Cloud Computing in Medical Imaging

Cover
Half Title
Title Page
Copyright Page
Dedication
Contents
Acknowledgements
Preface
Editors
Contributors
Chapter 1. Cloud Computing in Healthcare and Medical Imaging: A Brief Overview
	1.1 Introduction
	1.2 Adopting Cloud for Healthcare
	1.3 Related Work
	1.4 Conclusion
	References
Chapter 2. ISM and DEMATEL Analysis of H4.0 Enablers in the Indian Healthcare Industry
	2.1 Introduction
	2.2 Review of Literature
		2.2.1 Enablers of Health 4.0
	2.3 Research Methodology
		2.3.1 ISM Methodology
		2.3.2 DEMATEL Methodology
	2.4 Modeling the Enablers of the Indian Healthcare Industry by ISM Methodology
	2.5 MICMAC Analysis of the Enablers
	2.6 DEMATEL Analysis of the Enablers
	2.7 Discussion and Conclusion
	2.8 Implications of Research
	2.9 Limitations and Future Prospects of Research
	References
Chapter 3. Machine Learning Algorithms for Health Data Security: A Systematic Review
	3.1 Introduction
	3.2 Value of Fuels and Lignocellulose as Raw Material
	3.3 Research Question
		3.3.1 Search and Selection Strategy
		3.3.2 Selection Criteria
		3.3.3 Thermochemical Routes for Biomass Conversion to Fuels
		3.3.4 Observation
	3.4 Findings
		3.4.1 Systematic Search Results
	3.5 Motivation and Algorithms
		3.5.1 Health Data Security Using ML and DL Strategy
		3.5.2 Health Data Security Using Traditional Approach
		3.5.3 Mathematical Interpretation of the ML Models
		3.5.4 Support Vector Machine (SVM)
		3.5.5 Radial Basis Function (RBF) Kernel SVM
		3.5.6 Decision Tree (DT)
		3.5.7 Naïve Bayes Algorithm
		3.5.8 Complexity Analysis of the ML Models
	3.6 Conclusion and Future Work
	References
	Appendix 3.A
Chapter 4. Fog Computing in IoT-Based Healthcare Systems
	4.1 Introduction
	4.2 Concepts in Fog Computing
	4.3 Healthcare Systems
	4.4 Properties of Fog-Based Computing
		4.4.1 Privacy
		4.4.2 Energy Efficiency
		4.4.3 Bandwidth
		4.4.4 Scalability
		4.4.5 Dependability
	4.5 Fog Computing in IoT-Based Healthcare
		4.5.1 Computation Center
		4.5.2 Latency and Throughput
		4.5.3 Reliability
		4.5.4 Security
		4.5.5 Automatic Fog Computing
		4.5.6 Energy Effectiveness
	4.6 Conclusion
	References
Chapter 5. Medical Imaging and Healthcare Applications Using 5G
	5.1 Introductions: Background and Constraints of Traditional Healthcare Applications
	5.2 Opportunities Provided by Cloud Computing and 5G
	5.3 Medical Imaging with Cloud and 5G
		5.3.1 Medical Image Storage
		5.3.2 Medical-Image Processing
		5.3.3 Machine-Learning and AI
		5.3.4 Visualization and Virtual Reality (VR)/Augmented Reality (AR)
	5.4 The Impacts of 5G on Cloud Computing
	5.5 5G in Healthcare
		5.5.1 5G in Healthcare Applications with High Processing Requirements
		5.5.2 Benefit of 5G to Healthcare Applications
		5.5.3 An Example Application
	5.6 Introduction to 5G Technology
	5.7 Software Defined Network in 5G
	5.8 5G Architecture
		5.8.1 Logical Structure of 5G
		5.8.2 Slicing and Integrating with Broadband
	5.9 Edge Computing
	5.10 Conclusion
	References
Chapter 6. The Application of Cloud-Computing Technology to Improve Patients' Medical History Access to Clinicians for Quality of Care in the Fourth Industrial Revolution
	6.1 Introduction and Background
	6.2 Cloud-Computing Technology and Healthcare Services
	6.3 Problem Statement
	6.4 Purpose and Objective of the Study
	6.5 Methodology
	6.6 Discussion and Recommendations
		6.6.1 Proposed Framework
	6.7 Concluding Remarks
	References
Chapter 7. Diagnostic Imaging and Associated Services: Toward Interoperability and Cloud Computing
	7.1 Introduction
	7.2 DICOM and DICOMWeb
		7.2.1 DICOMWeb Search Service (QIDO-RS - Query Based on ID for DICOM Objects)
		7.2.2 DICOMWeb Retrieve Service (WADO-RS - Web Access to DICOM Persistent Objects)
		7.2.3 DICOMWeb Storage Service (STOW-RS - STore Over the Web)
		7.2.4 DICOMWeb Worklist Service (UPS-RS - Unified Procedure Step)
		7.2.5 DICOMWeb Capabilities Service
	7.3 Discussion
	7.4 Conclusion and Future Work
	References
Chapter 8. Health Monitoring Based on the Integrated Offer of Cloud-IoT Sensing Services
	8.1 Introduction
	8.2 Specific HM Architectural Solutions - An Overview
	8.3 Generic Sensing Service Scenario
	8.4 Integrated Sensing Service Offer Approach
		8.4.1 Main Roles and Business Interactions
		8.4.2 Operation Rules
	8.5 Service Offer Integrator Specificity
		8.5.1 SOI Business Model Specifications
		8.5.2 Core Entities of the SOI-MIS Data Structure
	8.6 Implementation Scenarios for Integrated Sensing Service Approach
	8.7 Conclusions
	References
Chapter 9. Sleep-Stage Identification Using Recurrent Neural Network for ECG Wearable-Sensor System
	9.1 Introduction
	9.2 Proposed Methods
		9.2.1 Data Collection of MIT-BIH Polysomnographic Dataset
		9.2.2 Pre-Processing of the Data
		9.2.3 First Algorithm: Long Short-Term Memory
		9.2.4 Second Algorithm: LSTM with Peephole Connection
		9.2.5 Third Algorithm: Gated Recurrent Unit
	9.3 Results
		9.3.1 Model Training and Evaluation
		9.3.2 Pre-Processing
		9.3.3 First Algorithm: Long Short-Term Memory
		9.3.4 Second Algorithm: LSTM with Peephole Connection
		9.3.5 Third Algorithm: Gated Recurrent Unit
	9.4 Conclusion
Chapter 10. Classification of Methods to Reduce Clinical Alarm Signals for Remote Patient Monitoring: A Critical Review
	10.1 Introduction
		10.1.1 Remote Patient-Monitoring Application Architecture
		10.1.2 Alarms in RPM
		10.1.3 False-Positive Alarms
	10.2 A Pentagon Approach
		10.2.1 Clinical Requirements
		10.2.2 Method Selection
		10.2.3 Design and Development
		10.2.4 Clinical Trial and Analysis
		10.2.5 Feedback Loop
	10.3 Classification Categories
		10.3.1 Physiological Data-Based Approach
			10.3.1.1 Customised Alarm Signals
			10.3.1.2 Machine Learning
			10.3.1.3 Time Delay
			10.3.1.4 Integration of Techniques
			10.3.1.5 Coalition Game Theory
			10.3.1.6 Sensor Fusion
			10.3.1.7 Pattern Discovery
		10.3.2 Clinical Device-Centric Approach
		10.3.3 Clinical Knowledge-Based Approach
			10.3.3.1 Pattern Match
			10.3.3.2 Team-Based Method
		10.3.4 Clinical Environment-Based Approaches
			10.3.4.1 Median Filters
			10.3.4.2 Dimension Reduction
	10.4 Results and Discussion
		10.4.1 Physiological Data
		10.4.2 Clinical Device-Centric
		10.4.3 Clinical Knowledge-Based
		10.4.4 Clinical Environment
	10.5 Conclusions
	Notes
	References
Chapter 11. Cloud Computing in Medical Imaging, Healthcare Technologies, and Services
	11.1 Introduction to Cloud Computing
		11.1.1 Essential Characteristics
		11.1.2 Service Models
		11.1.3 Deployment Models
		11.1.4 Introduction to Cloud Computing in Healthcare
	11.2 The Benefits of Cloud Computing in the Healthcare Domain
	11.3 Looking at the Past of Cloud Computing in Healthcare
	11.4 The Present Trends in Cloud-Computing Dynamics
	11.5 Analysis
		11.5.1 Comparison
		11.5.2 How Can It Move Forward?
	11.6 Conclusion and Future Scope
	References
Chapter 12. An Insight into Image Steganography for Medical Informatics
	12.1 Introduction
	12.2 Medical Image Steganography
	12.3 Classification of Image Steganography Based on Embedding Domain
		12.3.1 Spatial Domain Steganography
		12.3.2 Transform Domain Steganography
		12.3.3 Hybrid Domain
		12.3.4 Steganography Based on AI Approaches
	12.4 Image Steganography with Encryption
	12.5 Spread-Spectrum (SS)-Based Image Steganography
	12.6 Performance Evaluation
	12.7 Statistical and Analytical Measures Used
	12.8 Conclusion
	Funding
	References
Index