Hybrid Image Processing Methods for Medical Image Examination

ISBN-13: 9780367534967 / Angielski / Twarda / 2020 / 188 str.

Canada) Lin Fuhua (Athabasca University

Opis

This book focuses on implementation of a possible Hybrid Image Examination technique for medical images describing various image thresholding and segmentation methods along with essential details, such as test image preparation, implementation of a chosen thresholding operation, evaluation of threshold image, supported by pertinent case studies.

Spis treści

Chapter 1: Introduction

1. Introduction to Disease Screening

1. Screening for blood level infection
2. Screening for skin melanoma
3. Stomach ulcer screening
4. Screening for breast abnormality
5. Screening for brain abnormality
6. Screening for the fetal growth
7. Screening for retinal abnormality
8. Screening for lung abnormality
9. Heart disease screening
10. Osteoporosis
11. Screening of COVID-19 infection

2. Medical Image Recording Procedures
3. Summary

References

Chapter 2: Image Examination

1. Clinical Image Enhancement Techniques
2. Importance of Image Enhancement
3. Introduction to Enhancement Techniques

1. Artefact removal
2. Noise removal
3. Contrast enrichment
4. Edge detection
5. Restoration
6. Colour space correction
7. Image edge smoothening

1. Recent Advancements

1. Hybrid image examination technique
2. Need for multi-level thresholding
3. Thresholding
4. Implementation and evaluation of thresholding process

2. Summary

References

Chapter 3: Image Thresholding

1. Need for Thresholding of Medical Images
2. Bi-level and Multi-level threshold
3. Common Thresholding Methods
4. Thresholding for Grey Scale and RGB Images

3.4.1 Thresholding with Between-Class Variance

3.4.2 Thresholding with Entropy Functions

5. Choice of Threshold Scheme
6. Performance Issues
7. Evaluation and Confirmation of Thresholding Technique
8. Thresholding Methods
9. Restrictions in Traditional Threshold Selection Process
10. Need for Heuristic Algorithm
11. Selection of Heuristic Algorithm

1. Particle Swarm Optimization
2. Bacterial Foraging Optimization
3. Firefly Algorithm
4. Bat Algorithm
5. Cuckoo Search
6. Social Group Optimization
7. Teaching-Learning-Based Optimization
8. Jaya Algorithm

12. Introduction to Implementation
13. Monitoring Parameter

1. Objective function
2. Single and Multiple Objective function

14. Summary

References

Chapter 4: Image Segmentation

1. Requirement of Image Segmentation
2. Extraction of Image Regions with Segmentation

1. Morphological approach
2. Circle Detection
3. Watershed algorithm
4. Seed Region Growing
5. Principal Component Analysis
6. Local Binary Pattern
7. Graph Cut approach
8. Contour Based Approach
9. CNN based segmentation

3. Assessment and Validation of Segmentation
4. Construction of Confusion Matrix
5. Summary

References

Chapter 5: Medical Image Processing with Hybrid Image Processing Method

5.1 Introduction

1. Context
2. Methodology

1. Database
2. Thresholding
3. Otsu’s function
4. Brain Storm Optimization
5. Segmentation
6. Performance evaluation and validation

3. Results and Discussion
4. Summary

References

Chapter 6: Deep Learning for Medical Image Processing

1. Introduction
2. Implementation of CNN for image assessment
3. Transfer learning concepts

1. AlexNet
2. VGG-16
3. VGG-19

4. Medical Image Examination with Deep-Learning: Case study

1. Brain abnormality detection
2. Lung abnormality detection
3. Retinal abnormality detection
4. COVID-19 lesion detection

5. Summary

References

Chapter 7: Conclusion