Data Driven Approaches on Medical Imaging

Preface
Contents
Introduction of Medical Imaging Modalities
	1 Introduction
	2 Background Study
	3 Methodology
	4 Definition of Medical Imaging
	5 Overview of Different Modalities
		5.1 X-ray Imaging
		5.2 Computed Tomography (CT) Imaging
		5.3 Magnetic Resonance Imaging (MRI)
		5.4 Ultrasound Imaging
		5.5 Nuclear Medicine Imaging
		5.6 Electrical Impedance Tomography (EIT)
		5.7 Cardiovascular Imaging
	6 X-ray Imaging
		6.1 Basic Principles
		6.2 Typical Clinical Applications
	7 Computed Tomography (CT) Imaging
		7.1 Basic Principles
		7.2 Typical Clinical Applications
	8 MRI and Magnetic Resonance Microscopy (MRM)
		8.1 Basic Principles
		8.2 Typical Clinical Applications
	9 Nuclear Imaging
		9.1 Basic Principles
		9.2 Typical Clinical Applications
	10 Ultrasound Imaging
		10.1 Basic Principles
		10.2 Typical Clinical Applications
	11 Emerging Technologies for In Vivo Imaging
		11.1 Electrical Impedance Tomography (EIT)
			11.1.1 Basic Principles
			11.1.2 Limited Typical Clinical Usage
		11.2 Advancements and New Modalities
	12 Comparative Analysis
	13 Specialized Techniques
		13.1 Contrast-Enhanced MRI
		13.2 MR Approaches for Osteoarthritis
		13.3 Cardiovascular Imaging
		13.4 Medical Imaging Data Mining and Search
	14 Discussion and Conclusion
	Declaration
	References
Introduction to Medical Imaging Informatics
	1 Introduction
	2 Literature Review
	3 Medical Imaging Informatics
		3.1 Types of Medical Imaging Modalities
		3.2 Image Storage and Retrieval
		3.3 Image Analysis and Interpretation
	4 Image Processing
	5 Feature Engineering
	6 Machine Learning
		6.1 How Machine Learning Model Learn
		6.2 Types of Machine Learning
			6.2.1 Supervised Learning
			6.2.2 Unsupervised Learning
			6.2.3 Reinforcement Learning
		6.3 Limitations of Machine Learning
	7 Deep Learning
		7.1 How the Deep Learning Model Learns
		7.2 Different Types of Deep Learning Models
		7.3 Limitations of Deep Learning
	8 Importance of Data in Machine Learning and Deep Learning
	9 Recent Advancements in Computer Vision
		9.1 Deep Learning
		9.2 Transfer Learning
		9.3 Generative Adversarial Networks (GANs)
		9.4 Computer Vision in Robotics
		9.5 Augmented Reality (AR)
		9.6 Video Analysis
		9.7 Medical Image Analysis
	10 Conclusion and Future Direction
	Declaration
	References
Active Learning on Medical Image
	1 Introduction
	2 Literature Review
		2.1 Machine Learning in the Context of Medical Images
		2.2 Deep Learning in the Context of Medical Images
		2.3 Issue of Inadequately Labeled Medical Data
		2.4 Active Learning Concept for Medical Images
			2.4.1 General Algorithm
	3 Methodology
		3.1 Case Description with Dataset Information
		3.2 MRI Pre-processing
		3.3 Framework for Active Learning Based on Transfer Learning Knowledge
		3.4 Case Report and Analysis
	4 Conclusion
	Declaration
	References
Few Shot Learning for Medical Imaging: A Comparative Analysis of Methodologies and Formal Mathematical Framework
	1 Introduction
	2 Related Work
	3 Overview of Few Shots Learning
		3.1 Important Terms of Few-Shot Learning
	4 Few Shot Learning Classification-Based Algorithm
		4.1 Prototypical Networks
		4.2 Matching Networks
		4.3 Relational Networks
		4.4 Model-Agnostic Meta-learning
	5 Formal Mathematical Statements of Few Shot Learning Problems
		5.1 Problem 1 (Learning from New Examples)
		5.2 Solution of Problem 1 with Theorem
		5.3 Problem 2 (Learning from New Class)
		5.4 Solution of Problem 2 with Theorem
	6 Future Scope
	7 Conclusion
	Declaration
	References
Automl Systems for Medical Imaging
	1 Introduction
		1.1 New Hope
		1.2 Outline of the Chapter
	2 Background Study and Motivation
		2.1 Medical Image
		2.2 AutoML
			2.2.1 Automated Feature Engineering
			2.2.2 Automated Hyperparameter Optimization
			2.2.3 Neural Architecture Search (NAS)
		2.3 Why AutoML Over Traditional ML
	3 Application of AutoML in Medical Image
		3.1 Helps in Medical Diagnosis
		3.2 Machine Learning in Decision Making
		3.3 Personalized Medicine
		3.4 To Reduce the Risk of a Virus
		3.5 Medical Image Segmentation
		3.6 Medical Image Registration
		3.7 Medical Image Synthesis
		3.8 Medical Image Augmentation
		3.9 Generative Adversarial Networks (GANs)
	4 Challenges and Future Directions of Automatic Machine Learning in Medical Image
		4.1 The Availability and Quality of Data
		4.2 Data Privacy, Security, and Legal Issue
		4.3 Heterogeneity of Medical Imaging Data
		4.4 Lack of Existing Algorithms
		4.5 Understanding the Model
		4.6 Evaluation of Prediction Accuracy
		4.7 Algorithm Transparency
	5 Future Prospective and Unanswered Questions About Medical Image and AutoML
		5.1 Integration with Clinical Workflow
		5.2 Improve Model Performance
		5.3 Data Privacy and Ethics
		5.4 Integration with Other Technologies
	6 Conclusion
	Declaration
	References
Online Learning for X-Ray, CT or MRI
	1 Introduction
	2 Related Works
	3 Methodology
		3.1 Image Processing
		3.2 Machine Learning
		3.3 Deep Learning
			3.3.1 Custom CNN
			3.3.2 Transfer Learning
			3.3.3 CNN-ML
	4 Performance Analysis
	5 Conclusion
	Declaration
	References
Invariant Scattering Transform for Medical Imaging
	1 Introduction
	2 IST Background
		2.1 Signal Processing
		2.2 Challenges in Medical Image Processing and IST Solutions
		2.3 Key Steps and Process to Apply IST in Medical Imaging
		2.4 IST Parameters and Settings: Impact on Performance
		2.5 IST for Medical Image Segmentation, Classification, and Registration
		2.6 Dataset
	3 Related Work
	4 Discussions and Future Research Directions
	5 Conclusion
	Declaration
	References
Generative Adversarial Networks for Data Augmentation
	1 Introduction
	2 Literature Review
		2.1 Artificial Intelligence in the Context of Medical Images
		2.2 Issue of Scarcity of Medical Data
		2.3 Data Augmentation
		2.4 Concept of General Adversarial Network
		2.5 GAN Concept for Medical Images
	3 Methodology
		3.1 Data Collection
		3.2 MRI Pre-processing
		3.3 Workflow of GAN for Data Augmentation
			3.3.1 General Algorithm
		3.4 The Process of Data Augmentation Using GAN
		3.5 Data Augmentation Using Variational Auto-Encoders (VAEs)
		3.6 Result Analysis
	4 Conclusion
	Declaration
	References
Bias, Ethical Concerns, and Explainable Decision-Making in Medical Imaging Research
	1 Introduction
	2 Bias in Medical Imaging Research
		2.1 Acquisition Bias
		2.2 Processing Bias
		2.3 Interpretation Bias
		2.4 Patient-Related Bias
	3 Classification of Bias
		3.1 Spectrum Bias
		3.2 Verification Bias
		3.3 Reader Bias
		3.4 Prevalence Bias
		3.5 Interpretation Bias
		3.6 Selection Bias
		3.7 Information Bias
		3.8 Recall Bias
		3.9 Publication Bias
		3.10 Cognitive Bias
		3.11 Classification Bias
		3.12 Confounding Bias
	4 Addressing Fairness in for Medical Imaging
		4.1 Equitable and Inequitable Biases in Medical Imaging
		4.2 Qualitative and Quantitative Biases in Medical Imaging
	5 Ethical Concerns of Medical Imaging
		5.1 Privacy and Confidentiality
		5.2 Radiation Exposure
		5.3 Informed Consent
		5.4 Bias and Equity
		5.5 Resource Allocation
	6 Importance of Ethical Concern in Medical Imaging
		6.1 Factors of Ethical Concern in Medical Imaging
	7 Explainable Decision-Making in Medical Imaging Research
		7.1 The Importance of Explainable Decision-Making
		7.2 The Factors Contributing to Explainable Decision-Making in Medical Imaging
	8 Conclusions
	Declaration
	References
Case Studies on X-ray Imaging, MRI and Nuclear Imaging
	1 Introduction
	2 Background Study and Related Works
		2.1 Medical Imaging and Essential Study in Medical Science
			2.1.1 Medical Imaging
			2.1.2 X-ray in Medical Science
			2.1.3 MRI in Medical Science
			2.1.4 Nuclear Imaging in Medical Science
	3 Materials and Methodology of Study
		3.1 X-ray
			3.1.1 Materials
			3.1.2  Methodology
		3.2 MRI
			3.2.1 Materials
			3.2.2 Methodology
		3.3 Nuclear Imaging
	4 Result and Analysis
	5 Conclusion
	Declaration
	References
Index