Artificial Intelligence in Telemedicine: Processing of Biosignals and Medical images

Description

This book explores the role of artificial Intelligence in Telemedicine. It explains the concepts through the detailed study and processing of biosignals, physiological parameters, and medical images. The book focuses on computational algorithms in telemedicine for the processing of biosignals, physiological parameters, and medical Images. The book is presented in two section. The first section presents the role of computational algorithms in the processing of biosignal and medical images for disease diagnosis and treatment planning. Noise removal in ECG signal using an improved adaptive learning approach, classification of ECG signals using CNN for cardiac arrhythmia detection, EEG signal analysis for stroke detection, and EMG signal analysis for gesture classification were discussed in this section. Application of CNN in pertussis Diagnosis by temperature monitoring, physician handwriting recognition using deep learning model, melanoma detection using ABCD parameters, and transfer learning enabled heuristic approach for pneumonia detection was also discussed in this section The second section focus on the role of IoT and artificial intelligence in the healthcare sector. IoT in smart health care and applications of artificial intelligence in disease diagnosis and prediction was discussed in this section. The importance of 5G/6G in the pandemic scenario for telemedicine applications, wireless capsule endoscopy image compression, leukemia detection from the microscopic cell images, and genomic signal processing using numerical mapping techniques was also discussed in this section. This book can be used by a wide range of users including students, research scholars, faculty, and practitioners in the field of engineering for applications in biomedical signal, image analysis, and diagnosis. Cover Half Title Series Page Title Page Copyright Page Table of Contents Editors Contributors Part 1 Biosignal and Medical Image Processing for Disease Diagnosis Chapter 1 Lightweight One-Dimensional CNN for Cardiac Arrhythmia Classification 1.1 Introduction 1.2 Materials and Methods 1.2.1 ECG Data Set 1.2.2 Synthetic Data Generation 1.3 Proposed 1D Convolutional Neural Network 1.4 Results and Discussion 1.5 Conclusion References Chapter 2 An Automatic System for Pertussis Diagnosis with Temperature Monitoring Using CNN 2.1 Introduction 2.2 Related Works 2.3 Database Description for Pertussis Detection 2.4 Detection of Pertussis Using Convolution Neural Network 2.5 Temperature Monitoring 2.6 Results and Discussion 2.7 Conclusion References Chapter 3 DocPresRec: Doctor's Handwritten Prescription Recognition Using Deep Learning Algorithm 3.1 Introduction 3.2 Related Works 3.3 Proposed Framework 3.3.1 Backbone Network 3.3.2 Region Proposal Network 3.3.3 Fast R-CNN 3.3.4 Mask Branch 3.3.5 Character and Text Instance Segmentation 3.3.6 Spatial Attentional Module 3.3.7 Position Embedding 3.3.8 Spatial Attention with RNNs 3.3.9 Decoding 3.4 Experimental Analysis 3.4.1 Dataset 3.4.2 Implementation Details 3.5 Results and Discussion 3.6 Conclusion References Chapter 4 An Efficient Deep Learning Approach for Brain Stroke Detection: Application of Telemedicine 4.1 Introduction 4.2 Materials and Methods 4.2.1 Types of Strokes 4.2.2 Proposed Hybrid Method for Stroke Detection 4.2.3 Initialisation and Hyper-Parameter Setting 4.2.4 Image Processing and Telemedicine 4.2.5 Dataset Description 4.2.6 Performance Parameters 4.3 Results and Discussion 4.3.1 Experimental Setup 4.3.2 Training and Validation 4.3.3 Testing Phase 4.3.4 Performance of SPP-VGG-NiN 4.3.5 Performance Comparison 4.4 Conclusion References Chapter 5 An Automated Detection of Notable ABCD Diagnostics of Melanoma in Dermoscopic Images 5.1 Introduction 5.2 Literature Survey 5.2.1 Limitations of Existing Methods 5.2.2 Motivation and Contribution 5.3 Proposed Methodology 5.3.1 ABCD Features of Melanoma 5.3.2 Asymmetry 5.3.3 Borders 5.3.4 Color Variegation 5.3.5 Diameter 5.4 Results and Discussion 5.5 Conclusion and Future Work References Chapter 6 Comparative Study of CNN and LSTM-Based Hand Gesture Classification Using EMG Signals 6.1 Introduction: Background and Driving Forces 6.2 EMG-Based HGR Systems 6.2.1 Datasets 6.2.2 Generic System 6.2.3 Preprocessing 6.2.4 Segmentation 6.2.5 Feature Extraction 6.2.6 Classification 6.3 Related Works 6.4 Convolutional Neural Network 6.5 Long Short-Term Memory 6.6 Results and Discussion 6.7 Conclusion References Chapter 7 Improved Transfer Learning-Enabled Heuristic Technique for Pneumonia Detection on Graphical Processing Unit Platform 7.1 Introduction 7.2 Transfer Learning–Based Approach for Pneumonia Detection Using VGG16 Deep Learning Model 7.3 Convolutional Neural Networks 7.4 Results and Discussion 7.5 Evaluation Results for Classification Model 7.6 Conclusion References Chapter 8 Improved Adaptive Learning Framework for an Effective Removal of Noise in ECG Signal for Telemedicine System 8.1 Introduction 8.1.1 Background Study 8.2 An Improved Adaptive Learning Approach for ECG Signal Noise Removal 8.3 Wavelet Thresholding and Wavelet Decomposition 8.4 Yule-Walker Modeling 8.5 Hidden Markov Model 8.6 Experimental Analysis 8.7 Conclusion References Part 2 Role of Artificial Intelligence and IoT in Health Care Chapter 9 Human Disease Prediction System – Application of AI Techniques in Chronic Diseases 9.1 Introduction: Overview 9.2 Related Works 9.3 Data Mining Techniques in Disease Prediction 9.3.1 Intelligent Heart Disease Prediction System 9.3.2 Medical Diagnosis Using Back Propagation Algorithm 9.3.3 Disease Prediction System 9.3.4 Smart Health Prediction System 9.3.5 Chronic Kidney Disease Prediction 9.3.6 Machine Learning Over Big Data for Prediction 9.4 Neural Network Models 9.4.1 Real-Time Heart Disease Prediction System 9.4.2 Recommendation System Using Machine Learning and IoT 9.4.3 Decision Tree Classification Model 9.4.4 Classifier System Using Machine Learning Algorithms 9.5 Deep Learning Methods in Human Disease Prediction 9.5.1 Diabetic Retinopathy 9.5.2 Disease Diagnosis Based on Tongue Color Image Analysis 9.5.3 Skin Disease Image Recognition 9.5.4 COVID Care 9.6 Usage of Micro- or Nanorobots in Healthcare 9.7 Summary References Chapter 10 Internet of Things in Mental Healthcare Worldwide – A Study 10.1 Introduction 10.2 Healthcare System Architecture 10.3 Can the IoT Help with Your Mental Health? 10.3.1 IoT for Self-Care 10.3.2 IoT for Clinicians 10.3.3 Data Security Concerns 10.3.4 Progressive Steps 10.4 Role of Smart Devices and AI to Monitor Mental Health 10.4.1 A New, AI-Driven Era 10.4.2 Role of AI and IoT Technology in the Treatment of Mental Health Issues 10.5 Modernizing Mental Healthcare 10.6 IoT Will Challenge the Improved Plea on Mental Health Facilities Post-pandemic 10.7 IoT and the Future of Mental Health 10.7.1 Smart Wearable 10.7.2 Mobile Applications and Algorithms 10.7.3 Artificial Intelligence 10.7.4 Chatbots 10.7.5 E-Therapy 10.7.6 Smart Security and GPS Trackers 10.8 Benefits of IoT in Healthcare 10.9 Challenges of IoT in Healthcare 10.9.1 Data Security and Privacy 10.9.2 Integration: Multiple Devices and Protocols 10.9.3 Data Overload and Accuracy 10.9.4 Cost 10.10 Conclusion References Chapter 11 Internet of Things: A Promise to Smart Healthcare 11.1 Introduction 11.2 Internet of Things 11.3 IoT in Healthcare 11.4 Role of IoT in Various Disease Diagnosis and Prediction 11.4.1 Role of IoT in Diagnosis of Neurological Disorders 11.4.2 Role of IoT in Cancer Diagnosis 11.4.3 Role of IoT in Diabetes Diagnosis 11.4.4 Role of IoT in COVID-19 Diagnosis 11.5 Conclusion Acknowledgements References Chapter 12 A Brief Review on Wireless Capsule Endoscopy Image Compression 12.1 Introduction 12.2 Image Compression Clinical Perspective 12.3 Review of Compression Algorithms for Wireless Capsule Endoscopy Images 12.4 Near-Lossless Image Compression Algorithms 12.5 Low-Power and Low-Complexity Image Compression 12.6 Wireless Capsule Compression Using Intelligent Learning Models 12.7 Result and Discussion 12.8 Research Findings and Limitations 12.9 Conclusion References Chapter 13 A Comprehensive Review on Leukemia Diseases Based on Microscopic Blood Cell Images 13.1 Introduction 13.2 Preliminaries Study on Leukemia 13.3 Machine Learning and Deep Learning Approaches in Leukemia Detection 13.4 Systematic Review 13.5 Scrutinization Criterion of Publication on Leukemia 13.6 Performance Analysis 13.7 Overall Review of Research Findings 13.8 Defects with the Current System 13.9 Conclusion References Chapter 14 Effects of Numerical Mapping Techniques on Performance in Genomic Signal Processing 14.1 Introduction 14.2 Examination of DNA Numerical Mapping Techniques and Their Numerical Representations 14.2.1 Cartesian Coordinate Properties 14.2.2 Biochemical and Physicochemical Properties 14.2.3 Binary and Information Encoding 14.2.4 Primary Structure Properties 14.3 Conclusion References Chapter 15 Importance of 5G/6G in Telemedicine System During the Pandemic Situation 15.1 Introduction 15.2 Importance of Telemedicine 15.3 Realization of Telemedicine 15.4 Conclusion References Chapter 16 Applications of Artificial Intelligence Techniques in Healthcare Industry 16.1 Introduction 16.2 AI in Chronic Diseases 16.2.1 ML in Diabetes 16.2.2 ML in Cardiovascular Disease 16.2.3 Cardiovascular Risk Prediction 16.2.4 Credentials of Novel Cardiovascular Disease Phenotypes 16.2.5 Summary 16.3 AI in Algorithmic Medicine 16.3.1 Computer Vision 16.4 AI in Thyroidology 16.4.1 Ultrasound Image Classification 16.5 AI and Drug Discovery 16.5.1 High-Throughput Screening 16.5.2 Deep Learning–Based Virtual Screening 16.6 Case Study 16.6.1 Segmentation for Osteoporosis Detection From X-Ray and CT Images 16.6.2 Deep Learning Framework for Retinal Segmentation References Index