Applied Mathematics for Healthcare Intelligent Systems

Name: Applied Mathematics for Healthcare Intelligent Systems | Data Representation, Smart Healthcare, Deep Learning and Medical Imaging
Brand: De Gruyter Mouton
Price: 159.95 EUR
Availability: OnlineOnly

Data Representation, Smart Healthcare, Deep Learning and Medical Imaging

Monika Sethi Shivani Sood Saravjeet Singh Arfat Ahmad Khan(Editor)

De Gruyter Mouton (Publisher)

1st Edition

Published on 18. May 2026

XIII, 312 pages

E-Book

PDF with digital watermarking

System requirements

978-3-11-222622-3 (ISBN)

€159.95incl. 7% vat

System requirements

for PDF with digital watermarking

E-Book Single Licence

Available for download

Description

More details

Other editions

Persons

Dr Monika Sethi is professor in the Department of Computer Science and Engineering at Chitkara University, Punjab, India. She has over 15 years' experience in the field of teaching and research. Her research interests include Image Processing (ADNI-MRI Images), Deep Learning, Machine Learning, and Wireless Sensor Networks. Her teaching interests include C, C++, Python, Data Structures, Operating Systems, Computer System Architecture, Computer Graphics and Digital Electronics. She has published 28+ research papers in international journals and conferences (Scopus Indexed) and filed 14 patents (9 granted and 5 published). She is a member of the IEI. She holds a PhD degree in "Enhancing the Performance of Convolutional Neural Network for Alzheimer's disease Classification" from Chitkara University, Punjab and a MTech in (Power Efficient Hierarchical Centralized Routing in WSN) from NIT Hamirpur, India.

Dr Shivani Sood is an assistant professor in the Department of the School of Computer Applications at Lovely Professional University, Phagwara, Punjab, India. Her research interests include Pattern Recognition, Machine Learning, Image Processing, and Data science. Her teaching interests include Python, Java, C/C++, Advanced Data structures, and Data Structure. She has over 7 years of experience in academia, and research. She has filed 2 patents and published 10 articles in international journals and conferences. She holds a Master degree from Sri Sai College of Engineering College, Pathankot. Her specialization includes Advanced Java, Database management skills in their entrepreneurships training . She holds a Ph.D. degree in Computer Science on "Detection and classification of diseases on wheat crop using computer vision and machine learning techniques" in 2023 from Chitkara University (Punjab), India.

Dr Saravjeet Singh has a Ph.D. degree in computer science and engineering. Currently he is working as associate professor in the Department of Computer Science and Engineering at Chitkara University, Punjab, India. He has over 14 years of experience in research, development, and academia. His research interests include offline navigation systems, spatial databases, pattern recognition, mental disorders, and software engineering. He has published 55+ research papers in international journals and conferences (Scopus Indexed) and filed 8 patents.

Arfat Ahmad Khan received the B.Eng. degree in Electrical Engineering from The University of Lahore, Pakistan, in 2013, the M.Eng. degree in Electrical Engineering from the Government College University Lahore, Pakistan, in 2015, and the Ph.D. degree in Telecommunication and Computer Engineering from the Suranaree University of Technology, Thailand, in 2018. From 2014 to 2016, he was an RF Engineer with Etisalat, United Arab Emirates. From 2018 to 2022, he was a Lecturer and a Senior Researcher with the Suranaree University of Technology. He is currently a Senior Lecturer and a Researcher with Khon Kaen University, Thailand. He is rankedamong the world's top 2 percent scientists by Stanford University, USA and Elsevier. He has more 60 high impact factored research publications, where some of his publications are published in top ranked journals including but not limited to IEEE Transactions on Neural Systems and Rehabilitation Engineering, IEEE Transactions on Consumer Electronics, IEEE Transactions on Network Science and Management, IEEE Transactions on Vehicular Technology, Expert System with Applications, Biomedical Signal Processing and Control, CAAI Transactions on Intelligence System. His research interests include Machine, Deep, and Federated Learning for various applications including medical image processing, cyber security, speech recognition, agriculture, healthcare, and advanced wireless communications.

Content

Intro
Preface
Contents
List of Contributors
1 An In-Depth Analysis of Medical Imaging Modalities and the Transformative Potential of Deep Learning and Enhancing Diagnostic Accuracy in Healthcare
1.1 Introduction
1.1.1 Overview of Medical Imaging in Healthcare
1.2 Progression of Medical Imaging Procedures
1.2.1 Early Developments
1.2.2 Magnetic Resonance Imaging (MRI)
1.2.3 Ultrasound Imaging
1.2.4 Positron Emission Tomography (PET) and Functional Imaging
1.2.5 Artificial Intelligence and the Future of Medical Imaging
1.3 The Role of Artificial Intelligence and Deep Learning in Modern Diagnostics
1.3.1 Mathematical Foundations of Artificial Intelligence in Medical Imaging
1.3.2 Image Processing and Enhancement Using Artificial Intelligence
1.3.3 Artificial Intelligence in Disease Detection and Classification
1.3.4 Predictive Analytics and Personalized Medicine with Artificial Intelligence
1.4 Importance of Precision and Automation in Medical Imaging
1.4.1 The Mathematical Basis of Accuracy in Medical Imaging
1.4.1.1 Mathematical Models in Image Acquisition
1.4.1.2 Image Processing and Enhancement Through Mathematics
1.5 Medical Imaging Modalities: Principles and Applications
1.5.1 Optical Coherence Tomography (OCT)
1.5.1.1 Principle of OCT Imaging
1.5.1.2 Application in Ophthalmology
1.5.1.3 The Role of AI in OCT
1.5.2 Fundus Photography (FP) and Fluorescein Angiography (FA)
1.5.3 Magnetic Resonance Imaging (MRI)
1.5.4 Computed Tomography (CT)
1.5.5 Ultrasound
1.5.6 Positron Emission Tomography (PET)
1.6 Deep Learning in Medical Imaging
1.6.1 Fundamentals of Deep Learning
1.6.2 Deep Learning Models in Image Analysis
1.6.2.1 Benchmark Architectures: U-Net and TransUNet
1.6.2.2 Performance Indicators and Datasets in Deep Learning
1.6.3 Automated Image Processing and Feature Extraction
1.6.4 Predictive Analytics in Disease Progression
1.7 AI-Driven Enhancements in Medical Imaging
1.7.1 Computer-Aided Diagnosis (CAD) Systems
1.7.2 Real-Time Image Processing and Augmentation
1.7.3 Fusion of Imaging Data with Electronic Health Records (EHR)
1.7.4 Telemedicine and Remote Diagnosis
1.8 Challenges and Ethical Considerations
1.8.1 Data Privacy and Security
1.8.1.1 Challenges in Handling Medical Imaging Data
1.8.1.2 Bias in AI Algorithms
1.8.1.3 Concerns About Racial and Gender Bias in AI Models
1.8.2 Regulatory Approvals and Clinical Validation
1.8.2.1 Regulatory Agents for AI in Medical Imaging
1.8.3 Interpretability and Trust in AI
1.8.3.1 The Need for Explainable AI (XAI) in Clinical Settings
1.8.4 Physician-AI Collaboration
1.8.4.1 Ensuring AI Complements Rather than Replaces Human Expertise
1.9 Future Prospects and Innovations
1.9.1 Advancements in AI Algorithms
1.9.1.1 Self-Learning AI Models in Medical Imaging
1.9.2 Quantum Computing and Medical Imaging
1.9.2.1 Potential Impact on Real-Time Imaging and Deep Learning Efficiency
1.9.3 Integration with Wearable and Smart Devices
1.9.3.1 AI-Based Real-Time Health Monitoring
1.9.4 Global Impact and Accessibility
1.9.4.1 Expanding AI-Based Diagnostics in Low-Resource Settings
1.10 Conclusion
1.10.1 Summary of Key Insights
1.10.2 The Transformative Impact of AI in Medical Imaging
1.10.3 Future Roadmap for AI-Driven Healthcare Diagnostics
1.10.4 Future Outlook in Medical Imaging
References
2 A Deep Learning Architecture for Detecting Pneumonia in Chest X-rays: An Approach for Processing Medical Images
2.1 Introduction
2.2 Related Works
2.3 Proposed Methodology
2.3.1 Proposed Mathematical Model
2.4 Results
2.4.1 Dataset Description
2.4.2 Metrics
2.4.3 Discussion
2.5 Ethical, Legal, and Regulatory Considerations
2.6 Conclusion
References
3 Data Handling, Data Representation, and Preprocessing for Medical Image Processing
3.1 Introduction
3.1.1 Data Preparation in Medical Images
3.2 Transitioning from Conventional ML Techniques to DL
3.2.1 Benefits of Medical Image Processing
3.2.2 Medical Image Processing Work
3.3 Fundamental Concepts and Terminology
3.3.1 Machine Learning in Medical Imaging
3.3.2 Deep Learning in Medical Imaging
3.3.3 ML/DL Techniques for Medical Image Analysis
3.4 Challenges of the DL Applications in Medical Image Analysis
3.5 Conclusion
References
4 Deep Learning in Medical Imaging Modalities: A Comprehensive Analysis for Enhanced Diagnosis
4.1 Introduction
4.2 Image Processing Techniques for Medical Imaging
4.3 Deep Learning in Medical Imaging
4.4 Explainable AI (XAI) for Medical Diagnosis
4.5 Challenges and Future Directions
4.6 Conclusion
References
5 Deep Generative Learning: Foundations and Case Studies in Medical Image Processing
5.1 Introduction
5.2 Theoretical Foundations
5.2.1 Probability Distributions and Generative Models
5.2.2 Probability Distributions
5.2.3 Bayes' Theorem
5.2.4 Maximum Likelihood Estimation (MLE)
5.3 Types of Generative Models
5.3.1 Variational Autoencoders (VAEs)
5.3.2 Generative Adversarial Networks (GANs)
5.3.3 Autoregressive Models
5.3.4 Normalizing Flows
5.3.5 Diffusion Models
5.3.6 Energy-Based Models (EBMs)
5.3.7 Hybrid Models
5.4 Case Studies
5.4.1 Case Study 1: Tumor Detection in Brain MRI Scans Using Deep Learning
Methodology
Challenges
Future Directions
5.4.2 Case Study 2: Detection of Pneumonia in Chest X-Rays Using Deep Learning
Methodology
Results
Conclusion
5.5 Applications of Deep Generative Learning
5.5.1 Image and Video Generation
5.5.2 Data Augmentation
5.5.3 Drug Discovery and Healthcare
5.5.4 Text and Natural Language Processing
5.6 Challenges and Future Directions
5.6.1 Challenges in Deep Generative Learning
5.6.2 Emerging Trends and Research Areas
5.7 Conclusion
References
6 Explainable AI for Smart Healthcare
6.1 Introduction
6.1.1 Historical Evolution of AI in Medicine
6.1.2 Transformational Impact of AI in Healthcare
6.2 The Need for XAI in Healthcare
6.3 Transparency and Trust: Why Clinicians and the Patients Need to Understand AI-Driven Decisions
6.3.1 The Black-Box Problem in AI Healthcare Models
6.3.2 Real-World Example: AI in Medical Imaging
6.3.3 XAI for Enhancing Trust
6.4 Regulatory and Ethical Concerns: Compliance with the Healthcare Regulations (e.g., FDA and GDPR)
6.4.1 Ethical Issues in AI-Driven Healthcare
6.5 Enhancing Clinical Decision Support: How XAI Aids in Reducing Diagnostic Errors
6.5.1 AI as a Decision-Support Tool
6.6 Core Concepts of XAI
6.6.1 Definition of XAI
6.6.2 Key Characteristics of Explainable AI
6.6.3 Types of XAI: Model-Agnostic Versus Model-Specific Methods
6.6.4 Model-Specific XAI Methods
6.6.5 Techniques in XAI
6.7 Role of XAI in Medical Imaging and Diagnostics
6.7.1 Interpretable AI in Radiology: OCT, MRI, CT, and Fundus Imaging Applications
6.7.1.1 Why Explainability Matters in Medical Imaging
6.7.1.2 AI in OCT Imaging for Retinal Diseases
6.7.1.3 AI in MRI and CT for Neurological and Cancer Diagnosis
6.7.1.4 AI in Fundus Imaging for Retinal Disease Detection
6.8 Case Studies: Diabetic Retinopathy, Cancer Detection, and Neurodegenerative Disease Assessment
6.8.1 Case Study: XAI in Diabetic Retinopathy Detection
6.8.2 Case Study: AI-Driven Cancer Detection
6.8.3 Case Study: XAI in Neurodegenerative Disease Assessment
6.9 Enhancing Clinician Confidence: How Visualization Techniques Improve Trust
6.9.1 Why Clinicians Need Explainability in AI-Assisted Imaging
6.9.2 Visualization Techniques in XAI for Medical Imaging
6.10 XAI for Personalized Treatment and Predictive Analytics
6.10.1 Explainability in Risk Assessment Models: Cardiovascular, Diabetes, and Genetic Disorder Predictions
6.10.1.1 Role of AI in Risk Assessment
6.10.2 Drug Discovery and Precision Medicine: Understanding Molecular Interactions with AI
6.11 Challenges and Limitations of XAI in Healthcare
6.11.1 Trade-Offs and Computational Complexity
6.11.2 Balancing Accuracy Versus Explainability
6.11.3 Standardization and Validation Concerns
6.11.4 Regulatory Obstacles in XAI Implementation
6.11.5 Proposed Solutions for Standardization
6.11.6 Problems Affecting Adoption and Clinician Training
6.11.7 Exhibit: Artificial Intelligence in Cosmology
6.12 Conclusion
Key Takeaways
References
7 3D Reconstruction Techniques for Medical Imaging
7.1 Introduction to 3D Reconstruction Techniques for Medical Imaging
7.2 Fundamentals of 3D Reconstruction
7.3 Fundamentals of 3D Reconstruction
7.3.1 Principles of 3D Reconstruction in Medical Imaging
7.3.2 Techniques in 3D Imaging
7.4 Core Algorithms in 3D Reconstruction for Medical Imaging
7.4.1 Surface-Based Algorithms
7.4.2 Volume-Based Algorithms
7.4.3 Deep Learning-Based Technology
7.5 Technological Platforms for 3D Reconstruction
7.5.1 MILXView
7.5.2 Cloud Computing
7.5.3 Service-Oriented Architecture (SOA) in Medical Imaging
7.5.4 Platform for Imaging in Precision Medicine (PRISM)
7.5.5 Photoacoustic Imaging (PAI) as an Emerging Platform
7.6 Clinical Applications in Medical Imaging
7.6.1 Neurosurgery
7.6.2 Orthopedics
7.6.3 Cardiology
7.6.4 Oncology
7.6.5 Telemedicine
7.6.6 Blending Augmented and Virtual Reality (AR/VR)
7.7 Integration of 3D Reconstruction with Augmented and Virtual Reality (AR/VR)
7.8 Impact of 3D Imaging on Telemedicine
7.9 Limitations
References
8 Emerging Trends in Medical Imaging with Fog Computing
8.1 Introduction
8.2 Usage of Fog Computing in Medical Imaging
8.2.1 MRI Machines
8.2.2 CT Scans
8.2.3 X-Ray Machines in Healthcare
8.3 Role of Fog Computing in Medical Imaging
8.3.1 Low Latency and Real-Time Processing
8.3.2 Improved Reliability and Availability
8.3.3 Support for AI and Machine Learning Models
8.3.4 Scalability and Flexibility
8.3.5 Collaboration Across Healthcare Providers
8.4 Mathematical Models in Medical Imaging and Fog Computing
8.4.1 Distributed Image Processing in Fog Computing
8.4.2 Bandwidth and Latency Optimization
8.4.3 Task Offloading and Scheduling Models
8.4.4 Data Privacy and Security
8.4.5 Fault Tolerance and Reliability
8.5 Classification of Medical Imaging
8.5.1 X-Ray Imaging Techniques
8.5.2 CT Scan Imaging Techniques
8.5.3 MRI Imaging Techniques
8.6 Conclusions
References
9 In-Depth Analysis of Advanced Image Segmentation Techniques for Accurate Identification of Anatomical Structures and Pathologies in Medical Imaging
9.1 Introduction
9.1.1 Importance of image segmentation in medical imaging
9.2 Fundamentals of Medical Image Segmentation
9.2.1 Medical Imaging Modalities
9.3 Techniques for Image Segmentation
9.3.1 Traditional Image Segmentation Techniques
9.3.2 AI-Based Segmentation Methods
9.4 Applications of Image Segmentation in Medical Imaging
9.5 Analysis of Segmentation Techniques
9.6 Challenges in Medical Image Segmentation
9.7 Emerging Trends in Medical Image Segmentation
9.8 Conclusion
References
10 Revolutionizing Medical Image Interpretation with GANs in Healthcare
10.1 Introduction
10.2 GAN Architecture and Variants
10.2.1 Vanilla GAN (VGAN)
10.2.2 Fully Connected GAN (FCGAN)
10.2.3 CycleGAN
10.3 Mathematical Framework
10.4 Typical GAN Models
10.4.1 CGAN
10.4.2 DCGAN
10.4.3 Pix2Pix
10.4.4 WGAN and WGAN-GP
10.4.5 CycleGAN
10.4.6 Style GAN
10.5 Conventional applications of GAN
10.5.1 Image Processing
10.5.2 Wonderful Decision
10.5.3 Picture Editing
10.5.4 Face Photo Era at Excessive Decision
10.5.5 Face Thing Transformation
10.5.6 Domain Transformation
10.5.7 GANs in Scientific and Healthcare
10.5.8 Fashion Designing
10.6 Applications of GAN in Security
10.6.1 Statistics Security
10.6.2 Cyber Safety
10.6.3 Safety in AI
10.7 Open Problems and Proposed Solutions
10.7.1 Objective Function for Training GANs
10.7.2 Mentality Behind Solving GAN Training Problems
10.7.3 Mode Collapse
10.7.4 Instability of Adversarial Training
10.7.5 Lack of a Proper Evaluation Metric
10.7.6 Vanishing Gradient
10.7.7 Improving Training
10.8 Conclusion
References
11 AI-Driven Healthcare: Case Studies in Intelligent Systems and Applications
11.1 Introduction
11.2 Evolution of AI in Healthcare
11.3 Importance of Intelligent Systems in Modern Medicine
11.4 Fundamentals of AI in Healthcare
11.4.1 Overview of Machine Learning, Deep Learning, and NLP in Healthcare
11.4.2 Key AI techniques for Medical Applications
11.5 Case Studies in AI-Driven Healthcare Applications
11.5.1 AI for Early Detection of Cardiovascular Diseases
11.5.2 AI-Assisted Detection of Cancer in Histopathology
11.5.3 NLP-Based Chatbots for Patient Consultation
11.5.4 Automating Administrative Processes with AI
11.5.5 Wearable AI for Real-Time Health Monitoring
11.6 Challenges and Ethical Considerations
11.7 Future of AI in Healthcare
11.8 Results and their Significance
11.9 Novel Contributions
11.10 Future Work
11.11 Conclusion
References
12 Balancing Innovation and Integrity: Challenges in Deep Learning for Medical Imaging
12.1 Introduction
12.2 Overview of Deep Learning in Medical Imaging
12.3 Evolution of Deep Learning in Medical Imaging
12.3.1 Early Years: Rule-Based Systems to Machine Learning
12.3.2 The Deep Learning Revolution
12.3.3 Modern Advancements: Beyond CNNs
12.4 Clinical Applications
12.4.1 Diagnosis
12.4.2 Prognosis
12.4.3 Treatment Planning
12.5 Federated Learning in Medical Imaging
12.5.1 How Federated Learning Works
12.5.2 Advantages of Federated Learning in Healthcare
12.5.3 Challenges and Future Directions
12.6 Bias and Fairness in Deep Learning Models
12.6.1 Sources of Bias in Medical Imaging Datasets
12.6.2 Fairness Metrics and Evaluation Approaches
12.6.3 Bias Mitigation Strategies
12.6.4 Ethical and Regulatory Considerations
12.6.5 The Path Forward
12.7 Interpretability Techniques
12.8 Case Studies of Success Stories in Medical Imaging
12.8.1 Case Study 1: CT Imaging Augmented with AI for Diagnostics of Lung Cancer
12.8.2 Case Study 2: Screening for Diabetic Retinopathy Using AI-Powered Fundus Imaging
12.8.3 Case Study 3: Detecting Breast Cancer Using AI-Assisted Mammography
12.8.4 Case Study 4: Deep Learning-Based Automated Stroke Detection in MRI
12.8.5 Case Study 5: Detecting COVID-19 with AI-Enhanced Chest X-Rays
12.8.6 Comparative Summary of Case Studies
12.8.7 Cross-Domain Observations
12.9 Limitations
12.10 Conclusion
References
13 Transformers and Deep Learning in Medical Imaging: Future Directions and Impact
13.1 Introduction
13.2 Role of Deep Learning in Medical Imaging
13.3 CNN Components and Mathematical Foundations
13.4 Introduction to Transformers
13.5 Detailed Workflow of Self-Attention Mechanism
13.6 Comparative Advantages of Transformers over CNNS
13.7 Use Case: Tumor Segmentation Using Swin Transformers
13.8 Challenges and Limitations
13.9 Conclusion and Future Work
References
14 Cognitive Imaging: AI-Driven Transformation in Medical Diagnostics
14.1 Introduction
14.1.1 Artificial Intelligence (AI) and Deep Learning (DL)
14.1.2 Deep learning integration in medical imaging
14.1.3 Scope of Chapter
14.2 Major Imaging Modalities
14.3 Deep Learning
14.4 Applications of Deep Learning in Medical Imaging
14.5 Case Studies and Real-World Deployments
14.6 Challenges and Limitations
14.7 Future Directions and Innovations
14.8 Conclusion
References
15 Future of AI-ML and Their Potential Impact on Deep Learning Applications in Medical Diagnostics and Imaging
15.1 Introduction
15.2 Related Works
15.3 Progress in Medical Data Science Along the ML to DL Approach
15.3.1 ML to DL Interpretation of Medical Image Data
15.3.2 Personalized Medical Care Using Big Data
15.3.3 Medical Research Data
15.4 Medical and Healthcare Chatbot Technology
15.4.1 ChatGPT: The Latest Chatbot Technology Using Various Models
15.5 The Wide Range of Applications of ML and DL in Healthcare Administration
15.6 New Challenges to the Use of ML to DL in Healthcare
15.6.1 Standardization of Data
15.6.2 Creating Policies, Standards, and the Regulatory Framework
15.7 Conclusion
References
Mathematical Methods in the Digital Age

System requirements

Save as PDF Copy link into clipboard

Schweitzer Fachinformationen

Applied Mathematics for Healthcare Intelligent Systems

Description

More details

Other editions

Additional editions

Persons

Content

System requirements