In view of better results expected from examination of medical datasets (images) with hybrid (integration of thresholding and segmentation) image processing methods, this work focuses on implementation of possible hybrid image examination techniques for medical images. It describes various image thresholding and segmentation methods which are essential for the development of such a hybrid processing tool. Further, this book presents the essential details, such as test image preparation, implementation of a chosen thresholding operation, evaluation of threshold image, and implementation of segmentation procedure and its evaluation, supported by pertinent case studies. Aimed at researchers/graduate students in the medical image processing domain, image processing, and computer engineering, this book: Provides broad background on various image thresholding and segmentation techniques Discusses information on various assessment metrics and the confusion matrix Proposes integration of the thresholding technique with the bio-inspired algorithms Explores case studies including MRI, CT, dermoscopy, and ultrasound images Includes separate chapters on machine learning and deep learning for medical image processing
Author(s): Venkatesan Rajinikanth; E Priya; Hong Lin; Fuhua Lin
Publisher: CRC Press
Year: 2021
Language: English
Pages: 188
City: Boca Raton
Cover
Half Title
Series Page
Title Page
Copyright Page
Contents
Preface
Authors
1. Introduction
1.1. Introduction to Disease Screening
1.1.1. Screening of Blood Sample
1.1.2. Screening for Skin Melanoma
1.1.3. Stomach Ulcer Screening
1.1.4. Screening for Breast Abnormality
1.1.5. Screening for Brain Abnormality
1.1.6. Screening for the Fetal Growth
1.1.7. Screening for Retinal Abnormality
1.1.8. Screening for Lung Abnormality
1.1.9. Heart Disease Screening
1.1.10. Osteoporosis
1.1.11. Screening of COVID-19 Infection
1.2. Medical Image Recording Procedures
1.3. Summary
References
2. Image Examination
2.1. Clinical Image Enhancement Techniques
2.2. Importance of Image Enhancement
2.3. Introduction to Enhancement Techniques
2.3.1. Artifact Removal
2.3.2. Noise Removal
2.3.3. Contrast Enrichment
2.3.4. Edge Detection
2.3.5. Restoration
2.3.6. Color Space Correction
2.3.7. Image Edge Smoothing
2.4. Recent Advancements
2.4.1. Hybrid Image Examination Technique
2.4.2. Need for Multi-Level Thresholding
2.4.3. Thresholding
2.4.4. Implementation and Evaluation of Thresholding Process
2.5. Summary
References
3. Image Thresholding
3.1. Need for Thresholding of Medical Images
3.2. Bi-Level and Multi-Level Threshold
3.3. Common Thresholding Methods
3.4. Thresholding for Greyscale and RGB Images
3.4.1. Thresholding with Between-Class Variance
3.4.2. Thresholding with Entropy Functions
3.5. Choice of Threshold Scheme
3.6. Performance Issues
3.7. Evaluation and Confirmation of Thresholding Technique
3.8. Thresholding Methods
3.9. Restrictions in Traditional Threshold Selection Process
3.10. Need for Heuristic Algorithm
3.11. Selection of Heuristic Algorithm
3.11.1. Particle Swarm Optimization
3.11.2. Bacterial Foraging Optimization
3.11.3. Firefly Algorithm
3.11.4. Bat Algorithm
3.11.5. Cuckoo Search
3.11.6. Social Group Optimization
3.11.7. Teaching-Learning-Based Optimization
3.11.8. Jaya Algorithm
3.12. Introduction to Implementation
3.13. Monitoring Parameter
3.13.1. Objective Function
3.13.2. Single and Multiple Objective Function
3.14. Summary
References
4. Image Segmentation
4.1. Requirement of Image Segmentation
4.2. Extraction of Image Regions with Segmentation
4.2.1. Morphological Approach
4.2.2. Circle Detection
4.2.3. Watershed Algorithm
4.2.4. Seed Region Growing
4.2.5. Principal Component Analysis
4.2.6. Local Binary Pattern
4.2.7. Graph Cut Approach
4.2.8. Contour-Based Approach
4.2.9. CNN-Based Segmentation
4.2.9.1 HRNet
Multi-Resolution Sequential Sub-Network
Multi-Resolution Parallel Sub-Network
Multi-Scale Repeated Fusion
4.2.9.2 SegNet
4.2.9.3 UNet
4.2.9.4 VGG UNet
4.3. Assessment and Validation of Segmentation
4.4. Construction of Confusion Matrix
4.5. Summary
References
5. Medical Image Processing with Hybrid Image Processing Method
5.1. Introduction
5.2. Context
5.3. Methodology
5.3.1. Database
5.3.2. Thresholding
5.3.3. Otsu's Function
5.3.4. Brain Storm Optimization
5.3.5. Segmentation
5.3.6. Performance Evaluation and Validation
5.4. Results and Discussion
5.5. Summary
References
6. Deep Learning for Medical Image Processing
6.1. Introduction
6.2. Implementation of CNN for Image Assessment
6.3. Transfer Learning Concepts
6.3.1. AlexNet
6.3.2. VGG-16
6.3.3. VGG-19
6.4. Medical Image Examination with Deep-Learning: Case Study
6.4.1. Brain Abnormality Detection
6.4.2. Lung Abnormality Detection
6.4.3. Retinal Abnormality Detection
6.4.4. COVID-19 Lesion Detection
6.5. Summary
References
7. Conclusion
Index
