present an approach that uses dilated convolutional networks consisting of a series of 3×3 convolutions to segment vehicle tracks. The design of our networks considers the fact that remote sensing applications tend to operate in low power and have limited training data. As a result, we aim for small and efficient networks that can be trained end-to-end to learn natural track features entirely from limited training data. We demonstrate that our six-layer network, trained on just 90 images, is computationally efficient and improves the F-score on a standard dataset to 0.992, up from 0.959 obtained by the current state-of-the-art method.

Seismic signal auto-detecing from different features by using Convolutional Neural Network

NASA Astrophysics Data System (ADS)

Huang, Y.; Zhou, Y.; Yue, H.; Zhou, S.

2017-12-01

We try Convolutional Neural Network to detect some features of seismic data and compare their efficience. The features include whether a signal is seismic signal or noise and the arrival time of P and S phase and each feature correspond to a Convolutional Neural Network. We first use traditional STA/LTA to recongnize some events and then use templete matching to find more events as training set for the Neural Network. To make the training set more various, we add some noise to the seismic data and make some synthetic seismic data and noise. The 3-component raw signal and time-frequancy ananlyze are used as the input data for our neural network. Our Training is performed on GPUs to achieve efficient convergence. Our method improved the precision in comparison with STA/LTA and template matching. We will move to recurrent neural network to see if this kind network is better in detect P and S phase.

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

PubMed

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

2018-04-19

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

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

Acciarri, R.; Adams, C.; An, R.

Here, we present several studies of convolutional neural networks applied to data coming from the MicroBooNE detector, a liquid argon time projection chamber (LArTPC). The algorithms studied include the classification of single particle images, the localization of single particle and neutrino interactions in an image, and the detection of a simulated neutrino event overlaid with cosmic ray backgrounds taken from real detector data. These studies demonstrate the potential of convolutional neural networks for particle identification or event detection on simulated neutrino interactions. Lastly, we also address technical issues that arise when applying this technique to data from a large LArTPCmore » at or near ground level.« less

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

Acciarri, R.; Adams, C.; An, R.

We present several studies of convolutional neural networks applied to data coming from the MicroBooNE detector, a liquid argon time projection chamber (LArTPC). The algorithms studied include the classification of single particle images, the localization of single particle and neutrino interactions in an image, and the detection of a simulated neutrino event overlaid with cosmic ray backgrounds taken from real detector data. These studies demonstrate the potential of convolutional neural networks for particle identification or event detection on simulated neutrino interactions. We also address technical issues that arise when applying this technique to data from a large LArTPC at ormore » near ground level.« less

Magnetic field influences on the lateral dose response functions of photon-beam detectors: MC study of wall-less water-filled detectors with various densities.

PubMed

Looe, Hui Khee; Delfs, Björn; Poppinga, Daniela; Harder, Dietrich; Poppe, Björn

2017-06-21

The distortion of detector reading profiles across photon beams in the presence of magnetic fields is a developing subject of clinical photon-beam dosimetry. The underlying modification by the Lorentz force of a detector's lateral dose response function-the convolution kernel transforming the true cross-beam dose profile in water into the detector reading profile-is here studied for the first time. The three basic convolution kernels, the photon fluence response function, the dose deposition kernel, and the lateral dose response function, of wall-less cylindrical detectors filled with water of low, normal and enhanced density are shown by Monte Carlo simulation to be distorted in the prevailing direction of the Lorentz force. The asymmetric shape changes of these convolution kernels in a water medium and in magnetic fields of up to 1.5 T are confined to the lower millimetre range, and they depend on the photon beam quality, the magnetic flux density and the detector's density. The impact of this distortion on detector reading profiles is demonstrated using a narrow photon beam profile. For clinical applications it appears as favourable that the magnetic flux density dependent distortion of the lateral dose response function, as far as secondary electron transport is concerned, vanishes in the case of water-equivalent detectors of normal water density. By means of secondary electron history backtracing, the spatial distribution of the photon interactions giving rise either directly to secondary electrons or to scattered photons further downstream producing secondary electrons which contribute to the detector's signal, and their lateral shift due to the Lorentz force is elucidated. Electron history backtracing also serves to illustrate the correct treatment of the influences of the Lorentz force in the EGSnrc Monte Carlo code applied in this study.

Convolutional Neural Networks for 1-D Many-Channel Data

DTIC Science & Technology

Deep convolutional neural networks (CNNs) represent the state of the art in image recognition. The same properties that led to their success in that... crack detection ( 8,000 data points, 72 channels). Though the models predictive ability is limited to fitting the trend , its partial success suggests that...originally written to classify digits in the MNIST database (28 28 pixels, 1 channel), for use on 1-D acoustic data taken from experiments focused on

Fast space-varying convolution using matrix source coding with applications to camera stray light reduction.

PubMed

Wei, Jianing; Bouman, Charles A; Allebach, Jan P

2014-05-01

Many imaging applications require the implementation of space-varying convolution for accurate restoration and reconstruction of images. Here, we use the term space-varying convolution to refer to linear operators whose impulse response has slow spatial variation. In addition, these space-varying convolution operators are often dense, so direct implementation of the convolution operator is typically computationally impractical. One such example is the problem of stray light reduction in digital cameras, which requires the implementation of a dense space-varying deconvolution operator. However, other inverse problems, such as iterative tomographic reconstruction, can also depend on the implementation of dense space-varying convolution. While space-invariant convolution can be efficiently implemented with the fast Fourier transform, this approach does not work for space-varying operators. So direct convolution is often the only option for implementing space-varying convolution. In this paper, we develop a general approach to the efficient implementation of space-varying convolution, and demonstrate its use in the application of stray light reduction. Our approach, which we call matrix source coding, is based on lossy source coding of the dense space-varying convolution matrix. Importantly, by coding the transformation matrix, we not only reduce the memory required to store it; we also dramatically reduce the computation required to implement matrix-vector products. Our algorithm is able to reduce computation by approximately factoring the dense space-varying convolution operator into a product of sparse transforms. Experimental results show that our method can dramatically reduce the computation required for stray light reduction while maintaining high accuracy.

Protograph-Based Raptor-Like Codes

NASA Technical Reports Server (NTRS)

Divsalar, Dariush; Chen, Tsung-Yi; Wang, Jiadong; Wesel, Richard D.

2014-01-01

Theoretical analysis has long indicated that feedback improves the error exponent but not the capacity of pointto- point memoryless channels. The analytic and empirical results indicate that at short blocklength regime, practical rate-compatible punctured convolutional (RCPC) codes achieve low latency with the use of noiseless feedback. In 3GPP, standard rate-compatible turbo codes (RCPT) did not outperform the convolutional codes in the short blocklength regime. The reason is the convolutional codes for low number of states can be decoded optimally using Viterbi decoder. Despite excellent performance of convolutional codes at very short blocklengths, the strength of convolutional codes does not scale with the blocklength for a fixed number of states in its trellis.

Real time coarse orientation detection in MR scans using multi-planar deep convolutional neural networks

NASA Astrophysics Data System (ADS)

Bhatia, Parmeet S.; Reda, Fitsum; Harder, Martin; Zhan, Yiqiang; Zhou, Xiang Sean

2017-02-01

Automatically detecting anatomy orientation is an important task in medical image analysis. Specifically, the ability to automatically detect coarse orientation of structures is useful to minimize the effort of fine/accurate orientation detection algorithms, to initialize non-rigid deformable registration algorithms or to align models to target structures in model-based segmentation algorithms. In this work, we present a deep convolution neural network (DCNN)-based method for fast and robust detection of the coarse structure orientation, i.e., the hemi-sphere where the principal axis of a structure lies. That is, our algorithm predicts whether the principal orientation of a structure is in the northern hemisphere or southern hemisphere, which we will refer to as UP and DOWN, respectively, in the remainder of this manuscript. The only assumption of our method is that the entire structure is located within the scan's field-of-view (FOV). To efficiently solve the problem in 3D space, we formulated it as a multi-planar 2D deep learning problem. In the training stage, a large number coronal-sagittal slice pairs are constructed as 2-channel images to train a DCNN to classify whether a scan is UP or DOWN. During testing, we randomly sample a small number of coronal-sagittal 2-channel images and pass them through our trained network. Finally, coarse structure orientation is determined using majority voting. We tested our method on 114 Elbow MR Scans. Experimental results suggest that only five 2-channel images are sufficient to achieve a high success rate of 97.39%. Our method is also extremely fast and takes approximately 50 milliseconds per 3D MR scan. Our method is insensitive to the location of the structure in the FOV.

Automatic pedicles detection using convolutional neural network in a 3D spine reconstruction from biplanar radiographs

NASA Astrophysics Data System (ADS)

Bakhous, Christine; Aubert, Benjamin; Vazquez, Carlos; Cresson, Thierry; Parent, Stefan; De Guise, Jacques

2018-02-01

The 3D analysis of the spine deformities (scoliosis) has a high potential in its clinical diagnosis and treatment. In a biplanar radiographs context, a 3D analysis requires a 3D reconstruction from a pair of 2D X-rays. Whether being fully-/semiautomatic or manual, this task is complex because of the noise, the structure superimposition and partial information due to a limited projections number. Being involved in the axial vertebra rotation (AVR), which is a fundamental clinical parameter for scoliosis diagnosis, pedicles are important landmarks for the 3D spine modeling and pre-operative planning. In this paper, we focus on the extension of a fully-automatic 3D spine reconstruction method where the Vertebral Body Centers (VBCs) are automatically detected using Convolutional Neural Network (CNN) and then regularized using a Statistical Shape Model (SSM) framework. In this global process, pedicles are inferred statistically during the SSM regularization. Our contribution is to add a CNN-based regression model for pedicle detection allowing a better pedicle localization and improving the clinical parameters estimation (e.g. AVR, Cobb angle). Having 476 datasets including healthy patients and Adolescent Idiopathic Scoliosis (AIS) cases with different scoliosis grades (Cobb angles up to 116°), we used 380 for training, 48 for testing and 48 for validation. Adding the local CNN-based pedicle detection decreases the mean absolute error of the AVR by 10%. The 3D mean Euclidian distance error between detected pedicles and ground truth decreases by 17% and the maximum error by 19%. Moreover, a general improvement is observed in the 3D spine reconstruction and reflected in lower errors on the Cobb angle estimation.

Convolutional neural networks for transient candidate vetting in large-scale surveys

NASA Astrophysics Data System (ADS)

Gieseke, Fabian; Bloemen, Steven; van den Bogaard, Cas; Heskes, Tom; Kindler, Jonas; Scalzo, Richard A.; Ribeiro, Valério A. R. M.; van Roestel, Jan; Groot, Paul J.; Yuan, Fang; Möller, Anais; Tucker, Brad E.

2017-12-01

Current synoptic sky surveys monitor large areas of the sky to find variable and transient astronomical sources. As the number of detections per night at a single telescope easily exceeds several thousand, current detection pipelines make intensive use of machine learning algorithms to classify the detected objects and to filter out the most interesting candidates. A number of upcoming surveys will produce up to three orders of magnitude more data, which renders high-precision classification systems essential to reduce the manual and, hence, expensive vetting by human experts. We present an approach based on convolutional neural networks to discriminate between true astrophysical sources and artefacts in reference-subtracted optical images. We show that relatively simple networks are already competitive with state-of-the-art systems and that their quality can further be improved via slightly deeper networks and additional pre-processing steps - eventually yielding models outperforming state-of-the-art systems. In particular, our best model correctly classifies about 97.3 per cent of all 'real' and 99.7 per cent of all 'bogus' instances on a test set containing 1942 'bogus' and 227 'real' instances in total. Furthermore, the networks considered in this work can also successfully classify these objects at hand without relying on difference images, which might pave the way for future detection pipelines not containing image subtraction steps at all.

Performance Bounds on Two Concatenated, Interleaved Codes

NASA Technical Reports Server (NTRS)

Moision, Bruce; Dolinar, Samuel

2010-01-01

A method has been developed of computing bounds on the performance of a code comprised of two linear binary codes generated by two encoders serially concatenated through an interleaver. Originally intended for use in evaluating the performances of some codes proposed for deep-space communication links, the method can also be used in evaluating the performances of short-block-length codes in other applications. The method applies, more specifically, to a communication system in which following processes take place: At the transmitter, the original binary information that one seeks to transmit is first processed by an encoder into an outer code (Co) characterized by, among other things, a pair of numbers (n,k), where n (n > k)is the total number of code bits associated with k information bits and n k bits are used for correcting or at least detecting errors. Next, the outer code is processed through either a block or a convolutional interleaver. In the block interleaver, the words of the outer code are processed in blocks of I words. In the convolutional interleaver, the interleaving operation is performed bit-wise in N rows with delays that are multiples of B bits. The output of the interleaver is processed through a second encoder to obtain an inner code (Ci) characterized by (ni,ki). The output of the inner code is transmitted over an additive-white-Gaussian- noise channel characterized by a symbol signal-to-noise ratio (SNR) Es/No and a bit SNR Eb/No. At the receiver, an inner decoder generates estimates of bits. Depending on whether a block or a convolutional interleaver is used at the transmitter, the sequence of estimated bits is processed through a block or a convolutional de-interleaver, respectively, to obtain estimates of code words. Then the estimates of the code words are processed through an outer decoder, which generates estimates of the original information along with flags indicating which estimates are presumed to be correct and which are found to be erroneous. From the perspective of the present method, the topic of major interest is the performance of the communication system as quantified in the word-error rate and the undetected-error rate as functions of the SNRs and the total latency of the interleaver and inner code. The method is embodied in equations that describe bounds on these functions. Throughout the derivation of the equations that embody the method, it is assumed that the decoder for the outer code corrects any error pattern of t or fewer errors, detects any error pattern of s or fewer errors, may detect some error patterns of more than s errors, and does not correct any patterns of more than t errors. Because a mathematically complete description of the equations that embody the method and of the derivation of the equations would greatly exceed the space available for this article, it must suffice to summarize by reporting that the derivation includes consideration of several complex issues, including relationships between latency and memory requirements for block and convolutional codes, burst error statistics, enumeration of error-event intersections, and effects of different interleaving depths. In a demonstration, the method was used to calculate bounds on the performances of several communication systems, each based on serial concatenation of a (63,56) expurgated Hamming code with a convolutional inner code through a convolutional interleaver. The bounds calculated by use of the method were compared with results of numerical simulations of performances of the systems to show the regions where the bounds are tight (see figure).

Person detection, tracking and following using stereo camera

NASA Astrophysics Data System (ADS)

Wang, Xiaofeng; Zhang, Lilian; Wang, Duo; Hu, Xiaoping

2018-04-01

Person detection, tracking and following is a key enabling technology for mobile robots in many human-robot interaction applications. In this article, we present a system which is composed of visual human detection, video tracking and following. The detection is based on YOLO(You only look once), which applies a single convolution neural network(CNN) to the full image, thus can predict bounding boxes and class probabilities directly in one evaluation. Then the bounding box provides initial person position in image to initialize and train the KCF(Kernelized Correlation Filter), which is a video tracker based on discriminative classifier. At last, by using a stereo 3D sparse reconstruction algorithm, not only the position of the person in the scene is determined, but also it can elegantly solve the problem of scale ambiguity in the video tracker. Extensive experiments are conducted to demonstrate the effectiveness and robustness of our human detection and tracking system.

Applications of deep convolutional neural networks to digitized natural history collections.

PubMed

Schuettpelz, Eric; Frandsen, Paul B; Dikow, Rebecca B; Brown, Abel; Orli, Sylvia; Peters, Melinda; Metallo, Adam; Funk, Vicki A; Dorr, Laurence J

2017-01-01

Natural history collections contain data that are critical for many scientific endeavors. Recent efforts in mass digitization are generating large datasets from these collections that can provide unprecedented insight. Here, we present examples of how deep convolutional neural networks can be applied in analyses of imaged herbarium specimens. We first demonstrate that a convolutional neural network can detect mercury-stained specimens across a collection with 90% accuracy. We then show that such a network can correctly distinguish two morphologically similar plant families 96% of the time. Discarding the most challenging specimen images increases accuracy to 94% and 99%, respectively. These results highlight the importance of mass digitization and deep learning approaches and reveal how they can together deliver powerful new investigative tools.

ASIC-based architecture for the real-time computation of 2D convolution with large kernel size

NASA Astrophysics Data System (ADS)

Shao, Rui; Zhong, Sheng; Yan, Luxin

2015-12-01

Bidimensional convolution is a low-level processing algorithm of interest in many areas, but its high computational cost constrains the size of the kernels, especially in real-time embedded systems. This paper presents a hardware architecture for the ASIC-based implementation of 2-D convolution with medium-large kernels. Aiming to improve the efficiency of storage resources on-chip, reducing off-chip bandwidth of these two issues, proposed construction of a data cache reuse. Multi-block SPRAM to cross cached images and the on-chip ping-pong operation takes full advantage of the data convolution calculation reuse, design a new ASIC data scheduling scheme and overall architecture. Experimental results show that the structure can achieve 40× 32 size of template real-time convolution operations, and improve the utilization of on-chip memory bandwidth and on-chip memory resources, the experimental results show that the structure satisfies the conditions to maximize data throughput output , reducing the need for off-chip memory bandwidth.

Automatic lung nodule graph cuts segmentation with deep learning false positive reduction

NASA Astrophysics Data System (ADS)

Sun, Wenqing; Huang, Xia; Tseng, Tzu-Liang Bill; Qian, Wei

2017-03-01

To automatic detect lung nodules from CT images, we designed a two stage computer aided detection (CAD) system. The first stage is graph cuts segmentation to identify and segment the nodule candidates, and the second stage is convolutional neural network for false positive reduction. The dataset contains 595 CT cases randomly selected from Lung Image Database Consortium and Image Database Resource Initiative (LIDC/IDRI) and the 305 pulmonary nodules achieved diagnosis consensus by all four experienced radiologists were our detection targets. Consider each slice as an individual sample, 2844 nodules were included in our database. The graph cuts segmentation was conducted in a two-dimension manner, 2733 lung nodule ROIs are successfully identified and segmented. With a false positive reduction by a seven-layer convolutional neural network, 2535 nodules remain detected while the false positive dropped to 31.6%. The average F-measure of segmented lung nodule tissue is 0.8501.

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

NASA Astrophysics Data System (ADS)

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

2017-03-01

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

Two-phase deep convolutional neural network for reducing class skewness in histopathological images based breast cancer detection.

PubMed

Wahab, Noorul; Khan, Asifullah; Lee, Yeon Soo

2017-06-01

Different types of breast cancer are affecting lives of women across the world. Common types include Ductal carcinoma in situ (DCIS), Invasive ductal carcinoma (IDC), Tubular carcinoma, Medullary carcinoma, and Invasive lobular carcinoma (ILC). While detecting cancer, one important factor is mitotic count - showing how rapidly the cells are dividing. But the class imbalance problem, due to the small number of mitotic nuclei in comparison to the overwhelming number of non-mitotic nuclei, affects the performance of classification models. This work presents a two-phase model to mitigate the class biasness issue while classifying mitotic and non-mitotic nuclei in breast cancer histopathology images through a deep convolutional neural network (CNN). First, nuclei are segmented out using blue ratio and global binary thresholding. In Phase-1 a CNN is then trained on the segmented out 80×80 pixel patches based on a standard dataset. Hard non-mitotic examples are identified and augmented; mitotic examples are oversampled by rotation and flipping; whereas non-mitotic examples are undersampled by blue ratio histogram based k-means clustering. Based on this information from Phase-1, the dataset is modified for Phase-2 in order to reduce the effects of class imbalance. The proposed CNN architecture and data balancing technique yielded an F-measure of 0.79, and outperformed all the methods relying on specific handcrafted features, as well as those using a combination of handcrafted and CNN-generated features. Copyright © 2017 Elsevier Ltd. All rights reserved.

Tracking-by-detection of surgical instruments in minimally invasive surgery via the convolutional neural network deep learning-based method.

PubMed

Zhao, Zijian; Voros, Sandrine; Weng, Ying; Chang, Faliang; Li, Ruijian

2017-12-01

Worldwide propagation of minimally invasive surgeries (MIS) is hindered by their drawback of indirect observation and manipulation, while monitoring of surgical instruments moving in the operated body required by surgeons is a challenging problem. Tracking of surgical instruments by vision-based methods is quite lucrative, due to its flexible implementation via software-based control with no need to modify instruments or surgical workflow. A MIS instrument is conventionally split into a shaft and end-effector portions, while a 2D/3D tracking-by-detection framework is proposed, which performs the shaft tracking followed by the end-effector one. The former portion is described by line features via the RANSAC scheme, while the latter is depicted by special image features based on deep learning through a well-trained convolutional neural network. The method verification in 2D and 3D formulation is performed through the experiments on ex-vivo video sequences, while qualitative validation on in-vivo video sequences is obtained. The proposed method provides robust and accurate tracking, which is confirmed by the experimental results: its 3D performance in ex-vivo video sequences exceeds those of the available state-of -the-art methods. Moreover, the experiments on in-vivo sequences demonstrate that the proposed method can tackle the difficult condition of tracking with unknown camera parameters. Further refinements of the method will refer to the occlusion and multi-instrumental MIS applications.

Automatic Fabric Defect Detection with a Multi-Scale Convolutional Denoising Autoencoder Network Model.

PubMed

Mei, Shuang; Wang, Yudan; Wen, Guojun

2018-04-02

Fabric defect detection is a necessary and essential step of quality control in the textile manufacturing industry. Traditional fabric inspections are usually performed by manual visual methods, which are low in efficiency and poor in precision for long-term industrial applications. In this paper, we propose an unsupervised learning-based automated approach to detect and localize fabric defects without any manual intervention. This approach is used to reconstruct image patches with a convolutional denoising autoencoder network at multiple Gaussian pyramid levels and to synthesize detection results from the corresponding resolution channels. The reconstruction residual of each image patch is used as the indicator for direct pixel-wise prediction. By segmenting and synthesizing the reconstruction residual map at each resolution level, the final inspection result can be generated. This newly developed method has several prominent advantages for fabric defect detection. First, it can be trained with only a small amount of defect-free samples. This is especially important for situations in which collecting large amounts of defective samples is difficult and impracticable. Second, owing to the multi-modal integration strategy, it is relatively more robust and accurate compared to general inspection methods (the results at each resolution level can be viewed as a modality). Third, according to our results, it can address multiple types of textile fabrics, from simple to more complex. Experimental results demonstrate that the proposed model is robust and yields good overall performance with high precision and acceptable recall rates.

A Robust Deep-Learning-Based Detector for Real-Time Tomato Plant Diseases and Pests Recognition.

PubMed

Fuentes, Alvaro; Yoon, Sook; Kim, Sang Cheol; Park, Dong Sun

2017-09-04

Plant Diseases and Pests are a major challenge in the agriculture sector. An accurate and a faster detection of diseases and pests in plants could help to develop an early treatment technique while substantially reducing economic losses. Recent developments in Deep Neural Networks have allowed researchers to drastically improve the accuracy of object detection and recognition systems. In this paper, we present a deep-learning-based approach to detect diseases and pests in tomato plants using images captured in-place by camera devices with various resolutions. Our goal is to find the more suitable deep-learning architecture for our task. Therefore, we consider three main families of detectors: Faster Region-based Convolutional Neural Network (Faster R-CNN), Region-based Fully Convolutional Network (R-FCN), and Single Shot Multibox Detector (SSD), which for the purpose of this work are called "deep learning meta-architectures". We combine each of these meta-architectures with "deep feature extractors" such as VGG net and Residual Network (ResNet). We demonstrate the performance of deep meta-architectures and feature extractors, and additionally propose a method for local and global class annotation and data augmentation to increase the accuracy and reduce the number of false positives during training. We train and test our systems end-to-end on our large Tomato Diseases and Pests Dataset, which contains challenging images with diseases and pests, including several inter- and extra-class variations, such as infection status and location in the plant. Experimental results show that our proposed system can effectively recognize nine different types of diseases and pests, with the ability to deal with complex scenarios from a plant's surrounding area.

A Robust Deep-Learning-Based Detector for Real-Time Tomato Plant Diseases and Pests Recognition

PubMed Central

Yoon, Sook; Kim, Sang Cheol; Park, Dong Sun

2017-01-01

Plant Diseases and Pests are a major challenge in the agriculture sector. An accurate and a faster detection of diseases and pests in plants could help to develop an early treatment technique while substantially reducing economic losses. Recent developments in Deep Neural Networks have allowed researchers to drastically improve the accuracy of object detection and recognition systems. In this paper, we present a deep-learning-based approach to detect diseases and pests in tomato plants using images captured in-place by camera devices with various resolutions. Our goal is to find the more suitable deep-learning architecture for our task. Therefore, we consider three main families of detectors: Faster Region-based Convolutional Neural Network (Faster R-CNN), Region-based Fully Convolutional Network (R-FCN), and Single Shot Multibox Detector (SSD), which for the purpose of this work are called “deep learning meta-architectures”. We combine each of these meta-architectures with “deep feature extractors” such as VGG net and Residual Network (ResNet). We demonstrate the performance of deep meta-architectures and feature extractors, and additionally propose a method for local and global class annotation and data augmentation to increase the accuracy and reduce the number of false positives during training. We train and test our systems end-to-end on our large Tomato Diseases and Pests Dataset, which contains challenging images with diseases and pests, including several inter- and extra-class variations, such as infection status and location in the plant. Experimental results show that our proposed system can effectively recognize nine different types of diseases and pests, with the ability to deal with complex scenarios from a plant’s surrounding area. PMID:28869539

A FFT-based formulation for discrete dislocation dynamics in heterogeneous media

NASA Astrophysics Data System (ADS)

Bertin, N.; Capolungo, L.

2018-02-01

In this paper, an extension of the DDD-FFT approach presented in [1] is developed for heterogeneous elasticity. For such a purpose, an iterative spectral formulation in which convolutions are calculated in the Fourier space is developed to solve for the mechanical state associated with the discrete eigenstrain-based microstructural representation. With this, the heterogeneous DDD-FFT approach is capable of treating anisotropic and heterogeneous elasticity in a computationally efficient manner. In addition, a GPU implementation is presented to allow for further acceleration. As a first example, the approach is used to investigate the interaction between dislocations and second-phase particles, thereby demonstrating its ability to inherently incorporate image forces arising from elastic inhomogeneities.

The DTIC Review. Volume 2, Number 3: Optical and Infrared Detection and Countermeasures

DTIC Science & Technology

1996-10-01

are different from those en- countered in designing wavelets for other applications. For use in time- frequency analysis of signals, for example, it...view within the field of regard, and for high -fidelity simulation of optical blurring and temporal effects such as jitter. The real-time CLDWSG method ...integration methods or, for near spatially invariant FOV regions, by convolution methods or by way of the convolution theorem using OTF frequency -domain

Detection of high-grade small bowel obstruction on conventional radiography with convolutional neural networks.

PubMed

Cheng, Phillip M; Tejura, Tapas K; Tran, Khoa N; Whang, Gilbert

2018-05-01

The purpose of this pilot study is to determine whether a deep convolutional neural network can be trained with limited image data to detect high-grade small bowel obstruction patterns on supine abdominal radiographs. Grayscale images from 3663 clinical supine abdominal radiographs were categorized into obstructive and non-obstructive categories independently by three abdominal radiologists, and the majority classification was used as ground truth; 74 images were found to be consistent with small bowel obstruction. Images were rescaled and randomized, with 2210 images constituting the training set (39 with small bowel obstruction) and 1453 images constituting the test set (35 with small bowel obstruction). Weight parameters for the final classification layer of the Inception v3 convolutional neural network, previously trained on the 2014 Large Scale Visual Recognition Challenge dataset, were retrained on the training set. After training, the neural network achieved an AUC of 0.84 on the test set (95% CI 0.78-0.89). At the maximum Youden index (sensitivity + specificity-1), the sensitivity of the system for small bowel obstruction is 83.8%, with a specificity of 68.1%. The results demonstrate that transfer learning with convolutional neural networks, even with limited training data, may be used to train a detector for high-grade small bowel obstruction gas patterns on supine radiographs.

Convolutional Neural Network-Based Robot Navigation Using Uncalibrated Spherical Images †

PubMed Central

Ran, Lingyan; Zhang, Yanning; Zhang, Qilin; Yang, Tao

2017-01-01

Vision-based mobile robot navigation is a vibrant area of research with numerous algorithms having been developed, the vast majority of which either belong to the scene-oriented simultaneous localization and mapping (SLAM) or fall into the category of robot-oriented lane-detection/trajectory tracking. These methods suffer from high computational cost and require stringent labelling and calibration efforts. To address these challenges, this paper proposes a lightweight robot navigation framework based purely on uncalibrated spherical images. To simplify the orientation estimation, path prediction and improve computational efficiency, the navigation problem is decomposed into a series of classification tasks. To mitigate the adverse effects of insufficient negative samples in the “navigation via classification” task, we introduce the spherical camera for scene capturing, which enables 360° fisheye panorama as training samples and generation of sufficient positive and negative heading directions. The classification is implemented as an end-to-end Convolutional Neural Network (CNN), trained on our proposed Spherical-Navi image dataset, whose category labels can be efficiently collected. This CNN is capable of predicting potential path directions with high confidence levels based on a single, uncalibrated spherical image. Experimental results demonstrate that the proposed framework outperforms competing ones in realistic applications. PMID:28604624

An Automatic Diagnosis Method of Facial Acne Vulgaris Based on Convolutional Neural Network.

PubMed

Shen, Xiaolei; Zhang, Jiachi; Yan, Chenjun; Zhou, Hong

2018-04-11

In this paper, we present a new automatic diagnosis method for facial acne vulgaris which is based on convolutional neural networks (CNNs). To overcome the shortcomings of previous methods which were the inability to classify enough types of acne vulgaris. The core of our method is to extract features of images based on CNNs and achieve classification by classifier. A binary-classifier of skin-and-non-skin is used to detect skin area and a seven-classifier is used to achieve the classification task of facial acne vulgaris and healthy skin. In the experiments, we compare the effectiveness of our CNN and the VGG16 neural network which is pre-trained on the ImageNet data set. We use a ROC curve to evaluate the performance of binary-classifier and use a normalized confusion matrix to evaluate the performance of seven-classifier. The results of our experiments show that the pre-trained VGG16 neural network is effective in extracting features from facial acne vulgaris images. And the features are very useful for the follow-up classifiers. Finally, we try applying the classifiers both based on the pre-trained VGG16 neural network to assist doctors in facial acne vulgaris diagnosis.

Convolutional Neural Network-Based Robot Navigation Using Uncalibrated Spherical Images.

PubMed

Ran, Lingyan; Zhang, Yanning; Zhang, Qilin; Yang, Tao

2017-06-12

Vision-based mobile robot navigation is a vibrant area of research with numerous algorithms having been developed, the vast majority of which either belong to the scene-oriented simultaneous localization and mapping (SLAM) or fall into the category of robot-oriented lane-detection/trajectory tracking. These methods suffer from high computational cost and require stringent labelling and calibration efforts. To address these challenges, this paper proposes a lightweight robot navigation framework based purely on uncalibrated spherical images. To simplify the orientation estimation, path prediction and improve computational efficiency, the navigation problem is decomposed into a series of classification tasks. To mitigate the adverse effects of insufficient negative samples in the "navigation via classification" task, we introduce the spherical camera for scene capturing, which enables 360° fisheye panorama as training samples and generation of sufficient positive and negative heading directions. The classification is implemented as an end-to-end Convolutional Neural Network (CNN), trained on our proposed Spherical-Navi image dataset, whose category labels can be efficiently collected. This CNN is capable of predicting potential path directions with high confidence levels based on a single, uncalibrated spherical image. Experimental results demonstrate that the proposed framework outperforms competing ones in realistic applications.

A comparison study between MLP and convolutional neural network models for character recognition

NASA Astrophysics Data System (ADS)

Ben Driss, S.; Soua, M.; Kachouri, R.; Akil, M.

2017-05-01

Optical Character Recognition (OCR) systems have been designed to operate on text contained in scanned documents and images. They include text detection and character recognition in which characters are described then classified. In the classification step, characters are identified according to their features or template descriptions. Then, a given classifier is employed to identify characters. In this context, we have proposed the unified character descriptor (UCD) to represent characters based on their features. Then, matching was employed to ensure the classification. This recognition scheme performs a good OCR Accuracy on homogeneous scanned documents, however it cannot discriminate characters with high font variation and distortion.3 To improve recognition, classifiers based on neural networks can be used. The multilayer perceptron (MLP) ensures high recognition accuracy when performing a robust training. Moreover, the convolutional neural network (CNN), is gaining nowadays a lot of popularity for its high performance. Furthermore, both CNN and MLP may suffer from the large amount of computation in the training phase. In this paper, we establish a comparison between MLP and CNN. We provide MLP with the UCD descriptor and the appropriate network configuration. For CNN, we employ the convolutional network designed for handwritten and machine-printed character recognition (Lenet-5) and we adapt it to support 62 classes, including both digits and characters. In addition, GPU parallelization is studied to speed up both of MLP and CNN classifiers. Based on our experimentations, we demonstrate that the used real-time CNN is 2x more relevant than MLP when classifying characters.

Automated detection of pulmonary nodules in PET/CT images: Ensemble false-positive reduction using a convolutional neural network technique

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

Teramoto, Atsushi, E-mail: teramoto@fujita-hu.ac.jp; Fujita, Hiroshi; Yamamuro, Osamu

Purpose: Automated detection of solitary pulmonary nodules using positron emission tomography (PET) and computed tomography (CT) images shows good sensitivity; however, it is difficult to detect nodules in contact with normal organs, and additional efforts are needed so that the number of false positives (FPs) can be further reduced. In this paper, the authors propose an improved FP-reduction method for the detection of pulmonary nodules in PET/CT images by means of convolutional neural networks (CNNs). Methods: The overall scheme detects pulmonary nodules using both CT and PET images. In the CT images, a massive region is first detected using anmore » active contour filter, which is a type of contrast enhancement filter that has a deformable kernel shape. Subsequently, high-uptake regions detected by the PET images are merged with the regions detected by the CT images. FP candidates are eliminated using an ensemble method; it consists of two feature extractions, one by shape/metabolic feature analysis and the other by a CNN, followed by a two-step classifier, one step being rule based and the other being based on support vector machines. Results: The authors evaluated the detection performance using 104 PET/CT images collected by a cancer-screening program. The sensitivity in detecting candidates at an initial stage was 97.2%, with 72.8 FPs/case. After performing the proposed FP-reduction method, the sensitivity of detection was 90.1%, with 4.9 FPs/case; the proposed method eliminated approximately half the FPs existing in the previous study. Conclusions: An improved FP-reduction scheme using CNN technique has been developed for the detection of pulmonary nodules in PET/CT images. The authors’ ensemble FP-reduction method eliminated 93% of the FPs; their proposed method using CNN technique eliminates approximately half the FPs existing in the previous study. These results indicate that their method may be useful in the computer-aided detection of pulmonary nodules using PET/CT images.« less

Novel vehicle detection system based on stacked DoG kernel and AdaBoost

PubMed Central

Kang, Hyun Ho; Lee, Seo Won; You, Sung Hyun

2018-01-01

This paper proposes a novel vehicle detection system that can overcome some limitations of typical vehicle detection systems using AdaBoost-based methods. The performance of the AdaBoost-based vehicle detection system is dependent on its training data. Thus, its performance decreases when the shape of a target differs from its training data, or the pattern of a preceding vehicle is not visible in the image due to the light conditions. A stacked Difference of Gaussian (DoG)–based feature extraction algorithm is proposed to address this issue by recognizing common characteristics, such as the shadow and rear wheels beneath vehicles—of vehicles under various conditions. The common characteristics of vehicles are extracted by applying the stacked DoG shaped kernel obtained from the 3D plot of an image through a convolution method and investigating only certain regions that have a similar patterns. A new vehicle detection system is constructed by combining the novel stacked DoG feature extraction algorithm with the AdaBoost method. Experiments are provided to demonstrate the effectiveness of the proposed vehicle detection system under different conditions. PMID:29513727

Using convolutional decoding to improve time delay and phase estimation in digital communications

DOEpatents

Ormesher, Richard C [Albuquerque, NM; Mason, John J [Albuquerque, NM

2010-01-26

The time delay and/or phase of a communication signal received by a digital communication receiver can be estimated based on a convolutional decoding operation that the communication receiver performs on the received communication signal. If the original transmitted communication signal has been spread according to a spreading operation, a corresponding despreading operation can be integrated into the convolutional decoding operation.

Off-resonance artifacts correction with convolution in k-space (ORACLE).

PubMed

Lin, Wei; Huang, Feng; Simonotto, Enrico; Duensing, George R; Reykowski, Arne

2012-06-01

Off-resonance artifacts hinder the wider applicability of echo-planar imaging and non-Cartesian MRI methods such as radial and spiral. In this work, a general and rapid method is proposed for off-resonance artifacts correction based on data convolution in k-space. The acquired k-space is divided into multiple segments based on their acquisition times. Off-resonance-induced artifact within each segment is removed by applying a convolution kernel, which is the Fourier transform of an off-resonance correcting spatial phase modulation term. The field map is determined from the inverse Fourier transform of a basis kernel, which is calibrated from data fitting in k-space. The technique was demonstrated in phantom and in vivo studies for radial, spiral and echo-planar imaging datasets. For radial acquisitions, the proposed method allows the self-calibration of the field map from the imaging data, when an alternating view-angle ordering scheme is used. An additional advantage for off-resonance artifacts correction based on data convolution in k-space is the reusability of convolution kernels to images acquired with the same sequence but different contrasts. Copyright © 2011 Wiley-Liss, Inc.

Finding strong lenses in CFHTLS using convolutional neural networks

NASA Astrophysics Data System (ADS)

Jacobs, C.; Glazebrook, K.; Collett, T.; More, A.; McCarthy, C.

2017-10-01

We train and apply convolutional neural networks, a machine learning technique developed to learn from and classify image data, to Canada-France-Hawaii Telescope Legacy Survey (CFHTLS) imaging for the identification of potential strong lensing systems. An ensemble of four convolutional neural networks was trained on images of simulated galaxy-galaxy lenses. The training sets consisted of a total of 62 406 simulated lenses and 64 673 non-lens negative examples generated with two different methodologies. An ensemble of trained networks was applied to all of the 171 deg2 of the CFHTLS wide field image data, identifying 18 861 candidates including 63 known and 139 other potential lens candidates. A second search of 1.4 million early-type galaxies selected from the survey catalogue as potential deflectors, identified 2465 candidates including 117 previously known lens candidates, 29 confirmed lenses/high-quality lens candidates, 266 novel probable or potential lenses and 2097 candidates we classify as false positives. For the catalogue-based search we estimate a completeness of 21-28 per cent with respect to detectable lenses and a purity of 15 per cent, with a false-positive rate of 1 in 671 images tested. We predict a human astronomer reviewing candidates produced by the system would identify 20 probable lenses and 100 possible lenses per hour in a sample selected by the robot. Convolutional neural networks are therefore a promising tool for use in the search for lenses in current and forthcoming surveys such as the Dark Energy Survey and the Large Synoptic Survey Telescope.

Convolutional networks for vehicle track segmentation

DOE PAGES

Quach, Tu-Thach

2017-08-19

Existing methods to detect vehicle tracks in coherent change detection images, a product of combining two synthetic aperture radar images taken at different times of the same scene, rely on simple, fast models to label track pixels. These models, however, are unable to capture natural track features such as continuity and parallelism. More powerful, but computationally expensive models can be used in offline settings. We present an approach that uses dilated convolutional networks consisting of a series of 3-by-3 convolutions to segment vehicle tracks. The design of our networks considers the fact that remote sensing applications tend to operate inmore » low power and have limited training data. As a result, we aim for small, efficient networks that can be trained end-to-end to learn natural track features entirely from limited training data. We demonstrate that our 6-layer network, trained on just 90 images, is computationally efficient and improves the F-score on a standard dataset to 0.992, up from 0.959 obtained by the current state-of-the-art method.« less

Convolutional networks for vehicle track segmentation

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

Quach, Tu-Thach

Existing methods to detect vehicle tracks in coherent change detection images, a product of combining two synthetic aperture radar images taken at different times of the same scene, rely on simple, fast models to label track pixels. These models, however, are unable to capture natural track features such as continuity and parallelism. More powerful, but computationally expensive models can be used in offline settings. We present an approach that uses dilated convolutional networks consisting of a series of 3-by-3 convolutions to segment vehicle tracks. The design of our networks considers the fact that remote sensing applications tend to operate inmore » low power and have limited training data. As a result, we aim for small, efficient networks that can be trained end-to-end to learn natural track features entirely from limited training data. We demonstrate that our 6-layer network, trained on just 90 images, is computationally efficient and improves the F-score on a standard dataset to 0.992, up from 0.959 obtained by the current state-of-the-art method.« less

Pre-trained convolutional neural networks as feature extractors for tuberculosis detection.

PubMed

Lopes, U K; Valiati, J F

2017-10-01

It is estimated that in 2015, approximately 1.8 million people infected by tuberculosis died, most of them in developing countries. Many of those deaths could have been prevented if the disease had been detected at an earlier stage, but the most advanced diagnosis methods are still cost prohibitive for mass adoption. One of the most popular tuberculosis diagnosis methods is the analysis of frontal thoracic radiographs; however, the impact of this method is diminished by the need for individual analysis of each radiography by properly trained radiologists. Significant research can be found on automating diagnosis by applying computational techniques to medical images, thereby eliminating the need for individual image analysis and greatly diminishing overall costs. In addition, recent improvements on deep learning accomplished excellent results classifying images on diverse domains, but its application for tuberculosis diagnosis remains limited. Thus, the focus of this work is to produce an investigation that will advance the research in the area, presenting three proposals to the application of pre-trained convolutional neural networks as feature extractors to detect the disease. The proposals presented in this work are implemented and compared to the current literature. The obtained results are competitive with published works demonstrating the potential of pre-trained convolutional networks as medical image feature extractors. Copyright © 2017 Elsevier Ltd. All rights reserved.

Quantization and training of object detection networks with low-precision weights and activations

NASA Astrophysics Data System (ADS)

Yang, Bo; Liu, Jian; Zhou, Li; Wang, Yun; Chen, Jie

2018-01-01

As convolutional neural networks have demonstrated state-of-the-art performance in object recognition and detection, there is a growing need for deploying these systems on resource-constrained mobile platforms. However, the computational burden and energy consumption of inference for these networks are significantly higher than what most low-power devices can afford. To address these limitations, this paper proposes a method to train object detection networks with low-precision weights and activations. The probability density functions of weights and activations of each layer are first directly estimated using piecewise Gaussian models. Then, the optimal quantization intervals and step sizes for each convolution layer are adaptively determined according to the distribution of weights and activations. As the most computationally expensive convolutions can be replaced by effective fixed point operations, the proposed method can drastically reduce computation complexity and memory footprint. Performing on the tiny you only look once (YOLO) and YOLO architectures, the proposed method achieves comparable accuracy to their 32-bit counterparts. As an illustration, the proposed 4-bit and 8-bit quantized versions of the YOLO model achieve a mean average precision of 62.6% and 63.9%, respectively, on the Pascal visual object classes 2012 test dataset. The mAP of the 32-bit full-precision baseline model is 64.0%.

Classification of multispectral or hyperspectral satellite imagery using clustering of sparse approximations on sparse representations in learned dictionaries obtained using efficient convolutional sparse coding

DOEpatents

Moody, Daniela; Wohlberg, Brendt

2018-01-02

An approach for land cover classification, seasonal and yearly change detection and monitoring, and identification of changes in man-made features may use a clustering of sparse approximations (CoSA) on sparse representations in learned dictionaries. The learned dictionaries may be derived using efficient convolutional sparse coding to build multispectral or hyperspectral, multiresolution dictionaries that are adapted to regional satellite image data. Sparse image representations of images over the learned dictionaries may be used to perform unsupervised k-means clustering into land cover categories. The clustering process behaves as a classifier in detecting real variability. This approach may combine spectral and spatial textural characteristics to detect geologic, vegetative, hydrologic, and man-made features, as well as changes in these features over time.

DeepID-Net: Deformable Deep Convolutional Neural Networks for Object Detection.

PubMed

Ouyang, Wanli; Zeng, Xingyu; Wang, Xiaogang; Qiu, Shi; Luo, Ping; Tian, Yonglong; Li, Hongsheng; Yang, Shuo; Wang, Zhe; Li, Hongyang; Loy, Chen Change; Wang, Kun; Yan, Junjie; Tang, Xiaoou

2016-07-07

In this paper, we propose deformable deep convolutional neural networks for generic object detection. This new deep learning object detection framework has innovations in multiple aspects. In the proposed new deep architecture, a new deformation constrained pooling (def-pooling) layer models the deformation of object parts with geometric constraint and penalty. A new pre-training strategy is proposed to learn feature representations more suitable for the object detection task and with good generalization capability. By changing the net structures, training strategies, adding and removing some key components in the detection pipeline, a set of models with large diversity are obtained, which significantly improves the effectiveness of model averaging. The proposed approach improves the mean averaged precision obtained by RCNN [16], which was the state-of-the-art, from 31% to 50.3% on the ILSVRC2014 detection test set. It also outperforms the winner of ILSVRC2014, GoogLeNet, by 6.1%. Detailed component-wise analysis is also provided through extensive experimental evaluation, which provides a global view for people to understand the deep learning object detection pipeline.

Filtered back-projection algorithm for Compton telescopes

DOEpatents

Gunter, Donald L [Lisle, IL

2008-03-18

A method for the conversion of Compton camera data into a 2D image of the incident-radiation flux on the celestial sphere includes detecting coincident gamma radiation flux arriving from various directions of a 2-sphere. These events are mapped by back-projection onto the 2-sphere to produce a convolution integral that is subsequently stereographically projected onto a 2-plane to produce a second convolution integral which is deconvolved by the Fourier method to produce an image that is then projected onto the 2-sphere.

Groundwater response to changing water-use practices in sloping aquifers using convolution of transient response functions

USDA-ARS?s Scientific Manuscript database

An integrated foundation is presented to study the impacts of external forcings on irrigated agricultural systems. Individually, models are presented that simulate groundwater hydrogeology and econometric farm level crop choices and irrigated water use. The natural association between groundwater we...

Single Image Super-Resolution Based on Multi-Scale Competitive Convolutional Neural Network

PubMed Central

Qu, Xiaobo; He, Yifan

2018-01-01

Deep convolutional neural networks (CNNs) are successful in single-image super-resolution. Traditional CNNs are limited to exploit multi-scale contextual information for image reconstruction due to the fixed convolutional kernel in their building modules. To restore various scales of image details, we enhance the multi-scale inference capability of CNNs by introducing competition among multi-scale convolutional filters, and build up a shallow network under limited computational resources. The proposed network has the following two advantages: (1) the multi-scale convolutional kernel provides the multi-context for image super-resolution, and (2) the maximum competitive strategy adaptively chooses the optimal scale of information for image reconstruction. Our experimental results on image super-resolution show that the performance of the proposed network outperforms the state-of-the-art methods. PMID:29509666

Single Image Super-Resolution Based on Multi-Scale Competitive Convolutional Neural Network.

PubMed

Du, Xiaofeng; Qu, Xiaobo; He, Yifan; Guo, Di

2018-03-06

Deep convolutional neural networks (CNNs) are successful in single-image super-resolution. Traditional CNNs are limited to exploit multi-scale contextual information for image reconstruction due to the fixed convolutional kernel in their building modules. To restore various scales of image details, we enhance the multi-scale inference capability of CNNs by introducing competition among multi-scale convolutional filters, and build up a shallow network under limited computational resources. The proposed network has the following two advantages: (1) the multi-scale convolutional kernel provides the multi-context for image super-resolution, and (2) the maximum competitive strategy adaptively chooses the optimal scale of information for image reconstruction. Our experimental results on image super-resolution show that the performance of the proposed network outperforms the state-of-the-art methods.

Coset Codes Viewed as Terminated Convolutional Codes

NASA Technical Reports Server (NTRS)

Fossorier, Marc P. C.; Lin, Shu

1996-01-01

In this paper, coset codes are considered as terminated convolutional codes. Based on this approach, three new general results are presented. First, it is shown that the iterative squaring construction can equivalently be defined from a convolutional code whose trellis terminates. This convolutional code determines a simple encoder for the coset code considered, and the state and branch labelings of the associated trellis diagram become straightforward. Also, from the generator matrix of the code in its convolutional code form, much information about the trade-off between the state connectivity and complexity at each section, and the parallel structure of the trellis, is directly available. Based on this generator matrix, it is shown that the parallel branches in the trellis diagram of the convolutional code represent the same coset code C(sub 1), of smaller dimension and shorter length. Utilizing this fact, a two-stage optimum trellis decoding method is devised. The first stage decodes C(sub 1), while the second stage decodes the associated convolutional code, using the branch metrics delivered by stage 1. Finally, a bidirectional decoding of each received block starting at both ends is presented. If about the same number of computations is required, this approach remains very attractive from a practical point of view as it roughly doubles the decoding speed. This fact is particularly interesting whenever the second half of the trellis is the mirror image of the first half, since the same decoder can be implemented for both parts.

Applications of deep convolutional neural networks to digitized natural history collections

PubMed Central

Frandsen, Paul B.; Dikow, Rebecca B.; Brown, Abel; Orli, Sylvia; Peters, Melinda; Metallo, Adam; Funk, Vicki A.; Dorr, Laurence J.

2017-01-01

Abstract Natural history collections contain data that are critical for many scientific endeavors. Recent efforts in mass digitization are generating large datasets from these collections that can provide unprecedented insight. Here, we present examples of how deep convolutional neural networks can be applied in analyses of imaged herbarium specimens. We first demonstrate that a convolutional neural network can detect mercury-stained specimens across a collection with 90% accuracy. We then show that such a network can correctly distinguish two morphologically similar plant families 96% of the time. Discarding the most challenging specimen images increases accuracy to 94% and 99%, respectively. These results highlight the importance of mass digitization and deep learning approaches and reveal how they can together deliver powerful new investigative tools. PMID:29200929

A general contact mechanical formulation of multilayered structures and its application to deconvolute thickness/mechanical properties of glue used in surface force apparatus.

PubMed

Math, Souvik; Horn, Roger; Jayaram, Vikram; Biswas, Sanjay Kumar

2007-04-15

Currently data obtained from surface force apparatus experiments are convoluted with the mechanical response of glue of unknown thickness, used to bond mica sheets to the substrates. This paper describes a formulation to precisely deconvolute out the forces between the mica sheets by determining the thickness of glue, knowing the mechanical properties of the glue. The formulation consists of a general solution based on the noniterative Hankel transform of the Laplace equation. The generality is achieved by treating all the layers except the one in contact as an effective lumped system consisting of a set of springs in series, where each spring represents a layer. The solution is validated by nanoindentation of trilayer systems consisting of layers with widely diverse mechanical properties, some differing from each other by three orders of magnitude. SFA experiments are done with carefully metered slabs of glue. The proposed method is validated by comparing the actual glue thicknesses with those determined using the present analysis.

Electroencephalography Based Fusion Two-Dimensional (2D)-Convolution Neural Networks (CNN) Model for Emotion Recognition System.

PubMed

Kwon, Yea-Hoon; Shin, Sae-Byuk; Kim, Shin-Dug

2018-04-30

The purpose of this study is to improve human emotional classification accuracy using a convolution neural networks (CNN) model and to suggest an overall method to classify emotion based on multimodal data. We improved classification performance by combining electroencephalogram (EEG) and galvanic skin response (GSR) signals. GSR signals are preprocessed using by the zero-crossing rate. Sufficient EEG feature extraction can be obtained through CNN. Therefore, we propose a suitable CNN model for feature extraction by tuning hyper parameters in convolution filters. The EEG signal is preprocessed prior to convolution by a wavelet transform while considering time and frequency simultaneously. We use a database for emotion analysis using the physiological signals open dataset to verify the proposed process, achieving 73.4% accuracy, showing significant performance improvement over the current best practice models.

Convolutional neural network based side attack explosive hazard detection in three dimensional voxel radar

NASA Astrophysics Data System (ADS)

Brockner, Blake; Veal, Charlie; Dowdy, Joshua; Anderson, Derek T.; Williams, Kathryn; Luke, Robert; Sheen, David

2018-04-01

The identification followed by avoidance or removal of explosive hazards in past and/or present conflict zones is a serious threat for both civilian and military personnel. This is a challenging task as variability exists with respect to the objects, their environment and emplacement context, to name a few factors. A goal is the development of automatic or human-in-the-loop sensor technologies that leverage signal processing, data fusion and machine learning. Herein, we explore the detection of side attack explosive hazards (SAEHs) in three dimensional voxel space radar via different shallow and deep convolutional neural network (CNN) architectures. Dimensionality reduction is performed by using multiple projected images versus the raw three dimensional voxel data, which leads to noteworthy savings in input size and associated network hyperparameters. Last, we explore the accuracy and interpretation of solutions learned via random versus intelligent network weight initialization. Experiments are provided on a U.S. Army data set collected over different times, weather conditions, target types and concealments. Preliminary results indicate that deep learning can perform as good as, if not better, than a skilled domain expert, even in light of limited training data with a class imbalance.

A convolutional neural network to filter artifacts in spectroscopic MRI.

PubMed

Gurbani, Saumya S; Schreibmann, Eduard; Maudsley, Andrew A; Cordova, James Scott; Soher, Brian J; Poptani, Harish; Verma, Gaurav; Barker, Peter B; Shim, Hyunsuk; Cooper, Lee A D

2018-03-09

Proton MRSI is a noninvasive modality capable of generating volumetric maps of in vivo tissue metabolism without the need for ionizing radiation or injected contrast agent. Magnetic resonance spectroscopic imaging has been shown to be a viable imaging modality for studying several neuropathologies. However, a key hurdle in the routine clinical adoption of MRSI is the presence of spectral artifacts that can arise from a number of sources, possibly leading to false information. A deep learning model was developed that was capable of identifying and filtering out poor quality spectra. The core of the model used a tiled convolutional neural network that analyzed frequency-domain spectra to detect artifacts. When compared with a panel of MRS experts, our convolutional neural network achieved high sensitivity and specificity with an area under the curve of 0.95. A visualization scheme was implemented to better understand how the convolutional neural network made its judgement on single-voxel or multivoxel MRSI, and the convolutional neural network was embedded into a pipeline capable of producing whole-brain spectroscopic MRI volumes in real time. The fully automated method for assessment of spectral quality provides a valuable tool to support clinical MRSI or spectroscopic MRI studies for use in fields such as adaptive radiation therapy planning. © 2018 International Society for Magnetic Resonance in Medicine.

Towards dropout training for convolutional neural networks.

PubMed

Wu, Haibing; Gu, Xiaodong

2015-11-01

Recently, dropout has seen increasing use in deep learning. For deep convolutional neural networks, dropout is known to work well in fully-connected layers. However, its effect in convolutional and pooling layers is still not clear. This paper demonstrates that max-pooling dropout is equivalent to randomly picking activation based on a multinomial distribution at training time. In light of this insight, we advocate employing our proposed probabilistic weighted pooling, instead of commonly used max-pooling, to act as model averaging at test time. Empirical evidence validates the superiority of probabilistic weighted pooling. We also empirically show that the effect of convolutional dropout is not trivial, despite the dramatically reduced possibility of over-fitting due to the convolutional architecture. Elaborately designing dropout training simultaneously in max-pooling and fully-connected layers, we achieve state-of-the-art performance on MNIST, and very competitive results on CIFAR-10 and CIFAR-100, relative to other approaches without data augmentation. Finally, we compare max-pooling dropout and stochastic pooling, both of which introduce stochasticity based on multinomial distributions at pooling stage. Copyright © 2015 Elsevier Ltd. All rights reserved.

Classification of Alzheimer's Disease Based on Eight-Layer Convolutional Neural Network with Leaky Rectified Linear Unit and Max Pooling.

PubMed

Wang, Shui-Hua; Phillips, Preetha; Sui, Yuxiu; Liu, Bin; Yang, Ming; Cheng, Hong

2018-03-26

Alzheimer's disease (AD) is a progressive brain disease. The goal of this study is to provide a new computer-vision based technique to detect it in an efficient way. The brain-imaging data of 98 AD patients and 98 healthy controls was collected using data augmentation method. Then, convolutional neural network (CNN) was used, CNN is the most successful tool in deep learning. An 8-layer CNN was created with optimal structure obtained by experiences. Three activation functions (AFs): sigmoid, rectified linear unit (ReLU), and leaky ReLU. The three pooling-functions were also tested: average pooling, max pooling, and stochastic pooling. The numerical experiments demonstrated that leaky ReLU and max pooling gave the greatest result in terms of performance. It achieved a sensitivity of 97.96%, a specificity of 97.35%, and an accuracy of 97.65%, respectively. In addition, the proposed approach was compared with eight state-of-the-art approaches. The method increased the classification accuracy by approximately 5% compared to state-of-the-art methods.

A spectral nudging method for the ACCESS1.3 atmospheric model

NASA Astrophysics Data System (ADS)

Uhe, P.; Thatcher, M.

2015-06-01

A convolution-based method of spectral nudging of atmospheric fields is developed in the Australian Community Climate and Earth Systems Simulator (ACCESS) version 1.3 which uses the UK Met Office Unified Model version 7.3 as its atmospheric component. The use of convolutions allow for flexibility in application to different atmospheric grids. An approximation using one-dimensional convolutions is applied, improving the time taken by the nudging scheme by 10-30 times compared with a version using a two-dimensional convolution, without measurably degrading its performance. Care needs to be taken in the order of the convolutions and the frequency of nudging to obtain the best outcome. The spectral nudging scheme is benchmarked against a Newtonian relaxation method, nudging winds and air temperature towards ERA-Interim reanalyses. We find that the convolution approach can produce results that are competitive with Newtonian relaxation in both the effectiveness and efficiency of the scheme, while giving the added flexibility of choosing which length scales to nudge.

A spectral nudging method for the ACCESS1.3 atmospheric model

NASA Astrophysics Data System (ADS)

Uhe, P.; Thatcher, M.

2014-10-01

A convolution based method of spectral nudging of atmospheric fields is developed in the Australian Community Climate and Earth Systems Simulator (ACCESS) version 1.3 which uses the UK Met Office Unified Model version 7.3 as its atmospheric component. The use of convolutions allow flexibility in application to different atmospheric grids. An approximation using one-dimensional convolutions is applied, improving the time taken by the nudging scheme by 10 to 30 times compared with a version using a two-dimensional convolution, without measurably degrading its performance. Care needs to be taken in the order of the convolutions and the frequency of nudging to obtain the best outcome. The spectral nudging scheme is benchmarked against a Newtonian relaxation method, nudging winds and air temperature towards ERA-Interim reanalyses. We find that the convolution approach can produce results that are competitive with Newtonian relaxation in both the effectiveness and efficiency of the scheme, while giving the added flexibility of choosing which length scales to nudge.

Diagnosis and prediction of periodontally compromised teeth using a deep learning-based convolutional neural network algorithm.

PubMed

Lee, Jae-Hong; Kim, Do-Hyung; Jeong, Seong-Nyum; Choi, Seong-Ho

2018-04-01

The aim of the current study was to develop a computer-assisted detection system based on a deep convolutional neural network (CNN) algorithm and to evaluate the potential usefulness and accuracy of this system for the diagnosis and prediction of periodontally compromised teeth (PCT). Combining pretrained deep CNN architecture and a self-trained network, periapical radiographic images were used to determine the optimal CNN algorithm and weights. The diagnostic and predictive accuracy, sensitivity, specificity, positive predictive value, negative predictive value, receiver operating characteristic (ROC) curve, area under the ROC curve, confusion matrix, and 95% confidence intervals (CIs) were calculated using our deep CNN algorithm, based on a Keras framework in Python. The periapical radiographic dataset was split into training (n=1,044), validation (n=348), and test (n=348) datasets. With the deep learning algorithm, the diagnostic accuracy for PCT was 81.0% for premolars and 76.7% for molars. Using 64 premolars and 64 molars that were clinically diagnosed as severe PCT, the accuracy of predicting extraction was 82.8% (95% CI, 70.1%-91.2%) for premolars and 73.4% (95% CI, 59.9%-84.0%) for molars. We demonstrated that the deep CNN algorithm was useful for assessing the diagnosis and predictability of PCT. Therefore, with further optimization of the PCT dataset and improvements in the algorithm, a computer-aided detection system can be expected to become an effective and efficient method of diagnosing and predicting PCT.

Laser Welding Process Monitoring Systems: Advanced Signal Analysis for Quality Assurance

NASA Astrophysics Data System (ADS)

D'Angelo, Giuseppe

Laser material processing today is widely used in industry. Especially laser welding became one of the key-technologies, e. g., for the automotive sector. This is due to the improvement and development of new laser sources and the increasing knowledge gained at countless scientific research projects. Nevertheless, it is still not possible to use the full potential of this technology. Therefore, the introduction and application of quality-assuring systems is required. For a long time, the statement "the best sensor is no sensor" was often heard. Today, a change of paradigm can be observed. On the one hand, ISO 9000 and other by law enforced regulations have led to the understanding that quality monitoring is an essential tool in modern manufacturing and necessary in order to keep production results in deterministic boundaries. On the other hand, rising quality requirements not only set higher and higher requirements for the process technology but also demand qualityassurance measures which ensure the reliable recognition of process faults. As a result, there is a need for reliable online detection and correction of welding faults by means of an in-process monitoring. The chapter describes an advanced signals analysis technique to extract information from signals detected, during the laser welding process, by optical sensors. The technique is based on the method of reassignment which was first applied to the spectrogram by Kodera, Gendrin and de Villedary22,23 and later generalized to any bilinear time-frequency representation by Auger and Flandrin.24 Key to the method is a nonlinear convolution where the value of the convolution is not placed at the center of the convolution kernel but rather reassigned to the center of mass of the function within the kernel. The resulting reassigned representation yields significantly improved components localization. We compare the proposed time-frequency distributions by analyzing signals detected during the laser welding of tailored blanks, demonstrating the advantages of the reassigned representation, giving practical applicability to the proposed method.

Automated detection of nerve fiber layer defects on retinal fundus images using fully convolutional network for early diagnosis of glaucoma

NASA Astrophysics Data System (ADS)

Watanabe, Ryusuke; Muramatsu, Chisako; Ishida, Kyoko; Sawada, Akira; Hatanaka, Yuji; Yamamoto, Tetsuya; Fujita, Hiroshi

2017-03-01

Early detection of glaucoma is important to slow down progression of the disease and to prevent total vision loss. We have been studying an automated scheme for detection of a retinal nerve fiber layer defect (NFLD), which is one of the earliest signs of glaucoma on retinal fundus images. In our previous study, we proposed a multi-step detection scheme which consists of Gabor filtering, clustering and adaptive thresholding. The problems of the previous method were that the number of false positives (FPs) was still large and that the method included too many rules. In attempt to solve these problems, we investigated the end-to-end learning system without pre-specified features. A deep convolutional neural network (DCNN) with deconvolutional layers was trained to detect NFLD regions. In this preliminary investigation, we investigated effective ways of preparing the input images and compared the detection results. The optimal result was then compared with the result obtained by the previous method. DCNN training was carried out using original images of abnormal cases, original images of both normal and abnormal cases, ellipse-based polar transformed images, and transformed half images. The result showed that use of both normal and abnormal cases increased the sensitivity as well as the number of FPs. Although NFLDs are visualized with the highest contrast in green plane, the use of color images provided higher sensitivity than the use of green image only. The free response receiver operating characteristic curve using the transformed color images, which was the best among seven different sets studied, was comparable to that of the previous method. Use of DCNN has a potential to improve the generalizability of automated detection method of NFLDs and may be useful in assisting glaucoma diagnosis on retinal fundus images.

Deep convolutional networks for automated detection of posterior-element fractures on spine CT

NASA Astrophysics Data System (ADS)

Roth, Holger R.; Wang, Yinong; Yao, Jianhua; Lu, Le; Burns, Joseph E.; Summers, Ronald M.

2016-03-01

Injuries of the spine, and its posterior elements in particular, are a common occurrence in trauma patients, with potentially devastating consequences. Computer-aided detection (CADe) could assist in the detection and classification of spine fractures. Furthermore, CAD could help assess the stability and chronicity of fractures, as well as facilitate research into optimization of treatment paradigms. In this work, we apply deep convolutional networks (ConvNets) for the automated detection of posterior element fractures of the spine. First, the vertebra bodies of the spine with its posterior elements are segmented in spine CT using multi-atlas label fusion. Then, edge maps of the posterior elements are computed. These edge maps serve as candidate regions for predicting a set of probabilities for fractures along the image edges using ConvNets in a 2.5D fashion (three orthogonal patches in axial, coronal and sagittal planes). We explore three different methods for training the ConvNet using 2.5D patches along the edge maps of `positive', i.e. fractured posterior-elements and `negative', i.e. non-fractured elements. An experienced radiologist retrospectively marked the location of 55 displaced posterior-element fractures in 18 trauma patients. We randomly split the data into training and testing cases. In testing, we achieve an area-under-the-curve of 0.857. This corresponds to 71% or 81% sensitivities at 5 or 10 false-positives per patient, respectively. Analysis of our set of trauma patients demonstrates the feasibility of detecting posterior-element fractures in spine CT images using computer vision techniques such as deep convolutional networks.

Accelerating Convolutional Sparse Coding for Curvilinear Structures Segmentation by Refining SCIRD-TS Filter Banks.

PubMed

Annunziata, Roberto; Trucco, Emanuele

2016-11-01

Deep learning has shown great potential for curvilinear structure (e.g., retinal blood vessels and neurites) segmentation as demonstrated by a recent auto-context regression architecture based on filter banks learned by convolutional sparse coding. However, learning such filter banks is very time-consuming, thus limiting the amount of filters employed and the adaptation to other data sets (i.e., slow re-training). We address this limitation by proposing a novel acceleration strategy to speed-up convolutional sparse coding filter learning for curvilinear structure segmentation. Our approach is based on a novel initialisation strategy (warm start), and therefore it is different from recent methods improving the optimisation itself. Our warm-start strategy is based on carefully designed hand-crafted filters (SCIRD-TS), modelling appearance properties of curvilinear structures which are then refined by convolutional sparse coding. Experiments on four diverse data sets, including retinal blood vessels and neurites, suggest that the proposed method reduces significantly the time taken to learn convolutional filter banks (i.e., up to -82%) compared to conventional initialisation strategies. Remarkably, this speed-up does not worsen performance; in fact, filters learned with the proposed strategy often achieve a much lower reconstruction error and match or exceed the segmentation performance of random and DCT-based initialisation, when used as input to a random forest classifier.

Multiclass classification of obstructive sleep apnea/hypopnea based on a convolutional neural network from a single-lead electrocardiogram.

PubMed

Urtnasan, Erdenebayar; Park, Jong-Uk; Lee, Kyoung-Joung

2018-05-24

In this paper, we propose a convolutional neural network (CNN)-based deep learning architecture for multiclass classification of obstructive sleep apnea and hypopnea (OSAH) using single-lead electrocardiogram (ECG) recordings. OSAH is the most common sleep-related breathing disorder. Many subjects who suffer from OSAH remain undiagnosed; thus, early detection of OSAH is important. In this study, automatic classification of three classes-normal, hypopnea, and apnea-based on a CNN is performed. An optimal six-layer CNN model is trained on a training dataset (45,096 events) and evaluated on a test dataset (11,274 events). The training set (69 subjects) and test set (17 subjects) were collected from 86 subjects with length of approximately 6 h and segmented into 10 s durations. The proposed CNN model reaches a mean -score of 93.0 for the training dataset and 87.0 for the test dataset. Thus, proposed deep learning architecture achieved a high performance for multiclass classification of OSAH using single-lead ECG recordings. The proposed method can be employed in screening of patients suspected of having OSAH. © 2018 Institute of Physics and Engineering in Medicine.

Infrared variation reduction by simultaneous background suppression and target contrast enhancement for deep convolutional neural network-based automatic target recognition

NASA Astrophysics Data System (ADS)

Kim, Sungho

2017-06-01

Automatic target recognition (ATR) is a traditionally challenging problem in military applications because of the wide range of infrared (IR) image variations and the limited number of training images. IR variations are caused by various three-dimensional target poses, noncooperative weather conditions (fog and rain), and difficult target acquisition environments. Recently, deep convolutional neural network-based approaches for RGB images (RGB-CNN) showed breakthrough performance in computer vision problems, such as object detection and classification. The direct use of RGB-CNN to the IR ATR problem fails to work because of the IR database problems (limited database size and IR image variations). An IR variation-reduced deep CNN (IVR-CNN) to cope with the problems is presented. The problem of limited IR database size is solved by a commercial thermal simulator (OKTAL-SE). The second problem of IR variations is mitigated by the proposed shifted ramp function-based intensity transformation. This can suppress the background and enhance the target contrast simultaneously. The experimental results on the synthesized IR images generated by the thermal simulator (OKTAL-SE) validated the feasibility of IVR-CNN for military ATR applications.

Comparison between Frame-Constrained Fix-Pixel-Value and Frame-Free Spiking-Dynamic-Pixel ConvNets for Visual Processing

PubMed Central

Farabet, Clément; Paz, Rafael; Pérez-Carrasco, Jose; Zamarreño-Ramos, Carlos; Linares-Barranco, Alejandro; LeCun, Yann; Culurciello, Eugenio; Serrano-Gotarredona, Teresa; Linares-Barranco, Bernabe

2012-01-01

Most scene segmentation and categorization architectures for the extraction of features in images and patches make exhaustive use of 2D convolution operations for template matching, template search, and denoising. Convolutional Neural Networks (ConvNets) are one example of such architectures that can implement general-purpose bio-inspired vision systems. In standard digital computers 2D convolutions are usually expensive in terms of resource consumption and impose severe limitations for efficient real-time applications. Nevertheless, neuro-cortex inspired solutions, like dedicated Frame-Based or Frame-Free Spiking ConvNet Convolution Processors, are advancing real-time visual processing. These two approaches share the neural inspiration, but each of them solves the problem in different ways. Frame-Based ConvNets process frame by frame video information in a very robust and fast way that requires to use and share the available hardware resources (such as: multipliers, adders). Hardware resources are fixed- and time-multiplexed by fetching data in and out. Thus memory bandwidth and size is important for good performance. On the other hand, spike-based convolution processors are a frame-free alternative that is able to perform convolution of a spike-based source of visual information with very low latency, which makes ideal for very high-speed applications. However, hardware resources need to be available all the time and cannot be time-multiplexed. Thus, hardware should be modular, reconfigurable, and expansible. Hardware implementations in both VLSI custom integrated circuits (digital and analog) and FPGA have been already used to demonstrate the performance of these systems. In this paper we present a comparison study of these two neuro-inspired solutions. A brief description of both systems is presented and also discussions about their differences, pros and cons. PMID:22518097

Comparison between Frame-Constrained Fix-Pixel-Value and Frame-Free Spiking-Dynamic-Pixel ConvNets for Visual Processing.

PubMed

Farabet, Clément; Paz, Rafael; Pérez-Carrasco, Jose; Zamarreño-Ramos, Carlos; Linares-Barranco, Alejandro; Lecun, Yann; Culurciello, Eugenio; Serrano-Gotarredona, Teresa; Linares-Barranco, Bernabe

2012-01-01

Most scene segmentation and categorization architectures for the extraction of features in images and patches make exhaustive use of 2D convolution operations for template matching, template search, and denoising. Convolutional Neural Networks (ConvNets) are one example of such architectures that can implement general-purpose bio-inspired vision systems. In standard digital computers 2D convolutions are usually expensive in terms of resource consumption and impose severe limitations for efficient real-time applications. Nevertheless, neuro-cortex inspired solutions, like dedicated Frame-Based or Frame-Free Spiking ConvNet Convolution Processors, are advancing real-time visual processing. These two approaches share the neural inspiration, but each of them solves the problem in different ways. Frame-Based ConvNets process frame by frame video information in a very robust and fast way that requires to use and share the available hardware resources (such as: multipliers, adders). Hardware resources are fixed- and time-multiplexed by fetching data in and out. Thus memory bandwidth and size is important for good performance. On the other hand, spike-based convolution processors are a frame-free alternative that is able to perform convolution of a spike-based source of visual information with very low latency, which makes ideal for very high-speed applications. However, hardware resources need to be available all the time and cannot be time-multiplexed. Thus, hardware should be modular, reconfigurable, and expansible. Hardware implementations in both VLSI custom integrated circuits (digital and analog) and FPGA have been already used to demonstrate the performance of these systems. In this paper we present a comparison study of these two neuro-inspired solutions. A brief description of both systems is presented and also discussions about their differences, pros and cons.

No-reference image quality assessment based on statistics of convolution feature maps

NASA Astrophysics Data System (ADS)

Lv, Xiaoxin; Qin, Min; Chen, Xiaohui; Wei, Guo

2018-04-01

We propose a Convolutional Feature Maps (CFM) driven approach to accurately predict image quality. Our motivation bases on the finding that the Nature Scene Statistic (NSS) features on convolution feature maps are significantly sensitive to distortion degree of an image. In our method, a Convolutional Neural Network (CNN) is trained to obtain kernels for generating CFM. We design a forward NSS layer which performs on CFM to better extract NSS features. The quality aware features derived from the output of NSS layer is effective to describe the distortion type and degree an image suffered. Finally, a Support Vector Regression (SVR) is employed in our No-Reference Image Quality Assessment (NR-IQA) model to predict a subjective quality score of a distorted image. Experiments conducted on two public databases demonstrate the promising performance of the proposed method is competitive to state of the art NR-IQA methods.

Control system of hexacopter using color histogram footprint and convolutional neural network

NASA Astrophysics Data System (ADS)

Ruliputra, R. N.; Darma, S.

2017-07-01

The development of unmanned aerial vehicles (UAV) has been growing rapidly in recent years. The use of logic thinking which is implemented into the program algorithms is needed to make a smart system. By using visual input from a camera, UAV is able to fly autonomously by detecting a target. However, some weaknesses arose as usage in the outdoor environment might change the target's color intensity. Color histogram footprint overcomes the problem because it divides color intensity into separate bins that make the detection tolerant to the slight change of color intensity. Template matching compare its detection result with a template of the reference image to determine the target position and use it to position the vehicle in the middle of the target with visual feedback control based on Proportional-Integral-Derivative (PID) controller. Color histogram footprint method localizes the target by calculating the back projection of its histogram. It has an average success rate of 77 % from a distance of 1 meter. It can position itself in the middle of the target by using visual feedback control with an average positioning time of 73 seconds. After the hexacopter is in the middle of the target, Convolutional Neural Networks (CNN) classifies a number contained in the target image to determine a task depending on the classified number, either landing, yawing, or return to launch. The recognition result shows an optimum success rate of 99.2 %.

Automated detection of lung nodules with three-dimensional convolutional neural networks

NASA Astrophysics Data System (ADS)

Pérez, Gustavo; Arbeláez, Pablo

2017-11-01

Lung cancer is the cancer type with highest mortality rate worldwide. It has been shown that early detection with computer tomography (CT) scans can reduce deaths caused by this disease. Manual detection of cancer nodules is costly and time-consuming. We present a general framework for the detection of nodules in lung CT images. Our method consists of the pre-processing of a patient's CT with filtering and lung extraction from the entire volume using a previously calculated mask for each patient. From the extracted lungs, we perform a candidate generation stage using morphological operations, followed by the training of a three-dimensional convolutional neural network for feature representation and classification of extracted candidates for false positive reduction. We perform experiments on the publicly available LIDC-IDRI dataset. Our candidate extraction approach is effective to produce precise candidates with a recall of 99.6%. In addition, false positive reduction stage manages to successfully classify candidates and increases precision by a factor of 7.000.

Investigation of nucleation and growth processes of diamond films by atomic force microscopy

NASA Technical Reports Server (NTRS)

George, M. A.; Burger, A.; Collins, W. E.; Davidson, J. L.; Barnes, A. V.; Tolk, N. H.

1994-01-01

The nucleation and growth of plasma-enhanced chemical-vapor deposited polycrystalline diamond films were studied using atomic force microscopy (AFM). AFM images were obtained for (1) nucleated diamond films produced from depositions that were terminated during the initial stages of growth, (2) the silicon substrate-diamond film interface side of diamond films (1-4 micrometers thick) removed from the original surface of the substrate, and (3) the cross-sectional fracture surface of the film, including the Si/diamond interface. Pronounced tip effects were observed for early-stage diamond nucleation attributed to tip convolution in the AFM images. AFM images of the film's cross section and interface, however, were not highly affected by tip convolution, and the images indicate that the surface of the silicon substrate is initially covered by a small grained polycrystalline-like film and the formation of this precursor film is followed by nucleation of the diamond film on top of this layer. X-ray photoelectron spectroscopy spectra indicate that some silicon carbide is present in the precursor layer.

Trellises and Trellis-Based Decoding Algorithms for Linear Block Codes. Part 3

NASA Technical Reports Server (NTRS)

Lin, Shu

1998-01-01

Decoding algorithms based on the trellis representation of a code (block or convolutional) drastically reduce decoding complexity. The best known and most commonly used trellis-based decoding algorithm is the Viterbi algorithm. It is a maximum likelihood decoding algorithm. Convolutional codes with the Viterbi decoding have been widely used for error control in digital communications over the last two decades. This chapter is concerned with the application of the Viterbi decoding algorithm to linear block codes. First, the Viterbi algorithm is presented. Then, optimum sectionalization of a trellis to minimize the computational complexity of a Viterbi decoder is discussed and an algorithm is presented. Some design issues for IC (integrated circuit) implementation of a Viterbi decoder are considered and discussed. Finally, a new decoding algorithm based on the principle of compare-select-add is presented. This new algorithm can be applied to both block and convolutional codes and is more efficient than the conventional Viterbi algorithm based on the add-compare-select principle. This algorithm is particularly efficient for rate 1/n antipodal convolutional codes and their high-rate punctured codes. It reduces computational complexity by one-third compared with the Viterbi algorithm.

Pulmonary Nodule Classification with Deep Convolutional Neural Networks on Computed Tomography Images.

PubMed

Li, Wei; Cao, Peng; Zhao, Dazhe; Wang, Junbo

2016-01-01

Computer aided detection (CAD) systems can assist radiologists by offering a second opinion on early diagnosis of lung cancer. Classification and feature representation play critical roles in false-positive reduction (FPR) in lung nodule CAD. We design a deep convolutional neural networks method for nodule classification, which has an advantage of autolearning representation and strong generalization ability. A specified network structure for nodule images is proposed to solve the recognition of three types of nodules, that is, solid, semisolid, and ground glass opacity (GGO). Deep convolutional neural networks are trained by 62,492 regions-of-interest (ROIs) samples including 40,772 nodules and 21,720 nonnodules from the Lung Image Database Consortium (LIDC) database. Experimental results demonstrate the effectiveness of the proposed method in terms of sensitivity and overall accuracy and that it consistently outperforms the competing methods.

Three-Dimensional Terahertz Coded-Aperture Imaging Based on Matched Filtering and Convolutional Neural Network.

PubMed

Chen, Shuo; Luo, Chenggao; Wang, Hongqiang; Deng, Bin; Cheng, Yongqiang; Zhuang, Zhaowen

2018-04-26

As a promising radar imaging technique, terahertz coded-aperture imaging (TCAI) can achieve high-resolution, forward-looking, and staring imaging by producing spatiotemporal independent signals with coded apertures. However, there are still two problems in three-dimensional (3D) TCAI. Firstly, the large-scale reference-signal matrix based on meshing the 3D imaging area creates a heavy computational burden, thus leading to unsatisfactory efficiency. Secondly, it is difficult to resolve the target under low signal-to-noise ratio (SNR). In this paper, we propose a 3D imaging method based on matched filtering (MF) and convolutional neural network (CNN), which can reduce the computational burden and achieve high-resolution imaging for low SNR targets. In terms of the frequency-hopping (FH) signal, the original echo is processed with MF. By extracting the processed echo in different spike pulses separately, targets in different imaging planes are reconstructed simultaneously to decompose the global computational complexity, and then are synthesized together to reconstruct the 3D target. Based on the conventional TCAI model, we deduce and build a new TCAI model based on MF. Furthermore, the convolutional neural network (CNN) is designed to teach the MF-TCAI how to reconstruct the low SNR target better. The experimental results demonstrate that the MF-TCAI achieves impressive performance on imaging ability and efficiency under low SNR. Moreover, the MF-TCAI has learned to better resolve the low-SNR 3D target with the help of CNN. In summary, the proposed 3D TCAI can achieve: (1) low-SNR high-resolution imaging by using MF; (2) efficient 3D imaging by downsizing the large-scale reference-signal matrix; and (3) intelligent imaging with CNN. Therefore, the TCAI based on MF and CNN has great potential in applications such as security screening, nondestructive detection, medical diagnosis, etc.

Video Super-Resolution via Bidirectional Recurrent Convolutional Networks.

PubMed

Huang, Yan; Wang, Wei; Wang, Liang

2018-04-01

Super resolving a low-resolution video, namely video super-resolution (SR), is usually handled by either single-image SR or multi-frame SR. Single-Image SR deals with each video frame independently, and ignores intrinsic temporal dependency of video frames which actually plays a very important role in video SR. Multi-Frame SR generally extracts motion information, e.g., optical flow, to model the temporal dependency, but often shows high computational cost. Considering that recurrent neural networks (RNNs) can model long-term temporal dependency of video sequences well, we propose a fully convolutional RNN named bidirectional recurrent convolutional network for efficient multi-frame SR. Different from vanilla RNNs, 1) the commonly-used full feedforward and recurrent connections are replaced with weight-sharing convolutional connections. So they can greatly reduce the large number of network parameters and well model the temporal dependency in a finer level, i.e., patch-based rather than frame-based, and 2) connections from input layers at previous timesteps to the current hidden layer are added by 3D feedforward convolutions, which aim to capture discriminate spatio-temporal patterns for short-term fast-varying motions in local adjacent frames. Due to the cheap convolutional operations, our model has a low computational complexity and runs orders of magnitude faster than other multi-frame SR methods. With the powerful temporal dependency modeling, our model can super resolve videos with complex motions and achieve well performance.

Evaluation of a processing scheme for calcified atheromatous carotid artery detection in face/neck CBCT images

NASA Astrophysics Data System (ADS)

Matheus, B. R. N.; Centurion, B. S.; Rubira-Bullen, I. R. F.; Schiabel, H.

2017-03-01

Cone Beam Computed Tomography (CBCT), a kind of face and neck exams can be opportunity to identify, as an incidental finding, calcifications of the carotid artery (CACA). Given the similarity of the CACA with calcification found in several x-ray exams, this work suggests that a similar technique designed to detect breast calcifications in mammography images could be applied to detect such calcifications in CBCT. The method used a 3D version of the calcification detection technique [1], based on a signal enhancement using a convolution with a 3D Laplacian of Gaussian (LoG) function followed by removing the high contrast bone structure from the image. Initial promising results show a 71% sensitivity with 0.48 false positive per exam.

Multi-Object Tracking with Correlation Filter for Autonomous Vehicle.

PubMed

Zhao, Dawei; Fu, Hao; Xiao, Liang; Wu, Tao; Dai, Bin

2018-06-22

Multi-object tracking is a crucial problem for autonomous vehicle. Most state-of-the-art approaches adopt the tracking-by-detection strategy, which is a two-step procedure consisting of the detection module and the tracking module. In this paper, we improve both steps. We improve the detection module by incorporating the temporal information, which is beneficial for detecting small objects. For the tracking module, we propose a novel compressed deep Convolutional Neural Network (CNN) feature based Correlation Filter tracker. By carefully integrating these two modules, the proposed multi-object tracking approach has the ability of re-identification (ReID) once the tracked object gets lost. Extensive experiments were performed on the KITTI and MOT2015 tracking benchmarks. Results indicate that our approach outperforms most state-of-the-art tracking approaches.

Exploring DeepMedic for the purpose of segmenting white matter hyperintensity lesions

NASA Astrophysics Data System (ADS)

Lippert, Fiona; Cheng, Bastian; Golsari, Amir; Weiler, Florian; Gregori, Johannes; Thomalla, Götz; Klein, Jan

2018-02-01

DeepMedic, an open source software library based on a multi-channel multi-resolution 3D convolutional neural network, has recently been made publicly available for brain lesion segmentations. It has already been shown that segmentation tasks on MRI data of patients having traumatic brain injuries, brain tumors, and ischemic stroke lesions can be performed very well. In this paper we describe how it can efficiently be used for the purpose of detecting and segmenting white matter hyperintensity lesions. We examined if it can be applied to single-channel routine 2D FLAIR data. For evaluation, we annotated 197 datasets with different numbers and sizes of white matter hyperintensity lesions. Our experiments have shown that substantial results with respect to the segmentation quality can be achieved. Compared to the original parametrization of the DeepMedic neural network, the timings for training can be drastically reduced if adjusting corresponding training parameters, while at the same time the Dice coefficients remain nearly unchanged. This enables for performing a whole training process within a single day utilizing a NVIDIA GeForce GTX 580 graphics board which makes this library also very interesting for research purposes on low-end GPU hardware.

Video-based convolutional neural networks for activity recognition from robot-centric videos

NASA Astrophysics Data System (ADS)

Ryoo, M. S.; Matthies, Larry

2016-05-01

In this evaluation paper, we discuss convolutional neural network (CNN)-based approaches for human activity recognition. In particular, we investigate CNN architectures designed to capture temporal information in videos and their applications to the human activity recognition problem. There have been multiple previous works to use CNN-features for videos. These include CNNs using 3-D XYT convolutional filters, CNNs using pooling operations on top of per-frame image-based CNN descriptors, and recurrent neural networks to learn temporal changes in per-frame CNN descriptors. We experimentally compare some of these different representatives CNNs while using first-person human activity videos. We especially focus on videos from a robots viewpoint, captured during its operations and human-robot interactions.

A simplified approach to quasi-linear viscoelastic modeling

PubMed Central

Nekouzadeh, Ali; Pryse, Kenneth M.; Elson, Elliot L.; Genin, Guy M.

2007-01-01

The fitting of quasi-linear viscoelastic (QLV) constitutive models to material data often involves somewhat cumbersome numerical convolution. A new approach to treating quasi-linearity in one dimension is described and applied to characterize the behavior of reconstituted collagen. This approach is based on a new principle for including nonlinearity and requires considerably less computation than other comparable models for both model calibration and response prediction, especially for smoothly applied stretching. Additionally, the approach allows relaxation to adapt with the strain history. The modeling approach is demonstrated through tests on pure reconstituted collagen. Sequences of “ramp-and-hold” stretching tests were applied to rectangular collagen specimens. The relaxation force data from the “hold” was used to calibrate a new “adaptive QLV model” and several models from literature, and the force data from the “ramp” was used to check the accuracy of model predictions. Additionally, the ability of the models to predict the force response on a reloading of the specimen was assessed. The “adaptive QLV model” based on this new approach predicts collagen behavior comparably to or better than existing models, with much less computation. PMID:17499254

Airplane detection based on fusion framework by combining saliency model with Deep Convolutional Neural Networks

NASA Astrophysics Data System (ADS)

Dou, Hao; Sun, Xiao; Li, Bin; Deng, Qianqian; Yang, Xubo; Liu, Di; Tian, Jinwen

2018-03-01

Aircraft detection from very high resolution remote sensing images, has gained more increasing interest in recent years due to the successful civil and military applications. However, several problems still exist: 1) how to extract the high-level features of aircraft; 2) locating objects within such a large image is difficult and time consuming; 3) A common problem of multiple resolutions of satellite images still exists. In this paper, inspirited by biological visual mechanism, the fusion detection framework is proposed, which fusing the top-down visual mechanism (deep CNN model) and bottom-up visual mechanism (GBVS) to detect aircraft. Besides, we use multi-scale training method for deep CNN model to solve the problem of multiple resolutions. Experimental results demonstrate that our method can achieve a better detection result than the other methods.

tf_unet: Generic convolutional neural network U-Net implementation in Tensorflow

NASA Astrophysics Data System (ADS)

Akeret, Joel; Chang, Chihway; Lucchi, Aurelien; Refregier, Alexandre

2016-11-01

tf_unet mitigates radio frequency interference (RFI) signals in radio data using a special type of Convolutional Neural Network, the U-Net, that enables the classification of clean signal and RFI signatures in 2D time-ordered data acquired from a radio telescope. The code is not tied to a specific segmentation and can be used, for example, to detect radio frequency interference (RFI) in radio astronomy or galaxies and stars in widefield imaging data. This U-Net implementation can outperform classical RFI mitigation algorithms.

Single image super-resolution based on convolutional neural networks

NASA Astrophysics Data System (ADS)

Zou, Lamei; Luo, Ming; Yang, Weidong; Li, Peng; Jin, Liujia

2018-03-01

We present a deep learning method for single image super-resolution (SISR). The proposed approach learns end-to-end mapping between low-resolution (LR) images and high-resolution (HR) images. The mapping is represented as a deep convolutional neural network which inputs the LR image and outputs the HR image. Our network uses 5 convolution layers, which kernels size include 5×5, 3×3 and 1×1. In our proposed network, we use residual-learning and combine different sizes of convolution kernels at the same layer. The experiment results show that our proposed method performs better than the existing methods in reconstructing quality index and human visual effects on benchmarked images.

Classification of urine sediment based on convolution neural network

NASA Astrophysics Data System (ADS)

Pan, Jingjing; Jiang, Cunbo; Zhu, Tiantian

2018-04-01

By designing a new convolution neural network framework, this paper breaks the constraints of the original convolution neural network framework requiring large training samples and samples of the same size. Move and cropping the input images, generate the same size of the sub-graph. And then, the generated sub-graph uses the method of dropout, increasing the diversity of samples and preventing the fitting generation. Randomly select some proper subset in the sub-graphic set and ensure that the number of elements in the proper subset is same and the proper subset is not the same. The proper subsets are used as input layers for the convolution neural network. Through the convolution layer, the pooling, the full connection layer and output layer, we can obtained the classification loss rate of test set and training set. In the red blood cells, white blood cells, calcium oxalate crystallization classification experiment, the classification accuracy rate of 97% or more.

3D Convolutional Neural Network for Automatic Detection of Lung Nodules in Chest CT.

PubMed

Hamidian, Sardar; Sahiner, Berkman; Petrick, Nicholas; Pezeshk, Aria

2017-01-01

Deep convolutional neural networks (CNNs) form the backbone of many state-of-the-art computer vision systems for classification and segmentation of 2D images. The same principles and architectures can be extended to three dimensions to obtain 3D CNNs that are suitable for volumetric data such as CT scans. In this work, we train a 3D CNN for automatic detection of pulmonary nodules in chest CT images using volumes of interest extracted from the LIDC dataset. We then convert the 3D CNN which has a fixed field of view to a 3D fully convolutional network (FCN) which can generate the score map for the entire volume efficiently in a single pass. Compared to the sliding window approach for applying a CNN across the entire input volume, the FCN leads to a nearly 800-fold speed-up, and thereby fast generation of output scores for a single case. This screening FCN is used to generate difficult negative examples that are used to train a new discriminant CNN. The overall system consists of the screening FCN for fast generation of candidate regions of interest, followed by the discrimination CNN.

3D convolutional neural network for automatic detection of lung nodules in chest CT

NASA Astrophysics Data System (ADS)

Hamidian, Sardar; Sahiner, Berkman; Petrick, Nicholas; Pezeshk, Aria

2017-03-01

Deep convolutional neural networks (CNNs) form the backbone of many state-of-the-art computer vision systems for classification and segmentation of 2D images. The same principles and architectures can be extended to three dimensions to obtain 3D CNNs that are suitable for volumetric data such as CT scans. In this work, we train a 3D CNN for automatic detection of pulmonary nodules in chest CT images using volumes of interest extracted from the LIDC dataset. We then convert the 3D CNN which has a fixed field of view to a 3D fully convolutional network (FCN) which can generate the score map for the entire volume efficiently in a single pass. Compared to the sliding window approach for applying a CNN across the entire input volume, the FCN leads to a nearly 800-fold speed-up, and thereby fast generation of output scores for a single case. This screening FCN is used to generate difficult negative examples that are used to train a new discriminant CNN. The overall system consists of the screening FCN for fast generation of candidate regions of interest, followed by the discrimination CNN.

Quantifying the interplay effect in prostate IMRT delivery using a convolution-based method.

PubMed

Li, Haisen S; Chetty, Indrin J; Solberg, Timothy D

2008-05-01

The authors present a segment-based convolution method to account for the interplay effect between intrafraction organ motion and the multileaf collimator position for each particular segment in intensity modulated radiation therapy (IMRT) delivered in a step-and-shoot manner. In this method, the static dose distribution attributed to each segment is convolved with the probability density function (PDF) of motion during delivery of the segment, whereas in the conventional convolution method ("average-based convolution"), the static dose distribution is convolved with the PDF averaged over an entire fraction, an entire treatment course, or even an entire patient population. In the case of IMRT delivered in a step-and-shoot manner, the average-based convolution method assumes that in each segment the target volume experiences the same motion pattern (PDF) as that of population. In the segment-based convolution method, the dose during each segment is calculated by convolving the static dose with the motion PDF specific to that segment, allowing both intrafraction motion and the interplay effect to be accounted for in the dose calculation. Intrafraction prostate motion data from a population of 35 patients tracked using the Calypso system (Calypso Medical Technologies, Inc., Seattle, WA) was used to generate motion PDFs. These were then convolved with dose distributions from clinical prostate IMRT plans. For a single segment with a small number of monitor units, the interplay effect introduced errors of up to 25.9% in the mean CTV dose compared against the planned dose evaluated by using the PDF of the entire fraction. In contrast, the interplay effect reduced the minimum CTV dose by 4.4%, and the CTV generalized equivalent uniform dose by 1.3%, in single fraction plans. For entire treatment courses delivered in either a hypofractionated (five fractions) or conventional (> 30 fractions) regimen, the discrepancy in total dose due to interplay effect was negligible.

Cascaded Segmentation-Detection Networks for Word-Level Text Spotting.

PubMed

Qin, Siyang; Manduchi, Roberto

2017-11-01

We introduce an algorithm for word-level text spotting that is able to accurately and reliably determine the bounding regions of individual words of text "in the wild". Our system is formed by the cascade of two convolutional neural networks. The first network is fully convolutional and is in charge of detecting areas containing text. This results in a very reliable but possibly inaccurate segmentation of the input image. The second network (inspired by the popular YOLO architecture) analyzes each segment produced in the first stage, and predicts oriented rectangular regions containing individual words. No post-processing (e.g. text line grouping) is necessary. With execution time of 450 ms for a 1000 × 560 image on a Titan X GPU, our system achieves good performance on the ICDAR 2013, 2015 benchmarks [2], [1].

Convolutional neural network using generated data for SAR ATR with limited samples

NASA Astrophysics Data System (ADS)

Cong, Longjian; Gao, Lei; Zhang, Hui; Sun, Peng

2018-03-01

Being able to adapt all weather at all times, it has been a hot research topic that using Synthetic Aperture Radar(SAR) for remote sensing. Despite all the well-known advantages of SAR, it is hard to extract features because of its unique imaging methodology, and this challenge attracts the research interest of traditional Automatic Target Recognition(ATR) methods. With the development of deep learning technologies, convolutional neural networks(CNNs) give us another way out to detect and recognize targets, when a huge number of samples are available, but this premise is often not hold, when it comes to monitoring a specific type of ships. In this paper, we propose a method to enhance the performance of Faster R-CNN with limited samples to detect and recognize ships in SAR images.

Fast Detection of Airports on Remote Sensing Images with Single Shot MultiBox Detector

NASA Astrophysics Data System (ADS)

Xia, Fei; Li, HuiZhou

2018-01-01

This paper introduces a method for fast airport detection on remote sensing images (RSIs) using Single Shot MultiBox Detector (SSD). To our knowledge, this could be the first study which introduces an end-to-end detection model into airport detection on RSIs. Based on the common low-level features between natural images and RSIs, a convolution neural network trained on large amounts of natural images was transferred to tackle the airport detection problem with limited annotated data. To deal with the specific characteristics of RSIs, some related parameters in the SSD, such as the scales and layers, were modified for more accurate and rapider detection. The experiments show that the proposed method could achieve 83.5% Average Recall at 8 FPS on RSIs with the size of 1024*1024. In contrast to Faster R-CNN, an improvement on AP and speed could be obtained.

Siamese convolutional networks for tracking the spine motion

NASA Astrophysics Data System (ADS)

Liu, Yuan; Sui, Xiubao; Sun, Yicheng; Liu, Chengwei; Hu, Yong

2017-09-01

Deep learning models have demonstrated great success in various computer vision tasks such as image classification and object tracking. However, tracking the lumbar spine by digitalized video fluoroscopic imaging (DVFI), which can quantitatively analyze the motion mode of spine to diagnose lumbar instability, has not yet been well developed due to the lack of steady and robust tracking method. In this paper, we propose a novel visual tracking algorithm of the lumbar vertebra motion based on a Siamese convolutional neural network (CNN) model. We train a full-convolutional neural network offline to learn generic image features. The network is trained to learn a similarity function that compares the labeled target in the first frame with the candidate patches in the current frame. The similarity function returns a high score if the two images depict the same object. Once learned, the similarity function is used to track a previously unseen object without any adapting online. In the current frame, our tracker is performed by evaluating the candidate rotated patches sampled around the previous frame target position and presents a rotated bounding box to locate the predicted target precisely. Results indicate that the proposed tracking method can detect the lumbar vertebra steadily and robustly. Especially for images with low contrast and cluttered background, the presented tracker can still achieve good tracking performance. Further, the proposed algorithm operates at high speed for real time tracking.

Convolutional neural networks for the detection of diseased hearts using CT images and left atrium patches

NASA Astrophysics Data System (ADS)

Dormer, James D.; Halicek, Martin; Ma, Ling; Reilly, Carolyn M.; Schreibmann, Eduard; Fei, Baowei

2018-02-01

Cardiovascular disease is a leading cause of death in the United States. The identification of cardiac diseases on conventional three-dimensional (3D) CT can have many clinical applications. An automated method that can distinguish between healthy and diseased hearts could improve diagnostic speed and accuracy when the only modality available is conventional 3D CT. In this work, we proposed and implemented convolutional neural networks (CNNs) to identify diseased hears on CT images. Six patients with healthy hearts and six with previous cardiovascular disease events received chest CT. After the left atrium for each heart was segmented, 2D and 3D patches were created. A subset of the patches were then used to train separate convolutional neural networks using leave-one-out cross-validation of patient pairs. The results of the two neural networks were compared, with 3D patches producing the higher testing accuracy. The full list of 3D patches from the left atrium was then classified using the optimal 3D CNN model, and the receiver operating curves (ROCs) were produced. The final average area under the curve (AUC) from the ROC curves was 0.840 +/- 0.065 and the average accuracy was 78.9% +/- 5.9%. This demonstrates that the CNN-based method is capable of distinguishing healthy hearts from those with previous cardiovascular disease.

A pre-trained convolutional neural network based method for thyroid nodule diagnosis.

PubMed

Ma, Jinlian; Wu, Fa; Zhu, Jiang; Xu, Dong; Kong, Dexing

2017-01-01

In ultrasound images, most thyroid nodules are in heterogeneous appearances with various internal components and also have vague boundaries, so it is difficult for physicians to discriminate malignant thyroid nodules from benign ones. In this study, we propose a hybrid method for thyroid nodule diagnosis, which is a fusion of two pre-trained convolutional neural networks (CNNs) with different convolutional layers and fully-connected layers. Firstly, the two networks pre-trained with ImageNet database are separately trained. Secondly, we fuse feature maps learned by trained convolutional filters, pooling and normalization operations of the two CNNs. Finally, with the fused feature maps, a softmax classifier is used to diagnose thyroid nodules. The proposed method is validated on 15,000 ultrasound images collected from two local hospitals. Experiment results show that the proposed CNN based methods can accurately and effectively diagnose thyroid nodules. In addition, the fusion of the two CNN based models lead to significant performance improvement, with an accuracy of 83.02%±0.72%. These demonstrate the potential clinical applications of this method. Copyright © 2016 Elsevier B.V. All rights reserved.

A saliency-based approach to detection of infrared target

NASA Astrophysics Data System (ADS)

Chen, Yanfei; Sang, Nong; Dan, Zhiping

2013-10-01

Automatic target detection in infrared images is a hot research field of national defense technology. We propose a new saliency-based infrared target detection model in this paper, which is based on the fact that human focus of attention is directed towards the relevant target to interpret the most promising information. For a given image, the convolution of the image log amplitude spectrum with a low-pass Gaussian kernel of an appropriate scale is equivalent to an image saliency detector in the frequency domain. At the same time, orientation and shape features extracted are combined into a saliency map in the spatial domain. Our proposed model decides salient targets based on a final saliency map, which is generated by integration of the saliency maps in the frequency and spatial domain. At last, the size of each salient target is obtained by maximizing entropy of the final saliency map. Experimental results show that the proposed model can highlight both small and large salient regions in infrared image, as well as inhibit repeated distractors in cluttered image. In addition, its detecting efficiency has improved significantly.

Deep Convolutional Neural Networks for Computer-Aided Detection: CNN Architectures, Dataset Characteristics and Transfer Learning.

PubMed

Shin, Hoo-Chang; Roth, Holger R; Gao, Mingchen; Lu, Le; Xu, Ziyue; Nogues, Isabella; Yao, Jianhua; Mollura, Daniel; Summers, Ronald M

2016-05-01

Remarkable progress has been made in image recognition, primarily due to the availability of large-scale annotated datasets and deep convolutional neural networks (CNNs). CNNs enable learning data-driven, highly representative, hierarchical image features from sufficient training data. However, obtaining datasets as comprehensively annotated as ImageNet in the medical imaging domain remains a challenge. There are currently three major techniques that successfully employ CNNs to medical image classification: training the CNN from scratch, using off-the-shelf pre-trained CNN features, and conducting unsupervised CNN pre-training with supervised fine-tuning. Another effective method is transfer learning, i.e., fine-tuning CNN models pre-trained from natural image dataset to medical image tasks. In this paper, we exploit three important, but previously understudied factors of employing deep convolutional neural networks to computer-aided detection problems. We first explore and evaluate different CNN architectures. The studied models contain 5 thousand to 160 million parameters, and vary in numbers of layers. We then evaluate the influence of dataset scale and spatial image context on performance. Finally, we examine when and why transfer learning from pre-trained ImageNet (via fine-tuning) can be useful. We study two specific computer-aided detection (CADe) problems, namely thoraco-abdominal lymph node (LN) detection and interstitial lung disease (ILD) classification. We achieve the state-of-the-art performance on the mediastinal LN detection, and report the first five-fold cross-validation classification results on predicting axial CT slices with ILD categories. Our extensive empirical evaluation, CNN model analysis and valuable insights can be extended to the design of high performance CAD systems for other medical imaging tasks.

Surface EMG decomposition based on K-means clustering and convolution kernel compensation.

PubMed

Ning, Yong; Zhu, Xiangjun; Zhu, Shanan; Zhang, Yingchun

2015-03-01

A new approach has been developed by combining the K-mean clustering (KMC) method and a modified convolution kernel compensation (CKC) method for multichannel surface electromyogram (EMG) decomposition. The KMC method was first utilized to cluster vectors of observations at different time instants and then estimate the initial innervation pulse train (IPT). The CKC method, modified with a novel multistep iterative process, was conducted to update the estimated IPT. The performance of the proposed K-means clustering-Modified CKC (KmCKC) approach was evaluated by reconstructing IPTs from both simulated and experimental surface EMG signals. The KmCKC approach successfully reconstructed all 10 IPTs from the simulated surface EMG signals with true positive rates (TPR) of over 90% with a low signal-to-noise ratio (SNR) of -10 dB. More than 10 motor units were also successfully extracted from the 64-channel experimental surface EMG signals of the first dorsal interosseous (FDI) muscles when a contraction force was held at 8 N by using the KmCKC approach. A "two-source" test was further conducted with 64-channel surface EMG signals. The high percentage of common MUs and common pulses (over 92% at all force levels) between the IPTs reconstructed from the two independent groups of surface EMG signals demonstrates the reliability and capability of the proposed KmCKC approach in multichannel surface EMG decomposition. Results from both simulated and experimental data are consistent and confirm that the proposed KmCKC approach can successfully reconstruct IPTs with high accuracy at different levels of contraction.

Atomic-resolution single-spin magnetic resonance detection concept based on tunneling force microscopy

NASA Astrophysics Data System (ADS)

Payne, A.; Ambal, K.; Boehme, C.; Williams, C. C.

2015-05-01

A study of a force detected single-spin magnetic resonance measurement concept with atomic spatial resolution is presented. The method is based upon electrostatic force detection of spin-selection rule controlled single-electron tunneling between two electrically isolated paramagnetic states. Single-spin magnetic resonance detection is possible by measuring the force detected tunneling charge noise on and off spin resonance. Simulation results of this charge noise, based upon physical models of the tunneling and spin physics, are directly compared to measured atomic force microscopy system noise. The results show that the approach could provide single-spin measurement of electrically isolated qubit states with atomic spatial resolution at room temperature.

75 FR 77796 - Airworthiness Directives; Saab AB, Saab Aerosystems Model SAAB 2000 Airplanes

Federal Register 2010, 2011, 2012, 2013, 2014

2010-12-14

... of the horizontal stabilizer. Corrosion damage in these areas, if not detected and corrected, can... of the horizontal stabilizer. Corrosion damage in these areas, if not detected and corrected, can... convoluted tubing on the harness, applying corrosion prevention compound to the inspected area, making sure...

Clinical Assistant Diagnosis for Electronic Medical Record Based on Convolutional Neural Network.

PubMed

Yang, Zhongliang; Huang, Yongfeng; Jiang, Yiran; Sun, Yuxi; Zhang, Yu-Jin; Luo, Pengcheng

2018-04-20

Automatically extracting useful information from electronic medical records along with conducting disease diagnoses is a promising task for both clinical decision support(CDS) and neural language processing(NLP). Most of the existing systems are based on artificially constructed knowledge bases, and then auxiliary diagnosis is done by rule matching. In this study, we present a clinical intelligent decision approach based on Convolutional Neural Networks(CNN), which can automatically extract high-level semantic information of electronic medical records and then perform automatic diagnosis without artificial construction of rules or knowledge bases. We use collected 18,590 copies of the real-world clinical electronic medical records to train and test the proposed model. Experimental results show that the proposed model can achieve 98.67% accuracy and 96.02% recall, which strongly supports that using convolutional neural network to automatically learn high-level semantic features of electronic medical records and then conduct assist diagnosis is feasible and effective.

Rapid Target Detection in High Resolution Remote Sensing Images Using Yolo Model

NASA Astrophysics Data System (ADS)

Wu, Z.; Chen, X.; Gao, Y.; Li, Y.

2018-04-01

Object detection in high resolution remote sensing images is a fundamental and challenging problem in the field of remote sensing imagery analysis for civil and military application due to the complex neighboring environments, which can cause the recognition algorithms to mistake irrelevant ground objects for target objects. Deep Convolution Neural Network(DCNN) is the hotspot in object detection for its powerful ability of feature extraction and has achieved state-of-the-art results in Computer Vision. Common pipeline of object detection based on DCNN consists of region proposal, CNN feature extraction, region classification and post processing. YOLO model frames object detection as a regression problem, using a single CNN predicts bounding boxes and class probabilities in an end-to-end way and make the predict faster. In this paper, a YOLO based model is used for object detection in high resolution sensing images. The experiments on NWPU VHR-10 dataset and our airport/airplane dataset gain from GoogleEarth show that, compare with the common pipeline, the proposed model speeds up the detection process and have good accuracy.

Remote pedestrians detection at night time in FIR Image using contrast filtering and locally projected region based CNN

NASA Astrophysics Data System (ADS)

Kim, Taehwan; Kim, Sungho

2017-02-01

This paper presents a novel method to detect the remote pedestrians. After producing the human temperature based brightness enhancement image using the temperature data input, we generates the regions of interest (ROIs) by the multiscale contrast filtering based approach including the biased hysteresis threshold and clustering, remote pedestrian's height, pixel area and central position information. Afterwards, we conduct local vertical and horizontal projection based ROI refinement and weak aspect ratio based ROI limitation to solve the problem of region expansion in the contrast filtering stage. Finally, we detect the remote pedestrians by validating the final ROIs using transfer learning with convolutional neural network (CNN) feature, following non-maximal suppression (NMS) with strong aspect ratio limitation to improve the detection performance. In the experimental results, we confirmed that the proposed contrast filtering and locally projected region based CNN (CFLP-CNN) outperforms the baseline method by 8% in term of logaveraged miss rate. Also, the proposed method is more effective than the baseline approach and the proposed method provides the better regions that are suitably adjusted to the shape and appearance of remote pedestrians, which makes it detect the pedestrian that didn't find in the baseline approach and are able to help detect pedestrians by splitting the people group into a person.

Efficiency optimization of a fast Poisson solver in beam dynamics simulation

NASA Astrophysics Data System (ADS)

Zheng, Dawei; Pöplau, Gisela; van Rienen, Ursula

2016-01-01

Calculating the solution of Poisson's equation relating to space charge force is still the major time consumption in beam dynamics simulations and calls for further improvement. In this paper, we summarize a classical fast Poisson solver in beam dynamics simulations: the integrated Green's function method. We introduce three optimization steps of the classical Poisson solver routine: using the reduced integrated Green's function instead of the integrated Green's function; using the discrete cosine transform instead of discrete Fourier transform for the Green's function; using a novel fast convolution routine instead of an explicitly zero-padded convolution. The new Poisson solver routine preserves the advantages of fast computation and high accuracy. This provides a fast routine for high performance calculation of the space charge effect in accelerators.

Intelligent RF-Based Gesture Input Devices Implemented Using e-Textiles †

PubMed Central

Hughes, Dana; Profita, Halley; Radzihovsky, Sarah; Correll, Nikolaus

2017-01-01

We present an radio-frequency (RF)-based approach to gesture detection and recognition, using e-textile versions of common transmission lines used in microwave circuits. This approach allows for easy fabrication of input swatches that can detect a continuum of finger positions and similarly basic gestures, using a single measurement line. We demonstrate that the swatches can perform gesture detection when under thin layers of cloth or when weatherproofed, providing a high level of versatility not present with other types of approaches. Additionally, using small convolutional neural networks, low-level gestures can be identified with a high level of accuracy using a small, inexpensive microcontroller, allowing for an intelligent fabric that reports only gestures of interest, rather than a simple sensor requiring constant surveillance from an external computing device. The resulting e-textile smart composite has applications in controlling wearable devices by providing a simple, eyes-free mechanism to input simple gestures. PMID:28125010

[Medical computer-aided detection method based on deep learning].

PubMed

Tao, Pan; Fu, Zhongliang; Zhu, Kai; Wang, Lili

2018-03-01

This paper performs a comprehensive study on the computer-aided detection for the medical diagnosis with deep learning. Based on the region convolution neural network and the prior knowledge of target, this algorithm uses the region proposal network, the region of interest pooling strategy, introduces the multi-task loss function: classification loss, bounding box localization loss and object rotation loss, and optimizes it by end-to-end. For medical image it locates the target automatically, and provides the localization result for the next stage task of segmentation. For the detection of left ventricular in echocardiography, proposed additional landmarks such as mitral annulus, endocardial pad and apical position, were used to estimate the left ventricular posture effectively. In order to verify the robustness and effectiveness of the algorithm, the experimental data of ultrasonic and nuclear magnetic resonance images are selected. Experimental results show that the algorithm is fast, accurate and effective.

Intelligent RF-Based Gesture Input Devices Implemented Using e-Textiles.

PubMed

Hughes, Dana; Profita, Halley; Radzihovsky, Sarah; Correll, Nikolaus

2017-01-24

We present an radio-frequency (RF)-based approach to gesture detection and recognition, using e-textile versions of common transmission lines used in microwave circuits. This approach allows for easy fabrication of input swatches that can detect a continuum of finger positions and similarly basic gestures, using a single measurement line. We demonstrate that the swatches can perform gesture detection when under thin layers of cloth or when weatherproofed, providing a high level of versatility not present with other types of approaches. Additionally, using small convolutional neural networks, low-level gestures can be identified with a high level of accuracy using a small, inexpensive microcontroller, allowing for an intelligent fabric that reports only gestures of interest, rather than a simple sensor requiring constant surveillance from an external computing device. The resulting e-textile smart composite has applications in controlling wearable devices by providing a simple, eyes-free mechanism to input simple gestures.

Deep learning based state recognition of substation switches

NASA Astrophysics Data System (ADS)

Wang, Jin

2018-06-01

Different from the traditional method which recognize the state of substation switches based on the running rules of electrical power system, this work proposes a novel convolutional neuron network-based state recognition approach of substation switches. Inspired by the theory of transfer learning, we first establish a convolutional neuron network model trained on the large-scale image set ILSVRC2012, then the restricted Boltzmann machine is employed to replace the full connected layer of the convolutional neuron network and trained on our small image dataset of 110kV substation switches to get a stronger model. Experiments conducted on our image dataset of 110kV substation switches show that, the proposed approach can be applicable to the substation to reduce the running cost and implement the real unattended operation.

Hierarchical graphical-based human pose estimation via local multi-resolution convolutional neural network

NASA Astrophysics Data System (ADS)

Zhu, Aichun; Wang, Tian; Snoussi, Hichem

2018-03-01

This paper addresses the problems of the graphical-based human pose estimation in still images, including the diversity of appearances and confounding background clutter. We present a new architecture for estimating human pose using a Convolutional Neural Network (CNN). Firstly, a Relative Mixture Deformable Model (RMDM) is defined by each pair of connected parts to compute the relative spatial information in the graphical model. Secondly, a Local Multi-Resolution Convolutional Neural Network (LMR-CNN) is proposed to train and learn the multi-scale representation of each body parts by combining different levels of part context. Thirdly, a LMR-CNN based hierarchical model is defined to explore the context information of limb parts. Finally, the experimental results demonstrate the effectiveness of the proposed deep learning approach for human pose estimation.

Optimized color decomposition of localized whole slide images and convolutional neural network for intermediate prostate cancer classification

NASA Astrophysics Data System (ADS)

Zhou, Naiyun; Gao, Yi

2017-03-01

This paper presents a fully automatic approach to grade intermediate prostate malignancy with hematoxylin and eosin-stained whole slide images. Deep learning architectures such as convolutional neural networks have been utilized in the domain of histopathology for automated carcinoma detection and classification. However, few work show its power in discriminating intermediate Gleason patterns, due to sporadic distribution of prostate glands on stained surgical section samples. We propose optimized hematoxylin decomposition on localized images, followed by convolutional neural network to classify Gleason patterns 3+4 and 4+3 without handcrafted features or gland segmentation. Crucial glands morphology and structural relationship of nuclei are extracted twice in different color space by the multi-scale strategy to mimic pathologists' visual examination. Our novel classification scheme evaluated on 169 whole slide images yielded a 70.41% accuracy and corresponding area under the receiver operating characteristic curve of 0.7247.

Reconfigurable Gabor Filter For Fingerprint Recognition Using FPGA Verilog

NASA Astrophysics Data System (ADS)

Rosshidi, H. T.; Hadi, A. R.

2009-06-01

This paper present the implementations of Gabor filter for fingerprint recognition using Verilog HDL. This work demonstrates the application of Gabor Filter technique to enhance the fingerprint image. The incoming signal in form of image pixel will be filter out or convolute by the Gabor filter to define the ridge and valley regions of fingerprint. This is done with the application of a real time convolve based on Field Programmable Gate Array (FPGA) to perform the convolution operation. The main characteristic of the proposed approach are the usage of memory to store the incoming image pixel and the coefficient of the Gabor filter before the convolution matrix take place. The result was the signal convoluted with the Gabor coefficient.

Convolutional neural network for road extraction

NASA Astrophysics Data System (ADS)

Li, Junping; Ding, Yazhou; Feng, Fajie; Xiong, Baoyu; Cui, Weihong

2017-11-01

In this paper, the convolution neural network with large block input and small block output was used to extract road. To reflect the complex road characteristics in the study area, a deep convolution neural network VGG19 was conducted for road extraction. Based on the analysis of the characteristics of different sizes of input block, output block and the extraction effect, the votes of deep convolutional neural networks was used as the final road prediction. The study image was from GF-2 panchromatic and multi-spectral fusion in Yinchuan. The precision of road extraction was 91%. The experiments showed that model averaging can improve the accuracy to some extent. At the same time, this paper gave some advice about the choice of input block size and output block size.

Automated embolic signal detection using Deep Convolutional Neural Network.

PubMed

Sombune, Praotasna; Phienphanich, Phongphan; Phuechpanpaisal, Sutanya; Muengtaweepongsa, Sombat; Ruamthanthong, Anuchit; Tantibundhit, Charturong

2017-07-01

This work investigated the potential of Deep Neural Network in detection of cerebral embolic signal (ES) from transcranial Doppler ultrasound (TCD). The resulting system is aimed to couple with TCD devices in diagnosing a risk of stroke in real-time with high accuracy. The Adaptive Gain Control (AGC) approach developed in our previous study is employed to capture suspected ESs in real-time. By using spectrograms of the same TCD signal dataset as that of our previous work as inputs and the same experimental setup, Deep Convolutional Neural Network (CNN), which can learn features while training, was investigated for its ability to bypass the traditional handcrafted feature extraction and selection process. Extracted feature vectors from the suspected ESs are later determined whether they are of an ES, artifact (AF) or normal (NR) interval. The effectiveness of the developed system was evaluated over 19 subjects going under procedures generating emboli. The CNN-based system could achieve in average of 83.0% sensitivity, 80.1% specificity, and 81.4% accuracy, with considerably much less time consumption in development. The certainly growing set of training samples and computational resources will contribute to high performance. Besides having potential use in various clinical ES monitoring settings, continuation of this promising study will benefit developments of wearable applications by leveraging learnable features to serve demographic differentials.

A Real-Time Method to Estimate Speed of Object Based on Object Detection and Optical Flow Calculation

NASA Astrophysics Data System (ADS)

Liu, Kaizhan; Ye, Yunming; Li, Xutao; Li, Yan

2018-04-01

In recent years Convolutional Neural Network (CNN) has been widely used in computer vision field and makes great progress in lots of contents like object detection and classification. Even so, combining Convolutional Neural Network, which means making multiple CNN frameworks working synchronously and sharing their output information, could figure out useful message that each of them cannot provide singly. Here we introduce a method to real-time estimate speed of object by combining two CNN: YOLOv2 and FlowNet. In every frame, YOLOv2 provides object size; object location and object type while FlowNet providing the optical flow of whole image. On one hand, object size and object location help to select out the object part of optical flow image thus calculating out the average optical flow of every object. On the other hand, object type and object size help to figure out the relationship between optical flow and true speed by means of optics theory and priori knowledge. Therefore, with these two key information, speed of object can be estimated. This method manages to estimate multiple objects at real-time speed by only using a normal camera even in moving status, whose error is acceptable in most application fields like manless driving or robot vision.

CT-scout based, semi-automated vertebral morphometry after digital image enhancement.

PubMed

Glinkowski, Wojciech M; Narloch, Jerzy

2017-09-01

Radiographic diagnosis of osteoporotic vertebral fracture is necessary to reduce its substantial associated morbidity. Computed tomography (CT) scout has recently been demonstrated as a reliable technique for vertebral fracture diagnosis. Software assistance may help to overcome some limitations of that diagnostics. We aimed to evaluate whether digital image enhancement improved the capacity of one of the existing software to detect fractures semi-automatically. CT scanograms of patients suffering from osteoporosis, with or without vertebral fractures were analyzed. The original set of CT scanograms were triplicated and digitally modified to improve edge detection using three different techniques: SHARPENING, UNSHARP MASKING, and CONVOLUTION. The manual morphometric analysis identified 1485 vertebrae, 200 of which were classified as fractured. Unadjusted morphometry (AUTOMATED with no digital enhancement) found 63 fractures, 33 of which were true positive (i.e., it correctly identified 52% of the fractures); SHARPENING detected 57 fractures (30 true positives, 53%); UNSHARP MASKING yielded 30 (13 true positives, 43%); and CONVOLUTION found 24 fractures (9 true positives, 38%). The intra-reader reliability for height ratios did not significantly improve with image enhancement (kappa ranged 0.22-0.41 for adjusted measurements and 0.16-0.38 for unadjusted). Similarly, the inter-reader agreement for prevalent fractures did not significantly improve with image enhancement (kappa 0.29-0.56 and -0.01 to 0.23 for adjusted and unadjusted measurements, respectively). Our results suggest that digital image enhancement does not improve software-assisted vertebral fracture detection by CT scout. Copyright © 2017 Elsevier B.V. All rights reserved.

Aerial Images and Convolutional Neural Network for Cotton Bloom Detection.

PubMed

Xu, Rui; Li, Changying; Paterson, Andrew H; Jiang, Yu; Sun, Shangpeng; Robertson, Jon S

2017-01-01

Monitoring flower development can provide useful information for production management, estimating yield and selecting specific genotypes of crops. The main goal of this study was to develop a methodology to detect and count cotton flowers, or blooms, using color images acquired by an unmanned aerial system. The aerial images were collected from two test fields in 4 days. A convolutional neural network (CNN) was designed and trained to detect cotton blooms in raw images, and their 3D locations were calculated using the dense point cloud constructed from the aerial images with the structure from motion method. The quality of the dense point cloud was analyzed and plots with poor quality were excluded from data analysis. A constrained clustering algorithm was developed to register the same bloom detected from different images based on the 3D location of the bloom. The accuracy and incompleteness of the dense point cloud were analyzed because they affected the accuracy of the 3D location of the blooms and thus the accuracy of the bloom registration result. The constrained clustering algorithm was validated using simulated data, showing good efficiency and accuracy. The bloom count from the proposed method was comparable with the number counted manually with an error of -4 to 3 blooms for the field with a single plant per plot. However, more plots were underestimated in the field with multiple plants per plot due to hidden blooms that were not captured by the aerial images. The proposed methodology provides a high-throughput method to continuously monitor the flowering progress of cotton.

Multi-Frame Convolutional Neural Networks for Object Detection in Temporal Data

DTIC Science & Technology

2017-03-01

maximum 200 words) Given the problem of detecting objects in video , existing neural-network solutions rely on a post-processing step to combine...information across frames and strengthen conclusions. This technique has been successful for videos with simple, dominant objects but it cannot detect objects...Computer Science iii THIS PAGE INTENTIONALLY LEFT BLANK iv ABSTRACT Given the problem of detecting objects in video , existing neural-network solutions rely

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.

LightDenseYOLO: A Fast and Accurate Marker Tracker for Autonomous UAV Landing by Visible Light Camera Sensor on Drone.

PubMed

Nguyen, Phong Ha; Arsalan, Muhammad; Koo, Ja Hyung; Naqvi, Rizwan Ali; Truong, Noi Quang; Park, Kang Ryoung

2018-05-24

Autonomous landing of an unmanned aerial vehicle or a drone is a challenging problem for the robotics research community. Previous researchers have attempted to solve this problem by combining multiple sensors such as global positioning system (GPS) receivers, inertial measurement unit, and multiple camera systems. Although these approaches successfully estimate an unmanned aerial vehicle location during landing, many calibration processes are required to achieve good detection accuracy. In addition, cases where drones operate in heterogeneous areas with no GPS signal should be considered. To overcome these problems, we determined how to safely land a drone in a GPS-denied environment using our remote-marker-based tracking algorithm based on a single visible-light-camera sensor. Instead of using hand-crafted features, our algorithm includes a convolutional neural network named lightDenseYOLO to extract trained features from an input image to predict a marker's location by visible light camera sensor on drone. Experimental results show that our method significantly outperforms state-of-the-art object trackers both using and not using convolutional neural network in terms of both accuracy and processing time.

Vehicle parts detection based on Faster - RCNN with location constraints of vehicle parts feature point

NASA Astrophysics Data System (ADS)

Yang, Liqin; Sang, Nong; Gao, Changxin

2018-03-01

Vehicle parts detection plays an important role in public transportation safety and mobility. The detection of vehicle parts is to detect the position of each vehicle part. We propose a new approach by combining Faster RCNN and three level cascaded convolutional neural network (DCNN). The output of Faster RCNN is a series of bounding boxes with coordinate information, from which we can locate vehicle parts. DCNN can precisely predict feature point position, which is the center of vehicle part. We design an output strategy by combining these two results. There are two advantages for this. The quality of the bounding boxes are greatly improved, which means vehicle parts feature point position can be located more precise. Meanwhile we preserve the position relationship between vehicle parts and effectively improve the validity and reliability of the result. By using our algorithm, the performance of the vehicle parts detection improve obviously compared with Faster RCNN.

Deep learning based classification for head and neck cancer detection with hyperspectral imaging in an animal model

NASA Astrophysics Data System (ADS)

Ma, Ling; Lu, Guolan; Wang, Dongsheng; Wang, Xu; Chen, Zhuo Georgia; Muller, Susan; Chen, Amy; Fei, Baowei

2017-03-01

Hyperspectral imaging (HSI) is an emerging imaging modality that can provide a noninvasive tool for cancer detection and image-guided surgery. HSI acquires high-resolution images at hundreds of spectral bands, providing big data to differentiating different types of tissue. We proposed a deep learning based method for the detection of head and neck cancer with hyperspectral images. Since the deep learning algorithm can learn the feature hierarchically, the learned features are more discriminative and concise than the handcrafted features. In this study, we adopt convolutional neural networks (CNN) to learn the deep feature of pixels for classifying each pixel into tumor or normal tissue. We evaluated our proposed classification method on the dataset containing hyperspectral images from 12 tumor-bearing mice. Experimental results show that our method achieved an average accuracy of 91.36%. The preliminary study demonstrated that our deep learning method can be applied to hyperspectral images for detecting head and neck tumors in animal models.

Accurate Natural Trail Detection Using a Combination of a Deep Neural Network and Dynamic Programming.

PubMed

Adhikari, Shyam Prasad; Yang, Changju; Slot, Krzysztof; Kim, Hyongsuk

2018-01-10

This paper presents a vision sensor-based solution to the challenging problem of detecting and following trails in highly unstructured natural environments like forests, rural areas and mountains, using a combination of a deep neural network and dynamic programming. The deep neural network (DNN) concept has recently emerged as a very effective tool for processing vision sensor signals. A patch-based DNN is trained with supervised data to classify fixed-size image patches into "trail" and "non-trail" categories, and reshaped to a fully convolutional architecture to produce trail segmentation map for arbitrary-sized input images. As trail and non-trail patches do not exhibit clearly defined shapes or forms, the patch-based classifier is prone to misclassification, and produces sub-optimal trail segmentation maps. Dynamic programming is introduced to find an optimal trail on the sub-optimal DNN output map. Experimental results showing accurate trail detection for real-world trail datasets captured with a head mounted vision system are presented.

Transfer Function Bounds for Partial-unit-memory Convolutional Codes Based on Reduced State Diagram

NASA Technical Reports Server (NTRS)

Lee, P. J.

1984-01-01

The performance of a coding system consisting of a convolutional encoder and a Viterbi decoder is analytically found by the well-known transfer function bounding technique. For the partial-unit-memory byte-oriented convolutional encoder with m sub 0 binary memory cells and (k sub 0 m sub 0) inputs, a state diagram of 2(K) (sub 0) was for the transfer function bound. A reduced state diagram of (2 (m sub 0) +1) is used for easy evaluation of transfer function bounds for partial-unit-memory codes.

Automated sub-cortical brain structure segmentation combining spatial and deep convolutional features.

PubMed

Kushibar, Kaisar; Valverde, Sergi; González-Villà, Sandra; Bernal, Jose; Cabezas, Mariano; Oliver, Arnau; Lladó, Xavier

2018-06-15

Sub-cortical brain structure segmentation in Magnetic Resonance Images (MRI) has attracted the interest of the research community for a long time as morphological changes in these structures are related to different neurodegenerative disorders. However, manual segmentation of these structures can be tedious and prone to variability, highlighting the need for robust automated segmentation methods. In this paper, we present a novel convolutional neural network based approach for accurate segmentation of the sub-cortical brain structures that combines both convolutional and prior spatial features for improving the segmentation accuracy. In order to increase the accuracy of the automated segmentation, we propose to train the network using a restricted sample selection to force the network to learn the most difficult parts of the structures. We evaluate the accuracy of the proposed method on the public MICCAI 2012 challenge and IBSR 18 datasets, comparing it with different traditional and deep learning state-of-the-art methods. On the MICCAI 2012 dataset, our method shows an excellent performance comparable to the best participant strategy on the challenge, while performing significantly better than state-of-the-art techniques such as FreeSurfer and FIRST. On the IBSR 18 dataset, our method also exhibits a significant increase in the performance with respect to not only FreeSurfer and FIRST, but also comparable or better results than other recent deep learning approaches. Moreover, our experiments show that both the addition of the spatial priors and the restricted sampling strategy have a significant effect on the accuracy of the proposed method. In order to encourage the reproducibility and the use of the proposed method, a public version of our approach is available to download for the neuroimaging community. Copyright © 2018 The Authors. Published by Elsevier B.V. All rights reserved.

Real-Time Blob-Wise Sugar Beets VS Weeds Classification for Monitoring Fields Using Convolutional Neural Networks

NASA Astrophysics Data System (ADS)

Milioto, A.; Lottes, P.; Stachniss, C.

2017-08-01

UAVs are becoming an important tool for field monitoring and precision farming. A prerequisite for observing and analyzing fields is the ability to identify crops and weeds from image data. In this paper, we address the problem of detecting the sugar beet plants and weeds in the field based solely on image data. We propose a system that combines vegetation detection and deep learning to obtain a high-quality classification of the vegetation in the field into value crops and weeds. We implemented and thoroughly evaluated our system on image data collected from different sugar beet fields and illustrate that our approach allows for accurately identifying the weeds on the field.

Fast object detection algorithm based on HOG and CNN

NASA Astrophysics Data System (ADS)

Lu, Tongwei; Wang, Dandan; Zhang, Yanduo

2018-04-01

In the field of computer vision, object classification and object detection are widely used in many fields. The traditional object detection have two main problems:one is that sliding window of the regional selection strategy is high time complexity and have window redundancy. And the other one is that Robustness of the feature is not well. In order to solve those problems, Regional Proposal Network (RPN) is used to select candidate regions instead of selective search algorithm. Compared with traditional algorithms and selective search algorithms, RPN has higher efficiency and accuracy. We combine HOG feature and convolution neural network (CNN) to extract features. And we use SVM to classify. For TorontoNet, our algorithm's mAP is 1.6 percentage points higher. For OxfordNet, our algorithm's mAP is 1.3 percentage higher.

Deep Convolutional Framelet Denosing for Low-Dose CT via Wavelet Residual Network.

PubMed

Kang, Eunhee; Chang, Won; Yoo, Jaejun; Ye, Jong Chul

2018-06-01

Model-based iterative reconstruction algorithms for low-dose X-ray computed tomography (CT) are computationally expensive. To address this problem, we recently proposed a deep convolutional neural network (CNN) for low-dose X-ray CT and won the second place in 2016 AAPM Low-Dose CT Grand Challenge. However, some of the textures were not fully recovered. To address this problem, here we propose a novel framelet-based denoising algorithm using wavelet residual network which synergistically combines the expressive power of deep learning and the performance guarantee from the framelet-based denoising algorithms. The new algorithms were inspired by the recent interpretation of the deep CNN as a cascaded convolution framelet signal representation. Extensive experimental results confirm that the proposed networks have significantly improved performance and preserve the detail texture of the original images.

Deep architecture neural network-based real-time image processing for image-guided radiotherapy.

PubMed

Mori, Shinichiro

2017-08-01

To develop real-time image processing for image-guided radiotherapy, we evaluated several neural network models for use with different imaging modalities, including X-ray fluoroscopic image denoising. Setup images of prostate cancer patients were acquired with two oblique X-ray fluoroscopic units. Two types of residual network were designed: a convolutional autoencoder (rCAE) and a convolutional neural network (rCNN). We changed the convolutional kernel size and number of convolutional layers for both networks, and the number of pooling and upsampling layers for rCAE. The ground-truth image was applied to the contrast-limited adaptive histogram equalization (CLAHE) method of image processing. Network models were trained to keep the quality of the output image close to that of the ground-truth image from the input image without image processing. For image denoising evaluation, noisy input images were used for the training. More than 6 convolutional layers with convolutional kernels >5×5 improved image quality. However, this did not allow real-time imaging. After applying a pair of pooling and upsampling layers to both networks, rCAEs with >3 convolutions each and rCNNs with >12 convolutions with a pair of pooling and upsampling layers achieved real-time processing at 30 frames per second (fps) with acceptable image quality. Use of our suggested network achieved real-time image processing for contrast enhancement and image denoising by the use of a conventional modern personal computer. Copyright © 2017 Associazione Italiana di Fisica Medica. Published by Elsevier Ltd. All rights reserved.

A comparison of the convolution and TMR10 treatment planning algorithms for Gamma Knife® radiosurgery

PubMed Central

Wright, Gavin; Harrold, Natalie; Bownes, Peter

2018-01-01

Aims To compare the accuracies of the convolution and TMR10 Gamma Knife treatment planning algorithms, and assess the impact upon clinical practice of implementing convolution-based treatment planning. Methods Doses calculated by both algorithms were compared against ionisation chamber measurements in homogeneous and heterogeneous phantoms. Relative dose distributions calculated by both algorithms were compared against film-derived 2D isodose plots in a heterogeneous phantom, with distance-to-agreement (DTA) measured at the 80%, 50% and 20% isodose levels. A retrospective planning study compared 19 clinically acceptable metastasis convolution plans against TMR10 plans with matched shot times, allowing novel comparison of true dosimetric parameters rather than total beam-on-time. Gamma analysis and dose-difference analysis were performed on each pair of dose distributions. Results Both algorithms matched point dose measurement within ±1.1% in homogeneous conditions. Convolution provided superior point-dose accuracy in the heterogeneous phantom (-1.1% v 4.0%), with no discernible differences in relative dose distribution accuracy. In our study convolution-calculated plans yielded D99% 6.4% (95% CI:5.5%-7.3%,p<0.001) less than shot matched TMR10 plans. For gamma passing criteria 1%/1mm, 16% of targets had passing rates >95%. The range of dose differences in the targets was 0.2-4.6Gy. Conclusions Convolution provides superior accuracy versus TMR10 in heterogeneous conditions. Implementing convolution would result in increased target doses therefore its implementation may require a revaluation of prescription doses. PMID:29657896

Error control techniques for satellite and space communications

NASA Technical Reports Server (NTRS)

Costello, Daniel J., Jr.

1992-01-01

Worked performed during the reporting period is summarized. Construction of robustly good trellis codes for use with sequential decoding was developed. The robustly good trellis codes provide a much better trade off between free distance and distance profile. The unequal error protection capabilities of convolutional codes was studied. The problem of finding good large constraint length, low rate convolutional codes for deep space applications is investigated. A formula for computing the free distance of 1/n convolutional codes was discovered. Double memory (DM) codes, codes with two memory units per unit bit position, were studied; a search for optimal DM codes is being conducted. An algorithm for constructing convolutional codes from a given quasi-cyclic code was developed. Papers based on the above work are included in the appendix.

Real-time dose computation: GPU-accelerated source modeling and superposition/convolution

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

Jacques, Robert; Wong, John; Taylor, Russell

Purpose: To accelerate dose calculation to interactive rates using highly parallel graphics processing units (GPUs). Methods: The authors have extended their prior work in GPU-accelerated superposition/convolution with a modern dual-source model and have enhanced performance. The primary source algorithm supports both focused leaf ends and asymmetric rounded leaf ends. The extra-focal algorithm uses a discretized, isotropic area source and models multileaf collimator leaf height effects. The spectral and attenuation effects of static beam modifiers were integrated into each source's spectral function. The authors introduce the concepts of arc superposition and delta superposition. Arc superposition utilizes separate angular sampling for themore » total energy released per unit mass (TERMA) and superposition computations to increase accuracy and performance. Delta superposition allows single beamlet changes to be computed efficiently. The authors extended their concept of multi-resolution superposition to include kernel tilting. Multi-resolution superposition approximates solid angle ray-tracing, improving performance and scalability with a minor loss in accuracy. Superposition/convolution was implemented using the inverse cumulative-cumulative kernel and exact radiological path ray-tracing. The accuracy analyses were performed using multiple kernel ray samplings, both with and without kernel tilting and multi-resolution superposition. Results: Source model performance was <9 ms (data dependent) for a high resolution (400{sup 2}) field using an NVIDIA (Santa Clara, CA) GeForce GTX 280. Computation of the physically correct multispectral TERMA attenuation was improved by a material centric approach, which increased performance by over 80%. Superposition performance was improved by {approx}24% to 0.058 and 0.94 s for 64{sup 3} and 128{sup 3} water phantoms; a speed-up of 101-144x over the highly optimized Pinnacle{sup 3} (Philips, Madison, WI) implementation. Pinnacle{sup 3} times were 8.3 and 94 s, respectively, on an AMD (Sunnyvale, CA) Opteron 254 (two cores, 2.8 GHz). Conclusions: The authors have completed a comprehensive, GPU-accelerated dose engine in order to provide a substantial performance gain over CPU based implementations. Real-time dose computation is feasible with the accuracy levels of the superposition/convolution algorithm.« less

Human Brain Organoids on a Chip Reveal the Physics of Folding.

PubMed

Karzbrun, Eyal; Kshirsagar, Aditya; Cohen, Sidney R; Hanna, Jacob H; Reiner, Orly

2018-05-01

Human brain wrinkling has been implicated in neurodevelopmental disorders and yet its origins remain unknown. Polymer gel models suggest that wrinkling emerges spontaneously due to compression forces arising during differential swelling, but these ideas have not been tested in a living system. Here, we report the appearance of surface wrinkles during the in vitro development and self-organization of human brain organoids in a micro-fabricated compartment that supports in situ imaging over a timescale of weeks. We observe the emergence of convolutions at a critical cell density and maximal nuclear strain, which are indicative of a mechanical instability. We identify two opposing forces contributing to differential growth: cytoskeletal contraction at the organoid core and cell-cycle-dependent nuclear expansion at the organoid perimeter. The wrinkling wavelength exhibits linear scaling with tissue thickness, consistent with balanced bending and stretching energies. Lissencephalic (smooth brain) organoids display reduced convolutions, modified scaling and a reduced elastic modulus. Although the mechanism here does not include the neuronal migration seen in in vivo , it models the physics of the folding brain remarkably well. Our on-chip approach offers a means for studying the emergent properties of organoid development, with implications for the embryonic human brain.

Human brain organoids on a chip reveal the physics of folding

NASA Astrophysics Data System (ADS)

Karzbrun, Eyal; Kshirsagar, Aditya; Cohen, Sidney R.; Hanna, Jacob H.; Reiner, Orly

2018-05-01

Human brain wrinkling has been implicated in neurodevelopmental disorders and yet its origins remain unknown. Polymer gel models suggest that wrinkling emerges spontaneously due to compression forces arising during differential swelling, but these ideas have not been tested in a living system. Here, we report the appearance of surface wrinkles during the in vitro development and self-organization of human brain organoids in a microfabricated compartment that supports in situ imaging over a timescale of weeks. We observe the emergence of convolutions at a critical cell density and maximal nuclear strain, which are indicative of a mechanical instability. We identify two opposing forces contributing to differential growth: cytoskeletal contraction at the organoid core and cell-cycle-dependent nuclear expansion at the organoid perimeter. The wrinkling wavelength exhibits linear scaling with tissue thickness, consistent with balanced bending and stretching energies. Lissencephalic (smooth brain) organoids display reduced convolutions, modified scaling and a reduced elastic modulus. Although the mechanism here does not include the neuronal migration seen in vivo, it models the physics of the folding brain remarkably well. Our on-chip approach offers a means for studying the emergent properties of organoid development, with implications for the embryonic human brain.

Lung nodule detection from CT scans using 3D convolutional neural networks without candidate selection

NASA Astrophysics Data System (ADS)

Jenuwine, Natalia M.; Mahesh, Sunny N.; Furst, Jacob D.; Raicu, Daniela S.

2018-02-01

Early detection of lung nodules from CT scans is key to improving lung cancer treatment, but poses a significant challenge for radiologists due to the high throughput required of them. Computer-Aided Detection (CADe) systems aim to automatically detect these nodules with computer algorithms, thus improving diagnosis. These systems typically use a candidate selection step, which identifies all objects that resemble nodules, followed by a machine learning classifier which separates true nodules from false positives. We create a CADe system that uses a 3D convolutional neural network (CNN) to detect nodules in CT scans without a candidate selection step. Using data from the LIDC database, we train a 3D CNN to analyze subvolumes from anywhere within a CT scan and output the probability that each subvolume contains a nodule. Once trained, we apply our CNN to detect nodules from entire scans, by systematically dividing the scan into overlapping subvolumes which we input into the CNN to obtain the corresponding probabilities. By enabling our network to process an entire scan, we expect to streamline the detection process while maintaining its effectiveness. Our results imply that with continued training using an iterative training scheme, the one-step approach has the potential to be highly effective.

Dimensionality-varied convolutional neural network for spectral-spatial classification of hyperspectral data

NASA Astrophysics Data System (ADS)

Liu, Wanjun; Liang, Xuejian; Qu, Haicheng

2017-11-01

Hyperspectral image (HSI) classification is one of the most popular topics in remote sensing community. Traditional and deep learning-based classification methods were proposed constantly in recent years. In order to improve the classification accuracy and robustness, a dimensionality-varied convolutional neural network (DVCNN) was proposed in this paper. DVCNN was a novel deep architecture based on convolutional neural network (CNN). The input of DVCNN was a set of 3D patches selected from HSI which contained spectral-spatial joint information. In the following feature extraction process, each patch was transformed into some different 1D vectors by 3D convolution kernels, which were able to extract features from spectral-spatial data. The rest of DVCNN was about the same as general CNN and processed 2D matrix which was constituted by by all 1D data. So that the DVCNN could not only extract more accurate and rich features than CNN, but also fused spectral-spatial information to improve classification accuracy. Moreover, the robustness of network on water-absorption bands was enhanced in the process of spectral-spatial fusion by 3D convolution, and the calculation was simplified by dimensionality varied convolution. Experiments were performed on both Indian Pines and Pavia University scene datasets, and the results showed that the classification accuracy of DVCNN improved by 32.87% on Indian Pines and 19.63% on Pavia University scene than spectral-only CNN. The maximum accuracy improvement of DVCNN achievement was 13.72% compared with other state-of-the-art HSI classification methods, and the robustness of DVCNN on water-absorption bands noise was demonstrated.

A primitive study on unsupervised anomaly detection with an autoencoder in emergency head CT volumes

NASA Astrophysics Data System (ADS)

Sato, Daisuke; Hanaoka, Shouhei; Nomura, Yukihiro; Takenaga, Tomomi; Miki, Soichiro; Yoshikawa, Takeharu; Hayashi, Naoto; Abe, Osamu

2018-02-01

Purpose: The target disorders of emergency head CT are wide-ranging. Therefore, people working in an emergency department desire a computer-aided detection system for general disorders. In this study, we proposed an unsupervised anomaly detection method in emergency head CT using an autoencoder and evaluated the anomaly detection performance of our method in emergency head CT. Methods: We used a 3D convolutional autoencoder (3D-CAE), which contains 11 layers in the convolution block and 6 layers in the deconvolution block. In the training phase, we trained the 3D-CAE using 10,000 3D patches extracted from 50 normal cases. In the test phase, we calculated abnormalities of each voxel in 38 emergency head CT volumes (22 abnormal cases and 16 normal cases) for evaluation and evaluated the likelihood of lesion existence. Results: Our method achieved a sensitivity of 68% and a specificity of 88%, with an area under the curve of the receiver operating characteristic curve of 0.87. It shows that this method has a moderate accuracy to distinguish normal CT cases to abnormal ones. Conclusion: Our method has potentialities for anomaly detection in emergency head CT.

Convolution Comparison Pattern: An Efficient Local Image Descriptor for Fingerprint Liveness Detection

PubMed Central

Gottschlich, Carsten

2016-01-01

We present a new type of local image descriptor which yields binary patterns from small image patches. For the application to fingerprint liveness detection, we achieve rotation invariant image patches by taking the fingerprint segmentation and orientation field into account. We compute the discrete cosine transform (DCT) for these rotation invariant patches and attain binary patterns by comparing pairs of two DCT coefficients. These patterns are summarized into one or more histograms per image. Each histogram comprises the relative frequencies of pattern occurrences. Multiple histograms are concatenated and the resulting feature vector is used for image classification. We name this novel type of descriptor convolution comparison pattern (CCP). Experimental results show the usefulness of the proposed CCP descriptor for fingerprint liveness detection. CCP outperforms other local image descriptors such as LBP, LPQ and WLD on the LivDet 2013 benchmark. The CCP descriptor is a general type of local image descriptor which we expect to prove useful in areas beyond fingerprint liveness detection such as biological and medical image processing, texture recognition, face recognition and iris recognition, liveness detection for face and iris images, and machine vision for surface inspection and material classification. PMID:26844544

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.

Distribution System Audits, Leak Detection, and Repair: Kirtland Air Force Base Leak Detection and Repair Program

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

None

Water Best Management Practice #3 Fact Seet: Outlines how a leak detection and repair program helped Kirtland Air Force Base perform distribution system audits, leak detection, and repair to conserve water site-wide.

a Cloud Boundary Detection Scheme Combined with Aslic and Cnn Using ZY-3, GF-1/2 Satellite Imagery

NASA Astrophysics Data System (ADS)

Guo, Z.; Li, C.; Wang, Z.; Kwok, E.; Wei, X.

2018-04-01

Remote sensing optical image cloud detection is one of the most important problems in remote sensing data processing. Aiming at the information loss caused by cloud cover, a cloud detection method based on convolution neural network (CNN) is presented in this paper. Firstly, a deep CNN network is used to extract the multi-level feature generation model of cloud from the training samples. Secondly, the adaptive simple linear iterative clustering (ASLIC) method is used to divide the detected images into superpixels. Finally, the probability of each superpixel belonging to the cloud region is predicted by the trained network model, thereby generating a cloud probability map. The typical region of GF-1/2 and ZY-3 were selected to carry out the cloud detection test, and compared with the traditional SLIC method. The experiment results show that the average accuracy of cloud detection is increased by more than 5 %, and it can detected thin-thick cloud and the whole cloud boundary well on different imaging platforms.

A deep learning model observer for use in alterative forced choice virtual clinical trials

NASA Astrophysics Data System (ADS)

Alnowami, M.; Mills, G.; Awis, M.; Elangovanr, P.; Patel, M.; Halling-Brown, M.; Young, K. C.; Dance, D. R.; Wells, K.

2018-03-01

Virtual clinical trials (VCTs) represent an alternative assessment paradigm that overcomes issues of dose, high cost and delay encountered in conventional clinical trials for breast cancer screening. However, to fully utilize the potential benefits of VCTs requires a machine-based observer that can rapidly and realistically process large numbers of experimental conditions. To address this, a Deep Learning Model Observer (DLMO) was developed and trained to identify lesion targets from normal tissue in small (200 x 200 pixel) image segments, as used in Alternative Forced Choice (AFC) studies. The proposed network consists of 5 convolutional layers with 2x2 kernels and ReLU (Rectified Linear Unit) activations, followed by max pooling with size equal to the size of the final feature maps and three dense layers. The class outputs weights from the final fully connected dense layer are used to consider sets of n images in an n-AFC paradigm to determine the image most likely to contain a target. To examine the DLMO performance on clinical data, a training set of 2814 normal and 2814 biopsy-confirmed malignant mass targets were used. This produced a sensitivity of 0.90 and a specificity of 0.92 when presented with a test data set of 800 previously unseen clinical images. To examine the DLMOs minimum detectable contrast, a second dataset of 630 simulated backgrounds and 630 images with simulated lesion and spherical targets (4mm and 6mm diameter), produced contrast thresholds equivalent to/better than human observer performance for spherical targets, and comparable (12 % difference) for lesion targets.

A unitary convolution approximation for the impact-parameter dependent electronic energy loss

NASA Astrophysics Data System (ADS)

Schiwietz, G.; Grande, P. L.

1999-06-01

In this work, we propose a simple method to calculate the impact-parameter dependence of the electronic energy loss of bare ions for all impact parameters. This perturbative convolution approximation (PCA) is based on first-order perturbation theory, and thus, it is only valid for fast particles with low projectile charges. Using Bloch's stopping-power result and a simple scaling, we get rid of the restriction to low charge states and derive the unitary convolution approximation (UCA). Results of the UCA are then compared with full quantum-mechanical coupled-channel calculations for the impact-parameter dependent electronic energy loss.

Identification and Classification of Orthogonal Frequency Division Multiple Access (OFDMA) Signals Used in Next Generation Wireless Systems

DTIC Science & Technology

2012-03-01

advanced antenna systems AMC adaptive modulation and coding AWGN additive white Gaussian noise BPSK binary phase shift keying BS base station BTC ...QAM-16, and QAM-64, and coding types include convolutional coding (CC), convolutional turbo coding (CTC), block turbo coding ( BTC ), zero-terminating

Fourier-Accelerated Nodal Solvers (FANS) for homogenization problems

NASA Astrophysics Data System (ADS)

Leuschner, Matthias; Fritzen, Felix

2017-11-01

Fourier-based homogenization schemes are useful to analyze heterogeneous microstructures represented by 2D or 3D image data. These iterative schemes involve discrete periodic convolutions with global ansatz functions (mostly fundamental solutions). The convolutions are efficiently computed using the fast Fourier transform. FANS operates on nodal variables on regular grids and converges to finite element solutions. Compared to established Fourier-based methods, the number of convolutions is reduced by FANS. Additionally, fast iterations are possible by assembling the stiffness matrix. Due to the related memory requirement, the method is best suited for medium-sized problems. A comparative study involving established Fourier-based homogenization schemes is conducted for a thermal benchmark problem with a closed-form solution. Detailed technical and algorithmic descriptions are given for all methods considered in the comparison. Furthermore, many numerical examples focusing on convergence properties for both thermal and mechanical problems, including also plasticity, are presented.

An Impulse Based Substructuring approach for impact analysis and load case simulations

NASA Astrophysics Data System (ADS)

Rixen, Daniel J.; van der Valk, Paul L. C.

2013-12-01

In the present paper we outline the basic theory of assembling substructures for which the dynamics are described as Impulse Response Functions. The assembly procedure computes the time response of a system by evaluating per substructure the convolution product between the Impulse Response Functions and the applied forces, including the interface forces that are computed to satisfy the interface compatibility. We call this approach the Impulse Based Substructuring method since it transposes to the time domain the Frequency Based Substructuring approach. In the Impulse Based Substructuring technique the Impulse Response Functions of the substructures can be gathered either from experimental tests using a hammer impact or from time-integration of numerical submodels. In this paper the implementation of the method is outlined for the case when the impulse responses of the substructures are computed numerically. A simple bar example is shown in order to illustrate the concept. The Impulse Based Substructuring allows fast evaluation of impact response of a structure when the impulse response of its components is known. It can thus be used to efficiently optimize designs of consumer products by including impact behavior at the early stage of the design, but also for performing substructured simulations of complex structures such as offshore wind turbines.

Application of deep learning in determining IR precipitation occurrence: a Convolutional Neural Network model

NASA Astrophysics Data System (ADS)

Wang, C.; Hong, Y.

2017-12-01

Infrared (IR) information from Geostationary satellites can be used to retrieve precipitation at pretty high spatiotemporal resolutions. Traditional artificial intelligence (AI) methodologies, such as artificial neural networks (ANN), have been designed to build the relationship between near-surface precipitation and manually derived IR features in products including PERSIANN and PERSIANN-CCS. This study builds an automatic precipitation detection model based on IR data using Convolutional Neural Network (CNN) which is implemented by the newly developed deep learning framework, Caffe. The model judges whether there is rain or no rain at pixel level. Compared with traditional ANN methods, CNN can extract features inside the raw data automatically and thoroughly. In this study, IR data from GOES satellites and precipitation estimates from the next generation QPE (Q2) over the central United States are used as inputs and labels, respectively. The whole datasets during the study period (June to August in 2012) are randomly partitioned to three sub datasets (train, validation and test) to establish the model at the spatial resolution of 0.08°×0.08° and the temporal resolution of 1 hour. The experiments show great improvements of CNN in rain identification compared to the widely used IR-based precipitation product, i.e., PERSIANN-CCS. The overall gain in performance is about 30% for critical success index (CSI), 32% for probability of detection (POD) and 12% for false alarm ratio (FAR). Compared to other recent IR-based precipitation retrieval methods (e.g., PERSIANN-DL developed by University of California Irvine), our model is simpler with less parameters, but achieves equally or even better results. CNN has been applied in computer vision domain successfully, and our results prove the method is suitable for IR precipitation detection. Future studies can expand the application of CNN from precipitation occurrence decision to precipitation amount retrieval.

Electrochemical reduction of carbon fluorine bond in 4-fluorobenzonitrile Mechanistic analysis employing Marcus Hush quadratic activation-driving force relation

NASA Astrophysics Data System (ADS)

Muthukrishnan, A.; Sangaranarayanan, M. V.

2007-10-01

The reduction of carbon-fluorine bond in 4-fluorobenzonitrile in acetonitrile as the solvent, is analyzed using convolution potential sweep voltammetry and the dependence of the transfer coefficient on potential is investigated within the framework of Marcus-Hush quadratic activation-driving force theory. The validity of stepwise mechanism is inferred from solvent reorganization energy estimates as well as bond length calculations using B3LYP/6-31g(d) method. A novel method of estimating the standard reduction potential of the 4-fluorobenzonitrile in acetonitrile is proposed.

Adaptive Correlation Model for Visual Tracking Using Keypoints Matching and Deep Convolutional Feature.

PubMed

Li, Yuankun; Xu, Tingfa; Deng, Honggao; Shi, Guokai; Guo, Jie

2018-02-23

Although correlation filter (CF)-based visual tracking algorithms have achieved appealing results, there are still some problems to be solved. When the target object goes through long-term occlusions or scale variation, the correlation model used in existing CF-based algorithms will inevitably learn some non-target information or partial-target information. In order to avoid model contamination and enhance the adaptability of model updating, we introduce the keypoints matching strategy and adjust the model learning rate dynamically according to the matching score. Moreover, the proposed approach extracts convolutional features from a deep convolutional neural network (DCNN) to accurately estimate the position and scale of the target. Experimental results demonstrate that the proposed tracker has achieved satisfactory performance in a wide range of challenging tracking scenarios.

Breast tumor segmentation in DCE-MRI using fully convolutional networks with an application in radiogenomics

NASA Astrophysics Data System (ADS)

Zhang, Jun; Saha, Ashirbani; Zhu, Zhe; Mazurowski, Maciej A.

2018-02-01

Breast tumor segmentation based on dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) remains an active as well as a challenging problem. Previous studies often rely on manual annotation for tumor regions, which is not only time-consuming but also error-prone. Recent studies have shown high promise of deep learning-based methods in various segmentation problems. However, these methods are usually faced with the challenge of limited number (e.g., tens or hundreds) of medical images for training, leading to sub-optimal segmentation performance. Also, previous methods cannot efficiently deal with prevalent class-imbalance problems in tumor segmentation, where the number of voxels in tumor regions is much lower than that in the background area. To address these issues, in this study, we propose a mask-guided hierarchical learning (MHL) framework for breast tumor segmentation via fully convolutional networks (FCN). Our strategy is first decomposing the original difficult problem into several sub-problems and then solving these relatively simpler sub-problems in a hierarchical manner. To precisely identify locations of tumors that underwent a biopsy, we further propose an FCN model to detect two landmarks defined on nipples. Finally, based on both segmentation probability maps and our identified landmarks, we proposed to select biopsied tumors from all detected tumors via a tumor selection strategy using the pathology location. We validate our MHL method using data for 272 patients, and achieve a mean Dice similarity coefficient (DSC) of 0.72 in breast tumor segmentation. Finally, in a radiogenomic analysis, we show that a previously developed image features show a comparable performance for identifying luminal A subtype when applied to the automatic segmentation and a semi-manual segmentation demonstrating a high promise for fully automated radiogenomic analysis in breast cancer.

Fully Convolutional Network-Based Multifocus Image Fusion.

PubMed

Guo, Xiaopeng; Nie, Rencan; Cao, Jinde; Zhou, Dongming; Qian, Wenhua

2018-07-01

As the optical lenses for cameras always have limited depth of field, the captured images with the same scene are not all in focus. Multifocus image fusion is an efficient technology that can synthesize an all-in-focus image using several partially focused images. Previous methods have accomplished the fusion task in spatial or transform domains. However, fusion rules are always a problem in most methods. In this letter, from the aspect of focus region detection, we propose a novel multifocus image fusion method based on a fully convolutional network (FCN) learned from synthesized multifocus images. The primary novelty of this method is that the pixel-wise focus regions are detected through a learning FCN, and the entire image, not just the image patches, are exploited to train the FCN. First, we synthesize 4500 pairs of multifocus images by repeatedly using a gaussian filter for each image from PASCAL VOC 2012, to train the FCN. After that, a pair of source images is fed into the trained FCN, and two score maps indicating the focus property are generated. Next, an inversed score map is averaged with another score map to produce an aggregative score map, which take full advantage of focus probabilities in two score maps. We implement the fully connected conditional random field (CRF) on the aggregative score map to accomplish and refine a binary decision map for the fusion task. Finally, we exploit the weighted strategy based on the refined decision map to produce the fused image. To demonstrate the performance of the proposed method, we compare its fused results with several start-of-the-art methods not only on a gray data set but also on a color data set. Experimental results show that the proposed method can achieve superior fusion performance in both human visual quality and objective assessment.

A fully convolutional networks (FCN) based image segmentation algorithm in binocular imaging system

NASA Astrophysics Data System (ADS)

Long, Zourong; Wei, Biao; Feng, Peng; Yu, Pengwei; Liu, Yuanyuan

2018-01-01

This paper proposes an image segmentation algorithm with fully convolutional networks (FCN) in binocular imaging system under various circumstance. Image segmentation is perfectly solved by semantic segmentation. FCN classifies the pixels, so as to achieve the level of image semantic segmentation. Different from the classical convolutional neural networks (CNN), FCN uses convolution layers instead of the fully connected layers. So it can accept image of arbitrary size. In this paper, we combine the convolutional neural network and scale invariant feature matching to solve the problem of visual positioning under different scenarios. All high-resolution images are captured with our calibrated binocular imaging system and several groups of test data are collected to verify this method. The experimental results show that the binocular images are effectively segmented without over-segmentation. With these segmented images, feature matching via SURF method is implemented to obtain regional information for further image processing. The final positioning procedure shows that the results are acceptable in the range of 1.4 1.6 m, the distance error is less than 10mm.

Correlation optique en lumiere coherente (in French)

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

Fontanel, A.; Grau, G.

1971-03-01

This paper describes a general bidimensional two-step method of correlation (or convolution) making use of the theory of holography. In the first step the light diffracted by one of the two plane transparent objects to be correlated interferes with the light diffracted by the other one. The hologram thus generated is photographed in the focal image plane of a convergent lens. Owing to the quadratic detection property of the photographic emulsion, the square of the modulus of the product of the spectra of the two objects considered is recorded on the photographic plate. In the second step the convolution productmore » of the two objects appears when the hologram is illuminated with a beam of coherent light. In its geophysical application this optical method of convolution makes it easy for us to obtain the autocorrelogram of a seismic cross-section. This method also makes it possible to correlate each of the seismic traces by special precalculated optically-recorded filters.« less

Guerrilla Hunter Killer Smartbook

DTIC Science & Technology

2009-07-04

down the Host Nation Government vs . GH/K views by opposing sides. Observing the model becomes convoluted unless the relationship between these two...be measured only by land ownership , but by area of influence to where human needs can be marked by spheres of influence. Concentration inside of... franchisement amongst the populace if the efforts of external advisors and civil organizations (Coalition Forces), the Host Nation Government, or even the

Predicting High Quality AFQT with Youth Attitude Tracking Study Data

DTIC Science & Technology

1991-12-01

for propensities. The history of the art of mental aptitude and psychological testing is long and convoluted. Names like Sir Francis Galton of England...Qualification Test . The explanatory variables reflect individual demographic, educational and labor market characteristics at the time of YATS interview. The...the fiftieth percentile on the Armed Forces Qualification Test . The explanatory variables reflect individual demographic, educational and labor market

Fovea detection in optical coherence tomography using convolutional neural networks

NASA Astrophysics Data System (ADS)

Liefers, Bart; Venhuizen, Freerk G.; Theelen, Thomas; Hoyng, Carel; van Ginneken, Bram; Sánchez, Clara I.

2017-02-01

The fovea is an important clinical landmark that is used as a reference for assessing various quantitative measures, such as central retinal thickness or drusen count. In this paper we propose a novel method for automatic detection of the foveal center in Optical Coherence Tomography (OCT) scans. Although the clinician will generally aim to center the OCT scan on the fovea, post-acquisition image processing will give a more accurate estimate of the true location of the foveal center. A Convolutional Neural Network (CNN) was trained on a set of 781 OCT scans that classifies each pixel in the OCT B-scan with a probability of belonging to the fovea. Dilated convolutions were used to obtain a large receptive field, while maintaining pixel-level accuracy. In order to train the network more effectively, negative patches were sampled selectively after each epoch. After CNN classification of the entire OCT volume, the predicted foveal center was chosen as the voxel with maximum output probability, after applying an optimized three-dimensional Gaussian blurring. We evaluate the performance of our method on a data set of 99 OCT scans presenting different stages of Age-related Macular Degeneration (AMD). The fovea was correctly detected in 96:9% of the cases, with a mean distance error of 73 μm(+/-112 μm). This result was comparable to the performance of a second human observer who obtained a mean distance error of 69 μm (+/-94 μm). Experiments showed that the proposed method is accurate and robust even in retinas heavily affected by pathology.

Deep convolutional neural networks for classifying GPR B-scans

NASA Astrophysics Data System (ADS)

Besaw, Lance E.; Stimac, Philip J.

2015-05-01

Symmetric and asymmetric buried explosive hazards (BEHs) present real, persistent, deadly threats on the modern battlefield. Current approaches to mitigate these threats rely on highly trained operatives to reliably detect BEHs with reasonable false alarm rates using handheld Ground Penetrating Radar (GPR) and metal detectors. As computers become smaller, faster and more efficient, there exists greater potential for automated threat detection based on state-of-the-art machine learning approaches, reducing the burden on the field operatives. Recent advancements in machine learning, specifically deep learning artificial neural networks, have led to significantly improved performance in pattern recognition tasks, such as object classification in digital images. Deep convolutional neural networks (CNNs) are used in this work to extract meaningful signatures from 2-dimensional (2-D) GPR B-scans and classify threats. The CNNs skip the traditional "feature engineering" step often associated with machine learning, and instead learn the feature representations directly from the 2-D data. A multi-antennae, handheld GPR with centimeter-accurate positioning data was used to collect shallow subsurface data over prepared lanes containing a wide range of BEHs. Several heuristics were used to prevent over-training, including cross validation, network weight regularization, and "dropout." Our results show that CNNs can extract meaningful features and accurately classify complex signatures contained in GPR B-scans, complementing existing GPR feature extraction and classification techniques.

Convolutional neural networks for prostate cancer recurrence prediction

NASA Astrophysics Data System (ADS)

Kumar, Neeraj; Verma, Ruchika; Arora, Ashish; Kumar, Abhay; Gupta, Sanchit; Sethi, Amit; Gann, Peter H.

2017-03-01

Accurate prediction of the treatment outcome is important for cancer treatment planning. We present an approach to predict prostate cancer (PCa) recurrence after radical prostatectomy using tissue images. We used a cohort whose case vs. control (recurrent vs. non-recurrent) status had been determined using post-treatment follow up. Further, to aid the development of novel biomarkers of PCa recurrence, cases and controls were paired based on matching of other predictive clinical variables such as Gleason grade, stage, age, and race. For this cohort, tissue resection microarray with up to four cores per patient was available. The proposed approach is based on deep learning, and its novelty lies in the use of two separate convolutional neural networks (CNNs) - one to detect individual nuclei even in the crowded areas, and the other to classify them. To detect nuclear centers in an image, the first CNN predicts distance transform of the underlying (but unknown) multi-nuclear map from the input HE image. The second CNN classifies the patches centered at nuclear centers into those belonging to cases or controls. Voting across patches extracted from image(s) of a patient yields the probability of recurrence for the patient. The proposed approach gave 0.81 AUC for a sample of 30 recurrent cases and 30 non-recurrent controls, after being trained on an independent set of 80 case-controls pairs. If validated further, such an approach might help in choosing between a combination of treatment options such as active surveillance, radical prostatectomy, radiation, and hormone therapy. It can also generalize to the prediction of treatment outcomes in other cancers.

Deep Convolutional Neural Networks for Computer-Aided Detection: CNN Architectures, Dataset Characteristics and Transfer Learning

PubMed Central

Hoo-Chang, Shin; Roth, Holger R.; Gao, Mingchen; Lu, Le; Xu, Ziyue; Nogues, Isabella; Yao, Jianhua; Mollura, Daniel

2016-01-01

Remarkable progress has been made in image recognition, primarily due to the availability of large-scale annotated datasets (i.e. ImageNet) and the revival of deep convolutional neural networks (CNN). CNNs enable learning data-driven, highly representative, layered hierarchical image features from sufficient training data. However, obtaining datasets as comprehensively annotated as ImageNet in the medical imaging domain remains a challenge. There are currently three major techniques that successfully employ CNNs to medical image classification: training the CNN from scratch, using off-the-shelf pre-trained CNN features, and conducting unsupervised CNN pre-training with supervised fine-tuning. Another effective method is transfer learning, i.e., fine-tuning CNN models (supervised) pre-trained from natural image dataset to medical image tasks (although domain transfer between two medical image datasets is also possible). In this paper, we exploit three important, but previously understudied factors of employing deep convolutional neural networks to computer-aided detection problems. We first explore and evaluate different CNN architectures. The studied models contain 5 thousand to 160 million parameters, and vary in numbers of layers. We then evaluate the influence of dataset scale and spatial image context on performance. Finally, we examine when and why transfer learning from pre-trained ImageNet (via fine-tuning) can be useful. We study two specific computeraided detection (CADe) problems, namely thoraco-abdominal lymph node (LN) detection and interstitial lung disease (ILD) classification. We achieve the state-of-the-art performance on the mediastinal LN detection, with 85% sensitivity at 3 false positive per patient, and report the first five-fold cross-validation classification results on predicting axial CT slices with ILD categories. Our extensive empirical evaluation, CNN model analysis and valuable insights can be extended to the design of high performance CAD systems for other medical imaging tasks. PMID:26886976

Modern control techniques in active flutter suppression using a control moment gyro

NASA Technical Reports Server (NTRS)

Buchek, P. M.

1974-01-01

Development of organized synthesis techniques, using concepts of modern control theory was studied for the design of active flutter suppression systems for two and three-dimensional lifting surfaces, utilizing a control moment gyro (CMG) to generate the required control torques. Incompressible flow theory is assumed, with the unsteady aerodynamic forces and moments for arbitrary airfoil motion obtained by using the convolution integral based on Wagner's indicial lift function. Linear optimal control theory is applied to find particular optimal sets of gain values which minimize a quadratic performance function. The closed loop system's response to impulsive gust disturbances and the resulting control power requirements are investigated, and the system eigenvalues necessary to minimize the maximum value of control power are determined.

4He binding energy calculation including full tensor-force effects

NASA Astrophysics Data System (ADS)

Fonseca, A. C.

1989-09-01

The four-body equations of Alt, Grassberger, and Sandhas are solved in the version where the (2)+(2) subamplitudes are treated exactly by convolution, using one-term separable Yamaguchy nucleon-nucleon potentials in the 1S0 and 3S1-3D1 channels. The resulting jp=1/2+ and (3/2+ three-body subamplitudes are represented in a separable form using the energy-dependent pole expansion. Converged bound-state results are calculated for the first time using the full interaction, and are compared with those obtained from a simplified treatment of the tensor force. The Tjon line that correlates three-nucleon and four-nucleon binding energies is shown using different nucleon-nucleon potentials. In all calculations the Coulomb force has been neglected.

Detection of mass regions in mammograms by bilateral analysis adapted to breast density using similarity indexes and convolutional neural networks.

PubMed

Bandeira Diniz, João Otávio; Bandeira Diniz, Pedro Henrique; Azevedo Valente, Thales Levi; Corrêa Silva, Aristófanes; de Paiva, Anselmo Cardoso; Gattass, Marcelo

2018-03-01

The processing of medical image is an important tool to assist in minimizing the degree of uncertainty of the specialist, while providing specialists with an additional source of detect and diagnosis information. Breast cancer is the most common type of cancer that affects the female population around the world. It is also the most deadly type of cancer among women. It is the second most common type of cancer among all others. The most common examination to diagnose breast cancer early is mammography. In the last decades, computational techniques have been developed with the purpose of automatically detecting structures that maybe associated with tumors in mammography examination. This work presents a computational methodology to automatically detection of mass regions in mammography by using a convolutional neural network. The materials used in this work is the DDSM database. The method proposed consists of two phases: training phase and test phase. The training phase has 2 main steps: (1) create a model to classify breast tissue into dense and non-dense (2) create a model to classify regions of breast into mass and non-mass. The test phase has 7 step: (1) preprocessing; (2) registration; (3) segmentation; (4) first reduction of false positives; (5) preprocessing of regions segmented; (6) density tissue classification (7) second reduction of false positives where regions will be classified into mass and non-mass. The proposed method achieved 95.6% of accuracy in classify non-dense breasts tissue and 97,72% accuracy in classify dense breasts. To detect regions of mass in non-dense breast, the method achieved a sensitivity value of 91.5%, and specificity value of 90.7%, with 91% accuracy. To detect regions in dense breasts, our method achieved 90.4% of sensitivity and 96.4% of specificity, with accuracy of 94.8%. According to the results achieved by CNN, we demonstrate the feasibility of using convolutional neural networks on medical image processing techniques for classification of breast tissue and mass detection. Copyright © 2018 Elsevier B.V. All rights reserved.

Object-based detection of vehicles using combined optical and elevation data

NASA Astrophysics Data System (ADS)

Schilling, Hendrik; Bulatov, Dimitri; Middelmann, Wolfgang

2018-02-01

The detection of vehicles is an important and challenging topic that is relevant for many applications. In this work, we present a workflow that utilizes optical and elevation data to detect vehicles in remotely sensed urban data. This workflow consists of three consecutive stages: candidate identification, classification, and single vehicle extraction. Unlike in most previous approaches, fusion of both data sources is strongly pursued at all stages. While the first stage utilizes the fact that most man-made objects are rectangular in shape, the second and third stages employ machine learning techniques combined with specific features. The stages are designed to handle multiple sensor input, which results in a significant improvement. A detailed evaluation shows the benefits of our workflow, which includes hand-tailored features; even in comparison with classification approaches based on Convolutional Neural Networks, which are state of the art in computer vision, we could obtain a comparable or superior performance (F1 score of 0.96-0.94).

a Novel Deep Convolutional Neural Network for Spectral-Spatial Classification of Hyperspectral Data

NASA Astrophysics Data System (ADS)

Li, N.; Wang, C.; Zhao, H.; Gong, X.; Wang, D.

2018-04-01

Spatial and spectral information are obtained simultaneously by hyperspectral remote sensing. Joint extraction of these information of hyperspectral image is one of most import methods for hyperspectral image classification. In this paper, a novel deep convolutional neural network (CNN) is proposed, which extracts spectral-spatial information of hyperspectral images correctly. The proposed model not only learns sufficient knowledge from the limited number of samples, but also has powerful generalization ability. The proposed framework based on three-dimensional convolution can extract spectral-spatial features of labeled samples effectively. Though CNN has shown its robustness to distortion, it cannot extract features of different scales through the traditional pooling layer that only have one size of pooling window. Hence, spatial pyramid pooling (SPP) is introduced into three-dimensional local convolutional filters for hyperspectral classification. Experimental results with a widely used hyperspectral remote sensing dataset show that the proposed model provides competitive performance.

Detection of retinal changes from illumination normalized fundus images using convolutional neural networks

NASA Astrophysics Data System (ADS)

Adal, Kedir M.; van Etten, Peter G.; Martinez, Jose P.; Rouwen, Kenneth; Vermeer, Koenraad A.; van Vliet, Lucas J.

2017-03-01

Automated detection and quantification of spatio-temporal retinal changes is an important step to objectively assess disease progression and treatment effects for dynamic retinal diseases such as diabetic retinopathy (DR). However, detecting retinal changes caused by early DR lesions such as microaneurysms and dot hemorrhages from longitudinal pairs of fundus images is challenging due to intra and inter-image illumination variation between fundus images. This paper explores a method for automated detection of retinal changes from illumination normalized fundus images using a deep convolutional neural network (CNN), and compares its performance with two other CNNs trained separately on color and green channel fundus images. Illumination variation was addressed by correcting for the variability in the luminosity and contrast estimated from a large scale retinal regions. The CNN models were trained and evaluated on image patches extracted from a registered fundus image set collected from 51 diabetic eyes that were screened at two different time-points. The results show that using normalized images yield better performance than color and green channel images, suggesting that illumination normalization greatly facilitates CNNs to quickly and correctly learn distinctive local image features of DR related retinal changes.

Detection of Interictal Discharges With Convolutional Neural Networks Using Discrete Ordered Multichannel Intracranial EEG.

PubMed

Antoniades, Andreas; Spyrou, Loukianos; Martin-Lopez, David; Valentin, Antonio; Alarcon, Gonzalo; Sanei, Saeid; Cheong Took, Clive

2017-12-01

Detection algorithms for electroencephalography (EEG) data, especially in the field of interictal epileptiform discharge (IED) detection, have traditionally employed handcrafted features, which utilized specific characteristics of neural responses. Although these algorithms achieve high accuracy, mere detection of an IED holds little clinical significance. In this paper, we consider deep learning for epileptic subjects to accommodate automatic feature generation from intracranial EEG data, while also providing clinical insight. Convolutional neural networks are trained in a subject independent fashion to demonstrate how meaningful features are automatically learned in a hierarchical process. We illustrate how the convolved filters in the deepest layers provide insight toward the different types of IEDs within the group, as confirmed by our expert clinicians. The morphology of the IEDs found in filters can help evaluate the treatment of a patient. To improve the learning of the deep model, moderately different score classes are utilized as opposed to binary IED and non-IED labels. The resulting model achieves state-of-the-art classification performance and is also invariant to time differences between the IEDs. This paper suggests that deep learning is suitable for automatic feature generation from intracranial EEG data, while also providing insight into the data.

Deep learning classifier with optical coherence tomography images for early dental caries detection

NASA Astrophysics Data System (ADS)

Karimian, Nima; Salehi, Hassan S.; Mahdian, Mina; Alnajjar, Hisham; Tadinada, Aditya

2018-02-01

Dental caries is a microbial disease that results in localized dissolution of the mineral content of dental tissue. Despite considerable decline in the incidence of dental caries, it remains a major health problem in many societies. Early detection of incipient lesions at initial stages of demineralization can result in the implementation of non-surgical preventive approaches to reverse the demineralization process. In this paper, we present a novel approach combining deep convolutional neural networks (CNN) and optical coherence tomography (OCT) imaging modality for classification of human oral tissues to detect early dental caries. OCT images of oral tissues with various densities were input to a CNN classifier to determine variations in tissue densities resembling the demineralization process. The CNN automatically learns a hierarchy of increasingly complex features and a related classifier directly from training data sets. The initial CNN layer parameters were randomly selected. The training set is split into minibatches, with 10 OCT images per batch. Given a batch of training patches, the CNN employs two convolutional and pooling layers to extract features and then classify each patch based on the probabilities from the SoftMax classification layer (output-layer). Afterward, the CNN calculates the error between the classification result and the reference label, and then utilizes the backpropagation process to fine-tune all the layer parameters to minimize this error using batch gradient descent algorithm. We validated our proposed technique on ex-vivo OCT images of human oral tissues (enamel, cortical-bone, trabecular-bone, muscular-tissue, and fatty-tissue), which attested to effectiveness of our proposed method.

Identification of Cell Cycle-Regulated Genes by Convolutional Neural Network.

PubMed

Liu, Chenglin; Cui, Peng; Huang, Tao

2017-01-01

The cell cycle-regulated genes express periodically with the cell cycle stages, and the identification and study of these genes can provide a deep understanding of the cell cycle process. Large false positives and low overlaps are big problems in cell cycle-regulated gene detection. Here, a computational framework called DLGene was proposed for cell cycle-regulated gene detection. It is based on the convolutional neural network, a deep learning algorithm representing raw form of data pattern without assumption of their distribution. First, the expression data was transformed to categorical state data to denote the changing state of gene expression, and four different expression patterns were revealed for the reported cell cycle-regulated genes. Then, DLGene was applied to discriminate the non-cell cycle gene and the four subtypes of cell cycle genes. Its performances were compared with six traditional machine learning methods. At last, the biological functions of representative cell cycle genes for each subtype are analyzed. Our method showed better and more balanced performance of sensitivity and specificity comparing to other machine learning algorithms. The cell cycle genes had very different expression pattern with non-cell cycle genes and among the cell-cycle genes, there were four subtypes. Our method not only detects the cell cycle genes, but also describes its expression pattern, such as when its highest expression level is reached and how it changes with time. For each type, we analyzed the biological functions of the representative genes and such results provided novel insight to the cell cycle mechanisms. Copyright© Bentham Science Publishers; For any queries, please email at epub@benthamscience.org.

Concept for room temperature single-spin tunneling force microscopy with atomic spatial resolution

NASA Astrophysics Data System (ADS)

Payne, Adam

A study of a force detected single-spin magnetic resonance measurement concept with atomic spatial resolution is presented. The method is based upon electrostatic force detection of spin-selection rule controlled single electron tunneling between two electrically isolated paramagnetic states. Single-spin magnetic resonance detection is possible by measuring the force detected tunneling charge noise on and off spin resonance. Simulation results of this charge noise, based upon physical models of the tunneling and spin physics, are directly compared to measured atomic force microscopy (AFM) system noise. The results show that the approach could provide single-spin measurement of electrically isolated defect states with atomic spatial resolution at room temperature.

Pre-trained convolutional neural networks as feature extractors toward improved malaria parasite detection in thin blood smear images.

PubMed

Rajaraman, Sivaramakrishnan; Antani, Sameer K; Poostchi, Mahdieh; Silamut, Kamolrat; Hossain, Md A; Maude, Richard J; Jaeger, Stefan; Thoma, George R

2018-01-01

Malaria is a blood disease caused by the Plasmodium parasites transmitted through the bite of female Anopheles mosquito. Microscopists commonly examine thick and thin blood smears to diagnose disease and compute parasitemia. However, their accuracy depends on smear quality and expertise in classifying and counting parasitized and uninfected cells. Such an examination could be arduous for large-scale diagnoses resulting in poor quality. State-of-the-art image-analysis based computer-aided diagnosis (CADx) methods using machine learning (ML) techniques, applied to microscopic images of the smears using hand-engineered features demand expertise in analyzing morphological, textural, and positional variations of the region of interest (ROI). In contrast, Convolutional Neural Networks (CNN), a class of deep learning (DL) models promise highly scalable and superior results with end-to-end feature extraction and classification. Automated malaria screening using DL techniques could, therefore, serve as an effective diagnostic aid. In this study, we evaluate the performance of pre-trained CNN based DL models as feature extractors toward classifying parasitized and uninfected cells to aid in improved disease screening. We experimentally determine the optimal model layers for feature extraction from the underlying data. Statistical validation of the results demonstrates the use of pre-trained CNNs as a promising tool for feature extraction for this purpose.

Objective-lens-free Fiber-based Position Detection with Nanometer Resolution in a Fiber Optical Trapping System.

PubMed

Ti, Chaoyang; Ho-Thanh, Minh-Tri; Wen, Qi; Liu, Yuxiang

2017-10-13

Position detection with high accuracy is crucial for force calibration of optical trapping systems. Most existing position detection methods require high-numerical-aperture objective lenses, which are bulky, expensive, and difficult to miniaturize. Here, we report an affordable objective-lens-free, fiber-based position detection scheme with 2 nm spatial resolution and 150 MHz bandwidth. This fiber based detection mechanism enables simultaneous trapping and force measurements in a compact fiber optical tweezers system. In addition, we achieved more reliable signal acquisition with less distortion compared with objective based position detection methods, thanks to the light guiding in optical fibers and small distance between the fiber tips and trapped particle. As a demonstration of the fiber based detection, we used the fiber optical tweezers to apply a force on a cell membrane and simultaneously measure the cellular response.

Deep Neural Network for Structural Prediction and Lane Detection in Traffic Scene.

PubMed

Li, Jun; Mei, Xue; Prokhorov, Danil; Tao, Dacheng

2017-03-01

Hierarchical neural networks have been shown to be effective in learning representative image features and recognizing object classes. However, most existing networks combine the low/middle level cues for classification without accounting for any spatial structures. For applications such as understanding a scene, how the visual cues are spatially distributed in an image becomes essential for successful analysis. This paper extends the framework of deep neural networks by accounting for the structural cues in the visual signals. In particular, two kinds of neural networks have been proposed. First, we develop a multitask deep convolutional network, which simultaneously detects the presence of the target and the geometric attributes (location and orientation) of the target with respect to the region of interest. Second, a recurrent neuron layer is adopted for structured visual detection. The recurrent neurons can deal with the spatial distribution of visible cues belonging to an object whose shape or structure is difficult to explicitly define. Both the networks are demonstrated by the practical task of detecting lane boundaries in traffic scenes. The multitask convolutional neural network provides auxiliary geometric information to help the subsequent modeling of the given lane structures. The recurrent neural network automatically detects lane boundaries, including those areas containing no marks, without any explicit prior knowledge or secondary modeling.

Soft-sediment deformations (convolute lamination and load structures) in turbidites as indicators of flow reflections against bounding slopes

NASA Astrophysics Data System (ADS)

Tinterri, Roberto; Muzzi Magalhaes, Pierre; Tagliaferri, Alessio; Cunha, Rogerio S.; Laporta, Michele

2015-04-01

Soft-sediment deformations, such as convolute laminations, load structures and water escapes are very rapid deformations that occur in unconsolidated sediments near the depositional surface during or shortly after deposition and before significant diagenesis. These types of deformations develop when primary stratifications are deformed by a system of driving forces, while the sediment is temporarily in a weakened state due to the action of a deformation mechanism know as liquidization. This deformation occurs if the applied stress exceeds the sediment strength, either through an increase in the applied stress or through a temporary reduction in sediment strength. Liquidization mechanisms can be triggered by several agents, such as seismic shaking, rapid sedimentation with high-fallout rates or cyclic-pressure variations associated with storm waves or breaking waves. Consequently, soft-sediment deformations can be produced by different processes and form ubiquitous sedimentary structures characterizing many sedimentary environments. However, even though these types of structures are relatively well-known in terms of geometry and sedimentary characteristics, many doubts arise when the understanding of deformation and trigger mechanisms is attempted. As stressed also by the recent literature, the main problem lies in the fact that the existing approaches for the identification of triggering agents rely on criteria that are not diagnostic or not applicable to outcrop-based studies, because they are not always based on detailed facies analysis related to a paleoenvironmental-context approach. For this reason, this work discusses the significance of particular types of soft-sediment deformations that are very common in turbidite deposits, namely convolute laminations and load structures, especially on the basis of a deep knowledge of the stratigraphic framework and geological setting in which these structures are inserted. More precisely, detailed facies analyses of the turbidites containing these deformative structures show that they are genetically linked to contained-reflected beds in structurally-confined basins, suggesting a trigger mechanism associated with the cyclic-wave loading produced by flow impacts or reflected bores and internal waves related to ponded turbidity currents. The data that can demonstrate this hypothesis come from the foredeep turbidites of the Marnoso-arenacea Formation (northern Italy) and Annot Sandstones (southwestern France), where a basin scale high-resolution stratigraphic framework with bed-by-bed correlations is now available. These data show that the lateral and vertical distribution of convolute laminae and load structures is not random but has an evident depositional logic related to reflection processes against bounding slopes. Therefore, the main objectives of this work are: 1) to show that convolute laminae and load structures are strictly associated with other sedimentary structures that are unequivocally related to reflection and rebound processes of turbidity currents against morphological obstacles; 2) to show that their lateral and vertical distribution increases concomitantly with the number of contained-reflected beds in the proximity of structurally-controlled morphological highs; 3) to show that the increase in contained-reflected beds with convolute laminae is strictly related to the increase in the synsedimentary-structural uplifts producing more pronounced morphologic highs; 4) to discuss the processes that link soft-sediment deformations with cyclic-wave loading related to internal waves and bores produced by reflection processes.

Fuzzy Logic Module of Convolutional Neural Network for Handwritten Digits Recognition

NASA Astrophysics Data System (ADS)

Popko, E. A.; Weinstein, I. A.

2016-08-01

Optical character recognition is one of the important issues in the field of pattern recognition. This paper presents a method for recognizing handwritten digits based on the modeling of convolutional neural network. The integrated fuzzy logic module based on a structural approach was developed. Used system architecture adjusted the output of the neural network to improve quality of symbol identification. It was shown that proposed algorithm was flexible and high recognition rate of 99.23% was achieved.

Targets Mask U-Net for Wind Turbines Detection in Remote Sensing Images

NASA Astrophysics Data System (ADS)

Han, M.; Wang, H.; Wang, G.; Liu, Y.

2018-04-01

To detect wind turbines precisely and quickly in very high resolution remote sensing images (VHRRSI) we propose target mask U-Net. This convolution neural network (CNN), which is carefully designed to be a wide-field detector, models the pixel class assignment to wind turbines and their context information. The shadow, which is the context information of the target in this study, has been regarded as part of a wind turbine instance. We have trained the target mask U-Net on training dataset, which is composed of down sampled image blocks and instance mask blocks. Some post-processes have been integrated to eliminate wrong spots and produce bounding boxes of wind turbine instances. The evaluation metrics prove the reliability and effectiveness of our method for the average F1-score of our detection method is up to 0.97. The comparison of detection accuracy and time consuming with the weakly supervised targets detection method based on CNN illustrates the superiority of our method.

Evolutionary image simplification for lung nodule classification with convolutional neural networks.

PubMed

Lückehe, Daniel; von Voigt, Gabriele

2018-05-29

Understanding decisions of deep learning techniques is important. Especially in the medical field, the reasons for a decision in a classification task are as crucial as the pure classification results. In this article, we propose a new approach to compute relevant parts of a medical image. Knowing the relevant parts makes it easier to understand decisions. In our approach, a convolutional neural network is employed to learn structures of images of lung nodules. Then, an evolutionary algorithm is applied to compute a simplified version of an unknown image based on the learned structures by the convolutional neural network. In the simplified version, irrelevant parts are removed from the original image. In the results, we show simplified images which allow the observer to focus on the relevant parts. In these images, more than 50% of the pixels are simplified. The simplified pixels do not change the meaning of the images based on the learned structures by the convolutional neural network. An experimental analysis shows the potential of the approach. Besides the examples of simplified images, we analyze the run time development. Simplified images make it easier to focus on relevant parts and to find reasons for a decision. The combination of an evolutionary algorithm employing a learned convolutional neural network is well suited for the simplification task. From a research perspective, it is interesting which areas of the images are simplified and which parts are taken as relevant.

Nonlocal elasticity tensors in dislocation and disclination cores

DOE PAGES

Taupin, V.; Gbemou, K.; Fressengeas, C.; ...

2017-01-07

We introduced nonlocal elastic constitutive laws for crystals containing defects such as dislocations and disclinations. Additionally, the pointwise elastic moduli tensors adequately reflect the elastic response of defect-free regions by relating stresses to strains and couple-stresses to curvatures, elastic cross-moduli tensors relating strains to couple-stresses and curvatures to stresses within convolution integrals are derived from a nonlocal analysis of strains and curvatures in the defects cores. Sufficient conditions are derived for positive-definiteness of the resulting free energy, and stability of elastic solutions is ensured. The elastic stress/couple stress fields associated with prescribed dislocation/disclination density distributions and solving the momentum andmore » moment of momentum balance equations in periodic media are determined by using a Fast Fourier Transform spectral method. Here, the convoluted cross-moduli bring the following results: (i) Nonlocal stresses and couple stresses oppose their local counterparts in the defects core regions, playing the role of restoring forces and possibly ensuring spatio-temporal stability of the simulated defects, (ii) The couple stress fields are strongly affected by nonlocality. Such effects favor the stability of the simulated grain boundaries and allow investigating their elastic interactions with extrinsic defects, (iii) Driving forces inducing grain growth or refinement derive from the self-stress and couple stress fields of grain boundaries in nanocrystalline configurations.« less

Convolutional coding results for the MVM '73 X-band telemetry experiment

NASA Technical Reports Server (NTRS)

Layland, J. W.

1978-01-01

Results of simulation of several short-constraint-length convolutional codes using a noisy symbol stream obtained via the turnaround ranging channels of the MVM'73 spacecraft are presented. First operational use of this coding technique is on the Voyager mission. The relative performance of these codes in this environment is as previously predicted from computer-based simulations.

Chinese character recognition based on Gabor feature extraction and CNN

NASA Astrophysics Data System (ADS)

Xiong, Yudian; Lu, Tongwei; Jiang, Yongyuan

2018-03-01

As an important application in the field of text line recognition and office automation, Chinese character recognition has become an important subject of pattern recognition. However, due to the large number of Chinese characters and the complexity of its structure, there is a great difficulty in the Chinese character recognition. In order to solve this problem, this paper proposes a method of printed Chinese character recognition based on Gabor feature extraction and Convolution Neural Network(CNN). The main steps are preprocessing, feature extraction, training classification. First, the gray-scale Chinese character image is binarized and normalized to reduce the redundancy of the image data. Second, each image is convoluted with Gabor filter with different orientations, and the feature map of the eight orientations of Chinese characters is extracted. Third, the feature map through Gabor filters and the original image are convoluted with learning kernels, and the results of the convolution is the input of pooling layer. Finally, the feature vector is used to classify and recognition. In addition, the generalization capacity of the network is improved by Dropout technology. The experimental results show that this method can effectively extract the characteristics of Chinese characters and recognize Chinese characters.

Traffic sign recognition based on deep convolutional neural network

NASA Astrophysics Data System (ADS)

Yin, Shi-hao; Deng, Ji-cai; Zhang, Da-wei; Du, Jing-yuan

2017-11-01

Traffic sign recognition (TSR) is an important component of automated driving systems. It is a rather challenging task to design a high-performance classifier for the TSR system. In this paper, we propose a new method for TSR system based on deep convolutional neural network. In order to enhance the expression of the network, a novel structure (dubbed block-layer below) which combines network-in-network and residual connection is designed. Our network has 10 layers with parameters (block-layer seen as a single layer): the first seven are alternate convolutional layers and block-layers, and the remaining three are fully-connected layers. We train our TSR network on the German traffic sign recognition benchmark (GTSRB) dataset. To reduce overfitting, we perform data augmentation on the training images and employ a regularization method named "dropout". The activation function we employ in our network adopts scaled exponential linear units (SELUs), which can induce self-normalizing properties. To speed up the training, we use an efficient GPU to accelerate the convolutional operation. On the test dataset of GTSRB, we achieve the accuracy rate of 99.67%, exceeding the state-of-the-art results.

Blood vessels segmentation of hatching eggs based on fully convolutional networks

NASA Astrophysics Data System (ADS)

Geng, Lei; Qiu, Ling; Wu, Jun; Xiao, Zhitao

2018-04-01

FCN, trained end-to-end, pixels-to-pixels, predict result of each pixel. It has been widely used for semantic segmentation. In order to realize the blood vessels segmentation of hatching eggs, a method based on FCN is proposed in this paper. The training datasets are composed of patches extracted from very few images to augment data. The network combines with lower layer and deconvolution to enables precise segmentation. The proposed method frees from the problem that training deep networks need large scale samples. Experimental results on hatching eggs demonstrate that this method can yield more accurate segmentation outputs than previous researches. It provides a convenient reference for fertility detection subsequently.

Entanglement-assisted quantum convolutional coding

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

Wilde, Mark M.; Brun, Todd A.

2010-04-15

We show how to protect a stream of quantum information from decoherence induced by a noisy quantum communication channel. We exploit preshared entanglement and a convolutional coding structure to develop a theory of entanglement-assisted quantum convolutional coding. Our construction produces a Calderbank-Shor-Steane (CSS) entanglement-assisted quantum convolutional code from two arbitrary classical binary convolutional codes. The rate and error-correcting properties of the classical convolutional codes directly determine the corresponding properties of the resulting entanglement-assisted quantum convolutional code. We explain how to encode our CSS entanglement-assisted quantum convolutional codes starting from a stream of information qubits, ancilla qubits, and shared entangled bits.

Trellises and Trellis-Based Decoding Algorithms for Linear Block Codes

NASA Technical Reports Server (NTRS)

Lin, Shu

1998-01-01

A code trellis is a graphical representation of a code, block or convolutional, in which every path represents a codeword (or a code sequence for a convolutional code). This representation makes it possible to implement Maximum Likelihood Decoding (MLD) of a code with reduced decoding complexity. The most well known trellis-based MLD algorithm is the Viterbi algorithm. The trellis representation was first introduced and used for convolutional codes [23]. This representation, together with the Viterbi decoding algorithm, has resulted in a wide range of applications of convolutional codes for error control in digital communications over the last two decades. There are two major reasons for this inactive period of research in this area. First, most coding theorists at that time believed that block codes did not have simple trellis structure like convolutional codes and maximum likelihood decoding of linear block codes using the Viterbi algorithm was practically impossible, except for very short block codes. Second, since almost all of the linear block codes are constructed algebraically or based on finite geometries, it was the belief of many coding theorists that algebraic decoding was the only way to decode these codes. These two reasons seriously hindered the development of efficient soft-decision decoding methods for linear block codes and their applications to error control in digital communications. This led to a general belief that block codes are inferior to convolutional codes and hence, that they were not useful. Chapter 2 gives a brief review of linear block codes. The goal is to provide the essential background material for the development of trellis structure and trellis-based decoding algorithms for linear block codes in the later chapters. Chapters 3 through 6 present the fundamental concepts, finite-state machine model, state space formulation, basic structural properties, state labeling, construction procedures, complexity, minimality, and sectionalization of trellises. Chapter 7 discusses trellis decomposition and subtrellises for low-weight codewords. Chapter 8 first presents well known methods for constructing long powerful codes from short component codes or component codes of smaller dimensions, and then provides methods for constructing their trellises which include Shannon and Cartesian product techniques. Chapter 9 deals with convolutional codes, puncturing, zero-tail termination and tail-biting.Chapters 10 through 13 present various trellis-based decoding algorithms, old and new. Chapter 10 first discusses the application of the well known Viterbi decoding algorithm to linear block codes, optimum sectionalization of a code trellis to minimize computation complexity, and design issues for IC (integrated circuit) implementation of a Viterbi decoder. Then it presents a new decoding algorithm for convolutional codes, named Differential Trellis Decoding (DTD) algorithm. Chapter 12 presents a suboptimum reliability-based iterative decoding algorithm with a low-weight trellis search for the most likely codeword. This decoding algorithm provides a good trade-off between error performance and decoding complexity. All the decoding algorithms presented in Chapters 10 through 12 are devised to minimize word error probability. Chapter 13 presents decoding algorithms that minimize bit error probability and provide the corresponding soft (reliability) information at the output of the decoder. Decoding algorithms presented are the MAP (maximum a posteriori probability) decoding algorithm and the Soft-Output Viterbi Algorithm (SOVA) algorithm. Finally, the minimization of bit error probability in trellis-based MLD is discussed.

Deep convolutional neural network based antenna selection in multiple-input multiple-output system

NASA Astrophysics Data System (ADS)

Cai, Jiaxin; Li, Yan; Hu, Ying

2018-03-01

Antenna selection of wireless communication system has attracted increasing attention due to the challenge of keeping a balance between communication performance and computational complexity in large-scale Multiple-Input MultipleOutput antenna systems. Recently, deep learning based methods have achieved promising performance for large-scale data processing and analysis in many application fields. This paper is the first attempt to introduce the deep learning technique into the field of Multiple-Input Multiple-Output antenna selection in wireless communications. First, the label of attenuation coefficients channel matrix is generated by minimizing the key performance indicator of training antenna systems. Then, a deep convolutional neural network that explicitly exploits the massive latent cues of attenuation coefficients is learned on the training antenna systems. Finally, we use the adopted deep convolutional neural network to classify the channel matrix labels of test antennas and select the optimal antenna subset. Simulation experimental results demonstrate that our method can achieve better performance than the state-of-the-art baselines for data-driven based wireless antenna selection.

Pattern Recognition of Momentary Mental Workload Based on Multi-Channel Electrophysiological Data and Ensemble Convolutional Neural Networks.

PubMed

Zhang, Jianhua; Li, Sunan; Wang, Rubin

2017-01-01

In this paper, we deal with the Mental Workload (MWL) classification problem based on the measured physiological data. First we discussed the optimal depth (i.e., the number of hidden layers) and parameter optimization algorithms for the Convolutional Neural Networks (CNN). The base CNNs designed were tested according to five classification performance indices, namely Accuracy, Precision, F-measure, G-mean, and required training time. Then we developed an Ensemble Convolutional Neural Network (ECNN) to enhance the accuracy and robustness of the individual CNN model. For the ECNN design, three model aggregation approaches (weighted averaging, majority voting and stacking) were examined and a resampling strategy was used to enhance the diversity of individual CNN models. The results of MWL classification performance comparison indicated that the proposed ECNN framework can effectively improve MWL classification performance and is featured by entirely automatic feature extraction and MWL classification, when compared with traditional machine learning methods.

Integrating Online and Offline Three-Dimensional Deep Learning for Automated Polyp Detection in Colonoscopy Videos.

PubMed

Lequan Yu; Hao Chen; Qi Dou; Jing Qin; Pheng Ann Heng

2017-01-01

Automated polyp detection in colonoscopy videos has been demonstrated to be a promising way for colorectal cancer prevention and diagnosis. Traditional manual screening is time consuming, operator dependent, and error prone; hence, automated detection approach is highly demanded in clinical practice. However, automated polyp detection is very challenging due to high intraclass variations in polyp size, color, shape, and texture, and low interclass variations between polyps and hard mimics. In this paper, we propose a novel offline and online three-dimensional (3-D) deep learning integration framework by leveraging the 3-D fully convolutional network (3D-FCN) to tackle this challenging problem. Compared with the previous methods employing hand-crafted features or 2-D convolutional neural network, the 3D-FCN is capable of learning more representative spatio-temporal features from colonoscopy videos, and hence has more powerful discrimination capability. More importantly, we propose a novel online learning scheme to deal with the problem of limited training data by harnessing the specific information of an input video in the learning process. We integrate offline and online learning to effectively reduce the number of false positives generated by the offline network and further improve the detection performance. Extensive experiments on the dataset of MICCAI 2015 Challenge on Polyp Detection demonstrated the better performance of our method when compared with other competitors.

Full Waveform Modeling of Transient Electromagnetic Response Based on Temporal Interpolation and Convolution Method

NASA Astrophysics Data System (ADS)

Qi, Youzheng; Huang, Ling; Wu, Xin; Zhu, Wanhua; Fang, Guangyou; Yu, Gang

2017-07-01

Quantitative modeling of the transient electromagnetic (TEM) response requires consideration of the full transmitter waveform, i.e., not only the specific current waveform in a half cycle but also the bipolar repetition. In this paper, we present a novel temporal interpolation and convolution (TIC) method to facilitate the accurate TEM modeling. We first calculate the temporal basis response on a logarithmic scale using the fast digital-filter-based methods. Then, we introduce a function named hamlogsinc in the framework of discrete signal processing theory to reconstruct the basis function and to make the convolution with the positive half of the waveform. Finally, a superposition procedure is used to take account of the effect of previous bipolar waveforms. Comparisons with the established fast Fourier transform method demonstrate that our TIC method can get the same accuracy with a shorter computing time.

Improving deep convolutional neural networks with mixed maxout units.

PubMed

Zhao, Hui-Zhen; Liu, Fu-Xian; Li, Long-Yue

2017-01-01

Motivated by insights from the maxout-units-based deep Convolutional Neural Network (CNN) that "non-maximal features are unable to deliver" and "feature mapping subspace pooling is insufficient," we present a novel mixed variant of the recently introduced maxout unit called a mixout unit. Specifically, we do so by calculating the exponential probabilities of feature mappings gained by applying different convolutional transformations over the same input and then calculating the expected values according to their exponential probabilities. Moreover, we introduce the Bernoulli distribution to balance the maximum values with the expected values of the feature mappings subspace. Finally, we design a simple model to verify the pooling ability of mixout units and a Mixout-units-based Network-in-Network (NiN) model to analyze the feature learning ability of the mixout models. We argue that our proposed units improve the pooling ability and that mixout models can achieve better feature learning and classification performance.

An Ensemble Deep Convolutional Neural Network Model with Improved D-S Evidence Fusion for Bearing Fault Diagnosis.

PubMed

Li, Shaobo; Liu, Guokai; Tang, Xianghong; Lu, Jianguang; Hu, Jianjun

2017-07-28

Intelligent machine health monitoring and fault diagnosis are becoming increasingly important for modern manufacturing industries. Current fault diagnosis approaches mostly depend on expert-designed features for building prediction models. In this paper, we proposed IDSCNN, a novel bearing fault diagnosis algorithm based on ensemble deep convolutional neural networks and an improved Dempster-Shafer theory based evidence fusion. The convolutional neural networks take the root mean square (RMS) maps from the FFT (Fast Fourier Transformation) features of the vibration signals from two sensors as inputs. The improved D-S evidence theory is implemented via distance matrix from evidences and modified Gini Index. Extensive evaluations of the IDSCNN on the Case Western Reserve Dataset showed that our IDSCNN algorithm can achieve better fault diagnosis performance than existing machine learning methods by fusing complementary or conflicting evidences from different models and sensors and adapting to different load conditions.

Spatiotemporal Recurrent Convolutional Networks for Traffic Prediction in Transportation Networks

PubMed Central

Yu, Haiyang; Wu, Zhihai; Wang, Shuqin; Wang, Yunpeng; Ma, Xiaolei

2017-01-01

Predicting large-scale transportation network traffic has become an important and challenging topic in recent decades. Inspired by the domain knowledge of motion prediction, in which the future motion of an object can be predicted based on previous scenes, we propose a network grid representation method that can retain the fine-scale structure of a transportation network. Network-wide traffic speeds are converted into a series of static images and input into a novel deep architecture, namely, spatiotemporal recurrent convolutional networks (SRCNs), for traffic forecasting. The proposed SRCNs inherit the advantages of deep convolutional neural networks (DCNNs) and long short-term memory (LSTM) neural networks. The spatial dependencies of network-wide traffic can be captured by DCNNs, and the temporal dynamics can be learned by LSTMs. An experiment on a Beijing transportation network with 278 links demonstrates that SRCNs outperform other deep learning-based algorithms in both short-term and long-term traffic prediction. PMID:28672867

An Ensemble Deep Convolutional Neural Network Model with Improved D-S Evidence Fusion for Bearing Fault Diagnosis

PubMed Central

Li, Shaobo; Liu, Guokai; Tang, Xianghong; Lu, Jianguang

2017-01-01

Intelligent machine health monitoring and fault diagnosis are becoming increasingly important for modern manufacturing industries. Current fault diagnosis approaches mostly depend on expert-designed features for building prediction models. In this paper, we proposed IDSCNN, a novel bearing fault diagnosis algorithm based on ensemble deep convolutional neural networks and an improved Dempster–Shafer theory based evidence fusion. The convolutional neural networks take the root mean square (RMS) maps from the FFT (Fast Fourier Transformation) features of the vibration signals from two sensors as inputs. The improved D-S evidence theory is implemented via distance matrix from evidences and modified Gini Index. Extensive evaluations of the IDSCNN on the Case Western Reserve Dataset showed that our IDSCNN algorithm can achieve better fault diagnosis performance than existing machine learning methods by fusing complementary or conflicting evidences from different models and sensors and adapting to different load conditions. PMID:28788099

Deep Convolutional Neural Networks for Classifying Body Constitution Based on Face Image.

PubMed

Huan, Er-Yang; Wen, Gui-Hua; Zhang, Shi-Jun; Li, Dan-Yang; Hu, Yang; Chang, Tian-Yuan; Wang, Qing; Huang, Bing-Lin

2017-01-01

Body constitution classification is the basis and core content of traditional Chinese medicine constitution research. It is to extract the relevant laws from the complex constitution phenomenon and finally build the constitution classification system. Traditional identification methods have the disadvantages of inefficiency and low accuracy, for instance, questionnaires. This paper proposed a body constitution recognition algorithm based on deep convolutional neural network, which can classify individual constitution types according to face images. The proposed model first uses the convolutional neural network to extract the features of face image and then combines the extracted features with the color features. Finally, the fusion features are input to the Softmax classifier to get the classification result. Different comparison experiments show that the algorithm proposed in this paper can achieve the accuracy of 65.29% about the constitution classification. And its performance was accepted by Chinese medicine practitioners.

Spatiotemporal Recurrent Convolutional Networks for Traffic Prediction in Transportation Networks.

PubMed

Yu, Haiyang; Wu, Zhihai; Wang, Shuqin; Wang, Yunpeng; Ma, Xiaolei

2017-06-26

Predicting large-scale transportation network traffic has become an important and challenging topic in recent decades. Inspired by the domain knowledge of motion prediction, in which the future motion of an object can be predicted based on previous scenes, we propose a network grid representation method that can retain the fine-scale structure of a transportation network. Network-wide traffic speeds are converted into a series of static images and input into a novel deep architecture, namely, spatiotemporal recurrent convolutional networks (SRCNs), for traffic forecasting. The proposed SRCNs inherit the advantages of deep convolutional neural networks (DCNNs) and long short-term memory (LSTM) neural networks. The spatial dependencies of network-wide traffic can be captured by DCNNs, and the temporal dynamics can be learned by LSTMs. An experiment on a Beijing transportation network with 278 links demonstrates that SRCNs outperform other deep learning-based algorithms in both short-term and long-term traffic prediction.

Spectral-spatial classification of hyperspectral image using three-dimensional convolution network

NASA Astrophysics Data System (ADS)

Liu, Bing; Yu, Xuchu; Zhang, Pengqiang; Tan, Xiong; Wang, Ruirui; Zhi, Lu

2018-01-01

Recently, hyperspectral image (HSI) classification has become a focus of research. However, the complex structure of an HSI makes feature extraction difficult to achieve. Most current methods build classifiers based on complex handcrafted features computed from the raw inputs. The design of an improved 3-D convolutional neural network (3D-CNN) model for HSI classification is described. This model extracts features from both the spectral and spatial dimensions through the application of 3-D convolutions, thereby capturing the important discrimination information encoded in multiple adjacent bands. The designed model views the HSI cube data altogether without relying on any pre- or postprocessing. In addition, the model is trained in an end-to-end fashion without any handcrafted features. The designed model was applied to three widely used HSI datasets. The experimental results demonstrate that the 3D-CNN-based method outperforms conventional methods even with limited labeled training samples.

Automatic sleep stage classification of single-channel EEG by using complex-valued convolutional neural network.

PubMed

Zhang, Junming; Wu, Yan

2018-03-28

Many systems are developed for automatic sleep stage classification. However, nearly all models are based on handcrafted features. Because of the large feature space, there are so many features that feature selection should be used. Meanwhile, designing handcrafted features is a difficult and time-consuming task because the feature designing needs domain knowledge of experienced experts. Results vary when different sets of features are chosen to identify sleep stages. Additionally, many features that we may be unaware of exist. However, these features may be important for sleep stage classification. Therefore, a new sleep stage classification system, which is based on the complex-valued convolutional neural network (CCNN), is proposed in this study. Unlike the existing sleep stage methods, our method can automatically extract features from raw electroencephalography data and then classify sleep stage based on the learned features. Additionally, we also prove that the decision boundaries for the real and imaginary parts of a complex-valued convolutional neuron intersect orthogonally. The classification performances of handcrafted features are compared with those of learned features via CCNN. Experimental results show that the proposed method is comparable to the existing methods. CCNN obtains a better classification performance and considerably faster convergence speed than convolutional neural network. Experimental results also show that the proposed method is a useful decision-support tool for automatic sleep stage classification.

A Deep Learning Approach to Examine Ischemic ST Changes in Ambulatory ECG Recordings.

PubMed

Xiao, Ran; Xu, Yuan; Pelter, Michele M; Mortara, David W; Hu, Xiao

2018-01-01

Patients with suspected acute coronary syndrome (ACS) are at risk of transient myocardial ischemia (TMI), which could lead to serious morbidity or even mortality. Early detection of myocardial ischemia can reduce damage to heart tissues and improve patient condition. Significant ST change in the electrocardiogram (ECG) is an important marker for detecting myocardial ischemia during the rule-out phase of potential ACS. However, current ECG monitoring software is vastly underused due to excessive false alarms. The present study aims to tackle this problem by combining a novel image-based approach with deep learning techniques to improve the detection accuracy of significant ST depression change. The obtained convolutional neural network (CNN) model yields an average area under the curve (AUC) at 89.6% from an independent testing set. At selected optimal cutoff thresholds, the proposed model yields a mean sensitivity at 84.4% while maintaining specificity at 84.9%.

Automatic lumbar vertebrae detection based on feature fusion deep learning for partial occluded C-arm X-ray images.

PubMed

Yang Li; Wei Liang; Yinlong Zhang; Haibo An; Jindong Tan

2016-08-01

Automatic and accurate lumbar vertebrae detection is an essential step of image-guided minimally invasive spine surgery (IG-MISS). However, traditional methods still require human intervention due to the similarity of vertebrae, abnormal pathological conditions and uncertain imaging angle. In this paper, we present a novel convolutional neural network (CNN) model to automatically detect lumbar vertebrae for C-arm X-ray images. Training data is augmented by DRR and automatic segmentation of ROI is able to reduce the computational complexity. Furthermore, a feature fusion deep learning (FFDL) model is introduced to combine two types of features of lumbar vertebrae X-ray images, which uses sobel kernel and Gabor kernel to obtain the contour and texture of lumbar vertebrae, respectively. Comprehensive qualitative and quantitative experiments demonstrate that our proposed model performs more accurate in abnormal cases with pathologies and surgical implants in multi-angle views.

Rock images classification by using deep convolution neural network

NASA Astrophysics Data System (ADS)

Cheng, Guojian; Guo, Wenhui

2017-08-01

Granularity analysis is one of the most essential issues in authenticate under microscope. To improve the efficiency and accuracy of traditional manual work, an convolutional neural network based method is proposed for granularity analysis from thin section image, which chooses and extracts features from image samples while build classifier to recognize granularity of input image samples. 4800 samples from Ordos basin are used for experiments under colour spaces of HSV, YCbCr and RGB respectively. On the test dataset, the correct rate in RGB colour space is 98.5%, and it is believable in HSV and YCbCr colour space. The results show that the convolution neural network can classify the rock images with high reliability.

Patient-specific dosimetry based on quantitative SPECT imaging and 3D-DFT convolution

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

Akabani, G.; Hawkins, W.G.; Eckblade, M.B.

1999-01-01

The objective of this study was to validate the use of a 3-D discrete Fourier Transform (3D-DFT) convolution method to carry out the dosimetry for I-131 for soft tissues in radioimmunotherapy procedures. To validate this convolution method, mathematical and physical phantoms were used as a basis of comparison with Monte Carlo transport (MCT) calculations which were carried out using the EGS4 system code. The mathematical phantom consisted of a sphere containing uniform and nonuniform activity distributions. The physical phantom consisted of a cylinder containing uniform and nonuniform activity distributions. Quantitative SPECT reconstruction was carried out using the Circular Harmonic Transformmore » (CHT) algorithm.« less

Deep multi-scale location-aware 3D convolutional neural networks for automated detection of lacunes of presumed vascular origin.

PubMed

Ghafoorian, Mohsen; Karssemeijer, Nico; Heskes, Tom; Bergkamp, Mayra; Wissink, Joost; Obels, Jiri; Keizer, Karlijn; de Leeuw, Frank-Erik; Ginneken, Bram van; Marchiori, Elena; Platel, Bram

2017-01-01

Lacunes of presumed vascular origin (lacunes) are associated with an increased risk of stroke, gait impairment, and dementia and are a primary imaging feature of the small vessel disease. Quantification of lacunes may be of great importance to elucidate the mechanisms behind neuro-degenerative disorders and is recommended as part of study standards for small vessel disease research. However, due to the different appearance of lacunes in various brain regions and the existence of other similar-looking structures, such as perivascular spaces, manual annotation is a difficult, elaborative and subjective task, which can potentially be greatly improved by reliable and consistent computer-aided detection (CAD) routines. In this paper, we propose an automated two-stage method using deep convolutional neural networks (CNN). We show that this method has good performance and can considerably benefit readers. We first use a fully convolutional neural network to detect initial candidates. In the second step, we employ a 3D CNN as a false positive reduction tool. As the location information is important to the analysis of candidate structures, we further equip the network with contextual information using multi-scale analysis and integration of explicit location features. We trained, validated and tested our networks on a large dataset of 1075 cases obtained from two different studies. Subsequently, we conducted an observer study with four trained observers and compared our method with them using a free-response operating characteristic analysis. Shown on a test set of 111 cases, the resulting CAD system exhibits performance similar to the trained human observers and achieves a sensitivity of 0.974 with 0.13 false positives per slice. A feasibility study also showed that a trained human observer would considerably benefit once aided by the CAD system.

Convolutional Neural Network Based on Extreme Learning Machine for Maritime Ships Recognition in Infrared Images.

PubMed

Khellal, Atmane; Ma, Hongbin; Fei, Qing

2018-05-09

The success of Deep Learning models, notably convolutional neural networks (CNNs), makes them the favorable solution for object recognition systems in both visible and infrared domains. However, the lack of training data in the case of maritime ships research leads to poor performance due to the problem of overfitting. In addition, the back-propagation algorithm used to train CNN is very slow and requires tuning many hyperparameters. To overcome these weaknesses, we introduce a new approach fully based on Extreme Learning Machine (ELM) to learn useful CNN features and perform a fast and accurate classification, which is suitable for infrared-based recognition systems. The proposed approach combines an ELM based learning algorithm to train CNN for discriminative features extraction and an ELM based ensemble for classification. The experimental results on VAIS dataset, which is the largest dataset of maritime ships, confirm that the proposed approach outperforms the state-of-the-art models in term of generalization performance and training speed. For instance, the proposed model is up to 950 times faster than the traditional back-propagation based training of convolutional neural networks, primarily for low-level features extraction.

Channel coding for underwater acoustic single-carrier CDMA communication system

NASA Astrophysics Data System (ADS)

Liu, Lanjun; Zhang, Yonglei; Zhang, Pengcheng; Zhou, Lin; Niu, Jiong

2017-01-01

CDMA is an effective multiple access protocol for underwater acoustic networks, and channel coding can effectively reduce the bit error rate (BER) of the underwater acoustic communication system. For the requirements of underwater acoustic mobile networks based on CDMA, an underwater acoustic single-carrier CDMA communication system (UWA/SCCDMA) based on the direct-sequence spread spectrum is proposed, and its channel coding scheme is studied based on convolution, RA, Turbo and LDPC coding respectively. The implementation steps of the Viterbi algorithm of convolutional coding, BP and minimum sum algorithms of RA coding, Log-MAP and SOVA algorithms of Turbo coding, and sum-product algorithm of LDPC coding are given. An UWA/SCCDMA simulation system based on Matlab is designed. Simulation results show that the UWA/SCCDMA based on RA, Turbo and LDPC coding have good performance such that the communication BER is all less than 10-6 in the underwater acoustic channel with low signal to noise ratio (SNR) from -12 dB to -10dB, which is about 2 orders of magnitude lower than that of the convolutional coding. The system based on Turbo coding with Log-MAP algorithm has the best performance.

Fast tomosynthesis for lung cancer detection using the SBDX geometry

NASA Astrophysics Data System (ADS)

Fahrig, Rebecca; Pineda, Angel R.; Solomon, Edward G.; Leung, Ann N.; Pelc, Norbert J.

2003-06-01

Radiology-based lung-cancer detection is a high-contrast imaging task, consisting of the detection of a small mass of tissue within much lower density lung parenchyma. This imaging task requires removal of confounding image details, fast image acquisition (< 0.1 s for pericardial region), low dose (comparable to a chest x-ray), high resolution (< 0.25 mm in-plane) and patient positioning flexibility. We present an investigation of tomosynthesis, implemented using the Scanning-Beam Digital X-ray System (SBDX), to achieve these goals. We designed an image-based computer model of tomosynthesis using a high-resolution (0.15-mm isotropic voxels), low-noise CT volume image of a lung phantom, numerically added spherical lesions and convolution-based tomographic blurring. Lesion visibility was examined as a function of half-tomographic angle for 2.5 and 4.0 mm diameter lesions. Gaussian distributed noise was added to the projected images. For lesions 2.5 mm and 4.0 mm in diameter, half-tomographic angles of at least 6° and 9° respectively were necessary before visualization of the lesions improved. The addition of noise for a dose equivalent to 1/10 that used for a standard chest radiograph did not significantly impair lesion detection. The results are promising, indicating that lung-cancer detection using a modified SBDX system is possible.

Salient object detection based on multi-scale contrast.

PubMed

Wang, Hai; Dai, Lei; Cai, Yingfeng; Sun, Xiaoqiang; Chen, Long

2018-05-01

Due to the development of deep learning networks, a salient object detection based on deep learning networks, which are used to extract the features, has made a great breakthrough compared to the traditional methods. At present, the salient object detection mainly relies on very deep convolutional network, which is used to extract the features. In deep learning networks, an dramatic increase of network depth may cause more training errors instead. In this paper, we use the residual network to increase network depth and to mitigate the errors caused by depth increase simultaneously. Inspired by image simplification, we use color and texture features to obtain simplified image with multiple scales by means of region assimilation on the basis of super-pixels in order to reduce the complexity of images and to improve the accuracy of salient target detection. We refine the feature on pixel level by the multi-scale feature correction method to avoid the feature error when the image is simplified at the above-mentioned region level. The final full connection layer not only integrates features of multi-scale and multi-level but also works as classifier of salient targets. The experimental results show that proposed model achieves better results than other salient object detection models based on original deep learning networks. Copyright © 2018 Elsevier Ltd. All rights reserved.

Rapid Object Detection Systems, Utilising Deep Learning and Unmanned Aerial Systems (uas) for Civil Engineering Applications

NASA Astrophysics Data System (ADS)

Griffiths, D.; Boehm, J.

2018-05-01

With deep learning approaches now out-performing traditional image processing techniques for image understanding, this paper accesses the potential of rapid generation of Convolutional Neural Networks (CNNs) for applied engineering purposes. Three CNNs are trained on 275 UAS-derived and freely available online images for object detection of 3m2 segments of railway track. These includes two models based on the Faster RCNN object detection algorithm (Resnet and Incpetion-Resnet) as well as the novel onestage Focal Loss network architecture (Retinanet). Model performance was assessed with respect to three accuracy metrics. The first two consisted of Intersection over Union (IoU) with thresholds 0.5 and 0.1. The last assesses accuracy based on the proportion of track covered by object detection proposals against total track length. In under six hours of training (and two hours of manual labelling) the models detected 91.3 %, 83.1 % and 75.6 % of track in the 500 test images acquired from the UAS survey Retinanet, Resnet and Inception-Resnet respectively. We then discuss the potential for such applications of such systems within the engineering field for a range of scenarios.

Systematic evaluation of deep learning based detection frameworks for aerial imagery

NASA Astrophysics Data System (ADS)

Sommer, Lars; Steinmann, Lucas; Schumann, Arne; Beyerer, Jürgen

2018-04-01

Object detection in aerial imagery is crucial for many applications in the civil and military domain. In recent years, deep learning based object detection frameworks significantly outperformed conventional approaches based on hand-crafted features on several datasets. However, these detection frameworks are generally designed and optimized for common benchmark datasets, which considerably differ from aerial imagery especially in object sizes. As already demonstrated for Faster R-CNN, several adaptations are necessary to account for these differences. In this work, we adapt several state-of-the-art detection frameworks including Faster R-CNN, R-FCN, and Single Shot MultiBox Detector (SSD) to aerial imagery. We discuss adaptations that mainly improve the detection accuracy of all frameworks in detail. As the output of deeper convolutional layers comprise more semantic information, these layers are generally used in detection frameworks as feature map to locate and classify objects. However, the resolution of these feature maps is insufficient for handling small object instances, which results in an inaccurate localization or incorrect classification of small objects. Furthermore, state-of-the-art detection frameworks perform bounding box regression to predict the exact object location. Therefore, so called anchor or default boxes are used as reference. We demonstrate how an appropriate choice of anchor box sizes can considerably improve detection performance. Furthermore, we evaluate the impact of the performed adaptations on two publicly available datasets to account for various ground sampling distances or differing backgrounds. The presented adaptations can be used as guideline for further datasets or detection frameworks.

Development of a dual-modality, dual-view smartphone-based imaging system for oral cancer detection

NASA Astrophysics Data System (ADS)

Uthoff, Ross D.; Song, Bofan; Birur, Praveen; Kuriakose, Moni Abraham; Sunny, Sumsum; Suresh, Amritha; Patrick, Sanjana; Anbarani, Afarin; Spires, Oliver; Wilder-Smith, Petra; Liang, Rongguang

2018-02-01

Oral cancer is a rising health issue in many low and middle income countries (LMIC). Proposed is an implementation of autofluorescence imaging (AFI) and white light imaging (WLI) on a smartphone platform providing inexpensive early detection of cancerous conditions in the oral cavity. Interchangeable modules allow both whole mouth imaging for an overview of the patients' oral health and an intraoral imaging probe for localized information. Custom electronics synchronize image capture and external LED operation for the excitation of tissue fluorescence. A custom Android application captures images and an image processing algorithm provides likelihood estimates of cancerous conditions. Finally, all data can be uploaded to a cloud server where a convolutional neural network classifies the images and a remote specialist can provide diagnosis and triage instructions.

Detection and Classification of Whale Acoustic Signals

NASA Astrophysics Data System (ADS)

Xian, Yin

This dissertation focuses on two vital challenges in relation to whale acoustic signals: detection and classification. In detection, we evaluated the influence of the uncertain ocean environment on the spectrogram-based detector, and derived the likelihood ratio of the proposed Short Time Fourier Transform detector. Experimental results showed that the proposed detector outperforms detectors based on the spectrogram. The proposed detector is more sensitive to environmental changes because it includes phase information. In classification, our focus is on finding a robust and sparse representation of whale vocalizations. Because whale vocalizations can be modeled as polynomial phase signals, we can represent the whale calls by their polynomial phase coefficients. In this dissertation, we used the Weyl transform to capture chirp rate information, and used a two dimensional feature set to represent whale vocalizations globally. Experimental results showed that our Weyl feature set outperforms chirplet coefficients and MFCC (Mel Frequency Cepstral Coefficients) when applied to our collected data. Since whale vocalizations can be represented by polynomial phase coefficients, it is plausible that the signals lie on a manifold parameterized by these coefficients. We also studied the intrinsic structure of high dimensional whale data by exploiting its geometry. Experimental results showed that nonlinear mappings such as Laplacian Eigenmap and ISOMAP outperform linear mappings such as PCA and MDS, suggesting that the whale acoustic data is nonlinear. We also explored deep learning algorithms on whale acoustic data. We built each layer as convolutions with either a PCA filter bank (PCANet) or a DCT filter bank (DCTNet). With the DCT filter bank, each layer has different a time-frequency scale representation, and from this, one can extract different physical information. Experimental results showed that our PCANet and DCTNet achieve high classification rate on the whale vocalization data set. The word error rate of the DCTNet feature is similar to the MFSC in speech recognition tasks, suggesting that the convolutional network is able to reveal acoustic content of speech signals.

Systems and methods of detecting force and stress using tetrapod nanocrystal

DOEpatents

Choi, Charina L.; Koski, Kristie J.; Sivasankar, Sanjeevi; Alivisatos, A. Paul

2013-08-20

Systems and methods of detecting force on the nanoscale including methods for detecting force using a tetrapod nanocrystal by exposing the tetrapod nanocrystal to light, which produces a luminescent response by the tetrapod nanocrystal. The method continues with detecting a difference in the luminescent response by the tetrapod nanocrystal relative to a base luminescent response that indicates a force between a first and second medium or stresses or strains experienced within a material. Such systems and methods find use with biological systems to measure forces in biological events or interactions.

Information Operations in Iraq: The Mufsiddoon versus the U.S. and Coalition Forces

DTIC Science & Technology

2008-04-01

language against him; 2) branding the enemy as mufsidoon committing hirabah; 3) making better use of the media (particularly the local Iraqi media); 4...strategy is branding the terrorists as mufsidoon committing hirabah. Words are critically important and the U.S. can make better use of the Arabic...credibility among the Iraqis; 2) convoluted approval procedures for 10; 3) unintentionally reinforcing AQI’s branding efforts; 4) not understanding

Effective image differencing with convolutional neural networks for real-time transient hunting

NASA Astrophysics Data System (ADS)

Sedaghat, Nima; Mahabal, Ashish

2018-06-01

Large sky surveys are increasingly relying on image subtraction pipelines for real-time (and archival) transient detection. In this process one has to contend with varying point-spread function (PSF) and small brightness variations in many sources, as well as artefacts resulting from saturated stars and, in general, matching errors. Very often the differencing is done with a reference image that is deeper than individual images and the attendant difference in noise characteristics can also lead to artefacts. We present here a deep-learning approach to transient detection that encapsulates all the steps of a traditional image-subtraction pipeline - image registration, background subtraction, noise removal, PSF matching and subtraction - in a single real-time convolutional network. Once trained, the method works lightening-fast and, given that it performs multiple steps in one go, the time saved and false positives eliminated for multi-CCD surveys like Zwicky Transient Facility and Large Synoptic Survey Telescope will be immense, as millions of subtractions will be needed per night.

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

PubMed

Islam, Jyoti; Zhang, Yanqing

2018-05-31

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

Capacity, cutoff rate, and coding for a direct-detection optical channel

NASA Technical Reports Server (NTRS)

Massey, J. L.

1980-01-01

It is shown that Pierce's pulse position modulation scheme with 2 to the L pulse positions used on a self-noise-limited direct detection optical communication channel results in a 2 to the L-ary erasure channel that is equivalent to the parallel combination of L completely correlated binary erasure channels. The capacity of the full channel is the sum of the capacities of the component channels, but the cutoff rate of the full channel is shown to be much smaller than the sum of the cutoff rates. An interpretation of the cutoff rate is given that suggests a complexity advantage in coding separately on the component channels. It is shown that if short-constraint-length convolutional codes with Viterbi decoders are used on the component channels, then the performance and complexity compare favorably with the Reed-Solomon coding system proposed by McEliece for the full channel. The reasons for this unexpectedly fine performance by the convolutional code system are explored in detail, as are various facets of the channel structure.

Investigation on the kurtosis filter and the derivation of convolutional sparse filter for impulsive signature enhancement

NASA Astrophysics Data System (ADS)

Jia, Xiaodong; Zhao, Ming; Di, Yuan; Jin, Chao; Lee, Jay

2017-01-01

Minimum Entropy Deconvolution (MED) filter, which is a non-parametric approach for impulsive signature detection, has been widely studied recently. Although the merits of the MED filter are manifold, this method tends to over highlight the dominant peaks and its performance becomes less stable when strong noise exists. In order to better understand the behavior of the MED filter, this study first investigated the mathematical fundamentals of the MED filter and then explained the reason why the MED filter tends to over highlight the dominant peaks. In order to pursue finer solutions for weak impulsive signature enhancement, the Convolutional Sparse Filter (CSF) is originally proposed in this work and the derivation of the CSF is presented in details. The superiority of the proposed CSF over the MED filter is validated by both simulated data and experimental data. The results demonstrate that CSF is an effective method for impulsive signature enhancement that could be applied in rotating machines for incipient fault detection.

Advances of FishNet towards a fully automatic monitoring system for fish migration

NASA Astrophysics Data System (ADS)

Kratzert, Frederik; Mader, Helmut

2017-04-01

Restoring the continuum of river networks, affected by anthropogenic constructions, is one of the main objectives of the Water Framework Directive. Regarding fish migration, fish passes are a widely used measure. Often the functionality of these fish passes needs to be assessed by monitoring. Over the last years, we developed a new semi-automatic monitoring system (FishCam) which allows the contact free observation of fish migration in fish passes through videos. The system consists of a detection tunnel, equipped with a camera, a motion sensor and artificial light sources, as well as a software (FishNet), which helps to analyze the video data. In its latest version, the software is capable of detecting and tracking objects in the videos as well as classifying them into "fish" and "no-fish" objects. This allows filtering out the videos containing at least one fish (approx. 5 % of all grabbed videos) and reduces the manual labor to the analysis of these videos. In this state the entire system has already been used in over 20 different fish passes across Austria for a total of over 140 months of monitoring resulting in more than 1.4 million analyzed videos. As a next step towards a fully automatic monitoring system, a key feature is the automatized classification of the detected fish into their species, which is still an unsolved task in a fully automatic monitoring environment. Recent advances in the field of machine learning, especially image classification with deep convolutional neural networks, sound promising in order to solve this problem. In this study, different approaches for the fish species classification are tested. Besides an image-only based classification approach using deep convolutional neural networks, various methods that combine the power of convolutional neural networks as image descriptors with additional features, such as the fish length and the time of appearance, are explored. To facilitate the development and testing phase of this approach, a subset of six fish species of Austrian rivers and streams is considered in this study. All scripts and the data to reproduce the results of this study will be made publicly available on GitHub* at the beginning of the EGU2017 General Assembly. * https://github.com/kratzert/EGU2017_public/

Fast learning method for convolutional neural networks using extreme learning machine and its application to lane detection.

PubMed

Kim, Jihun; Kim, Jonghong; Jang, Gil-Jin; Lee, Minho

2017-03-01

Deep learning has received significant attention recently as a promising solution to many problems in the area of artificial intelligence. Among several deep learning architectures, convolutional neural networks (CNNs) demonstrate superior performance when compared to other machine learning methods in the applications of object detection and recognition. We use a CNN for image enhancement and the detection of driving lanes on motorways. In general, the process of lane detection consists of edge extraction and line detection. A CNN can be used to enhance the input images before lane detection by excluding noise and obstacles that are irrelevant to the edge detection result. However, training conventional CNNs requires considerable computation and a big dataset. Therefore, we suggest a new learning algorithm for CNNs using an extreme learning machine (ELM). The ELM is a fast learning method used to calculate network weights between output and hidden layers in a single iteration and thus, can dramatically reduce learning time while producing accurate results with minimal training data. A conventional ELM can be applied to networks with a single hidden layer; as such, we propose a stacked ELM architecture in the CNN framework. Further, we modify the backpropagation algorithm to find the targets of hidden layers and effectively learn network weights while maintaining performance. Experimental results confirm that the proposed method is effective in reducing learning time and improving performance. Copyright © 2016 Elsevier Ltd. All rights reserved.

SU-E-T-371: Evaluating the Convolution Algorithm of a Commercially Available Radiosurgery Irradiator Using a Novel Phantom

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

Cates, J; Drzymala, R

2015-06-15

Purpose: The purpose of this study was to develop and use a novel phantom to evaluate the accuracy and usefulness of the Leskell Gamma Plan convolution-based dose calculation algorithm compared with the current TMR10 algorithm. Methods: A novel phantom was designed to fit the Leskell Gamma Knife G Frame which could accommodate various materials in the form of one inch diameter, cylindrical plugs. The plugs were split axially to allow EBT2 film placement. Film measurements were made during two experiments. The first utilized plans generated on a homogeneous acrylic phantom setup using the TMR10 algorithm, with various materials inserted intomore » the phantom during film irradiation to assess the effect on delivered dose due to unplanned heterogeneities upstream in the beam path. The second experiment utilized plans made on CT scans of different heterogeneous setups, with one plan using the TMR10 dose calculation algorithm and the second using the convolution-based algorithm. Materials used to introduce heterogeneities included air, LDPE, polystyrene, Delrin, Teflon, and aluminum. Results: The data shows that, as would be expected, having heterogeneities in the beam path does induce dose delivery error when using the TMR10 algorithm, with the largest errors being due to the heterogeneities with electron densities most different from that of water, i.e. air, Teflon, and aluminum. Additionally, the Convolution algorithm did account for the heterogeneous material and provided a more accurate predicted dose, in extreme cases up to a 7–12% improvement over the TMR10 algorithm. The convolution algorithm expected dose was accurate to within 3% in all cases. Conclusion: This study proves that the convolution algorithm is an improvement over the TMR10 algorithm when heterogeneities are present. More work is needed to determine what the heterogeneity size/volume limits are where this improvement exists, and in what clinical and/or research cases this would be relevant.« less

Gastrointestinal bleeding detection in wireless capsule endoscopy images using handcrafted and CNN features.

PubMed

Xiao Jia; Meng, Max Q-H

2017-07-01

Gastrointestinal (GI) bleeding detection plays an essential role in wireless capsule endoscopy (WCE) examination. In this paper, we present a new approach for WCE bleeding detection that combines handcrafted (HC) features and convolutional neural network (CNN) features. Compared with our previous work, a smaller-scale CNN architecture is constructed to lower the computational cost. In experiments, we show that the proposed strategy is highly capable when training data is limited, and yields comparable or better results than the latest methods.

Microscopic medical image classification framework via deep learning and shearlet transform.

PubMed

Rezaeilouyeh, Hadi; Mollahosseini, Ali; Mahoor, Mohammad H

2016-10-01

Cancer is the second leading cause of death in US after cardiovascular disease. Image-based computer-aided diagnosis can assist physicians to efficiently diagnose cancers in early stages. Existing computer-aided algorithms use hand-crafted features such as wavelet coefficients, co-occurrence matrix features, and recently, histogram of shearlet coefficients for classification of cancerous tissues and cells in images. These hand-crafted features often lack generalizability since every cancerous tissue and cell has a specific texture, structure, and shape. An alternative approach is to use convolutional neural networks (CNNs) to learn the most appropriate feature abstractions directly from the data and handle the limitations of hand-crafted features. A framework for breast cancer detection and prostate Gleason grading using CNN trained on images along with the magnitude and phase of shearlet coefficients is presented. Particularly, we apply shearlet transform on images and extract the magnitude and phase of shearlet coefficients. Then we feed shearlet features along with the original images to our CNN consisting of multiple layers of convolution, max pooling, and fully connected layers. Our experiments show that using the magnitude and phase of shearlet coefficients as extra information to the network can improve the accuracy of detection and generalize better compared to the state-of-the-art methods that rely on hand-crafted features. This study expands the application of deep neural networks into the field of medical image analysis, which is a difficult domain considering the limited medical data available for such analysis.

Adaptive Enhancement of X-Band Marine Radar Imagery to Detect Oil Spill Segments

PubMed Central

Liu, Peng; Li, Ying; Xu, Jin; Zhu, Xueyuan

2017-01-01

Oil spills generate a large cost in environmental and economic terms. Their identification plays an important role in oil-spill response. We propose an oil spill detection method with improved adaptive enhancement on X-band marine radar systems. The radar images used in this paper were acquired on 21 July 2010, from the teaching-training ship “YUKUN” of the Dalian Maritime University. According to the shape characteristic of co-channel interference, two convolutional filters are used to detect the location of the interference, followed by a mean filter to erase the interference. Small objects, such as bright speckles, are taken as a mask in the radar image and improved by the Fields-of-Experts model. The region marked by strong reflected signals from the sea’s surface is selected to identify oil spills. The selected region is subject to improved adaptive enhancement designed based on features of radar images. With the proposed adaptive enhancement technique, calculated oil spill detection is comparable to visual interpretation in accuracy. PMID:29036892

Application of Deep Learning to Detect Precursors of Tropical Cyclone

NASA Astrophysics Data System (ADS)

Matsuoka, D.; Nakano, M.; Sugiyama, D.; Uchida, S.

2017-12-01

Tropical cyclones (TCs) affect significant damage to human society. Predicting TC generation as soon as possible is important issue in both academic and social perspectives. In the present work, we investigate the probability of predicting TCs seven days prior using deep neural networks. The training data is produced from 30-year cloud resolving global atmospheric simulation (NICAM) with 14 km horizontal resolution (Kodama et al., 2015). We employed a TCs tracking algorithm (Sugi et al., 2002; Nakano et al., 2015) to NICAM simulation data in order to generate supervised cloud images (horizontal sizes are 800-1,000km). We generate approximately one million images of "TCs (include their precursors)" and "not TCs (low pressure clouds)". We generate ten types of image classifier based on 2-dimensional convolutional neural network, includes four convolutional layers, three pooling layers and two fully connected layers. The final predicted results are obtained by these ensemble mean values. Generated classifiers are applied to untrained global simulation data (four million test images). As a result, we succeeded in predicting the precursors of TCs seven and five days before their formation with a Recall of 88.6% and 89.6% (Precision is 11.4%), respectively.

Bone age detection via carpogram analysis using convolutional neural networks

NASA Astrophysics Data System (ADS)

Torres, Felipe; Bravo, María. Alejandra; Salinas, Emmanuel; Triana, Gustavo; Arbeláez, Pablo

2017-11-01

Bone age assessment is a critical factor for determining delayed development in children, which can be a sign of pathologies such as endocrine diseases, growth abnormalities, chromosomal, neurological and congenital disorders among others. In this paper we present BoneNet, a methodology to assess automatically the skeletal maturity state in pediatric patients based on Convolutional Neural Networks. We train and evaluate our algorithm on a database of X-Ray images provided by the hospital Fundacion Santa Fe de Bogot ´ a with around 1500 images of patients between the ages 1 to 18. ´ We compare two different architectures to classify the given data in order to explore the generality of our method. To accomplish this, we define multiple binary age assessment problems, dividing the data by bone age and differentiating the patients by their gender. Thus, exploring several parameters, we develop BoneNet. Our approach is holistic, efficient, and modular, since it is possible for the specialists to use all the networks combined to determine how is the skeletal maturity of a patient. BoneNet achieves over 90% accuracy for most of the critical age thresholds, when differentiating the images between over or under a given age.

Recognition of Damaged Arrow-Road Markings by Visible Light Camera Sensor Based on Convolutional Neural Network.

PubMed

Vokhidov, Husan; Hong, Hyung Gil; Kang, Jin Kyu; Hoang, Toan Minh; Park, Kang Ryoung

2016-12-16

Automobile driver information as displayed on marked road signs indicates the state of the road, traffic conditions, proximity to schools, etc. These signs are important to insure the safety of the driver and pedestrians. They are also important input to the automated advanced driver assistance system (ADAS), installed in many automobiles. Over time, the arrow-road markings may be eroded or otherwise damaged by automobile contact, making it difficult for the driver to correctly identify the marking. Failure to properly identify an arrow-road marker creates a dangerous situation that may result in traffic accidents or pedestrian injury. Very little research exists that studies the problem of automated identification of damaged arrow-road marking painted on the road. In this study, we propose a method that uses a convolutional neural network (CNN) to recognize six types of arrow-road markings, possibly damaged, by visible light camera sensor. Experimental results with six databases of Road marking dataset, KITTI dataset, Málaga dataset 2009, Málaga urban dataset, Naver street view dataset, and Road/Lane detection evaluation 2013 dataset, show that our method outperforms conventional methods.

Recognition of Damaged Arrow-Road Markings by Visible Light Camera Sensor Based on Convolutional Neural Network

PubMed Central

Vokhidov, Husan; Hong, Hyung Gil; Kang, Jin Kyu; Hoang, Toan Minh; Park, Kang Ryoung

2016-01-01

Automobile driver information as displayed on marked road signs indicates the state of the road, traffic conditions, proximity to schools, etc. These signs are important to insure the safety of the driver and pedestrians. They are also important input to the automated advanced driver assistance system (ADAS), installed in many automobiles. Over time, the arrow-road markings may be eroded or otherwise damaged by automobile contact, making it difficult for the driver to correctly identify the marking. Failure to properly identify an arrow-road marker creates a dangerous situation that may result in traffic accidents or pedestrian injury. Very little research exists that studies the problem of automated identification of damaged arrow-road marking painted on the road. In this study, we propose a method that uses a convolutional neural network (CNN) to recognize six types of arrow-road markings, possibly damaged, by visible light camera sensor. Experimental results with six databases of Road marking dataset, KITTI dataset, Málaga dataset 2009, Málaga urban dataset, Naver street view dataset, and Road/Lane detection evaluation 2013 dataset, show that our method outperforms conventional methods. PMID:27999301

Deep Spatial-Temporal Joint Feature Representation for Video Object Detection.

PubMed

Zhao, Baojun; Zhao, Boya; Tang, Linbo; Han, Yuqi; Wang, Wenzheng

2018-03-04

With the development of deep neural networks, many object detection frameworks have shown great success in the fields of smart surveillance, self-driving cars, and facial recognition. However, the data sources are usually videos, and the object detection frameworks are mostly established on still images and only use the spatial information, which means that the feature consistency cannot be ensured because the training procedure loses temporal information. To address these problems, we propose a single, fully-convolutional neural network-based object detection framework that involves temporal information by using Siamese networks. In the training procedure, first, the prediction network combines the multiscale feature map to handle objects of various sizes. Second, we introduce a correlation loss by using the Siamese network, which provides neighboring frame features. This correlation loss represents object co-occurrences across time to aid the consistent feature generation. Since the correlation loss should use the information of the track ID and detection label, our video object detection network has been evaluated on the large-scale ImageNet VID dataset where it achieves a 69.5% mean average precision (mAP).

Offline signature verification using convolution Siamese network

NASA Astrophysics Data System (ADS)

Xing, Zi-Jian; Yin, Fei; Wu, Yi-Chao; Liu, Cheng-Lin

2018-04-01

This paper presents an offline signature verification approach using convolutional Siamese neural network. Unlike the existing methods which consider feature extraction and metric learning as two independent stages, we adopt a deepleaning based framework which combines the two stages together and can be trained end-to-end. The experimental results on two offline public databases (GPDSsynthetic and CEDAR) demonstrate the superiority of our method on the offline signature verification problem.

3-D Forward modeling of Induced Polarization Effects of Transient Electromagnetic Method

NASA Astrophysics Data System (ADS)

Wu, Y.; Ji, Y.; Guan, S.; Li, D.; Wang, A.

2017-12-01

In transient electromagnetic (TEM) detection, Induced polarization (IP) effects are so important that they cannot be ignored. The authors simulate the three-dimensional (3-D) induced polarization effects in time-domain directly by applying the finite-difference time-domain method (FDTD) based on Cole-Cole model. Due to the frequency dispersion characteristics of the electrical conductivity, the computations of convolution in the generalized Ohm's law of fractional order system makes the forward modeling particularly complicated. Firstly, we propose a method to approximate the fractional order function of Cole-Cole model using a lower order rational transfer function based on error minimum theory in the frequency domain. In this section, two auxiliary variables are introduced to transform nonlinear least square fitting problem of the fractional order system into a linear programming problem, thus avoiding having to solve a system of equations and nonlinear problems. Secondly, the time-domain expression of Cole-Cole model is obtained by using Inverse Laplace transform. Then, for the calculation of Ohm's law, we propose an e-index auxiliary equation of conductivity to transform the convolution to non-convolution integral; in this section, the trapezoid rule is applied to compute the integral. We then substitute the recursion equation into Maxwell's equations to derive the iterative equations of electromagnetic field using the FDTD method. Finally, we finish the stimulation of 3-D model and evaluate polarization parameters. The results are compared with those obtained from the digital filtering solution of the analytical equation in the homogeneous half space, as well as with the 3-D model results from the auxiliary ordinary differential equation method (ADE). Good agreements are obtained across the three methods. In terms of the 3-D model, the proposed method has higher efficiency and lower memory requirements as execution times and memory usage were reduced by 20% compared with ADE method.

Efficient Modeling of Gravity Fields Caused by Sources with Arbitrary Geometry and Arbitrary Density Distribution

NASA Astrophysics Data System (ADS)

Wu, Leyuan

2018-01-01

We present a brief review of gravity forward algorithms in Cartesian coordinate system, including both space-domain and Fourier-domain approaches, after which we introduce a truly general and efficient algorithm, namely the convolution-type Gauss fast Fourier transform (Conv-Gauss-FFT) algorithm, for 2D and 3D modeling of gravity potential and its derivatives due to sources with arbitrary geometry and arbitrary density distribution which are defined either by discrete or by continuous functions. The Conv-Gauss-FFT algorithm is based on the combined use of a hybrid rectangle-Gaussian grid and the fast Fourier transform (FFT) algorithm. Since the gravity forward problem in Cartesian coordinate system can be expressed as continuous convolution-type integrals, we first approximate the continuous convolution by a weighted sum of a series of shifted discrete convolutions, and then each shifted discrete convolution, which is essentially a Toeplitz system, is calculated efficiently and accurately by combining circulant embedding with the FFT algorithm. Synthetic and real model tests show that the Conv-Gauss-FFT algorithm can obtain high-precision forward results very efficiently for almost any practical model, and it works especially well for complex 3D models when gravity fields on large 3D regular grids are needed.

Accelerated Cartesian expansion (ACE) based framework for the rapid evaluation of diffusion, lossy wave, and Klein-Gordon potentials

DOE PAGES

Baczewski, Andrew David; Vikram, Melapudi; Shanker, Balasubramaniam; ...

2010-08-27

Diffusion, lossy wave, and Klein–Gordon equations find numerous applications in practical problems across a range of diverse disciplines. The temporal dependence of all three Green’s functions are characterized by an infinite tail. This implies that the cost complexity of the spatio-temporal convolutions, associated with evaluating the potentials, scales as O(N s 2N t 2), where N s and N t are the number of spatial and temporal degrees of freedom, respectively. In this paper, we discuss two new methods to rapidly evaluate these spatio-temporal convolutions by exploiting their block-Toeplitz nature within the framework of accelerated Cartesian expansions (ACE). The firstmore » scheme identifies a convolution relation in time amongst ACE harmonics and the fast Fourier transform (FFT) is used for efficient evaluation of these convolutions. The second method exploits the rank deficiency of the ACE translation operators with respect to time and develops a recursive numerical compression scheme for the efficient representation and evaluation of temporal convolutions. It is shown that the cost of both methods scales as O(N sN tlog 2N t). Furthermore, several numerical results are presented for the diffusion equation to validate the accuracy and efficacy of the fast algorithms developed here.« less

A convolutional neural network neutrino event classifier

DOE PAGES

Aurisano, A.; Radovic, A.; Rocco, D.; ...

2016-09-01

Here, convolutional neural networks (CNNs) have been widely applied in the computer vision community to solve complex problems in image recognition and analysis. We describe an application of the CNN technology to the problem of identifying particle interactions in sampling calorimeters used commonly in high energy physics and high energy neutrino physics in particular. Following a discussion of the core concepts of CNNs and recent innovations in CNN architectures related to the field of deep learning, we outline a specific application to the NOvA neutrino detector. This algorithm, CVN (Convolutional Visual Network) identifies neutrino interactions based on their topology withoutmore » the need for detailed reconstruction and outperforms algorithms currently in use by the NOvA collaboration.« less

A convolutional neural network neutrino event classifier

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

Aurisano, A.; Radovic, A.; Rocco, D.

Here, convolutional neural networks (CNNs) have been widely applied in the computer vision community to solve complex problems in image recognition and analysis. We describe an application of the CNN technology to the problem of identifying particle interactions in sampling calorimeters used commonly in high energy physics and high energy neutrino physics in particular. Following a discussion of the core concepts of CNNs and recent innovations in CNN architectures related to the field of deep learning, we outline a specific application to the NOvA neutrino detector. This algorithm, CVN (Convolutional Visual Network) identifies neutrino interactions based on their topology withoutmore » the need for detailed reconstruction and outperforms algorithms currently in use by the NOvA collaboration.« less

Deep Learning with Hierarchical Convolutional Factor Analysis

PubMed Central

Chen, Bo; Polatkan, Gungor; Sapiro, Guillermo; Blei, David; Dunson, David; Carin, Lawrence

2013-01-01

Unsupervised multi-layered (“deep”) models are considered for general data, with a particular focus on imagery. The model is represented using a hierarchical convolutional factor-analysis construction, with sparse factor loadings and scores. The computation of layer-dependent model parameters is implemented within a Bayesian setting, employing a Gibbs sampler and variational Bayesian (VB) analysis, that explicitly exploit the convolutional nature of the expansion. In order to address large-scale and streaming data, an online version of VB is also developed. The number of basis functions or dictionary elements at each layer is inferred from the data, based on a beta-Bernoulli implementation of the Indian buffet process. Example results are presented for several image-processing applications, with comparisons to related models in the literature. PMID:23787342

DeepPap: Deep Convolutional Networks for Cervical Cell Classification.

PubMed

Zhang, Ling; Le Lu; Nogues, Isabella; Summers, Ronald M; Liu, Shaoxiong; Yao, Jianhua

2017-11-01

Automation-assisted cervical screening via Pap smear or liquid-based cytology (LBC) is a highly effective cell imaging based cancer detection tool, where cells are partitioned into "abnormal" and "normal" categories. However, the success of most traditional classification methods relies on the presence of accurate cell segmentations. Despite sixty years of research in this field, accurate segmentation remains a challenge in the presence of cell clusters and pathologies. Moreover, previous classification methods are only built upon the extraction of hand-crafted features, such as morphology and texture. This paper addresses these limitations by proposing a method to directly classify cervical cells-without prior segmentation-based on deep features, using convolutional neural networks (ConvNets). First, the ConvNet is pretrained on a natural image dataset. It is subsequently fine-tuned on a cervical cell dataset consisting of adaptively resampled image patches coarsely centered on the nuclei. In the testing phase, aggregation is used to average the prediction scores of a similar set of image patches. The proposed method is evaluated on both Pap smear and LBC datasets. Results show that our method outperforms previous algorithms in classification accuracy (98.3%), area under the curve (0.99) values, and especially specificity (98.3%), when applied to the Herlev benchmark Pap smear dataset and evaluated using five-fold cross validation. Similar superior performances are also achieved on the HEMLBC (H&E stained manual LBC) dataset. Our method is promising for the development of automation-assisted reading systems in primary cervical screening.

Computer-aided classification of mammographic masses using the deep learning technology: a preliminary study

NASA Astrophysics Data System (ADS)

Qiu, Yuchen; Yan, Shiju; Tan, Maxine; Cheng, Samuel; Liu, Hong; Zheng, Bin

2016-03-01

Although mammography is the only clinically acceptable imaging modality used in the population-based breast cancer screening, its efficacy is quite controversy. One of the major challenges is how to help radiologists more accurately classify between benign and malignant lesions. The purpose of this study is to investigate a new mammographic mass classification scheme based on a deep learning method. In this study, we used an image dataset involving 560 regions of interest (ROIs) extracted from digital mammograms, which includes 280 malignant and 280 benign mass ROIs, respectively. An eight layer deep learning network was applied, which employs three pairs of convolution-max-pooling layers for automatic feature extraction and a multiple layer perception (MLP) classifier for feature categorization. In order to improve robustness of selected features, each convolution layer is connected with a max-pooling layer. A number of 20, 10, and 5 feature maps were utilized for the 1st, 2nd and 3rd convolution layer, respectively. The convolution networks are followed by a MLP classifier, which generates a classification score to predict likelihood of a ROI depicting a malignant mass. Among 560 ROIs, 420 ROIs were used as a training dataset and the remaining 140 ROIs were used as a validation dataset. The result shows that the new deep learning based classifier yielded an area under the receiver operation characteristic curve (AUC) of 0.810+/-0.036. This study demonstrated the potential superiority of using a deep learning based classifier to distinguish malignant and benign breast masses without segmenting the lesions and extracting the pre-defined image features.

Automatic diabetic retinopathy classification

NASA Astrophysics Data System (ADS)

Bravo, María. A.; Arbeláez, Pablo A.

2017-11-01

Diabetic retinopathy (DR) is a disease in which the retina is damaged due to augmentation in the blood pressure of small vessels. DR is the major cause of blindness for diabetics. It has been shown that early diagnosis can play a major role in prevention of visual loss and blindness. This work proposes a computer based approach for the detection of DR in back-of-the-eye images based on the use of convolutional neural networks (CNNs). Our CNN uses deep architectures to classify Back-of-the-eye Retinal Photographs (BRP) in 5 stages of DR. Our method combines several preprocessing images of BRP to obtain an ACA score of 50.5%. Furthermore, we explore subproblems by training a larger CNN of our main classification task.

Motor unit number estimation based on high-density surface electromyography decomposition.

PubMed

Peng, Yun; He, Jinbao; Yao, Bo; Li, Sheng; Zhou, Ping; Zhang, Yingchun

2016-09-01

To advance the motor unit number estimation (MUNE) technique using high density surface electromyography (EMG) decomposition. The K-means clustering convolution kernel compensation algorithm was employed to detect the single motor unit potentials (SMUPs) from high-density surface EMG recordings of the biceps brachii muscles in eight healthy subjects. Contraction forces were controlled at 10%, 20% and 30% of the maximal voluntary contraction (MVC). Achieved MUNE results and the representativeness of the SMUP pools were evaluated using a high-density weighted-average method. Mean numbers of motor units were estimated as 288±132, 155±87, 107±99 and 132±61 by using the developed new MUNE at 10%, 20%, 30% and 10-30% MVCs, respectively. Over 20 SMUPs were obtained at each contraction level, and the mean residual variances were lower than 10%. The new MUNE method allows a convenient and non-invasive collection of a large size of SMUP pool with great representativeness. It provides a useful tool for estimating the motor unit number of proximal muscles. The present new MUNE method successfully avoids the use of intramuscular electrodes or multiple electrical stimuli which is required in currently available MUNE techniques; as such the new MUNE method can minimize patient discomfort for MUNE tests. Copyright © 2016 International Federation of Clinical Neurophysiology. Published by Elsevier Ireland Ltd. All rights reserved.

A Demons algorithm for image registration with locally adaptive regularization.

PubMed

Cahill, Nathan D; Noble, J Alison; Hawkes, David J

2009-01-01

Thirion's Demons is a popular algorithm for nonrigid image registration because of its linear computational complexity and ease of implementation. It approximately solves the diffusion registration problem by successively estimating force vectors that drive the deformation toward alignment and smoothing the force vectors by Gaussian convolution. In this article, we show how the Demons algorithm can be generalized to allow image-driven locally adaptive regularization in a manner that preserves both the linear complexity and ease of implementation of the original Demons algorithm. We show that the proposed algorithm exhibits lower target registration error and requires less computational effort than the original Demons algorithm on the registration of serial chest CT scans of patients with lung nodules.

Convolutional coding techniques for data protection

NASA Technical Reports Server (NTRS)

Massey, J. L.

1975-01-01

Results of research on the use of convolutional codes in data communications are presented. Convolutional coding fundamentals are discussed along with modulation and coding interaction. Concatenated coding systems and data compression with convolutional codes are described.

Segmentation of left ventricle myocardium in porcine cardiac cine MR images using a hybrid of fully convolutional neural networks and convolutional LSTM

NASA Astrophysics Data System (ADS)

Zhang, Dongqing; Icke, Ilknur; Dogdas, Belma; Parimal, Sarayu; Sampath, Smita; Forbes, Joseph; Bagchi, Ansuman; Chin, Chih-Liang; Chen, Antong

2018-03-01

In the development of treatments for cardiovascular diseases, short axis cardiac cine MRI is important for the assessment of various structural and functional properties of the heart. In short axis cardiac cine MRI, Cardiac properties including the ventricle dimensions, stroke volume, and ejection fraction can be extracted based on accurate segmentation of the left ventricle (LV) myocardium. One of the most advanced segmentation methods is based on fully convolutional neural networks (FCN) and can be successfully used to do segmentation in cardiac cine MRI slices. However, the temporal dependency between slices acquired at neighboring time points is not used. Here, based on our previously proposed FCN structure, we proposed a new algorithm to segment LV myocardium in porcine short axis cardiac cine MRI by incorporating convolutional long short-term memory (Conv-LSTM) to leverage the temporal dependency. In this approach, instead of processing each slice independently in a conventional CNN-based approach, the Conv-LSTM architecture captures the dynamics of cardiac motion over time. In a leave-one-out experiment on 8 porcine specimens (3,600 slices), the proposed approach was shown to be promising by achieving average mean Dice similarity coefficient (DSC) of 0.84, Hausdorff distance (HD) of 6.35 mm, and average perpendicular distance (APD) of 1.09 mm when compared with manual segmentations, which improved the performance of our previous FCN-based approach (average mean DSC=0.84, HD=6.78 mm, and APD=1.11 mm). Qualitatively, our model showed robustness against low image quality and complications in the surrounding anatomy due to its ability to capture the dynamics of cardiac motion.

Data-based diffraction kernels for surface waves from convolution and correlation processes through active seismic interferometry

NASA Astrophysics Data System (ADS)

Chmiel, Malgorzata; Roux, Philippe; Herrmann, Philippe; Rondeleux, Baptiste; Wathelet, Marc

2018-05-01

We investigated the construction of diffraction kernels for surface waves using two-point convolution and/or correlation from land active seismic data recorded in the context of exploration geophysics. The high density of controlled sources and receivers, combined with the application of the reciprocity principle, allows us to retrieve two-dimensional phase-oscillation diffraction kernels (DKs) of surface waves between any two source or receiver points in the medium at each frequency (up to 15 Hz, at least). These DKs are purely data-based as no model calculations and no synthetic data are needed. They naturally emerge from the interference patterns of the recorded wavefields projected on the dense array of sources and/or receivers. The DKs are used to obtain multi-mode dispersion relations of Rayleigh waves, from which near-surface shear velocity can be extracted. Using convolution versus correlation with a grid of active sources is an important step in understanding the physics of the retrieval of surface wave Green's functions. This provides the foundation for future studies based on noise sources or active sources with a sparse spatial distribution.

An Automatic Detection System of Lung Nodule Based on Multi-Group Patch-Based Deep Learning Network.

PubMed

Jiang, Hongyang; Ma, He; Qian, Wei; Gao, Mengdi; Li, Yan

2017-07-14

High-efficiency lung nodule detection dramatically contributes to the risk assessment of lung cancer. It is a significant and challenging task to quickly locate the exact positions of lung nodules. Extensive work has been done by researchers around this domain for approximately two decades. However, previous computer aided detection (CADe) schemes are mostly intricate and time-consuming since they may require more image processing modules, such as the computed tomography (CT) image transformation, the lung nodule segmentation and the feature extraction, to construct a whole CADe system. It is difficult for those schemes to process and analyze enormous data when the medical images continue to increase. Besides, some state of the art deep learning schemes may be strict in the standard of database. This study proposes an effective lung nodule detection scheme based on multi-group patches cut out from the lung images, which are enhanced by the Frangi filter. Through combining two groups of images, a four-channel convolution neural networks (CNN) model is designed to learn the knowledge of radiologists for detecting nodules of four levels. This CADe scheme can acquire the sensitivity of 80.06% with 4.7 false positives per scan and the sensitivity of 94% with 15.1 false positives per scan. The results demonstrate that the multi-group patch-based learning system is efficient to improve the performance of lung nodule detection and greatly reduce the false positives under a huge amount of image data.

Deep neural network convolution (NNC) for three-class classification of diffuse lung disease opacities in high-resolution CT (HRCT): consolidation, ground-glass opacity (GGO), and normal opacity

NASA Astrophysics Data System (ADS)

Hashimoto, Noriaki; Suzuki, Kenji; Liu, Junchi; Hirano, Yasushi; MacMahon, Heber; Kido, Shoji

2018-02-01

Consolidation and ground-glass opacity (GGO) are two major types of opacities associated with diffuse lung diseases. Accurate detection and classification of such opacities are crucially important in the diagnosis of lung diseases, but the process is subjective, and suffers from interobserver variability. Our study purpose was to develop a deep neural network convolution (NNC) system for distinguishing among consolidation, GGO, and normal lung tissue in high-resolution CT (HRCT). We developed ensemble of two deep NNC models, each of which was composed of neural network regression (NNR) with an input layer, a convolution layer, a fully-connected hidden layer, and a fully-connected output layer followed by a thresholding layer. The output layer of each NNC provided a map for the likelihood of being each corresponding lung opacity of interest. The two NNC models in the ensemble were connected in a class-selection layer. We trained our NNC ensemble with pairs of input 2D axial slices and "teaching" probability maps for the corresponding lung opacity, which were obtained by combining three radiologists' annotations. We randomly selected 10 and 40 slices from HRCT scans of 172 patients for each class as a training and test set, respectively. Our NNC ensemble achieved an area under the receiver-operating-characteristic (ROC) curve (AUC) of 0.981 and 0.958 in distinction of consolidation and GGO, respectively, from normal opacity, yielding a classification accuracy of 93.3% among 3 classes. Thus, our deep-NNC-based system for classifying diffuse lung diseases achieved high accuracies for classification of consolidation, GGO, and normal opacity.

Apple flower detection using deep convolutional networks

USDA-ARS?s Scientific Manuscript database

In order to optimize fruit production, a portion of the flowers and fruitlets of apple trees must be removed early in the growing season. The proportion to be removed is determined by the bloom intensity, i.e., the number of flowers present in the orchard. Several automated computer vision systems...

76 FR 13072 - Airworthiness Directives; Saab AB, Saab Aerosystems Model SAAB 2000 Airplanes

Federal Register 2010, 2011, 2012, 2013, 2014

2011-03-10

... important to the structural integrity of the horizontal stabilizer. Corrosion damage in these areas, if not... structural integrity of the horizontal stabilizer. Corrosion damage in these areas, if not detected and... convoluted tubing on the harness, applying corrosion prevention compound to the inspected area, making sure...

DeepMoon: Convolutional neural network trainer to identify moon craters

NASA Astrophysics Data System (ADS)

Silburt, Ari; Zhu, Chenchong; Ali-Dib, Mohamad; Menou, Kristen; Jackson, Alan

2018-05-01

DeepMoon trains a convolutional neural net using data derived from a global digital elevation map (DEM) and catalog of craters to recognize craters on the Moon. The TensorFlow-based pipeline code is divided into three parts. The first generates a set images of the Moon randomly cropped from the DEM, with corresponding crater positions and radii. The second trains a convnet using this data, and the third validates the convnet's predictions.

Understanding of Object Detection Based on CNN Family and YOLO

NASA Astrophysics Data System (ADS)

Du, Juan

2018-04-01

As a key use of image processing, object detection has boomed along with the unprecedented advancement of Convolutional Neural Network (CNN) and its variants since 2012. When CNN series develops to Faster Region with CNN (R-CNN), the Mean Average Precision (mAP) has reached 76.4, whereas, the Frame Per Second (FPS) of Faster R-CNN remains 5 to 18 which is far slower than the real-time effect. Thus, the most urgent requirement of object detection improvement is to accelerate the speed. Based on the general introduction to the background and the core solution CNN, this paper exhibits one of the best CNN representatives You Only Look Once (YOLO), which breaks through the CNN family’s tradition and innovates a complete new way of solving the object detection with most simple and high efficient way. Its fastest speed has achieved the exciting unparalleled result with FPS 155, and its mAP can also reach up to 78.6, both of which have surpassed the performance of Faster R-CNN greatly. Additionally, compared with the latest most advanced solution, YOLOv2 achieves an excellent tradeoff between speed and accuracy as well as an object detector with strong generalization ability to represent the whole image.

Can surgical simulation be used to train detection and classification of neural networks?

PubMed

Zisimopoulos, Odysseas; Flouty, Evangello; Stacey, Mark; Muscroft, Sam; Giataganas, Petros; Nehme, Jean; Chow, Andre; Stoyanov, Danail

2017-10-01

Computer-assisted interventions (CAI) aim to increase the effectiveness, precision and repeatability of procedures to improve surgical outcomes. The presence and motion of surgical tools is a key information input for CAI surgical phase recognition algorithms. Vision-based tool detection and recognition approaches are an attractive solution and can be designed to take advantage of the powerful deep learning paradigm that is rapidly advancing image recognition and classification. The challenge for such algorithms is the availability and quality of labelled data used for training. In this Letter, surgical simulation is used to train tool detection and segmentation based on deep convolutional neural networks and generative adversarial networks. The authors experiment with two network architectures for image segmentation in tool classes commonly encountered during cataract surgery. A commercially-available simulator is used to create a simulated cataract dataset for training models prior to performing transfer learning on real surgical data. To the best of authors' knowledge, this is the first attempt to train deep learning models for surgical instrument detection on simulated data while demonstrating promising results to generalise on real data. Results indicate that simulated data does have some potential for training advanced classification methods for CAI systems.

Automatic phase aberration compensation for digital holographic microscopy based on deep learning background detection.

PubMed

Nguyen, Thanh; Bui, Vy; Lam, Van; Raub, Christopher B; Chang, Lin-Ching; Nehmetallah, George

2017-06-26

We propose a fully automatic technique to obtain aberration free quantitative phase imaging in digital holographic microscopy (DHM) based on deep learning. The traditional DHM solves the phase aberration compensation problem by manually detecting the background for quantitative measurement. This would be a drawback in real time implementation and for dynamic processes such as cell migration phenomena. A recent automatic aberration compensation approach using principle component analysis (PCA) in DHM avoids human intervention regardless of the cells' motion. However, it corrects spherical/elliptical aberration only and disregards the higher order aberrations. Traditional image segmentation techniques can be employed to spatially detect cell locations. Ideally, automatic image segmentation techniques make real time measurement possible. However, existing automatic unsupervised segmentation techniques have poor performance when applied to DHM phase images because of aberrations and speckle noise. In this paper, we propose a novel method that combines a supervised deep learning technique with convolutional neural network (CNN) and Zernike polynomial fitting (ZPF). The deep learning CNN is implemented to perform automatic background region detection that allows for ZPF to compute the self-conjugated phase to compensate for most aberrations.

Tandem mass spectrometry data quality assessment by self-convolution.

PubMed

Choo, Keng Wah; Tham, Wai Mun

2007-09-20

Many algorithms have been developed for deciphering the tandem mass spectrometry (MS) data sets. They can be essentially clustered into two classes. The first performs searches on theoretical mass spectrum database, while the second based itself on de novo sequencing from raw mass spectrometry data. It was noted that the quality of mass spectra affects significantly the protein identification processes in both instances. This prompted the authors to explore ways to measure the quality of MS data sets before subjecting them to the protein identification algorithms, thus allowing for more meaningful searches and increased confidence level of proteins identified. The proposed method measures the qualities of MS data sets based on the symmetric property of b- and y-ion peaks present in a MS spectrum. Self-convolution on MS data and its time-reversal copy was employed. Due to the symmetric nature of b-ions and y-ions peaks, the self-convolution result of a good spectrum would produce a highest mid point intensity peak. To reduce processing time, self-convolution was achieved using Fast Fourier Transform and its inverse transform, followed by the removal of the "DC" (Direct Current) component and the normalisation of the data set. The quality score was defined as the ratio of the intensity at the mid point to the remaining peaks of the convolution result. The method was validated using both theoretical mass spectra, with various permutations, and several real MS data sets. The results were encouraging, revealing a high percentage of positive prediction rates for spectra with good quality scores. We have demonstrated in this work a method for determining the quality of tandem MS data set. By pre-determining the quality of tandem MS data before subjecting them to protein identification algorithms, spurious protein predictions due to poor tandem MS data are avoided, giving scientists greater confidence in the predicted results. We conclude that the algorithm performs well and could potentially be used as a pre-processing for all mass spectrometry based protein identification tools.

Sexual dimorphism of sulcal morphology of the ferret cerebrum revealed by MRI-based sulcal surface morphometry

PubMed Central

Sawada, Kazuhiko; Horiuchi-Hirose, Miwa; Saito, Shigeyoshi; Aoki, Ichio

2015-01-01

The present study quantitatively assessed sexual dimorphism of cortical convolution and sulcal morphology in young adult ferrets by MRI-based sulcal surface morphometry. Ex vivo T1-weighted (short TR/TE) MRI of the ferret cerebrum was acquired with high spatial resolution at 7-tesla. The degree of cortical convolution, evaluated quantitatively based on 3D MRI data by sulcation index (SI), was significantly greater in males (0.553 ± 0.036) than in females (0.502 ± 0.043) (p < 0.001). The rostrocaudal distribution of the cortical convolution revealed a greater convolution in the frontal region of the cortex in males than in females and by a posterior extension of the convolution in the temporo-parieto-occipital region of males. Although the cerebral width in the frontal region was not different between sexes, the rhinal fissure and rostral region of splenial sulcus were more infolded in males than in females. On the contrary, the cerebral width was greater in males in the temporo-parieto-occipital region, and male-prominent posterior extension of infolding was noted in the lateral sulcus, caudal suprasylvian sulcus, pesudosylvian sulcus, hippocampal sulcus, and the caudal region of splenial sulcus. Notably, the caudal descending region of lateral sulcus was clearly infolded in males, but obscured in females. The present results suggest a region-related sexual dimorphism of the sulcal infolding, which is reflected by local cortical expansion in the ferret cerebrum. In particular, male-favored sulcal infolding with expansion of the temporo-parieto-occipital neocortex may be relevant to the human cerebral cortex regarding visuo-spatial and emotion processing, which are known to differ between sexes. The present results will provide fundamental information assessing sex-related changes in the regional sulcal infolding, when ferrets with experimentally-induced gyrification abnormality will be used as models for male-prevalent or male-earlier-onset neurodevelopmental disorders. PMID:25999821

Chromatin accessibility prediction via convolutional long short-term memory networks with k-mer embedding.

PubMed

Min, Xu; Zeng, Wanwen; Chen, Ning; Chen, Ting; Jiang, Rui

2017-07-15

Experimental techniques for measuring chromatin accessibility are expensive and time consuming, appealing for the development of computational approaches to predict open chromatin regions from DNA sequences. Along this direction, existing methods fall into two classes: one based on handcrafted k -mer features and the other based on convolutional neural networks. Although both categories have shown good performance in specific applications thus far, there still lacks a comprehensive framework to integrate useful k -mer co-occurrence information with recent advances in deep learning. We fill this gap by addressing the problem of chromatin accessibility prediction with a convolutional Long Short-Term Memory (LSTM) network with k -mer embedding. We first split DNA sequences into k -mers and pre-train k -mer embedding vectors based on the co-occurrence matrix of k -mers by using an unsupervised representation learning approach. We then construct a supervised deep learning architecture comprised of an embedding layer, three convolutional layers and a Bidirectional LSTM (BLSTM) layer for feature learning and classification. We demonstrate that our method gains high-quality fixed-length features from variable-length sequences and consistently outperforms baseline methods. We show that k -mer embedding can effectively enhance model performance by exploring different embedding strategies. We also prove the efficacy of both the convolution and the BLSTM layers by comparing two variations of the network architecture. We confirm the robustness of our model to hyper-parameters by performing sensitivity analysis. We hope our method can eventually reinforce our understanding of employing deep learning in genomic studies and shed light on research regarding mechanisms of chromatin accessibility. The source code can be downloaded from https://github.com/minxueric/ismb2017_lstm . tingchen@tsinghua.edu.cn or ruijiang@tsinghua.edu.cn. Supplementary materials are available at Bioinformatics online. © The Author 2017. Published by Oxford University Press. All rights reserved. For Permissions, please e-mail: journals.permissions@oup.com

Chromatin accessibility prediction via convolutional long short-term memory networks with k-mer embedding

PubMed Central

Min, Xu; Zeng, Wanwen; Chen, Ning; Chen, Ting; Jiang, Rui

2017-01-01

Abstract Motivation: Experimental techniques for measuring chromatin accessibility are expensive and time consuming, appealing for the development of computational approaches to predict open chromatin regions from DNA sequences. Along this direction, existing methods fall into two classes: one based on handcrafted k-mer features and the other based on convolutional neural networks. Although both categories have shown good performance in specific applications thus far, there still lacks a comprehensive framework to integrate useful k-mer co-occurrence information with recent advances in deep learning. Results: We fill this gap by addressing the problem of chromatin accessibility prediction with a convolutional Long Short-Term Memory (LSTM) network with k-mer embedding. We first split DNA sequences into k-mers and pre-train k-mer embedding vectors based on the co-occurrence matrix of k-mers by using an unsupervised representation learning approach. We then construct a supervised deep learning architecture comprised of an embedding layer, three convolutional layers and a Bidirectional LSTM (BLSTM) layer for feature learning and classification. We demonstrate that our method gains high-quality fixed-length features from variable-length sequences and consistently outperforms baseline methods. We show that k-mer embedding can effectively enhance model performance by exploring different embedding strategies. We also prove the efficacy of both the convolution and the BLSTM layers by comparing two variations of the network architecture. We confirm the robustness of our model to hyper-parameters by performing sensitivity analysis. We hope our method can eventually reinforce our understanding of employing deep learning in genomic studies and shed light on research regarding mechanisms of chromatin accessibility. Availability and implementation: The source code can be downloaded from https://github.com/minxueric/ismb2017_lstm. Contact: tingchen@tsinghua.edu.cn or ruijiang@tsinghua.edu.cn Supplementary information: Supplementary materials are available at Bioinformatics online. PMID:28881969

Real-time classification of vehicles by type within infrared imagery

NASA Astrophysics Data System (ADS)

Kundegorski, Mikolaj E.; Akçay, Samet; Payen de La Garanderie, Grégoire; Breckon, Toby P.

2016-10-01

Real-time classification of vehicles into sub-category types poses a significant challenge within infra-red imagery due to the high levels of intra-class variation in thermal vehicle signatures caused by aspects of design, current operating duration and ambient thermal conditions. Despite these challenges, infra-red sensing offers significant generalized target object detection advantages in terms of all-weather operation and invariance to visual camouflage techniques. This work investigates the accuracy of a number of real-time object classification approaches for this task within the wider context of an existing initial object detection and tracking framework. Specifically we evaluate the use of traditional feature-driven bag of visual words and histogram of oriented gradient classification approaches against modern convolutional neural network architectures. Furthermore, we use classical photogrammetry, within the context of current target detection and classification techniques, as a means of approximating 3D target position within the scene based on this vehicle type classification. Based on photogrammetric estimation of target position, we then illustrate the use of regular Kalman filter based tracking operating on actual 3D vehicle trajectories. Results are presented using a conventional thermal-band infra-red (IR) sensor arrangement where targets are tracked over a range of evaluation scenarios.

A novel end-to-end classifier using domain transferred deep convolutional neural networks for biomedical images.

PubMed

Pang, Shuchao; Yu, Zhezhou; Orgun, Mehmet A

2017-03-01

Highly accurate classification of biomedical images is an essential task in the clinical diagnosis of numerous medical diseases identified from those images. Traditional image classification methods combined with hand-crafted image feature descriptors and various classifiers are not able to effectively improve the accuracy rate and meet the high requirements of classification of biomedical images. The same also holds true for artificial neural network models directly trained with limited biomedical images used as training data or directly used as a black box to extract the deep features based on another distant dataset. In this study, we propose a highly reliable and accurate end-to-end classifier for all kinds of biomedical images via deep learning and transfer learning. We first apply domain transferred deep convolutional neural network for building a deep model; and then develop an overall deep learning architecture based on the raw pixels of original biomedical images using supervised training. In our model, we do not need the manual design of the feature space, seek an effective feature vector classifier or segment specific detection object and image patches, which are the main technological difficulties in the adoption of traditional image classification methods. Moreover, we do not need to be concerned with whether there are large training sets of annotated biomedical images, affordable parallel computing resources featuring GPUs or long times to wait for training a perfect deep model, which are the main problems to train deep neural networks for biomedical image classification as observed in recent works. With the utilization of a simple data augmentation method and fast convergence speed, our algorithm can achieve the best accuracy rate and outstanding classification ability for biomedical images. We have evaluated our classifier on several well-known public biomedical datasets and compared it with several state-of-the-art approaches. We propose a robust automated end-to-end classifier for biomedical images based on a domain transferred deep convolutional neural network model that shows a highly reliable and accurate performance which has been confirmed on several public biomedical image datasets. Copyright © 2017 Elsevier Ireland Ltd. All rights reserved.

Transfer Learning with Convolutional Neural Networks for Classification of Abdominal Ultrasound Images.

PubMed

Cheng, Phillip M; Malhi, Harshawn S

2017-04-01

The purpose of this study is to evaluate transfer learning with deep convolutional neural networks for the classification of abdominal ultrasound images. Grayscale images from 185 consecutive clinical abdominal ultrasound studies were categorized into 11 categories based on the text annotation specified by the technologist for the image. Cropped images were rescaled to 256 × 256 resolution and randomized, with 4094 images from 136 studies constituting the training set, and 1423 images from 49 studies constituting the test set. The fully connected layers of two convolutional neural networks based on CaffeNet and VGGNet, previously trained on the 2012 Large Scale Visual Recognition Challenge data set, were retrained on the training set. Weights in the convolutional layers of each network were frozen to serve as fixed feature extractors. Accuracy on the test set was evaluated for each network. A radiologist experienced in abdominal ultrasound also independently classified the images in the test set into the same 11 categories. The CaffeNet network classified 77.3% of the test set images accurately (1100/1423 images), with a top-2 accuracy of 90.4% (1287/1423 images). The larger VGGNet network classified 77.9% of the test set accurately (1109/1423 images), with a top-2 accuracy of VGGNet was 89.7% (1276/1423 images). The radiologist classified 71.7% of the test set images correctly (1020/1423 images). The differences in classification accuracies between both neural networks and the radiologist were statistically significant (p < 0.001). The results demonstrate that transfer learning with convolutional neural networks may be used to construct effective classifiers for abdominal ultrasound images.

Improving deep convolutional neural networks with mixed maxout units

PubMed Central

Liu, Fu-xian; Li, Long-yue

2017-01-01

Motivated by insights from the maxout-units-based deep Convolutional Neural Network (CNN) that “non-maximal features are unable to deliver” and “feature mapping subspace pooling is insufficient,” we present a novel mixed variant of the recently introduced maxout unit called a mixout unit. Specifically, we do so by calculating the exponential probabilities of feature mappings gained by applying different convolutional transformations over the same input and then calculating the expected values according to their exponential probabilities. Moreover, we introduce the Bernoulli distribution to balance the maximum values with the expected values of the feature mappings subspace. Finally, we design a simple model to verify the pooling ability of mixout units and a Mixout-units-based Network-in-Network (NiN) model to analyze the feature learning ability of the mixout models. We argue that our proposed units improve the pooling ability and that mixout models can achieve better feature learning and classification performance. PMID:28727737

Detection of colorectal masses in CT colonography: application of deep residual networks for differentiating masses from normal colon anatomy

NASA Astrophysics Data System (ADS)

Näppi, Janne J.; Hironaka, Toru; Yoshida, Hiroyuki

2018-02-01

Even though the clinical consequences of a missed colorectal cancer far outweigh those of a missed polyp, there has been little work on computer-aided detection (CADe) for colorectal masses in CT colonography (CTC). One of the problems is that it is not clear how to manually design mathematical image-based features that could be used to differentiate effectively between masses and certain types of normal colon anatomy such as ileocecal valves (ICVs). Deep learning has demonstrated ability to automatically determine effective discriminating features in many image-based problems. Recently, residual networks (ResNets) were developed to address the practical problems of constructing deep network architectures for optimizing the performance of deep learning. In this pilot study, we compared the classification performance of a conventional 2D-convolutional ResNet (2D-ResNet) with that of a volumetric 3D-convolutional ResNet (3D-ResNet) in differentiating masses from normal colon anatomy in CTC. For the development and evaluation of the ResNets, 695 volumetric images of biopsy-proven colorectal masses, ICVs, haustral folds, and rectal tubes were sampled from 196 clinical CTC cases and divided randomly into independent training, validation, and test datasets. The training set was expanded by use of volumetric data augmentation. Our preliminary results on the 140 test samples indicate that it is feasible to train a deep volumetric 3D-ResNet for performing effective image-based discriminations in CTC. The 3D-ResNet slightly outperformed the 2D-ResNet in the discrimination of masses and normal colon anatomy, but the statistical difference between their very high classification accuracies was not significant. The highest classification accuracy was obtained by combining the mass-likelihood estimates of the 2D- and 3D-ResNets, which enabled correct classification of all of the masses.

DeepAnomaly: Combining Background Subtraction and Deep Learning for Detecting Obstacles and Anomalies in an Agricultural Field.

PubMed

Christiansen, Peter; Nielsen, Lars N; Steen, Kim A; Jørgensen, Rasmus N; Karstoft, Henrik

2016-11-11

Convolutional neural network (CNN)-based systems are increasingly used in autonomous vehicles for detecting obstacles. CNN-based object detection and per-pixel classification (semantic segmentation) algorithms are trained for detecting and classifying a predefined set of object types. These algorithms have difficulties in detecting distant and heavily occluded objects and are, by definition, not capable of detecting unknown object types or unusual scenarios. The visual characteristics of an agriculture field is homogeneous, and obstacles, like people, animals and other obstacles, occur rarely and are of distinct appearance compared to the field. This paper introduces DeepAnomaly, an algorithm combining deep learning and anomaly detection to exploit the homogenous characteristics of a field to perform anomaly detection. We demonstrate DeepAnomaly as a fast state-of-the-art detector for obstacles that are distant, heavily occluded and unknown. DeepAnomaly is compared to state-of-the-art obstacle detectors including "Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks" (RCNN). In a human detector test case, we demonstrate that DeepAnomaly detects humans at longer ranges (45-90 m) than RCNN. RCNN has a similar performance at a short range (0-30 m). However, DeepAnomaly has much fewer model parameters and (182 ms/25 ms =) a 7.28-times faster processing time per image. Unlike most CNN-based methods, the high accuracy, the low computation time and the low memory footprint make it suitable for a real-time system running on a embedded GPU (Graphics Processing Unit).

DeepAnomaly: Combining Background Subtraction and Deep Learning for Detecting Obstacles and Anomalies in an Agricultural Field

PubMed Central

Christiansen, Peter; Nielsen, Lars N.; Steen, Kim A.; Jørgensen, Rasmus N.; Karstoft, Henrik

2016-01-01

Convolutional neural network (CNN)-based systems are increasingly used in autonomous vehicles for detecting obstacles. CNN-based object detection and per-pixel classification (semantic segmentation) algorithms are trained for detecting and classifying a predefined set of object types. These algorithms have difficulties in detecting distant and heavily occluded objects and are, by definition, not capable of detecting unknown object types or unusual scenarios. The visual characteristics of an agriculture field is homogeneous, and obstacles, like people, animals and other obstacles, occur rarely and are of distinct appearance compared to the field. This paper introduces DeepAnomaly, an algorithm combining deep learning and anomaly detection to exploit the homogenous characteristics of a field to perform anomaly detection. We demonstrate DeepAnomaly as a fast state-of-the-art detector for obstacles that are distant, heavily occluded and unknown. DeepAnomaly is compared to state-of-the-art obstacle detectors including “Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks” (RCNN). In a human detector test case, we demonstrate that DeepAnomaly detects humans at longer ranges (45–90 m) than RCNN. RCNN has a similar performance at a short range (0–30 m). However, DeepAnomaly has much fewer model parameters and (182 ms/25 ms =) a 7.28-times faster processing time per image. Unlike most CNN-based methods, the high accuracy, the low computation time and the low memory footprint make it suitable for a real-time system running on a embedded GPU (Graphics Processing Unit). PMID:27845717

Shallow Transits—Deep Learning. I. Feasibility Study of Deep Learning to Detect Periodic Transits of Exoplanets

NASA Astrophysics Data System (ADS)

Zucker, Shay; Giryes, Raja

2018-04-01

Transits of habitable planets around solar-like stars are expected to be shallow, and to have long periods, which means low information content. The current bottleneck in the detection of such transits is caused in large part by the presence of red (correlated) noise in the light curves obtained from the dedicated space telescopes. Based on the groundbreaking results deep learning achieves in many signal and image processing applications, we propose to use deep neural networks to solve this problem. We present a feasibility study, in which we applied a convolutional neural network on a simulated training set. The training set comprised light curves received from a hypothetical high-cadence space-based telescope. We simulated the red noise by using Gaussian Processes with a wide variety of hyper-parameters. We then tested the network on a completely different test set simulated in the same way. Our study proves that very difficult cases can indeed be detected. Furthermore, we show how detection trends can be studied and detection biases quantified. We have also checked the robustness of the neural-network performance against practical artifacts such as outliers and discontinuities, which are known to affect space-based high-cadence light curves. Future work will allow us to use the neural networks to characterize the transit model and identify individual transits. This new approach will certainly be an indispensable tool for the detection of habitable planets in the future planet-detection space missions such as PLATO.

Detection and Localization of Robotic Tools in Robot-Assisted Surgery Videos Using Deep Neural Networks for Region Proposal and Detection.

PubMed

Sarikaya, Duygu; Corso, Jason J; Guru, Khurshid A

2017-07-01

Video understanding of robot-assisted surgery (RAS) videos is an active research area. Modeling the gestures and skill level of surgeons presents an interesting problem. The insights drawn may be applied in effective skill acquisition, objective skill assessment, real-time feedback, and human-robot collaborative surgeries. We propose a solution to the tool detection and localization open problem in RAS video understanding, using a strictly computer vision approach and the recent advances of deep learning. We propose an architecture using multimodal convolutional neural networks for fast detection and localization of tools in RAS videos. To the best of our knowledge, this approach will be the first to incorporate deep neural networks for tool detection and localization in RAS videos. Our architecture applies a region proposal network (RPN) and a multimodal two stream convolutional network for object detection to jointly predict objectness and localization on a fusion of image and temporal motion cues. Our results with an average precision of 91% and a mean computation time of 0.1 s per test frame detection indicate that our study is superior to conventionally used methods for medical imaging while also emphasizing the benefits of using RPN for precision and efficiency. We also introduce a new data set, ATLAS Dione, for RAS video understanding. Our data set provides video data of ten surgeons from Roswell Park Cancer Institute, Buffalo, NY, USA, performing six different surgical tasks on the daVinci Surgical System (dVSS) with annotations of robotic tools per frame.

DCMDN: Deep Convolutional Mixture Density Network

NASA Astrophysics Data System (ADS)

D'Isanto, Antonio; Polsterer, Kai Lars

2017-09-01

Deep Convolutional Mixture Density Network (DCMDN) estimates probabilistic photometric redshift directly from multi-band imaging data by combining a version of a deep convolutional network with a mixture density network. The estimates are expressed as Gaussian mixture models representing the probability density functions (PDFs) in the redshift space. In addition to the traditional scores, the continuous ranked probability score (CRPS) and the probability integral transform (PIT) are applied as performance criteria. DCMDN is able to predict redshift PDFs independently from the type of source, e.g. galaxies, quasars or stars and renders pre-classification of objects and feature extraction unnecessary; the method is extremely general and allows the solving of any kind of probabilistic regression problems based on imaging data, such as estimating metallicity or star formation rate in galaxies.

The trellis complexity of convolutional codes

NASA Technical Reports Server (NTRS)

Mceliece, R. J.; Lin, W.

1995-01-01

It has long been known that convolutional codes have a natural, regular trellis structure that facilitates the implementation of Viterbi's algorithm. It has gradually become apparent that linear block codes also have a natural, though not in general a regular, 'minimal' trellis structure, which allows them to be decoded with a Viterbi-like algorithm. In both cases, the complexity of the Viterbi decoding algorithm can be accurately estimated by the number of trellis edges per encoded bit. It would, therefore, appear that we are in a good position to make a fair comparison of the Viterbi decoding complexity of block and convolutional codes. Unfortunately, however, this comparison is somewhat muddled by the fact that some convolutional codes, the punctured convolutional codes, are known to have trellis representations that are significantly less complex than the conventional trellis. In other words, the conventional trellis representation for a convolutional code may not be the minimal trellis representation. Thus, ironically, at present we seem to know more about the minimal trellis representation for block than for convolutional codes. In this article, we provide a remedy, by developing a theory of minimal trellises for convolutional codes. (A similar theory has recently been given by Sidorenko and Zyablov). This allows us to make a direct performance-complexity comparison for block and convolutional codes. A by-product of our work is an algorithm for choosing, from among all generator matrices for a given convolutional code, what we call a trellis-minimal generator matrix, from which the minimal trellis for the code can be directly constructed. Another by-product is that, in the new theory, punctured convolutional codes no longer appear as a special class, but simply as high-rate convolutional codes whose trellis complexity is unexpectedly small.

Feature recognition and detection for ancient architecture based on machine vision

NASA Astrophysics Data System (ADS)

Zou, Zheng; Wang, Niannian; Zhao, Peng; Zhao, Xuefeng

2018-03-01

Ancient architecture has a very high historical and artistic value. The ancient buildings have a wide variety of textures and decorative paintings, which contain a lot of historical meaning. Therefore, the research and statistics work of these different compositional and decorative features play an important role in the subsequent research. However, until recently, the statistics of those components are mainly by artificial method, which consumes a lot of labor and time, inefficiently. At present, as the strong support of big data and GPU accelerated training, machine vision with deep learning as the core has been rapidly developed and widely used in many fields. This paper proposes an idea to recognize and detect the textures, decorations and other features of ancient building based on machine vision. First, classify a large number of surface textures images of ancient building components manually as a set of samples. Then, using the convolution neural network to train the samples in order to get a classification detector. Finally verify its precision.

FPGA based hardware optimized implementation of signal processing system for LFM pulsed radar

NASA Astrophysics Data System (ADS)

Azim, Noor ul; Jun, Wang

2016-11-01

Signal processing is one of the main parts of any radar system. Different signal processing algorithms are used to extract information about different parameters like range, speed, direction etc, of a target in the field of radar communication. This paper presents LFM (Linear Frequency Modulation) pulsed radar signal processing algorithms which are used to improve target detection, range resolution and to estimate the speed of a target. Firstly, these algorithms are simulated in MATLAB to verify the concept and theory. After the conceptual verification in MATLAB, the simulation is converted into implementation on hardware using Xilinx FPGA. Chosen FPGA is Xilinx Virtex-6 (XC6LVX75T). For hardware implementation pipeline optimization is adopted and also other factors are considered for resources optimization in the process of implementation. Focusing algorithms in this work for improving target detection, range resolution and speed estimation are hardware optimized fast convolution processing based pulse compression and pulse Doppler processing.

Performance of MIMO-OFDM using convolution codes with QAM modulation

NASA Astrophysics Data System (ADS)

Astawa, I. Gede Puja; Moegiharto, Yoedy; Zainudin, Ahmad; Salim, Imam Dui Agus; Anggraeni, Nur Annisa

2014-04-01

Performance of Orthogonal Frequency Division Multiplexing (OFDM) system can be improved by adding channel coding (error correction code) to detect and correct errors that occur during data transmission. One can use the convolution code. This paper present performance of OFDM using Space Time Block Codes (STBC) diversity technique use QAM modulation with code rate ½. The evaluation is done by analyzing the value of Bit Error Rate (BER) vs Energy per Bit to Noise Power Spectral Density Ratio (Eb/No). This scheme is conducted 256 subcarrier which transmits Rayleigh multipath fading channel in OFDM system. To achieve a BER of 10-3 is required 10dB SNR in SISO-OFDM scheme. For 2×2 MIMO-OFDM scheme requires 10 dB to achieve a BER of 10-3. For 4×4 MIMO-OFDM scheme requires 5 dB while adding convolution in a 4x4 MIMO-OFDM can improve performance up to 0 dB to achieve the same BER. This proves the existence of saving power by 3 dB of 4×4 MIMO-OFDM system without coding, power saving 7 dB of 2×2 MIMO-OFDM and significant power savings from SISO-OFDM system.

Characterizing Surfaces of the Wide Bandgap Semiconductor Ilmenite with Scanning Probe Microcopies

NASA Technical Reports Server (NTRS)

Wilkins, R.; Powell, Kirk St. A.

1997-01-01

Ilmenite (FeTiO3) is a wide bandgap semiconductor with an energy gap of about 2.5eV. Initial radiation studies indicate that ilmenite has properties suited for radiation tolerant applications, as well as a variety of other electronic applications. Two scanning probe microscopy methods have been used to characterize the surface of samples taken from Czochralski grown single crystals. The two methods, atomic force microscopy (AFM) and scanning tunneling microscopy (STM), are based on different physical principles and therefore provide different information about the samples. AFM provides a direct, three-dimensional image of the surface of the samples, while STM give a convolution of topographic and electronic properties of the surface. We will discuss the differences between the methods and present preliminary data of each method for ilmenite samples.

A Robust Gold Deconvolution Approach for LiDAR Waveform Data Processing to Characterize Vegetation Structure

NASA Astrophysics Data System (ADS)

Zhou, T.; Popescu, S. C.; Krause, K.; Sheridan, R.; Ku, N. W.

2014-12-01

Increasing attention has been paid in the remote sensing community to the next generation Light Detection and Ranging (lidar) waveform data systems for extracting information on topography and the vertical structure of vegetation. However, processing waveform lidar data raises some challenges compared to analyzing discrete return data. The overall goal of this study was to present a robust de-convolution algorithm- Gold algorithm used to de-convolve waveforms in a lidar dataset acquired within a 60 x 60m study area located in the Harvard Forest in Massachusetts. The waveform lidar data was collected by the National Ecological Observatory Network (NEON). Specific objectives were to: (1) explore advantages and limitations of various waveform processing techniques to derive topography and canopy height information; (2) develop and implement a novel de-convolution algorithm, the Gold algorithm, to extract elevation and canopy metrics; and (3) compare results and assess accuracy. We modeled lidar waveforms with a mixture of Gaussian functions using the Non-least squares (NLS) algorithm implemented in R and derived a Digital Terrain Model (DTM) and canopy height. We compared our waveform-derived topography and canopy height measurements using the Gold de-convolution algorithm to results using the Richardson-Lucy algorithm. Our findings show that the Gold algorithm performed better than the Richardson-Lucy algorithm in terms of recovering the hidden echoes and detecting false echoes for generating a DTM, which indicates that the Gold algorithm could potentially be applied to processing of waveform lidar data to derive information on terrain elevation and canopy characteristics.

Fabric defect detection based on visual saliency using deep feature and low-rank recovery

NASA Astrophysics Data System (ADS)

Liu, Zhoufeng; Wang, Baorui; Li, Chunlei; Li, Bicao; Dong, Yan

2018-04-01

Fabric defect detection plays an important role in improving the quality of fabric product. In this paper, a novel fabric defect detection method based on visual saliency using deep feature and low-rank recovery was proposed. First, unsupervised training is carried out by the initial network parameters based on MNIST large datasets. The supervised fine-tuning of fabric image library based on Convolutional Neural Networks (CNNs) is implemented, and then more accurate deep neural network model is generated. Second, the fabric images are uniformly divided into the image block with the same size, then we extract their multi-layer deep features using the trained deep network. Thereafter, all the extracted features are concentrated into a feature matrix. Third, low-rank matrix recovery is adopted to divide the feature matrix into the low-rank matrix which indicates the background and the sparse matrix which indicates the salient defect. In the end, the iterative optimal threshold segmentation algorithm is utilized to segment the saliency maps generated by the sparse matrix to locate the fabric defect area. Experimental results demonstrate that the feature extracted by CNN is more suitable for characterizing the fabric texture than the traditional LBP, HOG and other hand-crafted features extraction method, and the proposed method can accurately detect the defect regions of various fabric defects, even for the image with complex texture.

Bruxism force detection by a piezoelectric film-based recording device in sleeping humans.

PubMed

Baba, Kazuyoshi; Clark, Glenn T; Watanabe, Tatsutomi; Ohyama, Takashi

2003-01-01

To test the reliability and utility of a force-based bruxism detection system (Intra-Splint Force Detector [ISFD]) for multiple night recordings of forceful tooth-to-splint contacts in sleeping human subjects in their home environment. Bruxism-type forces, i.e., forceful tooth-to-splint contacts, during the night were recorded with this system in 12 subjects (6 bruxers and 6 controls) for 5 nights in their home environment; a laboratory-based nocturnal polysomnogram (NPSG) study was also performed on 1 of these subjects. All 12 subjects were able to use the device without substantial difficulty on a nightly basis. The bruxer group exhibited bruxism events of significantly longer duration than the control group (27 seconds/hour versus 7.4 seconds/hour, P < .01). A NPSG study performed on 1 subject revealed that, when the masseter muscle electromyogram (EMG) was used as a "gold standard," the ISFD had a sensitivity of 0.89. The correlation coefficient between the duration of events detected by the ISFD and the EMG was also 0.89. These results suggest that the ISFD is a system that can be used easily by the subjects and that has a reasonable reliability for bruxism detection as reflected in forceful tooth-to-splint contacts during sleep.

Improving energy efficiency in handheld biometric applications

NASA Astrophysics Data System (ADS)

Hoyle, David C.; Gale, John W.; Schultz, Robert C.; Rakvic, Ryan N.; Ives, Robert W.

2012-06-01

With improved smartphone and tablet technology, it is becoming increasingly feasible to implement powerful biometric recognition algorithms on portable devices. Typical iris recognition algorithms, such as Ridge Energy Direction (RED), utilize two-dimensional convolution in their implementation. This paper explores the energy consumption implications of 12 different methods of implementing two-dimensional convolution on a portable device. Typically, convolution is implemented using floating point operations. If a given algorithm implemented integer convolution vice floating point convolution, it could drastically reduce the energy consumed by the processor. The 12 methods compared include 4 major categories: Integer C, Integer Java, Floating Point C, and Floating Point Java. Each major category is further divided into 3 implementations: variable size looped convolution, static size looped convolution, and unrolled looped convolution. All testing was performed using the HTC Thunderbolt with energy measured directly using a Tektronix TDS5104B Digital Phosphor oscilloscope. Results indicate that energy savings as high as 75% are possible by using Integer C versus Floating Point C. Considering the relative proportion of processing time that convolution is responsible for in a typical algorithm, the savings in energy would likely result in significantly greater time between battery charges.

Learning Oriented Region-based Convolutional Neural Networks for Building Detection in Satellite Remote Sensing Images

NASA Astrophysics Data System (ADS)

Chen, C.; Gong, W.; Hu, Y.; Chen, Y.; Ding, Y.

2017-05-01

The automated building detection in aerial images is a fundamental problem encountered in aerial and satellite images analysis. Recently, thanks to the advances in feature descriptions, Region-based CNN model (R-CNN) for object detection is receiving an increasing attention. Despite the excellent performance in object detection, it is problematic to directly leverage the features of R-CNN model for building detection in single aerial image. As we know, the single aerial image is in vertical view and the buildings possess significant directional feature. However, in R-CNN model, direction of the building is ignored and the detection results are represented by horizontal rectangles. For this reason, the detection results with horizontal rectangle cannot describe the building precisely. To address this problem, in this paper, we proposed a novel model with a key feature related to orientation, namely, Oriented R-CNN (OR-CNN). Our contributions are mainly in the following two aspects: 1) Introducing a new oriented layer network for detecting the rotation angle of building on the basis of the successful VGG-net R-CNN model; 2) the oriented rectangle is proposed to leverage the powerful R-CNN for remote-sensing building detection. In experiments, we establish a complete and bran-new data set for training our oriented R-CNN model and comprehensively evaluate the proposed method on a publicly available building detection data set. We demonstrate State-of-the-art results compared with the previous baseline methods.

Research on image retrieval using deep convolutional neural network combining L1 regularization and PRelu activation function

NASA Astrophysics Data System (ADS)

QingJie, Wei; WenBin, Wang

2017-06-01

In this paper, the image retrieval using deep convolutional neural network combined with regularization and PRelu activation function is studied, and improves image retrieval accuracy. Deep convolutional neural network can not only simulate the process of human brain to receive and transmit information, but also contains a convolution operation, which is very suitable for processing images. Using deep convolutional neural network is better than direct extraction of image visual features for image retrieval. However, the structure of deep convolutional neural network is complex, and it is easy to over-fitting and reduces the accuracy of image retrieval. In this paper, we combine L1 regularization and PRelu activation function to construct a deep convolutional neural network to prevent over-fitting of the network and improve the accuracy of image retrieval

Deep learning of contrast-coated serrated polyps for computer-aided detection in CT colonography

NASA Astrophysics Data System (ADS)

Näppi, Janne J.; Pickhardt, Perry; Kim, David H.; Hironaka, Toru; Yoshida, Hiroyuki

2017-03-01

Serrated polyps were previously believed to be benign lesions with no cancer potential. However, recent studies have revealed a novel molecular pathway where also serrated polyps can develop into colorectal cancer. CT colonography (CTC) can detect serrated polyps using the radiomic biomarker of contrast coating, but this requires expertise from the reader and current computer-aided detection (CADe) systems have not been designed to detect the contrast coating. The purpose of this study was to develop a novel CADe method that makes use of deep learning to detect serrated polyps based on their contrast-coating biomarker in CTC. In the method, volumetric shape-based features are used to detect polyp sites over soft-tissue and fecal-tagging surfaces of the colon. The detected sites are imaged using multi-angular 2D image patches. A deep convolutional neural network (DCNN) is used to review the image patches for the presence of polyps. The DCNN-based polyp-likelihood estimates are merged into an aggregate likelihood index where highest values indicate the presence of a polyp. For pilot evaluation, the proposed DCNN-CADe method was evaluated with a 10-fold cross-validation scheme using 101 colonoscopy-confirmed cases with 144 biopsy-confirmed serrated polyps from a CTC screening program, where the patients had been prepared for CTC with saline laxative and fecal tagging by barium and iodine-based diatrizoate. The average per-polyp sensitivity for serrated polyps >=6 mm in size was 93+/-7% at 0:8+/-1:8 false positives per patient on average. The detection accuracy was substantially higher that of a conventional CADe system. Our results indicate that serrated polyps can be detected automatically at high accuracy in CTC.

Sparse image reconstruction for molecular imaging.

PubMed

Ting, Michael; Raich, Raviv; Hero, Alfred O

2009-06-01

The application that motivates this paper is molecular imaging at the atomic level. When discretized at subatomic distances, the volume is inherently sparse. Noiseless measurements from an imaging technology can be modeled by convolution of the image with the system point spread function (psf). Such is the case with magnetic resonance force microscopy (MRFM), an emerging technology where imaging of an individual tobacco mosaic virus was recently demonstrated with nanometer resolution. We also consider additive white Gaussian noise (AWGN) in the measurements. Many prior works of sparse estimators have focused on the case when H has low coherence; however, the system matrix H in our application is the convolution matrix for the system psf. A typical convolution matrix has high coherence. This paper, therefore, does not assume a low coherence H. A discrete-continuous form of the Laplacian and atom at zero (LAZE) p.d.f. used by Johnstone and Silverman is formulated, and two sparse estimators derived by maximizing the joint p.d.f. of the observation and image conditioned on the hyperparameters. A thresholding rule that generalizes the hard and soft thresholding rule appears in the course of the derivation. This so-called hybrid thresholding rule, when used in the iterative thresholding framework, gives rise to the hybrid estimator, a generalization of the lasso. Estimates of the hyperparameters for the lasso and hybrid estimator are obtained via Stein's unbiased risk estimate (SURE). A numerical study with a Gaussian psf and two sparse images shows that the hybrid estimator outperforms the lasso.

Establishing Malware Attribution and Binary Provenance Using Multicompilation Techniques

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

Ramshaw, M. J.

2017-07-28

Malware is a serious problem for computer systems and costs businesses and customers billions of dollars a year in addition to compromising their private information. Detecting malware is particularly difficult because malware source code can be compiled in many different ways and generate many different digital signatures, which causes problems for most anti-malware programs that rely on static signature detection. Our project uses a convolutional neural network to identify malware programs but these require large amounts of data to be effective. Towards that end, we gather thousands of source code files from publicly available programming contest sites and compile themmore » with several different compilers and flags. Building upon current research, we then transform these binary files into image representations and use them to train a long-term recurrent convolutional neural network that will eventually be used to identify how a malware binary was compiled. This information will include the compiler, version of the compiler and the options used in compilation, information which can be critical in determining where a malware program came from and even who authored it.« less

Deep convolutional neural network for classifying Fusarium wilt of radish from unmanned aerial vehicles

NASA Astrophysics Data System (ADS)

Ha, Jin Gwan; Moon, Hyeonjoon; Kwak, Jin Tae; Hassan, Syed Ibrahim; Dang, Minh; Lee, O. New; Park, Han Yong

2017-10-01

Recently, unmanned aerial vehicles (UAVs) have gained much attention. In particular, there is a growing interest in utilizing UAVs for agricultural applications such as crop monitoring and management. We propose a computerized system that is capable of detecting Fusarium wilt of radish with high accuracy. The system adopts computer vision and machine learning techniques, including deep learning, to process the images captured by UAVs at low altitudes and to identify the infected radish. The whole radish field is first segmented into three distinctive regions (radish, bare ground, and mulching film) via a softmax classifier and K-means clustering. Then, the identified radish regions are further classified into healthy radish and Fusarium wilt of radish using a deep convolutional neural network (CNN). In identifying radish, bare ground, and mulching film from a radish field, we achieved an accuracy of ≥97.4%. In detecting Fusarium wilt of radish, the CNN obtained an accuracy of 93.3%. It also outperformed the standard machine learning algorithm, obtaining 82.9% accuracy. Therefore, UAVs equipped with computational techniques are promising tools for improving the quality and efficiency of agriculture today.

Convolution-based estimation of organ dose in tube current modulated CT

NASA Astrophysics Data System (ADS)

Tian, Xiaoyu; Segars, W. Paul; Dixon, Robert L.; Samei, Ehsan

2016-05-01

Estimating organ dose for clinical patients requires accurate modeling of the patient anatomy and the dose field of the CT exam. The modeling of patient anatomy can be achieved using a library of representative computational phantoms (Samei et al 2014 Pediatr. Radiol. 44 460-7). The modeling of the dose field can be challenging for CT exams performed with a tube current modulation (TCM) technique. The purpose of this work was to effectively model the dose field for TCM exams using a convolution-based method. A framework was further proposed for prospective and retrospective organ dose estimation in clinical practice. The study included 60 adult patients (age range: 18-70 years, weight range: 60-180 kg). Patient-specific computational phantoms were generated based on patient CT image datasets. A previously validated Monte Carlo simulation program was used to model a clinical CT scanner (SOMATOM Definition Flash, Siemens Healthcare, Forchheim, Germany). A practical strategy was developed to achieve real-time organ dose estimation for a given clinical patient. CTDIvol-normalized organ dose coefficients ({{h}\\text{Organ}} ) under constant tube current were estimated and modeled as a function of patient size. Each clinical patient in the library was optimally matched to another computational phantom to obtain a representation of organ location/distribution. The patient organ distribution was convolved with a dose distribution profile to generate {{≤ft(\\text{CTD}{{\\text{I}}\\text{vol}}\\right)}\\text{organ, \\text{convolution}}} values that quantified the regional dose field for each organ. The organ dose was estimated by multiplying {{≤ft(\\text{CTD}{{\\text{I}}\\text{vol}}\\right)}\\text{organ, \\text{convolution}}} with the organ dose coefficients ({{h}\\text{Organ}} ). To validate the accuracy of this dose estimation technique, the organ dose of the original clinical patient was estimated using Monte Carlo program with TCM profiles explicitly modeled. The discrepancy between the estimated organ dose and dose simulated using TCM Monte Carlo program was quantified. We further compared the convolution-based organ dose estimation method with two other strategies with different approaches of quantifying the irradiation field. The proposed convolution-based estimation method showed good accuracy with the organ dose simulated using the TCM Monte Carlo simulation. The average percentage error (normalized by CTDIvol) was generally within 10% across all organs and modulation profiles, except for organs located in the pelvic and shoulder regions. This study developed an improved method that accurately quantifies the irradiation field under TCM scans. The results suggested that organ dose could be estimated in real-time both prospectively (with the localizer information only) and retrospectively (with acquired CT data).

Artificial intelligence in diagnosis of obstructive lung disease: current status and future potential.

PubMed

Das, Nilakash; Topalovic, Marko; Janssens, Wim

2018-03-01

The application of artificial intelligence in the diagnosis of obstructive lung diseases is an exciting phenomenon. Artificial intelligence algorithms work by finding patterns in data obtained from diagnostic tests, which can be used to predict clinical outcomes or to detect obstructive phenotypes. The purpose of this review is to describe the latest trends and to discuss the future potential of artificial intelligence in the diagnosis of obstructive lung diseases. Machine learning has been successfully used in automated interpretation of pulmonary function tests for differential diagnosis of obstructive lung diseases. Deep learning models such as convolutional neural network are state-of-the art for obstructive pattern recognition in computed tomography. Machine learning has also been applied in other diagnostic approaches such as forced oscillation test, breath analysis, lung sound analysis and telemedicine with promising results in small-scale studies. Overall, the application of artificial intelligence has produced encouraging results in the diagnosis of obstructive lung diseases. However, large-scale studies are still required to validate current findings and to boost its adoption by the medical community.

Deep multi-scale convolutional neural network for hyperspectral image classification

NASA Astrophysics Data System (ADS)

Zhang, Feng-zhe; Yang, Xia

2018-04-01

In this paper, we proposed a multi-scale convolutional neural network for hyperspectral image classification task. Firstly, compared with conventional convolution, we utilize multi-scale convolutions, which possess larger respective fields, to extract spectral features of hyperspectral image. We design a deep neural network with a multi-scale convolution layer which contains 3 different convolution kernel sizes. Secondly, to avoid overfitting of deep neural network, dropout is utilized, which randomly sleeps neurons, contributing to improve the classification accuracy a bit. In addition, new skills like ReLU in deep learning is utilized in this paper. We conduct experiments on University of Pavia and Salinas datasets, and obtained better classification accuracy compared with other methods.

A street rubbish detection algorithm based on Sift and RCNN

NASA Astrophysics Data System (ADS)

Yu, XiPeng; Chen, Zhong; Zhang, Shuo; Zhang, Ting

2018-02-01

This paper presents a street rubbish detection algorithm based on image registration with Sift feature and RCNN. Firstly, obtain the rubbish region proposal on the real-time street image and set up the CNN convolution neural network trained by the rubbish samples set consists of rubbish and non-rubbish images; Secondly, for every clean street image, obtain the Sift feature and do image registration with the real-time street image to obtain the differential image, the differential image filters a lot of background information, obtain the rubbish region proposal rect where the rubbish may appear on the differential image by the selective search algorithm. Then, the CNN model is used to detect the image pixel data in each of the region proposal on the real-time street image. According to the output vector of the CNN, it is judged whether the rubbish is in the region proposal or not. If it is rubbish, the region proposal on the real-time street image is marked. This algorithm avoids the large number of false detection caused by the detection on the whole image because the CNN is used to identify the image only in the region proposal on the real-time street image that may appear rubbish. Different from the traditional object detection algorithm based on the region proposal, the region proposal is obtained on the differential image not whole real-time street image, and the number of the invalid region proposal is greatly reduced. The algorithm has the high mean average precision (mAP).

The convolutional differentiator method for numerical modelling of acoustic and elastic wavefields

NASA Astrophysics Data System (ADS)

Zhang, Zhong-Jie; Teng, Ji-Wen; Yang, Ding-Hui

1996-02-01

Based on the techniques of forward and inverse Fourier transformation, the authors discussed the design scheme of ordinary differentiator used and applied in the simulation of acoustic and elastic wavefields in isotropic media respectively. To compress Gibbs effects by truncation effectively, Hanning window is introduced in. The model computation shows that, the convolutional differentiator method has the advantages of rapidity, low requirements of computer’s inner storage and high precision, which is a potential method of numerical simulation.

Deep convolutional neural networks for estimating porous material parameters with ultrasound tomography

NASA Astrophysics Data System (ADS)

Lähivaara, Timo; Kärkkäinen, Leo; Huttunen, Janne M. J.; Hesthaven, Jan S.

2018-02-01

We study the feasibility of data based machine learning applied to ultrasound tomography to estimate water-saturated porous material parameters. In this work, the data to train the neural networks is simulated by solving wave propagation in coupled poroviscoelastic-viscoelastic-acoustic media. As the forward model, we consider a high-order discontinuous Galerkin method while deep convolutional neural networks are used to solve the parameter estimation problem. In the numerical experiment, we estimate the material porosity and tortuosity while the remaining parameters which are of less interest are successfully marginalized in the neural networks-based inversion. Computational examples confirms the feasibility and accuracy of this approach.

Emotional textile image classification based on cross-domain convolutional sparse autoencoders with feature selection

NASA Astrophysics Data System (ADS)

Li, Zuhe; Fan, Yangyu; Liu, Weihua; Yu, Zeqi; Wang, Fengqin

2017-01-01

We aim to apply sparse autoencoder-based unsupervised feature learning to emotional semantic analysis for textile images. To tackle the problem of limited training data, we present a cross-domain feature learning scheme for emotional textile image classification using convolutional autoencoders. We further propose a correlation-analysis-based feature selection method for the weights learned by sparse autoencoders to reduce the number of features extracted from large size images. First, we randomly collect image patches on an unlabeled image dataset in the source domain and learn local features with a sparse autoencoder. We then conduct feature selection according to the correlation between different weight vectors corresponding to the autoencoder's hidden units. We finally adopt a convolutional neural network including a pooling layer to obtain global feature activations of textile images in the target domain and send these global feature vectors into logistic regression models for emotional image classification. The cross-domain unsupervised feature learning method achieves 65% to 78% average accuracy in the cross-validation experiments corresponding to eight emotional categories and performs better than conventional methods. Feature selection can reduce the computational cost of global feature extraction by about 50% while improving classification performance.

Deep convolutional neural network processing of aerial stereo imagery to monitor vulnerable zones near power lines

NASA Astrophysics Data System (ADS)

Qayyum, Abdul; Saad, Naufal M.; Kamel, Nidal; Malik, Aamir Saeed

2018-01-01

The monitoring of vegetation near high-voltage transmission power lines and poles is tedious. Blackouts present a huge challenge to power distribution companies and often occur due to tree growth in hilly and rural areas. There are numerous methods of monitoring hazardous overgrowth that are expensive and time-consuming. Accurate estimation of tree and vegetation heights near power poles can prevent the disruption of power transmission in vulnerable zones. This paper presents a cost-effective approach based on a convolutional neural network (CNN) algorithm to compute the height (depth maps) of objects proximal to power poles and transmission lines. The proposed CNN extracts and classifies features by employing convolutional pooling inputs to fully connected data layers that capture prominent features from stereo image patches. Unmanned aerial vehicle or satellite stereo image datasets can thus provide a feasible and cost-effective approach that identifies threat levels based on height and distance estimations of hazardous vegetation and other objects. Results were compared with extant disparity map estimation techniques, such as graph cut, dynamic programming, belief propagation, and area-based methods. The proposed method achieved an accuracy rate of 90%.

Heart rate detection from an electronic weighing scale.

PubMed

González-Landaeta, R; Casas, O; Pallàs-Areny, R

2008-08-01

We propose a novel technique for beat-to-beat heart rate detection based on the ballistocardiographic (BCG) force signal from a subject standing on a common electronic weighing scale. The detection relies on sensing force variations related to the blood acceleration in the aorta, works even if wearing footwear and does not require any sensors attached to the body because it uses the load cells in the scale. We have devised an approach to estimate the sensitivity and frequency response of three commercial weighing scales to assess their capability to detect the BCG force signal. Static sensitivities ranged from 490 nV V(-1) N(-1) to 1670 nV V(-1) N(-1). The frequency response depended on the subject's mass but it was broad enough for heart rate estimation. We have designed an electronic pulse detection system based on off-the-shelf integrated circuits to sense heart-beat-related force variations of about 0.24 N. The signal-to-noise ratio of the main peaks of the force signal detected was higher than 30 dB. A Bland-Altman plot was used to compare the RR time intervals estimated from the ECG and BCG force signals for 17 volunteers. The error was +/-21 ms, which makes the proposed technique suitable for short-term monitoring of the heart rate.

Manufacture and quality control of interconnecting wire hardnesses, Volume 1

NASA Technical Reports Server (NTRS)

1972-01-01

A standard is presented for manufacture, installation, and quality control of eight types of interconnecting wire harnesses. The processes, process controls, and inspection and test requirements reflected are based on acknowledgment of harness design requirements, acknowledgment of harness installation requirements, identification of the various parts, materials, etc., utilized in harness manufacture, and formulation of a typical manufacturing flow diagram for identification of each manufacturing and quality control process, operation, inspection, and test. The document covers interconnecting wire harnesses defined in the design standard, including type 1, enclosed in fluorocarbon elastomer convolute, tubing; type 2, enclosed in TFE convolute tubing lines with fiberglass braid; type 3, enclosed in TFE convolute tubing; and type 5, combination of types 3 and 4. Knowledge gained through experience on the Saturn 5 program coupled with recent advances in techniques, materials, and processes was incorporated.

Demonstration of human kidney differentiation antigens with monoclonal antibodies.

PubMed

Candelier, J J; Couillin, P; Bellon, G; Le Pendu, J; Eydoux, P; Boue, A

1988-10-01

Six human differentiation antigens (EE24.6, EG9.11, EG14.1, EI16.1, EK8.1, EK17.1) have been defined using monoclonal antibodies obtained from mice immunized with embryonic kidney cells. Their histologic distribution was determined on frozen sections of embryonic, fetal, and adult human kidneys by immunofluorescence assay. EE24.6, an ureteral bud marker, was detected only on the germ layer of mature kidney urothelium. EG9.11 and EG14.1 were detected on the S-shaped bodies and also on the adult proximal convoluted tubule for the former and the glomerular basement membrane for the latter. EI16.1, a marker of condensed mesenchyme, was detected only on epithelial cells of adult proximal convoluted tubule. EK8.1 was found in the mesangium, connective tissue, and with particularly dense labeling in the basement membranes. This labeling pattern was present throughout renal organogenesis. EK17.1 recognized both cell and plasma human fibronectins. Staining for all antibodies was nearly identical in mesonephros and metanephros. These results demonstate that some antigens follow their embryonic destiny. They indicate an antigenic similarity between the mesonephros and the metanephros and, therefore, a very early appearance of these antigens. During differentiation, these antigens concentrate on more defined structures, and staining became increased with an increased degree of differentiation.

Towards automatic pulmonary nodule management in lung cancer screening with deep learning

NASA Astrophysics Data System (ADS)

Ciompi, Francesco; Chung, Kaman; van Riel, Sarah J.; Setio, Arnaud Arindra Adiyoso; Gerke, Paul K.; Jacobs, Colin; Th. Scholten, Ernst; Schaefer-Prokop, Cornelia; Wille, Mathilde M. W.; Marchianò, Alfonso; Pastorino, Ugo; Prokop, Mathias; van Ginneken, Bram

2017-04-01

The introduction of lung cancer screening programs will produce an unprecedented amount of chest CT scans in the near future, which radiologists will have to read in order to decide on a patient follow-up strategy. According to the current guidelines, the workup of screen-detected nodules strongly relies on nodule size and nodule type. In this paper, we present a deep learning system based on multi-stream multi-scale convolutional networks, which automatically classifies all nodule types relevant for nodule workup. The system processes raw CT data containing a nodule without the need for any additional information such as nodule segmentation or nodule size and learns a representation of 3D data by analyzing an arbitrary number of 2D views of a given nodule. The deep learning system was trained with data from the Italian MILD screening trial and validated on an independent set of data from the Danish DLCST screening trial. We analyze the advantage of processing nodules at multiple scales with a multi-stream convolutional network architecture, and we show that the proposed deep learning system achieves performance at classifying nodule type that surpasses the one of classical machine learning approaches and is within the inter-observer variability among four experienced human observers.

Towards automatic pulmonary nodule management in lung cancer screening with deep learning.

PubMed

Ciompi, Francesco; Chung, Kaman; van Riel, Sarah J; Setio, Arnaud Arindra Adiyoso; Gerke, Paul K; Jacobs, Colin; Scholten, Ernst Th; Schaefer-Prokop, Cornelia; Wille, Mathilde M W; Marchianò, Alfonso; Pastorino, Ugo; Prokop, Mathias; van Ginneken, Bram

2017-04-19

The introduction of lung cancer screening programs will produce an unprecedented amount of chest CT scans in the near future, which radiologists will have to read in order to decide on a patient follow-up strategy. According to the current guidelines, the workup of screen-detected nodules strongly relies on nodule size and nodule type. In this paper, we present a deep learning system based on multi-stream multi-scale convolutional networks, which automatically classifies all nodule types relevant for nodule workup. The system processes raw CT data containing a nodule without the need for any additional information such as nodule segmentation or nodule size and learns a representation of 3D data by analyzing an arbitrary number of 2D views of a given nodule. The deep learning system was trained with data from the Italian MILD screening trial and validated on an independent set of data from the Danish DLCST screening trial. We analyze the advantage of processing nodules at multiple scales with a multi-stream convolutional network architecture, and we show that the proposed deep learning system achieves performance at classifying nodule type that surpasses the one of classical machine learning approaches and is within the inter-observer variability among four experienced human observers.

Towards automatic pulmonary nodule management in lung cancer screening with deep learning

PubMed Central

Ciompi, Francesco; Chung, Kaman; van Riel, Sarah J.; Setio, Arnaud Arindra Adiyoso; Gerke, Paul K.; Jacobs, Colin; Th. Scholten, Ernst; Schaefer-Prokop, Cornelia; Wille, Mathilde M. W.; Marchianò, Alfonso; Pastorino, Ugo; Prokop, Mathias; van Ginneken, Bram

2017-01-01

The introduction of lung cancer screening programs will produce an unprecedented amount of chest CT scans in the near future, which radiologists will have to read in order to decide on a patient follow-up strategy. According to the current guidelines, the workup of screen-detected nodules strongly relies on nodule size and nodule type. In this paper, we present a deep learning system based on multi-stream multi-scale convolutional networks, which automatically classifies all nodule types relevant for nodule workup. The system processes raw CT data containing a nodule without the need for any additional information such as nodule segmentation or nodule size and learns a representation of 3D data by analyzing an arbitrary number of 2D views of a given nodule. The deep learning system was trained with data from the Italian MILD screening trial and validated on an independent set of data from the Danish DLCST screening trial. We analyze the advantage of processing nodules at multiple scales with a multi-stream convolutional network architecture, and we show that the proposed deep learning system achieves performance at classifying nodule type that surpasses the one of classical machine learning approaches and is within the inter-observer variability among four experienced human observers. PMID:28422152

Early sinkhole detection using a drone-based thermal camera and image processing

NASA Astrophysics Data System (ADS)

Lee, Eun Ju; Shin, Sang Young; Ko, Byoung Chul; Chang, Chunho

2016-09-01

Accurate advance detection of the sinkholes that are occurring more frequently now is an important way of preventing human fatalities and property damage. Unlike naturally occurring sinkholes, human-induced ones in urban areas are typically due to groundwater disturbances and leaks of water and sewage caused by large-scale construction. Although many sinkhole detection methods have been developed, it is still difficult to predict sinkholes that occur in depth areas. In addition, conventional methods are inappropriate for scanning a large area because of their high cost. Therefore, this paper uses a drone combined with a thermal far-infrared (FIR) camera to detect potential sinkholes over a large area based on computer vision and pattern classification techniques. To make a standard dataset, we dug eight holes of depths 0.5-2 m in increments of 0.5 m and with a maximum width of 1 m. We filmed these using the drone-based FIR camera at a height of 50 m. We first detect candidate regions by analysing cold spots in the thermal images based on the fact that a sinkhole typically has a lower thermal energy than its background. Then, these regions are classified into sinkhole and non-sinkhole classes using a pattern classifier. In this study, we ensemble the classification results based on a light convolutional neural network (CNN) and those based on a Boosted Random Forest (BRF) with handcrafted features. We apply the proposed ensemble method successfully to sinkhole data for various sizes and depths in different environments, and prove that the CNN ensemble and the BRF one with handcrafted features are better at detecting sinkholes than other classifiers or standalone CNN.

A real-time multi-scale 2D Gaussian filter based on FPGA

NASA Astrophysics Data System (ADS)

Luo, Haibo; Gai, Xingqin; Chang, Zheng; Hui, Bin

2014-11-01

Multi-scale 2-D Gaussian filter has been widely used in feature extraction (e.g. SIFT, edge etc.), image segmentation, image enhancement, image noise removing, multi-scale shape description etc. However, their computational complexity remains an issue for real-time image processing systems. Aimed at this problem, we propose a framework of multi-scale 2-D Gaussian filter based on FPGA in this paper. Firstly, a full-hardware architecture based on parallel pipeline was designed to achieve high throughput rate. Secondly, in order to save some multiplier, the 2-D convolution is separated into two 1-D convolutions. Thirdly, a dedicate first in first out memory named as CAFIFO (Column Addressing FIFO) was designed to avoid the error propagating induced by spark on clock. Finally, a shared memory framework was designed to reduce memory costs. As a demonstration, we realized a 3 scales 2-D Gaussian filter on a single ALTERA Cyclone III FPGA chip. Experimental results show that, the proposed framework can computing a Multi-scales 2-D Gaussian filtering within one pixel clock period, is further suitable for real-time image processing. Moreover, the main principle can be popularized to the other operators based on convolution, such as Gabor filter, Sobel operator and so on.

Spoof Detection for Finger-Vein Recognition System Using NIR Camera.

PubMed

Nguyen, Dat Tien; Yoon, Hyo Sik; Pham, Tuyen Danh; Park, Kang Ryoung

2017-10-01

Finger-vein recognition, a new and advanced biometrics recognition method, is attracting the attention of researchers because of its advantages such as high recognition performance and lesser likelihood of theft and inaccuracies occurring on account of skin condition defects. However, as reported by previous researchers, it is possible to attack a finger-vein recognition system by using presentation attack (fake) finger-vein images. As a result, spoof detection, named as presentation attack detection (PAD), is necessary in such recognition systems. Previous attempts to establish PAD methods primarily focused on designing feature extractors by hand (handcrafted feature extractor) based on the observations of the researchers about the difference between real (live) and presentation attack finger-vein images. Therefore, the detection performance was limited. Recently, the deep learning framework has been successfully applied in computer vision and delivered superior results compared to traditional handcrafted methods on various computer vision applications such as image-based face recognition, gender recognition and image classification. In this paper, we propose a PAD method for near-infrared (NIR) camera-based finger-vein recognition system using convolutional neural network (CNN) to enhance the detection ability of previous handcrafted methods. Using the CNN method, we can derive a more suitable feature extractor for PAD than the other handcrafted methods using a training procedure. We further process the extracted image features to enhance the presentation attack finger-vein image detection ability of the CNN method using principal component analysis method (PCA) for dimensionality reduction of feature space and support vector machine (SVM) for classification. Through extensive experimental results, we confirm that our proposed method is adequate for presentation attack finger-vein image detection and it can deliver superior detection results compared to CNN-based methods and other previous handcrafted methods.

Spoof Detection for Finger-Vein Recognition System Using NIR Camera

PubMed Central

Nguyen, Dat Tien; Yoon, Hyo Sik; Pham, Tuyen Danh; Park, Kang Ryoung

2017-01-01

Finger-vein recognition, a new and advanced biometrics recognition method, is attracting the attention of researchers because of its advantages such as high recognition performance and lesser likelihood of theft and inaccuracies occurring on account of skin condition defects. However, as reported by previous researchers, it is possible to attack a finger-vein recognition system by using presentation attack (fake) finger-vein images. As a result, spoof detection, named as presentation attack detection (PAD), is necessary in such recognition systems. Previous attempts to establish PAD methods primarily focused on designing feature extractors by hand (handcrafted feature extractor) based on the observations of the researchers about the difference between real (live) and presentation attack finger-vein images. Therefore, the detection performance was limited. Recently, the deep learning framework has been successfully applied in computer vision and delivered superior results compared to traditional handcrafted methods on various computer vision applications such as image-based face recognition, gender recognition and image classification. In this paper, we propose a PAD method for near-infrared (NIR) camera-based finger-vein recognition system using convolutional neural network (CNN) to enhance the detection ability of previous handcrafted methods. Using the CNN method, we can derive a more suitable feature extractor for PAD than the other handcrafted methods using a training procedure. We further process the extracted image features to enhance the presentation attack finger-vein image detection ability of the CNN method using principal component analysis method (PCA) for dimensionality reduction of feature space and support vector machine (SVM) for classification. Through extensive experimental results, we confirm that our proposed method is adequate for presentation attack finger-vein image detection and it can deliver superior detection results compared to CNN-based methods and other previous handcrafted methods. PMID:28974031

Framework for Detection and Localization of Extreme Climate Event with Pixel Recursive Super Resolution

NASA Astrophysics Data System (ADS)

Kim, S. K.; Lee, J.; Zhang, C.; Ames, S.; Williams, D. N.

2017-12-01

Deep learning techniques have been successfully applied to solve many problems in climate and geoscience using massive-scaled observed and modeled data. For extreme climate event detections, several models based on deep neural networks have been recently proposed and attend superior performance that overshadows all previous handcrafted expert based method. The issue arising, though, is that accurate localization of events requires high quality of climate data. In this work, we propose framework capable of detecting and localizing extreme climate events in very coarse climate data. Our framework is based on two models using deep neural networks, (1) Convolutional Neural Networks (CNNs) to detect and localize extreme climate events, and (2) Pixel recursive recursive super resolution model to reconstruct high resolution climate data from low resolution climate data. Based on our preliminary work, we have presented two CNNs in our framework for different purposes, detection and localization. Our results using CNNs for extreme climate events detection shows that simple neural nets can capture the pattern of extreme climate events with high accuracy from very coarse reanalysis data. However, localization accuracy is relatively low due to the coarse resolution. To resolve this issue, the pixel recursive super resolution model reconstructs the resolution of input of localization CNNs. We present a best networks using pixel recursive super resolution model that synthesizes details of tropical cyclone in ground truth data while enhancing their resolution. Therefore, this approach not only dramat- ically reduces the human effort, but also suggests possibility to reduce computing cost required for downscaling process to increase resolution of data.

Automated Grading of Age-Related Macular Degeneration From Color Fundus Images Using Deep Convolutional Neural Networks.

PubMed

Burlina, Philippe M; Joshi, Neil; Pekala, Michael; Pacheco, Katia D; Freund, David E; Bressler, Neil M

2017-11-01

Age-related macular degeneration (AMD) affects millions of people throughout the world. The intermediate stage may go undetected, as it typically is asymptomatic. However, the preferred practice patterns for AMD recommend identifying individuals with this stage of the disease to educate how to monitor for the early detection of the choroidal neovascular stage before substantial vision loss has occurred and to consider dietary supplements that might reduce the risk of the disease progressing from the intermediate to the advanced stage. Identification, though, can be time-intensive and requires expertly trained individuals. To develop methods for automatically detecting AMD from fundus images using a novel application of deep learning methods to the automated assessment of these images and to leverage artificial intelligence advances. Deep convolutional neural networks that are explicitly trained for performing automated AMD grading were compared with an alternate deep learning method that used transfer learning and universal features and with a trained clinical grader. Age-related macular degeneration automated detection was applied to a 2-class classification problem in which the task was to distinguish the disease-free/early stages from the referable intermediate/advanced stages. Using several experiments that entailed different data partitioning, the performance of the machine algorithms and human graders in evaluating over 130 000 images that were deidentified with respect to age, sex, and race/ethnicity from 4613 patients against a gold standard included in the National Institutes of Health Age-related Eye Disease Study data set was evaluated. Accuracy, receiver operating characteristics and area under the curve, and kappa score. The deep convolutional neural network method yielded accuracy (SD) that ranged between 88.4% (0.5%) and 91.6% (0.1%), the area under the receiver operating characteristic curve was between 0.94 and 0.96, and kappa coefficient (SD) between 0.764 (0.010) and 0.829 (0.003), which indicated a substantial agreement with the gold standard Age-related Eye Disease Study data set. Applying a deep learning-based automated assessment of AMD from fundus images can produce results that are similar to human performance levels. This study demonstrates that automated algorithms could play a role that is independent of expert human graders in the current management of AMD and could address the costs of screening or monitoring, access to health care, and the assessment of novel treatments that address the development or progression of AMD.

Quantitative Detection of Small Molecule/DNA Complexes Employing a Force-Based and Label-Free DNA-Microarray

PubMed Central

Ho, Dominik; Dose, Christian; Albrecht, Christian H.; Severin, Philip; Falter, Katja; Dervan, Peter B.; Gaub, Hermann E.

2009-01-01

Force-based ligand detection is a promising method to characterize molecular complexes label-free at physiological conditions. Because conventional implementations of this technique, e.g., based on atomic force microscopy or optical traps, are low-throughput and require extremely sensitive and sophisticated equipment, this approach has to date found only limited application. We present a low-cost, chip-based assay, which combines high-throughput force-based detection of dsDNA·ligand interactions with the ease of fluorescence detection. Within the comparative unbinding force assay, many duplicates of a target DNA duplex are probed against a defined reference DNA duplex each. The fractions of broken target and reference DNA duplexes are determined via fluorescence. With this assay, we investigated the DNA binding behavior of artificial pyrrole-imidazole polyamides. These small compounds can be programmed to target specific dsDNA sequences and distinguish between D- and L-DNA. We found that titration with polyamides specific for a binding motif, which is present in the target DNA duplex and not in the reference DNA duplex, reliably resulted in a shift toward larger fractions of broken reference bonds. From the concentration dependence nanomolar to picomolar dissociation constants of dsDNA·ligand complexes were determined, agreeing well with prior quantitative DNAase footprinting experiments. This finding corroborates that the forced unbinding of dsDNA in presence of a ligand is a nonequilibrium process that produces a snapshot of the equilibrium distribution between dsDNA and dsDNA·ligand complexes. PMID:19486688

Trade Study for Neutron Transport at Low Earth Orbit: Adding Fidelity to DIORAMA

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

McClanahan, Tucker Caden; Wakeford, Daniel Tyler

The Distributed Infrastructure Offering Real-Time Access to Modeling and Analysis (DIORAMA) software provides performance modeling capabilities of the United States Nuclear Detonation Detection System (USNDS) with a focus on the characterization of Space-Based Nuclear Detonation Detection (SNDD) instrument performance [1]. A case study was done to add the neutron propagation capabilities of DIORAMA to low earth orbit (LEO), and compare the back-calculated incident energy from the time-of- ight (TOF) spectrum with the scored incident energy spectrum. As the scoring altitude lowers, the time increase due to scattering takes up much more of the fraction of total TOF; whereas at geosynchronousmore » earth orbit (GEO), the time increase due to scattering is a negligible fraction of the total TOF [2]. The scattering smears out the TOF enough to make the back-calculation of the initial energy spectrum from the TOF spectrum very convoluted.« less

Development of a Deep Learning Algorithm for Automatic Diagnosis of Diabetic Retinopathy.

PubMed

Raju, Manoj; Pagidimarri, Venkatesh; Barreto, Ryan; Kadam, Amrit; Kasivajjala, Vamsichandra; Aswath, Arun

2017-01-01

This paper mainly focuses on the deep learning application in classifying the stage of diabetic retinopathy and detecting the laterality of the eye using funduscopic images. Diabetic retinopathy is a chronic, progressive, sight-threatening disease of the retinal blood vessels. Ophthalmologists diagnose diabetic retinopathy through early funduscopic screening. Normally, there is a time delay in reporting and intervention, apart from the financial cost and risk of blindness associated with it. Using a convolutional neural network based approach for automatic diagnosis of diabetic retinopathy, we trained the prediction network on the publicly available Kaggle dataset. Approximately 35,000 images were used to train the network, which observed a sensitivity of 80.28% and a specificity of 92.29% on the validation dataset of ~53,000 images. Using 8,810 images, the network was trained for detecting the laterality of the eye and observed an accuracy of 93.28% on the validation set of 8,816 images.

Probing biomolecular interaction forces using an anharmonic acoustic technique for selective detection of bacterial spores.

PubMed

Ghosh, Sourav K; Ostanin, Victor P; Johnson, Christian L; Lowe, Christopher R; Seshia, Ashwin A

2011-11-15

Receptor-based detection of pathogens often suffers from non-specific interactions, and as most detection techniques cannot distinguish between affinities of interactions, false positive responses remain a plaguing reality. Here, we report an anharmonic acoustic based method of detection that addresses the inherent weakness of current ligand dependant assays. Spores of Bacillus subtilis (Bacillus anthracis simulant) were immobilized on a thickness-shear mode AT-cut quartz crystal functionalized with anti-spore antibody and the sensor was driven by a pure sinusoidal oscillation at increasing amplitude. Biomolecular interaction forces between the coupled spores and the accelerating surface caused a nonlinear modulation of the acoustic response of the crystal. In particular, the deviation in the third harmonic of the transduced electrical response versus oscillation amplitude of the sensor (signal) was found to be significant. Signals from the specifically-bound spores were clearly distinguishable in shape from those of the physisorbed streptavidin-coated polystyrene microbeads. The analytical model presented here enables estimation of the biomolecular interaction forces from the measured response. Thus, probing biomolecular interaction forces using the described technique can quantitatively detect pathogens and distinguish specific from non-specific interactions, with potential applicability to rapid point-of-care detection. This also serves as a potential tool for rapid force-spectroscopy, affinity-based biomolecular screening and mapping of molecular interaction networks. Copyright © 2011 Elsevier B.V. All rights reserved.

Automatic Organ Segmentation for CT Scans Based on Super-Pixel and Convolutional Neural Networks.

PubMed

Liu, Xiaoming; Guo, Shuxu; Yang, Bingtao; Ma, Shuzhi; Zhang, Huimao; Li, Jing; Sun, Changjian; Jin, Lanyi; Li, Xueyan; Yang, Qi; Fu, Yu

2018-04-20

Accurate segmentation of specific organ from computed tomography (CT) scans is a basic and crucial task for accurate diagnosis and treatment. To avoid time-consuming manual optimization and to help physicians distinguish diseases, an automatic organ segmentation framework is presented. The framework utilized convolution neural networks (CNN) to classify pixels. To reduce the redundant inputs, the simple linear iterative clustering (SLIC) of super-pixels and the support vector machine (SVM) classifier are introduced. To establish the perfect boundary of organs in one-pixel-level, the pixels need to be classified step-by-step. First, the SLIC is used to cut an image into grids and extract respective digital signatures. Next, the signature is classified by the SVM, and the rough edges are acquired. Finally, a precise boundary is obtained by the CNN, which is based on patches around each pixel-point. The framework is applied to abdominal CT scans of livers and high-resolution computed tomography (HRCT) scans of lungs. The experimental CT scans are derived from two public datasets (Sliver 07 and a Chinese local dataset). Experimental results show that the proposed method can precisely and efficiently detect the organs. This method consumes 38 s/slice for liver segmentation. The Dice coefficient of the liver segmentation results reaches to 97.43%. For lung segmentation, the Dice coefficient is 97.93%. This finding demonstrates that the proposed framework is a favorable method for lung segmentation of HRCT scans.

Localization and diagnosis framework for pediatric cataracts based on slit-lamp images using deep features of a convolutional neural network

PubMed Central

Zhang, Kai; Long, Erping; Cui, Jiangtao; Zhu, Mingmin; An, Yingying; Zhang, Jia; Liu, Zhenzhen; Lin, Zhuoling; Li, Xiaoyan; Chen, Jingjing; Cao, Qianzhong; Li, Jing; Wu, Xiaohang; Wang, Dongni

2017-01-01

Slit-lamp images play an essential role for diagnosis of pediatric cataracts. We present a computer vision-based framework for the automatic localization and diagnosis of slit-lamp images by identifying the lens region of interest (ROI) and employing a deep learning convolutional neural network (CNN). First, three grading degrees for slit-lamp images are proposed in conjunction with three leading ophthalmologists. The lens ROI is located in an automated manner in the original image using two successive applications of Candy detection and the Hough transform, which are cropped, resized to a fixed size and used to form pediatric cataract datasets. These datasets are fed into the CNN to extract high-level features and implement automatic classification and grading. To demonstrate the performance and effectiveness of the deep features extracted in the CNN, we investigate the features combined with support vector machine (SVM) and softmax classifier and compare these with the traditional representative methods. The qualitative and quantitative experimental results demonstrate that our proposed method offers exceptional mean accuracy, sensitivity and specificity: classification (97.07%, 97.28%, and 96.83%) and a three-degree grading area (89.02%, 86.63%, and 90.75%), density (92.68%, 91.05%, and 93.94%) and location (89.28%, 82.70%, and 93.08%). Finally, we developed and deployed a potential automatic diagnostic software for ophthalmologists and patients in clinical applications to implement the validated model. PMID:28306716

Her2Net: A Deep Framework for Semantic Segmentation and Classification of Cell Membranes and Nuclei in Breast Cancer Evaluation.

PubMed

Saha, Monjoy; Chakraborty, Chandan

2018-05-01

We present an efficient deep learning framework for identifying, segmenting, and classifying cell membranes and nuclei from human epidermal growth factor receptor-2 (HER2)-stained breast cancer images with minimal user intervention. This is a long-standing issue for pathologists because the manual quantification of HER2 is error-prone, costly, and time-consuming. Hence, we propose a deep learning-based HER2 deep neural network (Her2Net) to solve this issue. The convolutional and deconvolutional parts of the proposed Her2Net framework consisted mainly of multiple convolution layers, max-pooling layers, spatial pyramid pooling layers, deconvolution layers, up-sampling layers, and trapezoidal long short-term memory (TLSTM). A fully connected layer and a softmax layer were also used for classification and error estimation. Finally, HER2 scores were calculated based on the classification results. The main contribution of our proposed Her2Net framework includes the implementation of TLSTM and a deep learning framework for cell membrane and nucleus detection, segmentation, and classification and HER2 scoring. Our proposed Her2Net achieved 96.64% precision, 96.79% recall, 96.71% F-score, 93.08% negative predictive value, 98.33% accuracy, and a 6.84% false-positive rate. Our results demonstrate the high accuracy and wide applicability of the proposed Her2Net in the context of HER2 scoring for breast cancer evaluation.

An image-space parallel convolution filtering algorithm based on shadow map

NASA Astrophysics Data System (ADS)

Li, Hua; Yang, Huamin; Zhao, Jianping

2017-07-01

Shadow mapping is commonly used in real-time rendering. In this paper, we presented an accurate and efficient method of soft shadows generation from planar area lights. First this method generated a depth map from light's view, and analyzed the depth-discontinuities areas as well as shadow boundaries. Then these areas were described as binary values in the texture map called binary light-visibility map, and a parallel convolution filtering algorithm based on GPU was enforced to smooth out the boundaries with a box filter. Experiments show that our algorithm is an effective shadow map based method that produces perceptually accurate soft shadows in real time with more details of shadow boundaries compared with the previous works.

Automatic coronary artery calcium scoring in cardiac CT angiography using paired convolutional neural networks.

PubMed

Wolterink, Jelmer M; Leiner, Tim; de Vos, Bob D; van Hamersvelt, Robbert W; Viergever, Max A; Išgum, Ivana

2016-12-01

The amount of coronary artery calcification (CAC) is a strong and independent predictor of cardiovascular events. CAC is clinically quantified in cardiac calcium scoring CT (CSCT), but it has been shown that cardiac CT angiography (CCTA) may also be used for this purpose. We present a method for automatic CAC quantification in CCTA. This method uses supervised learning to directly identify and quantify CAC without a need for coronary artery extraction commonly used in existing methods. The study included cardiac CT exams of 250 patients for whom both a CCTA and a CSCT scan were available. To restrict the volume-of-interest for analysis, a bounding box around the heart is automatically determined. The bounding box detection algorithm employs a combination of three ConvNets, where each detects the heart in a different orthogonal plane (axial, sagittal, coronal). These ConvNets were trained using 50 cardiac CT exams. In the remaining 200 exams, a reference standard for CAC was defined in CSCT and CCTA. Out of these, 100 CCTA scans were used for training, and the remaining 100 for evaluation of a voxel classification method for CAC identification. The method uses ConvPairs, pairs of convolutional neural networks (ConvNets). The first ConvNet in a pair identifies voxels likely to be CAC, thereby discarding the majority of non-CAC-like voxels such as lung and fatty tissue. The identified CAC-like voxels are further classified by the second ConvNet in the pair, which distinguishes between CAC and CAC-like negatives. Given the different task of each ConvNet, they share their architecture, but not their weights. Input patches are either 2.5D or 3D. The ConvNets are purely convolutional, i.e. no pooling layers are present and fully connected layers are implemented as convolutions, thereby allowing efficient voxel classification. The performance of individual 2.5D and 3D ConvPairs with input sizes of 15 and 25 voxels, as well as the performance of ensembles of these ConvPairs, were evaluated by a comparison with reference annotations in CCTA and CSCT. In all cases, ensembles of ConvPairs outperformed their individual members. The best performing individual ConvPair detected 72% of lesions in the test set, with on average 0.85 false positive (FP) errors per scan. The best performing ensemble combined all ConvPairs and obtained a sensitivity of 71% at 0.48 FP errors per scan. For this ensemble, agreement with the reference mass score in CSCT was excellent (ICC 0.944 [0.918-0.962]). Aditionally, based on the Agatston score in CCTA, this ensemble assigned 83% of patients to the same cardiovascular risk category as reference CSCT. In conclusion, CAC can be accurately automatically identified and quantified in CCTA using the proposed pattern recognition method. This might obviate the need to acquire a dedicated CSCT scan for CAC scoring, which is regularly acquired prior to a CCTA, and thus reduce the CT radiation dose received by patients. Copyright © 2016 Elsevier B.V. All rights reserved.

Producing data-based sensitivity kernels from convolution and correlation in exploration geophysics.

NASA Astrophysics Data System (ADS)

Chmiel, M. J.; Roux, P.; Herrmann, P.; Rondeleux, B.

2016-12-01

Many studies have shown that seismic interferometry can be used to estimate surface wave arrivals by correlation of seismic signals recorded at a pair of locations. In the case of ambient noise sources, the convergence towards the surface wave Green's functions is obtained with the criterion of equipartitioned energy. However, seismic acquisition with active, controlled sources gives more possibilities when it comes to interferometry. The use of controlled sources makes it possible to recover the surface wave Green's function between two points using either correlation or convolution. We investigate the convolutional and correlational approaches using land active-seismic data from exploration geophysics. The data were recorded on 10,710 vertical receivers using 51,808 sources (seismic vibrator trucks). The sources spacing is the same in both X and Y directions (30 m) which is known as a "carpet shooting". The receivers are placed in parallel lines with a spacing 150 m in the X direction and 30 m in the Y direction. Invoking spatial reciprocity between sources and receivers, correlation and convolution functions can thus be constructed between either pairs of receivers or pairs of sources. Benefiting from the dense acquisition, we extract sensitivity kernels from correlation and convolution measurements of the seismic data. These sensitivity kernels are subsequently used to produce phase-velocity dispersion curves between two points and to separate the higher mode from the fundamental mode for surface waves. Potential application to surface wave cancellation is also envisaged.

Yarn-dyed fabric defect classification based on convolutional neural network

NASA Astrophysics Data System (ADS)

Jing, Junfeng; Dong, Amei; Li, Pengfei; Zhang, Kaibing

2017-09-01

Considering that manual inspection of the yarn-dyed fabric can be time consuming and inefficient, we propose a yarn-dyed fabric defect classification method by using a convolutional neural network (CNN) based on a modified AlexNet. CNN shows powerful ability in performing feature extraction and fusion by simulating the learning mechanism of human brain. The local response normalization layers in AlexNet are replaced by the batch normalization layers, which can enhance both the computational efficiency and classification accuracy. In the training process of the network, the characteristics of the defect are extracted step by step and the essential features of the image can be obtained from the fusion of the edge details with several convolution operations. Then the max-pooling layers, the dropout layers, and the fully connected layers are employed in the classification model to reduce the computation cost and extract more precise features of the defective fabric. Finally, the results of the defect classification are predicted by the softmax function. The experimental results show promising performance with an acceptable average classification rate and strong robustness on yarn-dyed fabric defect classification.

Classification of amyotrophic lateral sclerosis disease based on convolutional neural network and reinforcement sample learning algorithm.

PubMed

Sengur, Abdulkadir; Akbulut, Yaman; Guo, Yanhui; Bajaj, Varun

2017-12-01

Electromyogram (EMG) signals contain useful information of the neuromuscular diseases like amyotrophic lateral sclerosis (ALS). ALS is a well-known brain disease, which can progressively degenerate the motor neurons. In this paper, we propose a deep learning based method for efficient classification of ALS and normal EMG signals. Spectrogram, continuous wavelet transform (CWT), and smoothed pseudo Wigner-Ville distribution (SPWVD) have been employed for time-frequency (T-F) representation of EMG signals. A convolutional neural network is employed to classify these features. In it, Two convolution layers, two pooling layer, a fully connected layer and a lost function layer is considered in CNN architecture. The CNN architecture is trained with the reinforcement sample learning strategy. The efficiency of the proposed implementation is tested on publicly available EMG dataset. The dataset contains 89 ALS and 133 normal EMG signals with 24 kHz sampling frequency. Experimental results show 96.80% accuracy. The obtained results are also compared with other methods, which show the superiority of the proposed method.

Multi-focus image fusion with the all convolutional neural network

NASA Astrophysics Data System (ADS)

Du, Chao-ben; Gao, She-sheng

2018-01-01

A decision map contains complete and clear information about the image to be fused, which is crucial to various image fusion issues, especially multi-focus image fusion. However, in order to get a satisfactory image fusion effect, getting a decision map is very necessary and usually difficult to finish. In this letter, we address this problem with convolutional neural network (CNN), aiming to get a state-of-the-art decision map. The main idea is that the max-pooling of CNN is replaced by a convolution layer, the residuals are propagated backwards by gradient descent, and the training parameters of the individual layers of the CNN are updated layer by layer. Based on this, we propose a new all CNN (ACNN)-based multi-focus image fusion method in spatial domain. We demonstrate that the decision map obtained from the ACNN is reliable and can lead to high-quality fusion results. Experimental results clearly validate that the proposed algorithm can obtain state-of-the-art fusion performance in terms of both qualitative and quantitative evaluations.

A chest-shape target automatic detection method based on Deformable Part Models

NASA Astrophysics Data System (ADS)

Zhang, Mo; Jin, Weiqi; Li, Li

2016-10-01

Automatic weapon platform is one of the important research directions at domestic and overseas, it needs to accomplish fast searching for the object to be shot under complex background. Therefore, fast detection for given target is the foundation of further task. Considering that chest-shape target is common target of shoot practice, this paper treats chestshape target as the target and studies target automatic detection method based on Deformable Part Models. The algorithm computes Histograms of Oriented Gradient(HOG) features of the target and trains a model using Latent variable Support Vector Machine(SVM); In this model, target image is divided into several parts then we can obtain foot filter and part filters; Finally, the algorithm detects the target at the HOG features pyramid with method of sliding window. The running time of extracting HOG pyramid with lookup table can be shorten by 36%. The result indicates that this algorithm can detect the chest-shape target in natural environments indoors or outdoors. The true positive rate of detection reaches 76% with many hard samples, and the false positive rate approaches 0. Running on a PC (Intel(R)Core(TM) i5-4200H CPU) with C++ language, the detection time of images with the resolution of 640 × 480 is 2.093s. According to TI company run library about image pyramid and convolution for DM642 and other hardware, our detection algorithm is expected to be implemented on hardware platform, and it has application prospect in actual system.

A Computer-Aided Diagnosis System for Measuring Carotid Artery Intima-Media Thickness (IMT) Using Quaternion Vectors.

PubMed

Kutbay, Uğurhan; Hardalaç, Fırat; Akbulut, Mehmet; Akaslan, Ünsal; Serhatlıoğlu, Selami

2016-06-01

This study aims investigating adjustable distant fuzzy c-means segmentation on carotid Doppler images, as well as quaternion-based convolution filters and saliency mapping procedures. We developed imaging software that will simplify the measurement of carotid artery intima-media thickness (IMT) on saliency mapping images. Additionally, specialists evaluated the present images and compared them with saliency mapping images. In the present research, we conducted imaging studies of 25 carotid Doppler images obtained by the Department of Cardiology at Fırat University. After implementing fuzzy c-means segmentation and quaternion-based convolution on all Doppler images, we obtained a model that can be analyzed easily by the doctors using a bottom-up saliency model. These methods were applied to 25 carotid Doppler images and then interpreted by specialists. In the present study, we used color-filtering methods to obtain carotid color images. Saliency mapping was performed on the obtained images, and the carotid artery IMT was detected and interpreted on the obtained images from both methods and the raw images are shown in Results. Also these results were investigated by using Mean Square Error (MSE) for the raw IMT images and the method which gives the best performance is the Quaternion Based Saliency Mapping (QBSM). 0,0014 and 0,000191 mm(2) MSEs were obtained for artery lumen diameters and plaque diameters in carotid arteries respectively. We found that computer-based image processing methods used on carotid Doppler could aid doctors' in their decision-making process. We developed software that could ease the process of measuring carotid IMT for cardiologists and help them to evaluate their findings.

The testicular sperm ducts and genital kidney of male Ambystoma maculatum (Amphibia, Urodela, Ambystomatidae).

PubMed

Siegel, Dustin S; Aldridge, Robert D; Rheubert, Justin L; Gribbins, Kevin M; Sever, David M; Trauth, Stanley E

2013-03-01

The ducts associated with sperm transport from the testicular lobules to the Wolffian ducts in Ambystoma maculatum were examined with transmission electron microscopy. Based on the ultrastructure and historical precedence, new terminology for this network of ducts is proposed that better represents primary hypotheses of homology. Furthermore, the terminology proposed better characterizes the distinct regions of the sperm transport ducts in salamanders based on anatomy and should, therefore, lead to more accurate comparisons in the future. While developing the above ontology, we also tested the hypothesis that nephrons from the genital kidney are modified from those of the pelvic kidney due to the fact that the former nephrons function in sperm transport. Our ultrastructural analysis of the genital kidney supports this hypothesis, as the basal plasma membrane of distinct functional regions of the nephron (proximal convoluted tubule, distal convoluted tubule, and collecting tubule) appear less folded (indicating decreased surface area and reduced reabsorption efficiency) and the proximal convoluted tubule possesses ciliated epithelial cells along its entire length. Furthermore, visible luminal filtrate is absent from the nephrons of the genital kidney throughout their entire length. Thus, it appears that the nephrons of the genital kidney have reduced reabsorptive capacity and ciliated cells of the proximal convoluted tubule may increase the movement of immature sperm through the sperm transport ducts or aid in the mixing of seminal fluids within the ducts. Copyright © 2012 Wiley Periodicals, Inc.

Method and Apparatus to Access Optimum Strength During Processing of Precipitation Strengthened Alloys

NASA Technical Reports Server (NTRS)

Cantrell, John H. (Inventor); Yost, William T. (Inventor)

2001-01-01

A method and apparatus are provided which enable the nondestructive testing of strength of a heat treated alloy. An alloy is insonified with an ultrasonic signal. The resulting convoluted signal is detected and the acoustic nonlinearity parameter is determined. The acoustic nonlinearity parameter shows a peak corresponding to a peak in material strength.

Image quality of mixed convolution kernel in thoracic computed tomography.

PubMed

Neubauer, Jakob; Spira, Eva Maria; Strube, Juliane; Langer, Mathias; Voss, Christian; Kotter, Elmar

2016-11-01

The mixed convolution kernel alters his properties geographically according to the depicted organ structure, especially for the lung. Therefore, we compared the image quality of the mixed convolution kernel to standard soft and hard kernel reconstructions for different organ structures in thoracic computed tomography (CT) images.Our Ethics Committee approved this prospective study. In total, 31 patients who underwent contrast-enhanced thoracic CT studies were included after informed consent. Axial reconstructions were performed with hard, soft, and mixed convolution kernel. Three independent and blinded observers rated the image quality according to the European Guidelines for Quality Criteria of Thoracic CT for 13 organ structures. The observers rated the depiction of the structures in all reconstructions on a 5-point Likert scale. Statistical analysis was performed with the Friedman Test and post hoc analysis with the Wilcoxon rank-sum test.Compared to the soft convolution kernel, the mixed convolution kernel was rated with a higher image quality for lung parenchyma, segmental bronchi, and the border between the pleura and the thoracic wall (P < 0.03). Compared to the hard convolution kernel, the mixed convolution kernel was rated with a higher image quality for aorta, anterior mediastinal structures, paratracheal soft tissue, hilar lymph nodes, esophagus, pleuromediastinal border, large and medium sized pulmonary vessels and abdomen (P < 0.004) but a lower image quality for trachea, segmental bronchi, lung parenchyma, and skeleton (P < 0.001).The mixed convolution kernel cannot fully substitute the standard CT reconstructions. Hard and soft convolution kernel reconstructions still seem to be mandatory for thoracic CT.

A Fast Numerical Method for Max-Convolution and the Application to Efficient Max-Product Inference in Bayesian Networks.

PubMed

Serang, Oliver

2015-08-01

Observations depending on sums of random variables are common throughout many fields; however, no efficient solution is currently known for performing max-product inference on these sums of general discrete distributions (max-product inference can be used to obtain maximum a posteriori estimates). The limiting step to max-product inference is the max-convolution problem (sometimes presented in log-transformed form and denoted as "infimal convolution," "min-convolution," or "convolution on the tropical semiring"), for which no O(k log(k)) method is currently known. Presented here is an O(k log(k)) numerical method for estimating the max-convolution of two nonnegative vectors (e.g., two probability mass functions), where k is the length of the larger vector. This numerical max-convolution method is then demonstrated by performing fast max-product inference on a convolution tree, a data structure for performing fast inference given information on the sum of n discrete random variables in O(nk log(nk)log(n)) steps (where each random variable has an arbitrary prior distribution on k contiguous possible states). The numerical max-convolution method can be applied to specialized classes of hidden Markov models to reduce the runtime of computing the Viterbi path from nk(2) to nk log(k), and has potential application to the all-pairs shortest paths problem.

Performance of Serially Concatenated Convolutional Codes with Binary Modulation in AWGN and Noise Jamming over Rayleigh Fading Channels

DTIC Science & Technology

2001-09-01

Rate - compatible punctured convolutional codes (RCPC codes ) and their applications,” IEEE...ABSTRACT In this dissertation, the bit error rates for serially concatenated convolutional codes (SCCC) for both BPSK and DPSK modulation with...INTENTIONALLY LEFT BLANK i EXECUTIVE SUMMARY In this dissertation, the bit error rates of serially concatenated convolutional codes

DSN telemetry system performance with convolutionally coded data using operational maximum-likelihood convolutional decoders

NASA Technical Reports Server (NTRS)

Benjauthrit, B.; Mulhall, B.; Madsen, B. D.; Alberda, M. E.

1976-01-01

The DSN telemetry system performance with convolutionally coded data using the operational maximum-likelihood convolutional decoder (MCD) being implemented in the Network is described. Data rates from 80 bps to 115.2 kbps and both S- and X-band receivers are reported. The results of both one- and two-way radio losses are included.

Performance of the ICAO standard core service modulation and coding techniques

NASA Technical Reports Server (NTRS)

Lodge, John; Moher, Michael

1988-01-01

Aviation binary phase shift keying (A-BPSK) is described and simulated performance results are given that demonstrate robust performance in the presence of hardlimiting amplifiers. The performance of coherently-detected A-BPSK with rate 1/2 convolutional coding are given. The performance loss due to the Rician fading was shown to be less than 1 dB over the simulated range. A partially coherent detection scheme that does not require carrier phase recovery was described. This scheme exhibits similiar performance to coherent detection, at high bit error rates, while it is superior at lower bit error rates.

Violent Interaction Detection in Video Based on Deep Learning

NASA Astrophysics Data System (ADS)

Zhou, Peipei; Ding, Qinghai; Luo, Haibo; Hou, Xinglin

2017-06-01

Violent interaction detection is of vital importance in some video surveillance scenarios like railway stations, prisons or psychiatric centres. Existing vision-based methods are mainly based on hand-crafted features such as statistic features between motion regions, leading to a poor adaptability to another dataset. En lightened by the development of convolutional networks on common activity recognition, we construct a FightNet to represent the complicated visual violence interaction. In this paper, a new input modality, image acceleration field is proposed to better extract the motion attributes. Firstly, each video is framed as RGB images. Secondly, optical flow field is computed using the consecutive frames and acceleration field is obtained according to the optical flow field. Thirdly, the FightNet is trained with three kinds of input modalities, i.e., RGB images for spatial networks, optical flow images and acceleration images for temporal networks. By fusing results from different inputs, we conclude whether a video tells a violent event or not. To provide researchers a common ground for comparison, we have collected a violent interaction dataset (VID), containing 2314 videos with 1077 fight ones and 1237 no-fight ones. By comparison with other algorithms, experimental results demonstrate that the proposed model for violent interaction detection shows higher accuracy and better robustness.

An Efficient Neural-Network-Based Microseismic Monitoring Platform for Hydraulic Fracture on an Edge Computing Architecture.

PubMed

Zhang, Xiaopu; Lin, Jun; Chen, Zubin; Sun, Feng; Zhu, Xi; Fang, Gengfa

2018-06-05

Microseismic monitoring is one of the most critical technologies for hydraulic fracturing in oil and gas production. To detect events in an accurate and efficient way, there are two major challenges. One challenge is how to achieve high accuracy due to a poor signal-to-noise ratio (SNR). The other one is concerned with real-time data transmission. Taking these challenges into consideration, an edge-computing-based platform, namely Edge-to-Center LearnReduce, is presented in this work. The platform consists of a data center with many edge components. At the data center, a neural network model combined with convolutional neural network (CNN) and long short-term memory (LSTM) is designed and this model is trained by using previously obtained data. Once the model is fully trained, it is sent to edge components for events detection and data reduction. At each edge component, a probabilistic inference is added to the neural network model to improve its accuracy. Finally, the reduced data is delivered to the data center. Based on experiment results, a high detection accuracy (over 96%) with less transmitted data (about 90%) was achieved by using the proposed approach on a microseismic monitoring system. These results show that the platform can simultaneously improve the accuracy and efficiency of microseismic monitoring.

Visual Persons Behavior Diary Generation Model based on Trajectories and Pose Estimation

NASA Astrophysics Data System (ADS)

Gang, Chen; Bin, Chen; Yuming, Liu; Hui, Li

2018-03-01

The behavior pattern of persons was the important output of the surveillance analysis. This paper focus on the generation model of visual person behavior diary. The pipeline includes the person detection, tracking, and the person behavior classify. This paper adopts the deep convolutional neural model YOLO (You Only Look Once)V2 for person detection module. Multi person tracking was based on the detection framework. The Hungarian assignment algorithm was used to the matching. The person appearance model was integrated by HSV color model and Hash code model. The person object motion was estimated by the Kalman Filter. The multi objects were matching with exist tracklets through the appearance and motion location distance by the Hungarian assignment method. A long continuous trajectory for one person was get by the spatial-temporal continual linking algorithm. And the face recognition information was used to identify the trajectory. The trajectories with identification information can be used to generate the visual diary of person behavior based on the scene context information and person action estimation. The relevant modules are tested in public data sets and our own capture video sets. The test results show that the method can be used to generate the visual person behavior pattern diary with certain accuracy.

Deconvolving the Fate of Carbon in Coastal Sediments

NASA Astrophysics Data System (ADS)

Van der Voort, Tessa S.; Mannu, Utsav; Blattmann, Thomas M.; Bao, Rui; Zhao, Meixun; Eglinton, Timothy I.

2018-05-01

Coastal oceans play a crucial role in the global carbon cycle, and are increasingly affected by anthropogenic forcing. Understanding carbon cycling in coastal environments is hindered by convoluted sources and myriad processes that vary over a range of spatial and temporal scales. In this study, we deconvolve the complex mosaic of organic carbon manifested in Chinese Marginal Sea (CMS) sediments using a novel numerical clustering algorithm based on 14C and total OC content. Results reveal five regions that encompass geographically distinct depositional settings. Complementary statistical analyses reveal contrasting region-dependent controls on carbon dynamics and composition. Overall, clustering is shown to be highly effective in demarcating areas of distinct organic facies by disentangling intertwined organic geochemical patterns resulting from superimposed effects of OC provenance, reworking and deposition on a shelf region exhibiting pronounced spatial heterogeneity. This information will aid in constraining region-specific budgets of carbon burial and carbon cycle processes.

A Technology Analysis to Support Acquisition of UAVs for Gulf Coalition Forces Operations

DTIC Science & Technology

2017-06-01

their selection of the most suitable and cost-effective unmanned aerial vehicles to support detection operations. This study uses Map Aware Non ...being detected by Gulf Coalition Forces and improved time to detect them, support the use of UAVs in detection missions. Computer experimentations and...aerial vehicles to support detection operations. We use Map Aware Non - Uniform Automata, an agent-based simulation software platform, for the

Generalized type II hybrid ARQ scheme using punctured convolutional coding

NASA Astrophysics Data System (ADS)

Kallel, Samir; Haccoun, David

1990-11-01

A method is presented to construct rate-compatible convolutional (RCC) codes from known high-rate punctured convolutional codes, obtained from best-rate 1/2 codes. The construction method is rather simple and straightforward, and still yields good codes. Moreover, low-rate codes can be obtained without any limit on the lowest achievable code rate. Based on the RCC codes, a generalized type-II hybrid ARQ scheme, which combines the benefits of the modified type-II hybrid ARQ strategy of Hagenauer (1988) with the code-combining ARQ strategy of Chase (1985), is proposed and analyzed. With the proposed generalized type-II hybrid ARQ strategy, the throughput increases as the starting coding rate increases, and as the channel degrades, it tends to merge with the throughput of rate 1/2 type-II hybrid ARQ schemes with code combining, thus allowing the system to be flexible and adaptive to channel conditions, even under wide noise variations and severe degradations.

Rethinking Skin Lesion Segmentation in a Convolutional Classifier.

PubMed

Burdick, Jack; Marques, Oge; Weinthal, Janet; Furht, Borko

2017-10-18

Melanoma is a fatal form of skin cancer when left undiagnosed. Computer-aided diagnosis systems powered by convolutional neural networks (CNNs) can improve diagnostic accuracy and save lives. CNNs have been successfully used in both skin lesion segmentation and classification. For reasons heretofore unclear, previous works have found image segmentation to be, conflictingly, both detrimental and beneficial to skin lesion classification. We investigate the effect of expanding the segmentation border to include pixels surrounding the target lesion. Ostensibly, segmenting a target skin lesion will remove inessential information, non-lesion skin, and artifacts to aid in classification. Our results indicate that segmentation border enlargement produces, to a certain degree, better results across all metrics of interest when using a convolutional based classifier built using the transfer learning paradigm. Consequently, preprocessing methods which produce borders larger than the actual lesion can potentially improve classifier performance, more than both perfect segmentation, using dermatologist created ground truth masks, and no segmentation altogether.

Combining convolutional neural networks and Hough Transform for classification of images containing lines

NASA Astrophysics Data System (ADS)

Sheshkus, Alexander; Limonova, Elena; Nikolaev, Dmitry; Krivtsov, Valeriy

2017-03-01

In this paper, we propose an expansion of convolutional neural network (CNN) input features based on Hough Transform. We perform morphological contrasting of source image followed by Hough Transform, and then use it as input for some convolutional filters. Thus, CNNs computational complexity and the number of units are not affected. Morphological contrasting and Hough Transform are the only additional computational expenses of introduced CNN input features expansion. Proposed approach was demonstrated on the example of CNN with very simple structure. We considered two image recognition problems, that were object classification on CIFAR-10 and printed character recognition on private dataset with symbols taken from Russian passports. Our approach allowed to reach noticeable accuracy improvement without taking much computational effort, which can be extremely important in industrial recognition systems or difficult problems utilising CNNs, like pressure ridge analysis and classification.

NMR diffusion simulation based on conditional random walk.

PubMed

Gudbjartsson, H; Patz, S

1995-01-01

The authors introduce here a new, very fast, simulation method for free diffusion in a linear magnetic field gradient, which is an extension of the conventional Monte Carlo (MC) method or the convolution method described by Wong et al. (in 12th SMRM, New York, 1993, p.10). In earlier NMR-diffusion simulation methods, such as the finite difference method (FD), the Monte Carlo method, and the deterministic convolution method, the outcome of the calculations depends on the simulation time step. In the authors' method, however, the results are independent of the time step, although, in the convolution method the step size has to be adequate for spins to diffuse to adjacent grid points. By always selecting the largest possible time step the computation time can therefore be reduced. Finally the authors point out that in simple geometric configurations their simulation algorithm can be used to reduce computation time in the simulation of restricted diffusion.

Biometrics encryption combining palmprint with two-layer error correction codes

NASA Astrophysics Data System (ADS)

Li, Hengjian; Qiu, Jian; Dong, Jiwen; Feng, Guang

2017-07-01

To bridge the gap between the fuzziness of biometrics and the exactitude of cryptography, based on combining palmprint with two-layer error correction codes, a novel biometrics encryption method is proposed. Firstly, the randomly generated original keys are encoded by convolutional and cyclic two-layer coding. The first layer uses a convolution code to correct burst errors. The second layer uses cyclic code to correct random errors. Then, the palmprint features are extracted from the palmprint images. Next, they are fused together by XORing operation. The information is stored in a smart card. Finally, the original keys extraction process is the information in the smart card XOR the user's palmprint features and then decoded with convolutional and cyclic two-layer code. The experimental results and security analysis show that it can recover the original keys completely. The proposed method is more secure than a single password factor, and has higher accuracy than a single biometric factor.