This book covers computer vision-based applications in digital healthcare industry 4.0, including different computer vision techniques, image classification, image segmentations, and object detection. Various application case studies from domains such as science, engineering, and social networking are introduced, along with their architecture and how they leverage various technologies, such as edge computing and cloud computing. It also covers applications of computer vision in tumor detection, cancer detection, combating COVID-19, and patient monitoring.
Features:
- Provides a state-of-the-art computer vision application in the digital health care industry.
- Reviews advances in computer vision and data science technologies for analyzing information on human function and disability.
- Includes practical implementation of computer vision application using recent tools and software.
- Explores computer vision-enabled medical/clinical data security in the cloud.
- Includes case studies from the leading computer vision integrated vendors like Amazon, Microsoft, IBM, and Google.
This book is aimed at researchers and graduate students in bioengineering, intelligent systems, and computer science and engineering.
Author(s): P. Karthikeyan, Polinpapilinho F. Katina, R. Rajagopal
Series: Computational Intelligence Techniques
Publisher: CRC Press
Year: 2023
Language: English
Pages: 185
City: Boca Raton
Cover
Half Title
Series Page
Title Page
Copyright Page
Contents
Preface
Acknowledgments
List of Contributors
About the Editors
Chapter 1: Introduction to Computer Vision Aided Data Analytics in Healthcare Industry 4.0
1.1. Introduction
1.1.1. Insights Derived from Data that Can Enhance Patient Care
1.1.2. Transforming Data into Valuable Ideas
1.1.3. Patients' Expectations Are Evolving
1.2. Applications of Computer Vision in Healthcare Application
1.3. Computer Vision Challenges and Solutions
1.3.1. Inadequate Hardware
1.3.2. Poor Data Quality
1.3.2.1. Poor Quality
1.3.2.2. Lack of Training Data
1.4. Weak Planning for Model Development
1.5. Time Shortage
1.6. Introduction to Image Processing
1.7. The Future of Computer Vision
1.7.1. A More Comprehensive Range of Functions
1.7.2. Learning with Limited Training Data
1.7.3. Learning without Explicit Supervision
1.7.4. Artificial Intelligence and Medical Analytics
1.7.5. Utilizing Analytics to Enhance Results
1.8. Importance of Healthcare Data
1.9. Benefits of Healthcare Data Analytics
1.9.1. Healthcare Predictive Analytics
1.9.2. Treatment of Patients at High Risk
1.9.2.1. Patient Satisfaction
1.9.2.2. Industry Innovation
1.9.2.3. Address Human Fallibility
1.9.2.4 Cost-cutting
1.10. Healthcare Data Analytics Challenges
1.10.1. The Growing Role of the Health Data Analyst
1.10.2. Skills Needed by Health Data Analysts
1.10.3. Where Will Health Data Analysts Be Employed?
1.11. Summary
References
Chapter 2: Deep Learning Techniques for Foetal and Infant Data Processing in a Medical Context
2.1. Introduction
2.2. Traditional Ultrasound Image Analysis
2.2.1. Uses
2.2.2. Benefits/Risks
2.3. Artificial Intelligence for Foetal Ultrasound Image Analysis
2.4. Deep Learning for Foetal Ultrasound Image Analysis
2.5. Survey Strategy
2.6. Publicly Available Data Sets
2.7. Heart-Based Foetal Ultrasound Analysis
2.8. Discussion of the Study Strategy
2.9. Case Study
2.9.1. Heart Foetal Analysis Using Machine Learning
2.9.2. Foetal Analysis Using Deep Learning
2.10. Conclusion
2.11. Future Scope
2.12. Summary
References
Chapter 3: Analysis of Detecting Brain Tumors Using Deep Learning Algorithms
3.1. Introduction
3.2. Deep Learning in Medical Images
3.3. Literature Review
3.4. Brain Tumor Issues and Challenges
3.5. Analysis Study
3.5.1. An Improved Extreme Learning Machine with Probabilistic Scaling
3.5.1.1. Image Denoising
3.5.1.2. Feature Extraction
3.5.1.3. Feature Selection
3.5.1.4. Similarity Measures
3.5.1.5. Classification Using Improved ELMPS
3.5.2. A Deep Belief Network with the Grey Wolf Optimization Algorithm
3.5.2.1. Preprocessing
3.5.2.2. Segmentation
3.5.2.3. Feature Extraction
3.5.2.4. Classification
3.5.2.5. Grey Wolf Optimization
3.6. Result and Discussion
3.7. Summary
References
Chapter 4: Secured Data Dissemination in a Real-Time Healthcare System
4.1. Introduction
4.2. Secured Data Framework
4.3. Framework Structure
4.3.1. Registration and Key Distribution
4.3.2. Advanced Encryption Standard Key Generation
4.3.3. Encrypted Data Dissemination via Cloud
4.3.4. Raspberry Pi Configuration
4.4. Coding Principles
4.4.1. Value Conventions
4.4.2. Script Writing and Commenting Standard
4.4.3. Message Box Format
4.5. Summary
References
Chapter 5: Modality Classification of Human Emotions
5.1. Introduction
5.2. Linguistic Emotions
5.3. Recording of Emotional States Changes through EEG
5.4. Methodology
5.5. EEG Data Sets
5.6. Experimentation
5.7. Conclusion
5.7.1. Future Scope
5.8. Summary
References
Chapter 6: COVID-19 Alert Zone Detection Using OpenCV
6.1. Introduction
6.2. Framework Environment
6.2.1. Constraints
6.2.1.1. No User-Friendly User Interface for Software
6.2.1.2. Too Much Workload for Staff
6.2.1.3. Does Not Predict the Safety Percentage
6.2.1.4. Accuracy Decreases
6.3. Framework Structure
6.4. Architecture Diagram
6.4.1. Creating a User Interface Using Tkinter
6.4.2. Processing Photos through YOLOv4
6.4.3. Screening Video through YOLOv4
6.4.4. Enhancing the Output Parameter
6.4.5. Implementation of Real-Time Detection through the Camera
6.5. Summary
6.6. Future Enhancement
References
Chapter 7: Feature Fusion Model for Heart Disease Diagnosis
7.1. Introduction
7.2. Feature Representation in Heart Disease Diagnosis
7.3. Feature Fusion Method
7.4. Classification for Weighted Feature Fusion
7.5. Results
7.6. Conclusion
References
Chapter 8: Deep Learning and Its Applications in Healthcare
8.1. Introduction
8.2. Classification
8.3. Deep Learning Algorithms
8.4. Deep Learning in Health Care
8.4.1. Abnormality Detection in Radiology
8.4.2. Dermoscopic Medical Image Segmentation
8.4.3. Deep Learning in Surgical Robotics
8.5. Applications of Deep Learning in Healthcare
8.5.1. Drug Discovery
8.5.2. Medical Imaging and Diagnostics
8.5.3. Simplifying Clinical Trials
8.5.4. Personalized Treatment
8.5.5. Improved Health Records and Patient Monitoring
8.5.6. Health Insurance and Fraud Detection
8.5.7. Deep Learning and NLP
8.5.8. Genomic Analysis
8.5.9. Mental Health
8.5.10. COVID-19
8.6. Advantages of Deep Learning in the Healthcare Industry
8.6.1. A More Accurate Meter
8.6.2. Early Disease Recognition
8.6.3. Enhanced Medical Procedures Efficiency
8.6.4. Automatic Generation of Medical Reports
8.6.5. Interactive Medical Imaging
8.7. Uses
8.7.1. Deep Neural Networks
8.7.2. Convolutional Neural Networks
8.7.3. Recurrent Neural Networks
8.7.4. Generative Adversarial Networks
8.8. Summary
References
Chapter 9: Future of Computer Vision Application in Digital Healthcare
9.1. Introduction
9.1.1. How Does Computer Vision Work
9.1.1.1. Acquiring an Image
9.1.1.2. Processing Acquired Images
9.1.1.3. Understanding the Image
9.2. The Six Steps to Creating a Successful Computer Vision POC (Proof of Concept)
9.2.1. Identify the Business Problem
9.2.2. Define the Success Criteria
9.3. Trends in Computer Vision
9.3.1. Popular Computer Vision Tools
9.3.2. Most Common Datasets Used
9.3.3. Common Tasks Associated with Computer Vision
9.4. Classification of Image
9.4.1. Detecting Objects
9.4.2. Segmentation of Images
9.4.3. Person and Face Recognition
9.4.4. Edge Detections
9.4.5. Image Restoration
9.4.6. Features Matching
9.4.6.1. Role of Computer Vision
9.5. Phases of Computer Vision
9.6. Advantages of Computer Vision
9.7. Summary
References
Chapter 10: Study of Computer Vision Applications in Healthcare Industry 4.0
10.1. Introduction
10.2. Gauss Surgical
10.2.1. Study Population and Surgical Cases
10.2.2. Hemoglobin Loss and Blood Loss Measurements
10.3. Case Study: Vision System Traceability in Medical Device Manufacturing Applications
10.4. Case Study: Medical Parts Get a Clinical Checkup
10.4.1. Parallel Patterns
10.5. Case Study: Medical Wells Scrutinized by Vision
10.5.1. Color Check
10.6. Case Study: Computer Vision for Monitoring Tumors Using Image Segmentation
10.6.1. Monitoring Tumors in the Liver
10.6.2. Image Acquisition
10.6.3. Analyzing the Image
10.6.4. Applying the Insights
10.7. Case Study: Detection of Cancer with Computer Vision
10.7.1. Identifying Neutrophils with Computer Vision
10.8. Case Study: Computer Vision for Predictive Analytics and Therapy
10.8.1. Resulting Images Pictures
10.9. Summary
References
Index