Chee-Peng Lim, Vaidya A., Yen-Wei Chen, Jain T., Jain L.C. (eds.) Artificial Intelligence and Machine Learning for Healthcare: Vol. 1: Image and Data Analytics

Cham: Springer, 2022. — 239 p.Artificial intelligence (AI) and machine learning (ML) have transformed many standard and conventional methods in undertaking health and well-being issues of humans. AL/ML-based systems and tools play a critical role in this digital and big data era to address a variety of medical and healthcare problems, improving treatments and quality of care for patients.
This edition on AI and ML for healthcare consists of two volumes. The first presents selected AI and ML studies on medical imaging and healthcare data analytics, while the second unveils emerging methodologies and trends in AI and ML for delivering better medical treatments and healthcare services in the future.
In this first volume, progresses in AI and ML technologies for medical image, video, and signal processing as well as health information and data analytics are presented. These selected studies offer readers theoretical and practical knowledge and ideas pertaining to recent advances in AI and ML for effective and efficient image and data analytics, leading to state-of-the-art AI and ML technologies for advancing the healthcare sector.An Introduction to Artificial Intelligence in Healthcare
Introduction to Artificial Intelligence
Artificial Intelligence in Healthcare
Natural Language Processing (NLP) Technology
Machine Learning (ML) Algorithms
Artificial Neural Networks
Bayesian Classifier
Classification/Decision Trees Random Forest
Survival Regression Models
Cluster Analysis
Advantages of Artificial Intelligence in Healthcare
Limitations of Artificial Intelligence in Healthcare
Successful Applications of Artificial Intelligence in Healthcare
Conclusions
Appendix
Books
Radiomics: Approach to Precision MedicineMaterials and Methods
Building of a Database
Segmentation of Target Volume
Extraction and Selection of Useful Radiomics Features
Model Building Based on Machine Learning Technologies
Results and Discussion
ConclusionsArtificial Intelligence Based Strategies for Data-Driven Radial MRIRelated Work
Sparse Sampling Strategies
Contribution of the Manuscript
Problem Statement and Framework Description
Relationship Between Radial Projections and Image
Image Reconstruction, Resolution and Noise
Super-Resolution
Framework Details
Noise Threshold upper TT
Results and DiscussionUnsupervised Domain Adaptation Approach for Liver Tumor Detection in Multi-phase CT ImagesDomain-Shift Problem
Domain Adaptation
Domain Adaptation Using Adversarial Learning
Anchor-free Detector
Proposed Multi-phase Domain Adaptation Framework Using Adversarial Domain Classification Loss
Proposed Multi-phase Domain Adaptation Framework Using Adversarial Learning with Maximum Square Loss
Maximum Square Loss
Overall Framework with Adversarial Domain Classification and Maximum Square Loss
Experiments
Implementation Details
Dataset
Evaluation
Results
ConclusionsMulti-stage Synthetic Image Generation for the Semantic Segmentation of Medical ImagesRelated Works
Synthetic Image Generation
Image-to-Image Translation
Retinal Image Synthesis and Segmentation
Chest X-ray Image Synthesis and Segmentation
Multi-stage Image Synthesis
Image Generation
Evaluation of Multi-stage Methods
Datasets
Segmentation Network
Experimental Setup
Two-Stage Method Evaluation
Three-Stage Method Evaluation
ConclusionsClassification of Arrhythmia Signals Using Hybrid Convolutional Neural Network (CNN) ModelLiterature Review
Methodology
Results and Discussion
Conclusions
Appendix
Appendix
AppendixPolyp Segmentation with Deep Ensembles and Data AugmentationRelated Methods
Overview of the Propose System
Loss Functions
Data Augmentation
Shadows
Contrast and Motion Blur
Color Mapping
Experimental Results
Data and Testing Protocol
Experiments
ConclusionsAutistic Verbal Behavior ParametersEstate of the Art
Proposal, Materials and Methods
Testing Protocol
Analysis of Tests
Conclusions and Future WorkAdvances in Modelling Hospital Medical Wards
Introduction and Problem Addressed
Case Study and Data Analysis
Methodology and ResultsTracking Person-Centred Care Experiences Alongside Other Success Measures in Hearing Rehabilitation
Person-Centred Care in Research and Practice
Situated Action—Understanding the Context as a Basis for Meaningful Measures
Situated AI for Achieving High-Quality Person-Centred Care
Co-design for Person-Centred Care Measures
Co-design of Evaluation Instruments
Artificial Intelligence and PCC
Case Study: Co-creation of PCC Measures and Dashboard with Hearing Rehabilitation Provider
Method
Results
Stakeholder Workshops—Development of Tools
Stakeholder Feedback
Piloting the Dashboard
Discussion
Summary of Case Study
Discussion on Opportunities and Challenges for AI
Quality of Data
ConclusionsBioGNN: How Graph Neural Networks Can Solve Biological Problems
Overview of the Research Area
Biological Problems on Graphs
Deep Learning Models for Biological Graphs
Graph Neural Networks
The Graph Neural Network Model
Composite Graph Neural Networks
Layered Graph Neural Networks
Approximation Power of Graph Neural Networks
Software Implementation
Biological Applications
Prediction of Protein-Protein Interfaces
Drug Side-Effect Prediction
Molecular Graph Generation
Conclusions and Future Perspectives