Artificial Intelligence Applications for Health Care

Cover
Half Title
Title Page
Copyright Page
Dedication
Contents
Foreword
Preface
Acknowledgement
Editors Biographies
Contributors
1. A Survey of Machine Learning in Healthcare
	1.1 Introduction
	1.2 Artificial Intelligence
		1.2.1 Machine Learning
			1.2.1.1 Steps in Developing an ML System
			1.2.1.2 Types of Machine Learning
		1.2.2 Deep Learning
		1.2.3 The Major Types of DL
	1.3 Applications of ML in Healthcare
		1.3.1 Cardiovascular Diseases
		1.3.2 Medical Imaging
		1.3.3 Drug Discovery/Manufacturing
		1.3.4 Electronic Health Records
		1.3.5 Clinical Decision Support System
		1.3.6 Surgical Robotics
		1.3.7 Precision Medicine
		1.3.8 Population Health Management
		1.3.9 mHealth and Smart Devices
		1.3.10 AI for Tackling Pandemic
	1.4 ML Use Cases in Healthcare
	1.5 Limitations and Challenges in Adoption of AI in Healthcare
	1.6 Conclusion
	Acknowledgements
	References
2. A Review on Biomedical Signals with Fundamentals of Digital Signal Processing
	2.1 Introduction
	2.2 Biomedical Signals
		2.2.1 Electrocardiogram (ECG) Signal
			2.2.1.1 ECG Terminology and Recording
			2.2.1.2 Different Types of Recording Techniques
			2.2.1.3 ECG Processing
			2.2.1.4 Common Problems
			2.2.1.5 Common ECG Applications
			2.2.1.5.1 Review of Recent and New Applications of ECG
		2.2.2 Electroencephalogram (EEG) Signal
			2.2.2.1 Basic Terminology and Recording
			2.2.2.2 Types of EEG Signals
			2.2.2.3 EEG Processing
			2.2.2.4 Common Problems
			2.2.2.5 EEG Applications
		2.2.3 Electromyography (EMG)
			2.2.3.1 EMG Signal Recording
			2.2.3.2 EMG Signal Processing
			2.2.3.3 Common Problems
			2.2.3.4 EMG Applications
		2.2.4 Electro-Oculogram (EOG)
			2.2.4.1 EOG Signal Recording
			2.2.4.2 EOG Processing
			2.2.4.3 Common Problems
			2.2.4.4 Applications of EOG Signal
	References
3. Images in Radiology: Concepts of Image Acquisition and the Nature of Images
	3.1 Introduction
	3.2 Radiography
	3.3 Ultrasonography
	3.4 Computed Tomography
		3.4.1 Noncontrast and Contrast-Enhanced CT
		3.4.2 High-Resolution CT
		3.4.3 CT Angiography/Venography
		3.4.4 Cardiac CT/Coronary CT Angiography
		3.4.5 CT Perfusion
	3.5 Magnetic Resonance Imaging (MRI)
		3.5.1 Contrast-Enhanced MRI
		3.5.2 MRI Perfusion
		3.5.3 MR Spectroscopy
		3.5.4 Diffusion-Weighted and Diffusion Tensor MRI
		3.5.5 Cardiac MRI
	3.6 Digital Subtraction Angiography
	3.7 Conclusion
	References
4. Fundamentals of Artificial Intelligence and Computational Intelligence Techniques with Their Applications in Healthcare Systems
	4.1 Introduction
	4.2 Healthcare Data
		4.2.1 Clinical Data
			4.2.1.1 Image Data
			4.2.1.2 Signal Data
		4.2.2 Omics Data
			4.2.2.1 Genomic Data
			4.2.2.2 Transcriptomic Data
			4.2.2.3 Proteomic Data
	4.3 Diseases Targeted by AI
	4.4 Computational Intelligence Techniques and Their Applications
		4.4.1 Artificial Neural Network
		4.4.2 Evolutionary Computation
		4.4.3 Fuzzy Systems
	4.5 No-Code AI Tools
	4.6 Performance Parameters
	4.7 Challenges
	4.8 Conclusion
	References
5. Machine Learning Approach with Data Normalization Technique for Early Stage Detection of Hypothyroidism
	5.1 Introduction
		5.1.1 Related Work
	5.2 Material and Methods
		5.2.1 System Framework
		5.2.2 Hypothyroid Disease (HD) Dataset
		5.2.3 Min-Max Scaler Technique
		5.2.4 ML Classifiers
		5.2.5 Performance Measures
	5.3 Results
	5.4 Discussions
	5.5 Conclusion
	References
6. GPU-based Medical Image Segmentation: Brain MRI Analysis Using 3D Slicer
	6.1 Introduction
	6.2 Related Works
	6.3 Image Segmentation Techniques
		6.3.1 Seeded Region Growing
		6.3.2 Watershed
		6.3.3 Level Set Approaches/Methods
		6.3.4 Active Contours
	6.4 GPU Segmentation Demonstration: NVIDIA AIAA
	6.5 Conclusion
	References
7. Preliminary Study of Retinal Lesions Classification on Retinal Fundus Images for the Diagnosis of Retinal Diseases
	7.1 Introduction
	7.2 Retinal Imaging Modalities
	7.3 Fundus Imaging
		7.3.1 Fundus Image Formation
	7.4 Eye Anatomy and Retinal Diseases
		7.4.1 Normal Retina
		7.4.2 Retinal Lesions Associated with Various Retinal Diseases
			7.4.2.1 Dark Lesions
			7.4.2.2 Microaneurysms
			7.4.2.3 Haemorrhages
			7.4.2.4 Bright Lesions
			7.4.2.5 Exudates
			7.4.2.6 Cotton Wool Spots
	7.5 Need and Challenges in Computer Aided Retinal Diseases Detection Method
	7.6 Need and Challenges in Retinal Image Enhancement
	7.7 Need and Challenges in Characterization of Anatomical Structures and Lesions
		7.7.1 Segmentation of Retinal Blood Vasculature
		7.7.2 Detection of Optic Disk
		7.7.3 Segmentation of Retinal Lesions
	7.8 Need and Challenges in Computer Aided Classification and Grading Method
	7.9 Conclusion
	References
8. Automatic Screening of COVID-19 Based on CT Scan Images Through Extreme Gradient Boosting
	8.1 Introduction
	8.2 Methodology
		8.2.1 Traditional Methods
		8.2.2 Proposed Method
			8.2.2.1 Histogram of Oriented Gradients (HOG) Features
			8.2.2.2 Local Binary Pattern (LBP) Features
			8.2.2.3 KAZE Features
			8.2.2.4 SIFT Features
			8.2.2.5 Speeded Up Robust Features (SURF)
			8.2.2.6 Normalization
			8.2.2.7 Principal Component Analysis (PCA)
		8.2.3 Datasets Used
		8.2.4 Experiments Performed
			8.2.4.1 Adaboost
			8.2.4.2 Bagging
			8.2.4.3 k-Nearest Neighbor
			8.2.4.4 Naïve Bayesian Classification
			8.2.4.5 Random Forest
			8.2.4.6 Support Vector Machine (SVM)
			8.2.4.7 Extreme Gradient Boosting (XGB)
	8.3 Results
		8.3.1 Comparative Study
	8.4 Conclusion and Future Works
	References
9. Investigations on Convolutional Neural Network in Classification of the Chest X-Ray Images for COVID-19 and Pneumonia
	9.1 Introduction
	9.2 Dataset and Processing
	9.3 Methodology
	9.4 Results
	9.5 Conclusion
	References
10. Improving the Detection of Abdominal and Mediastinal Lymph Nodes in CT Images Using Attention U-Net Based Deep Learning Model
	10.1 Introduction
	10.2 Methodology
		10.2.1 Dataset Details
	10.3 Training Configuration and Experimental Setup
	10.4 Results
	10.5 Discussions
	10.6 Conclusion and Future Work
	10.7 Future Work
	References
11. Swarm Optimized Hybrid Layer Decomposition and Reconstruction Model for Multi-Modal Neurological Image Fusion
	11.1 Introduction
	11.2 Methodology
		11.2.1 Hybrid Layer Decomposition
		11.2.2 Whale Optimization Algorithm
		11.2.3 Proposed Method
		11.2.4 Dataset
		11.2.5 Experiments Performed
		11.2.6 Performance Metrics
	11.3 Results and Discussions
		11.3.1 Performance Comparison of Source and Fused Images
		11.3.2 Performance Comparison for Anatomical-Anatomical Image Fusion
		11.3.3 Performance Comparison for Anatomical-Functional Image Fusion
	11.4 Conclusion
	References
12. Hybrid Seeker Optimization Algorithm-based Accurate Image Clustering for Automatic Psoriasis Lesion Detection
	12.1 Introduction
	12.2 Methodology
		12.2.1 Database
		12.2.2 Seeker Optimization Algorithm
		12.2.3 Hybrid Seeker Optimization Algorithm (HSOA)
		12.2.4 Post Processing
	12.3 Results
		12.3.1 Experimental Results
	12.4 Discussions
	12.5 Conclusion
	Acknowledgment
	References
13. A COVID-19 Tracker for Medical Front-Liners
	13.1 Introduction
	13.2 Methodology
		13.2.1 Background
		13.2.2 Proposed System
		13.2.3 System Requirements
		13.2.4 Technical Details
	13.3 Modules
		13.3.1 Data Collection and Pre-processing
		13.3.2 Geocoding and Geotagging Patients
		13.3.3 Assigning Health Center and Field Worker
		13.3.4 Hospital Management System
		13.3.5 Ambulance Management System
		13.3.6 Report Generation
			13.3.6.1 Patient Discharge Report
			13.3.6.2 Custom Data Reports
		13.3.7 Analytics
	13.4 Mathematical Model
	13.5 Results
	13.6 Applications
	13.7 Conclusion
	13.8 Future Work
	References
14. Implementation of One Dimensional Convolutional Neural Network for ECG Classification on Python Platform
	14.1 Introduction
	14.2 Overview of 1D-CNN
		14.2.1 Convolutional Block
		14.2.2 Output Block
		14.2.3 Training of Model
		14.2.4 Python Platform
	14.3 Database 01
	14.4 Implementation of 1D-CNN Model 1 for Binary Classification
	14.5 Model Evaluation (Results)
	14.6 Database 02
	14.7 Implementation of 1D-CNN Model 2 for Multi Class Classification
	14.8 Model Evaluation for Multi-Class Classification (Results)
	14.9 Conclusion
	References
15. Pneumonia Detection from X-Ray Images by Two Dimensional Convolutional Neural Network on Python Platform
	15.1 Introduction
		15.1.1 Architecture Overview of Two-Dimensional Convolutional Neural Network (2DCNN)
	15.2 Dataset
	15.3 Implemented Models of CNN
		15.3.1 Model 1 for Binary Classification of X-Ray Images
		15.3.2 Model 2 for Binary Classification of X-Ray Images
	15.4 Model Evaluation
	15.5 Results
		15.5.1 Performance Evaluation of Model 1
		15.5.2 Performance Evaluation of Model 2
	15.6 Conclusion
	References
Index