The Experts below are selected from a list of 27 Experts worldwide ranked by ideXlab platform
Ren Jinchang - One of the best experts on this subject based on the ideXlab platform.
-
Breast cancer detection using deep convolutional neural networks and support vector machines
'PeerJ', 2019Co-Authors: Ragab, Dina A., Sharkas Maha, Marshall Stephen, Ren JinchangAbstract:It is important to detect breast cancer as early as possible. In this manuscript, a new methodology for classifying breast cancer using deep learning and some segmentation techniques are introduced. A new computer aided detection (CAD) system is proposed for classifying benign and malignant mass tumors in breast mammography images. In this CAD system, two segmentation approaches are used. The first approach involves determining the region of interest (ROI) manually, while the second approach uses the technique of threshold and region based. The deep convolutional neural network (DCNN) is used for feature extraction. A well-known DCNN architecture named AlexNet is used and is fine-tuned to classify two classes instead of 1000 classes. The last fully connected (fc) layer is connected to the support vector machine (SVM) classifier to obtain better accuracy. The results are obtained using the following publicly available datasets (1) the digital database for screening mammography (DDSM); and (2) the Curated Breast Imaging Subset of DDSM (CBIS-DDSM). Training on a large number of data gives high accuracy rate. Nevertheless, the biomedical datasets contain a relatively small number of samples due to limited patient volume. Accordingly, data augmentation is a method for increasing the size of the input data by generating new data from the original input data. There are many forms for the data augmentation; the one used here is the rotation. The accuracy of the new-trained DCNN architecture is 71.01% when cropping the ROI manually from the mammogram. The highest area under the curve (AUC) achieved was 0.88 (88%) for the samples obtained from both segmentation techniques. Moreover, when using the samples obtained from the CBIS-DDSM, the accuracy of the DCNN is increased to 73.6%. Consequently, the SVM accuracy becomes 87.2% with an AUC equaling to 0.94 (94%). This is the highest AUC value compared to previous work using the same conditions
Ragab, Dina A. - One of the best experts on this subject based on the ideXlab platform.
-
Breast cancer detection using deep convolutional neural networks and support vector machines
'PeerJ', 2019Co-Authors: Ragab, Dina A., Sharkas Maha, Marshall Stephen, Ren JinchangAbstract:It is important to detect breast cancer as early as possible. In this manuscript, a new methodology for classifying breast cancer using deep learning and some segmentation techniques are introduced. A new computer aided detection (CAD) system is proposed for classifying benign and malignant mass tumors in breast mammography images. In this CAD system, two segmentation approaches are used. The first approach involves determining the region of interest (ROI) manually, while the second approach uses the technique of threshold and region based. The deep convolutional neural network (DCNN) is used for feature extraction. A well-known DCNN architecture named AlexNet is used and is fine-tuned to classify two classes instead of 1000 classes. The last fully connected (fc) layer is connected to the support vector machine (SVM) classifier to obtain better accuracy. The results are obtained using the following publicly available datasets (1) the digital database for screening mammography (DDSM); and (2) the Curated Breast Imaging Subset of DDSM (CBIS-DDSM). Training on a large number of data gives high accuracy rate. Nevertheless, the biomedical datasets contain a relatively small number of samples due to limited patient volume. Accordingly, data augmentation is a method for increasing the size of the input data by generating new data from the original input data. There are many forms for the data augmentation; the one used here is the rotation. The accuracy of the new-trained DCNN architecture is 71.01% when cropping the ROI manually from the mammogram. The highest area under the curve (AUC) achieved was 0.88 (88%) for the samples obtained from both segmentation techniques. Moreover, when using the samples obtained from the CBIS-DDSM, the accuracy of the DCNN is increased to 73.6%. Consequently, the SVM accuracy becomes 87.2% with an AUC equaling to 0.94 (94%). This is the highest AUC value compared to previous work using the same conditions
Marshall Stephen - One of the best experts on this subject based on the ideXlab platform.
-
Breast cancer detection using deep convolutional neural networks and support vector machines
'PeerJ', 2019Co-Authors: Ragab, Dina A., Sharkas Maha, Marshall Stephen, Ren JinchangAbstract:It is important to detect breast cancer as early as possible. In this manuscript, a new methodology for classifying breast cancer using deep learning and some segmentation techniques are introduced. A new computer aided detection (CAD) system is proposed for classifying benign and malignant mass tumors in breast mammography images. In this CAD system, two segmentation approaches are used. The first approach involves determining the region of interest (ROI) manually, while the second approach uses the technique of threshold and region based. The deep convolutional neural network (DCNN) is used for feature extraction. A well-known DCNN architecture named AlexNet is used and is fine-tuned to classify two classes instead of 1000 classes. The last fully connected (fc) layer is connected to the support vector machine (SVM) classifier to obtain better accuracy. The results are obtained using the following publicly available datasets (1) the digital database for screening mammography (DDSM); and (2) the Curated Breast Imaging Subset of DDSM (CBIS-DDSM). Training on a large number of data gives high accuracy rate. Nevertheless, the biomedical datasets contain a relatively small number of samples due to limited patient volume. Accordingly, data augmentation is a method for increasing the size of the input data by generating new data from the original input data. There are many forms for the data augmentation; the one used here is the rotation. The accuracy of the new-trained DCNN architecture is 71.01% when cropping the ROI manually from the mammogram. The highest area under the curve (AUC) achieved was 0.88 (88%) for the samples obtained from both segmentation techniques. Moreover, when using the samples obtained from the CBIS-DDSM, the accuracy of the DCNN is increased to 73.6%. Consequently, the SVM accuracy becomes 87.2% with an AUC equaling to 0.94 (94%). This is the highest AUC value compared to previous work using the same conditions
Sharkas Maha - One of the best experts on this subject based on the ideXlab platform.
-
Breast cancer detection using deep convolutional neural networks and support vector machines
'PeerJ', 2019Co-Authors: Ragab, Dina A., Sharkas Maha, Marshall Stephen, Ren JinchangAbstract:It is important to detect breast cancer as early as possible. In this manuscript, a new methodology for classifying breast cancer using deep learning and some segmentation techniques are introduced. A new computer aided detection (CAD) system is proposed for classifying benign and malignant mass tumors in breast mammography images. In this CAD system, two segmentation approaches are used. The first approach involves determining the region of interest (ROI) manually, while the second approach uses the technique of threshold and region based. The deep convolutional neural network (DCNN) is used for feature extraction. A well-known DCNN architecture named AlexNet is used and is fine-tuned to classify two classes instead of 1000 classes. The last fully connected (fc) layer is connected to the support vector machine (SVM) classifier to obtain better accuracy. The results are obtained using the following publicly available datasets (1) the digital database for screening mammography (DDSM); and (2) the Curated Breast Imaging Subset of DDSM (CBIS-DDSM). Training on a large number of data gives high accuracy rate. Nevertheless, the biomedical datasets contain a relatively small number of samples due to limited patient volume. Accordingly, data augmentation is a method for increasing the size of the input data by generating new data from the original input data. There are many forms for the data augmentation; the one used here is the rotation. The accuracy of the new-trained DCNN architecture is 71.01% when cropping the ROI manually from the mammogram. The highest area under the curve (AUC) achieved was 0.88 (88%) for the samples obtained from both segmentation techniques. Moreover, when using the samples obtained from the CBIS-DDSM, the accuracy of the DCNN is increased to 73.6%. Consequently, the SVM accuracy becomes 87.2% with an AUC equaling to 0.94 (94%). This is the highest AUC value compared to previous work using the same conditions
Dave Shreiner - One of the best experts on this subject based on the ideXlab platform.
-
OpenGL Reference Manual: The Official Reference Document to OpenGL, Version 1.2
1999Co-Authors: Dave ShreinerAbstract:From the Publisher: OpenGL is a powerful software interface used to produce high-quality computer generated images and interactive graphics applications by rendering 2D and 3D geometric objects, bitmaps, and color images. Officially sanctioned by the OpenGL Architecture Review Board (ARB), the OpenGL® Reference Manual, Third Edition, is the comprehensive and definitive documentation of all OpenGL functions. This third edition covers OpenGL Version 1.2, including its newest features: 3D texture mapping; multitexturing; mipmapped texture level-of-detail control; new pixel storage formats, including packed and reversed (BGRA) formats; rescaling vertex normals; and specular lighting after texturing. In addition, this book documents the newest routines in the OpenGL Utility Library (GLU 1.3) and added functionality in the OpenGL extension to the X Window System (GLX 1.3). The comprehensive reference section documents each set of related OpenGL commands. Each reference page contains: A description of the command's parameters The effects on rendering and the OpenGL state by the command Examples Errors generated by functions References to related functions This book also includes a conceptual overview of OpenGL, a summary of commands and routines, a chapter on defined constants and associated commands, and a description of the ARB extensions, including multitexture and the Imaging Subset. The OpenGL Technical Library provides tutorial and reference books for OpenGL. The Library enables programmers to gain a practical understanding of OpenGL and shows them how to unlock its full potential. Originallydeveloped by SGI, the Library continues to evolve under the auspices of the Architecture Review Board (ARB), an industry consortium responsible for guiding the evolution of OpenGL and related technologies. The OpenGL ARB is composed of industry leaders, such as 3Dlabs, Compaq, Evans & Sutherland, Hewlett-Packard, IBM, Intel, Intergraph, Microsoft, NVIDIA, and SGI. The OpenGL® Reference Manual, Third Edition, has been completely revised and updated for OpenGL, Version 1.2, by Dave Shreiner, in collaboration with the ARB. 0201657651B04062001
-
OpenGL Programming Guide: The Official Guide to Learning OpenGL, Version 1.2
1999Co-Authors: Mason Woo, Jackie Neider, Tom Davis, Dave ShreinerAbstract:From the Publisher: OpenGL is a powerful software interface used to produce high-quality computer generated images and interactive applications using 2D and 3D objects and color bitmaps and images. The OpenGL Programming Guide, Third Edition, provides definitive and comprehensive information on OpenGL and the OpenGL Utility Library. This book discusses all OpenGL functions and their syntax shows how to use those functions to create interactive applications and realistic color images. You will find clear explanations of OpenGL functionality and many basic computer graphics techniques such as building and rendering 3D models; interactively viewing objects from different perspective points; and using shading, lighting, and texturing effects for greater realism. In addition, this book provides in-depth coverage of advanced techniques, including texture mapping, antialiasing, fog and atmospheric effects, NURBS, image processing, and more. The text also explores other key topics such as enhancing performance, OpenGL extensions, and cross-platform techniques. This third edition has been extensively updated to include the newest features of OpenGL, Version 1.2, including: 3D texture mapping Multitexturing New pixel storage formats, including packed and reversed (BGRA) formats Specular lighting after texturing The OpenGL Imaging Subset New GLU routines and functionality Numerous code examples are provided to practical programming techniques. The color plate section illustrates the power and sophistication of the newest version of OpenGL. The OpenGL Technical Library provides tutorial and reference books for OpenGL. The library enables programmers to gain a practical understanding of OpenGL and shows them how to unlock its full potential. The OpenGL Technical Library was originally developed by SGI and continues to evelove under the auspices of the Architecture Review Board (ARB), an industry consortium responsible for guiding the evolution of OpenGL and related technologies. The OpenGL ARB is composed of industry leaders, such as 3Dlabs, Compaq, Evans & Sutherland, Hewlett-Packard, IBM, Intel, Intergraph, Microsoft, NVIDIA, and SGI. The OpenGL Programming Guide, Third Edition was written by Mason Woo, Jackie Neider, Tom Davis, and Dave Shreiner.
