Muutke küpsiste eelistusi

Deep Learning for Chest Radiographs: Computer-Aided Classification [Pehme köide]

(CSIR-CSIO, Chandigarh, Institute of Engineers (IEI), India), (Professor in the Department of Computer Science & Engineering at Govind Ballabh P), (Govind Ballabh Pant Institute of Engineering and Technology, Pauri Garhwal, Uttarakhand),
  • Formaat: Paperback / softback, 228 pages, kõrgus x laius: 235x191 mm, kaal: 500 g, 60 illustrations (20 in full color); Illustrations
  • Sari: Primers in Biomedical Imaging Devices and Systems
  • Ilmumisaeg: 22-Jul-2021
  • Kirjastus: Academic Press Inc
  • ISBN-10: 0323901840
  • ISBN-13: 9780323901840
Teised raamatud teemal:
Deep Learning for Chest Radiographs: Computer-Aided ClassificationSuurem pilt
  • Formaat: Paperback / softback, 228 pages, kõrgus x laius: 235x191 mm, kaal: 500 g, 60 illustrations (20 in full color); Illustrations
  • Sari: Primers in Biomedical Imaging Devices and Systems
  • Ilmumisaeg: 22-Jul-2021
  • Kirjastus: Academic Press Inc
  • ISBN-10: 0323901840
  • ISBN-13: 9780323901840
Teised raamatud teemal:
Püsilink: https://www.kriso.ee/db/9780323901840.html
Märksõnad:

Deep Learning for Chest Radiographs enumerates different strategies implemented by the authors for designing an efficient convolution neural network-based computer-aided classification (CAC) system for binary classification of chest radiographs into "Normal" and "Pneumonia." Pneumonia is an infectious disease mostly caused by a bacteria or a virus. The prime targets of this infectious disease are children below the age of 5 and adults above the age of 65, mostly due to their poor immunity and lower rates of recovery. Globally, pneumonia has prevalent footprints and kills more children as compared to any other immunity-based disease, causing up to 15% of child deaths per year, especially in developing countries. Out of all the available imaging modalities, such as computed tomography, radiography or X-ray, magnetic resonance imaging, ultrasound, and so on, chest radiographs are most widely used for differential diagnosis between Normal and Pneumonia. In the CAC system designs implemented in this book, a total of 200 chest radiograph images consisting of 100 Normal images and 100 Pneumonia images have been used. These chest radiographs are augmented using geometric transformations, such as rotation, translation, and flipping, to increase the size of the dataset for efficient training of the Convolutional Neural Networks (CNNs). A total of 12 experiments were conducted for the binary classification of chest radiographs into Normal and Pneumonia. It also includes in-depth implementation strategies of exhaustive experimentation carried out using transfer learning-based approaches with decision fusion, deep feature extraction, feature selection, feature dimensionality reduction, and machine learning-based classifiers for implementation of end-to-end CNN-based CAC system designs, lightweight CNN-based CAC system designs, and hybrid CAC system designs for chest radiographs.

This book is a valuable resource for academicians, researchers, clinicians, postgraduate and graduate students in medical imaging, CAC, computer-aided diagnosis, computer science and engineering, electrical and electronics engineering, biomedical engineering, bioinformatics, bioengineering, and professionals from the IT industry.

  • Provides insights into the theory, algorithms, implementation, and application of deep-learning techniques for medical images such as transfer learning using pretrained CNNs, series networks, directed acyclic graph networks, lightweight CNN models, deep feature extraction, and conventional machine learning approaches for feature selection, feature dimensionality reduction, and classification using support vector machine, neuro-fuzzy classifiers
  • Covers the various augmentation techniques that can be used with medical images and the CNN-based CAC system designs for binary classification of medical images focusing on chest radiographs
  • Investigates the development of an optimal CAC system design with deep feature extraction and classification of chest radiographs by comparing the performance of 12 different CAC system designs
Preface ix
Acknowledgments xi
Chapter 1 Introduction
1(34)
1.1 Motivation
1(1)
1.2 Introduction to deep learning
2(10)
1.3 Why deep learning in medical image analysis?
12(1)
1.4 Medical imaging
13(12)
1.4.1 Features in medical images
13(6)
1.4.2 Types of medical imaging modalities for analysis of chest tissue
19(5)
1.4.3 Why chest radiographs?
24(1)
1.5 Description of normal and pneumonia chest radiographs
25(1)
1.6 Objective of the book
26(2)
1.7 Book chapter outline
28(7)
References
28(5)
Further reading
33(2)
Chapter 2 Review of related work
35(24)
2.1 Introduction
35(1)
2.2 Overview of the studies based on the classification of chest radiographs
35(20)
2.2.1 Overview of machine learning-based studies for the classification of chest radiographs
35(1)
2.2.2 Overview of deep learning-based studies for the classification of chest radiographs
36(19)
2.3 Concluding remarks
55(4)
References
55(4)
Chapter 3 Methodology adopted for designing of computer-aided classification systems for chest radiographs
59(58)
3.1 Introduction
59(1)
3.2 What is a CAC system?
59(1)
3.3 Need for CAC systems
60(1)
3.4 Need for CAC systems for chest radiographs
60(1)
3.5 Types of classifier designs for CAC systems
61(4)
3.5.1 On the basis of number output classes
62(2)
3.5.2 On the basis of learning approach
64(1)
3.6 Deep learning-based CAC system design
65(2)
3.6.1 On the basis of network connection
65(1)
3.6.2 On the basis of network architecture
66(1)
3.7 Workflow adopted in the present work
67(7)
3.8 Implementation details
74(16)
3.8.1 Hardware and software specifications
74(1)
3.8.2 MATLAB Deep Learning Toolbox
74(2)
3.8.3 Installing Pre-trained networks
76(1)
3.8.4 Key hyperparameters of deep learning-based networks
77(12)
3.8.5 Key hyperparameters of deep learning-based convolution neural networks used in the present work
89(1)
3.9 Dataset: Kaggle chest X-ray dataset
90(2)
3.10 Dataset description
92(1)
3.11 Dataset generation
93(17)
3.11.1 Preprocessing module: Image resizing
93(3)
3.11.2 Dataset bifurcation
96(2)
3.11.3 Augmentation module: Dataset augmentation
98(12)
3.12 Concluding remarks
110(7)
References
110(4)
Further reading
114(3)
Chapter 4 End-to-end pre-trained CNN-based computer-aided classification system design for chest radiographs
117(24)
4.1 Introduction
117(1)
4.2 Experimental workflow
117(1)
4.3 Transfer learning-based convolutional neural network design
117(3)
4.4 Architecture of end-to-end pre-trained CNNs used in the present work
120(4)
4.4.1 Series end-to-end pre-trained CNN model: AlexNet
120(2)
4.4.2 Directed acyclic graph end-to-end pre-trained CNN model: ResNetl8
122(1)
4.4.3 DAG end-to-end pre-trained CNN model: GoogLeNet
122(2)
4.5 Decision fusion
124(4)
4.6 Experiments and results
128(8)
4.7 Concluding remarks
136(5)
References
137(2)
Further reading
139(2)
Chapter 5 Hybrid computer-aided classification system design using end-to-end CNN-based deep feature extraction and ANFC-LH classifier for chest radiographs
141(16)
5.1 Introduction
141(1)
5.2 Experimental workflow
141(1)
5.3 Deep feature extraction
141(5)
5.3.1 GoogLeNet as a deep feature extractor
143(3)
5.4 Feature selection
146(2)
5.4.1 Correlation-based feature selection
147(1)
5.4.2 Feature selection using ANFC-LH
147(1)
5.5 Adaptive neuro-fuzzy classifier
148(1)
5.6 Experiment and result
149(1)
5.7 Concluding remarks
149(8)
References
152(5)
Chapter 6 Hybrid computer-aided classification system design using end-to-end Pre-trained CNN-based deep feature extraction and PCA-SVM classifier for chest radiographs
157(10)
6.1 Introduction
157(1)
6.2 Experimental workflow
157(1)
6.3 Deep feature extraction
157(2)
6.4 Feature selection and dimensionality reduction
159(1)
6.4.1 Correlation-based feature selection
159(1)
6.4.2 PCA-based feature dimensionality reduction
159(1)
6.5 SVM classifier
160(1)
6.6 Experiment and result
161(1)
6.7 Concluding remarks
161(6)
References
163(2)
Further reading
165(2)
Chapter 7 Lightweight end-to-end Pre-trained CNN-based computer-aided classification system design for chest radiographs
167(18)
7.1 Introduction
167(1)
7.2 Experimental workflow
167(1)
7.3 Lightweight CNN model
167(1)
7.4 Architecture of lightweight Pre-trained CNN networks used in the present work
168(4)
7.4.1 DAG lightweight end-to-end Pre-trained CNN model: SqueezeNet
168(1)
7.4.2 DAG lightweight end-to-end Pre-trained CNN model: ShuffleNet
169(1)
7.4.3 DAG lightweight end-to-end Pre-trained CNN model: MobileNetV2
169(3)
7.5 Decision fusion
172(1)
7.6 Experiments and results
172(8)
7.7 Concluding remarks
180(5)
References
181(2)
Further reading
183(2)
Chapter 8 Hybrid computer-aided classification system design using lightweight end-to-end Pre-trained CNN-based deep feature extraction and ANFC-LH classifier for chest radiographs
185(12)
8.1 Introduction
185(1)
8.2 Experimental workflow
185(1)
8.3 Deep feature extraction
185(4)
8.3.1 Lightweight MobileNetV2 CNN model as deep feature extractor
186(3)
8.4 Feature selection
189(1)
84.1 Correlation-based feature selection
189(1)
8.4.2 Feature selection using ANFC-LH
189(1)
8.5 Adaptive neuro-fuzzy classifier
190(1)
8.6 Experiment and results
191(2)
8.7 Concluding remarks
193(4)
References
193(2)
Further reading
195(2)
Chapter 9 Hybrid computer-aided classification system design using lightweight end-to-end Pre-trained CNN-based deep feature extraction and PCA-SVM classifier for chest radiographs
197(8)
9.1 Introduction
197(1)
9.2 Experimental workflow
197(1)
9.3 Deep feature extraction
197(2)
9.4 Feature selection and dimensionality reduction
199(1)
9.4.1 Correlation-based feature selection
199(1)
9.4.2 PCA-based feature dimensionality reduction
199(1)
9.5 SVM classifier
200(1)
9.6 Experiment and results
200(1)
9.7 Concluding remarks
201(4)
References
201(2)
Further reading
203(2)
Chapter 10 Comparative analysis of computer-aided classification systems designed for chest radiographs: Conclusion and future scope
205(6)
10.1 Introduction
205(1)
10.2 Conclusion: End-to-end pretrained CNN-based CAC system design for chest radiographs
205(1)
10.3 Conclusion: Hybrid CAC system design using end-to-end pretrained CNN-based deep feature extraction and ANFC-LH, PCA-SVM classifiers for chest radiographs
206(1)
10.4 Conclusion: Lightweight end-to-end pretrained CNN-based CAC system design for chest radiographs
206(1)
10.5 Conclusion: Hybrid CAC system design using lightweight end-to-end pretrained CNN-based deep feature extraction and ANFC-LH, PCA-SVM classifiers for chest radiographs
206(1)
10.6 Comparison of the different CNN-based CAC systems designed in the present work for the binary classification of chest radiographs
206(2)
10.7 Future scope
208(3)
Index 211
Yashvi Chandola received her B-Tech (Hons.) in Computer Science and Engineering from Women Institute of Technology, Dehradun, Uttarakhand in 2018. She has completed her M-Tech (Hons.) in Computer Science and Engineering from Govind Ballabh Pant Institute of Engineering and Technology, Pauri Garhwal, Uttarakhand in 2020. Her research interests include application of machine learning and deep learning algorithms for analysis of medical images. Jitendra Virmani received his B-Tech (Hons.) in Instrumentation Engineering from Sant Longowal Institute of Engineering and Technology, Punjab in 1999 and M-Tech in Electrical Engineering with specialization in Measurement and Instrumentation from the Indian Institute of Technology, Roorkee in 2006. He served in the academia for nine years before joining the PhD programme in 2009 at Biomedical Instrumentation Laboratory, Electrical Engineering Department, Indian Institute of Technology, Roorkee as a full time Research Scholar under MHRD Assistantship. He received his PhD from the Indian Institute of Technology, Roorkee in 2013. After his PhD he served in Academia for Jaypee University of Information Technology, Solan, Himachal Pradesh and Thapar Institute of Engineering and Technology, Patiala, Punjab before joining CSIR-CSIO, Chandigarh in August 2016. He is presently working at CSIR-CSIO, Chandigarh. He is a Life member of the Institute of Engineers (IEI), India and Computer Society of India. He has published 85 papers in various journals, conferences and Book chapters with various reputed publishers. He has delivered more than 35 expert talks on various platforms basically on application of machine learning and deep learning algorithms for medical images. He is Editorial Board Member of International Journal of Image Mining published by Inderscience Publishers. His research interests include application of machine learning and deep learning algorithms for analysis of medical images. H.S Bhadauria received his B-Tech in Computer Science and Engineering from Aligarh Muslim University, Aligarh in 1999, and M-Tech in Electronics Engineering from Aligarh Muslim University, Aligarh in 2004. He received his PhD on Detection and Segmentation of Brain Hemorrhage using CT images from Biomedical Signal and Image Processing Laboratory, Indian Institute of Technology - Roorkee in 2013. During his PhD he worked on enhancing the detection and segmentation of brain hemorrhage using CT imaging modality. He has served in academia for more than 12 years. He is presently serving as a Professor in the Department of Computer Science & Engineering at Govind Ballabh Pant Institute of Engineering and Technology, Pauri Garhwal, Uttarakhand. He is a life member of Institute of Engineers (IEI), India. He has published more than 60 research papers in International and National Journals and Conferences. His areas of research interest are Digital Image and Digital Signal Processing. Papendra Kumar received his B.E in Computer Science and Engineering from Govind Ballabh Pant Institute of Engineering and Technology, Pauri Garhwal, Uttarakhand in 2007 and M-Tech in Digital Signal Processing from Govind Ballabh Pant Institute of Engineering and Technology, Pauri Garhwal, Uttarakhand in 2011. He is presently serving as an Assistant Professor in the Department of Computer Science & Engineering at Govind Ballabh Pant Institute of Engineering and Technology, Pauri Garhwal, Uttarakhand. His areas of research interest are Digital Image and Digital Signal Processing.