This book aims to provide physicians and scientists with the basics of Artificial Intelligence (AI) with a special focus on medical imaging. The contents of the book provide an introduction to the main topics of artificial intelligence currently applied on medical image analysis.
The book starts with a chapter explaining the basic terms used in artificial intelligence for novice readers and embarks on a series of chapters each one of which provides the basics on one AI-related topic. The second chapter presents the programming languages and available automated tools that enable the development of AI applications for medical imaging. The third chapter endeavours to analyse the main traditional machine learning techniques, explaining algorithms such as random forests, support vector machines as well as basic neural networks. The applications of those machines on the analysis of radiomics data is expanded in the fourth chapter to allow the understanding of algorithms used to build classifiers for the diagnosis of disease processes with the use of radiomics. Chapter five provides the basics of natural language processing which has revolutionized the analysis of complex radiological reports and chapter six affords a succinct introduction to convolutional neural networks which have revolutionized medical image analysis enabling automated image-based diagnosis, image enhancement (e.g. denoising), protocolling etc. The penultimate chapter provides an introduction to data preprocessing for use in the aforementioned artificial intelligence applications. The book concludes with a chapter demonstrating AI-based tools already in radiological practice while providing an insight about the foreseeable future.
It will be a valuable resource for radiologists, computer scientists and postgraduate students working on medical image analysis.
Author(s): Michail E. Klontzas; Salvatore Claudio Fanni; Emanuele Neri;
Series: Imaging Informatics for Healthcare Professionals
Edition: 1
Publisher: Springer Nature Switzerland
Year: 2023
Language: English
Commentary: Medicine//Technology//Imaging Informatics//Radiology
Pages: viii; 165
City: Cham
Tags: Imaging / Radiology; Health Informatics; Deep Learning; Machine Learning; Radiomics; Informatics; Natural Language Processing; NLP; Artificial Intelligence; AI;
Preface
Contents
1 What Is Artificial Intelligence: History and Basic Definitions
1.1 Twentieth Century: Setting the Foundations of Artificial Intelligence
1.1.1 Artificial Intelligence
1.1.2 Machine Learning
1.1.2.1 Neural Networks
1.2 The Period 2000–2020
References
2 Using Commercial and Open-Source Tools for Artificial Intelligence: A Case Demonstration on a Complete Radiomics Pipeline
2.1 Introduction
2.2 Image Segmentation
2.3 Image Pre-processing
2.4 Radiomics Extraction
2.5 Radiomics Modeling
2.6 From Theory to Practice
2.7 Discussion
2.8 Conclusion
References
3 Introduction to Machine Learning in Medicine
3.1 Introduction
3.2 What Is Machine Learning?
3.3 Principal ML Algorithms
3.3.1 Supervised Machine Learning
3.3.1.1 Linear Regression
3.3.1.2 Support Vector Machine
3.3.1.3 Random Decision Forest
3.3.1.4 Extreme Gradient Boosting
3.3.1.5 Naive Bayes
3.3.2 Unsupervised Machine Learning
3.3.2.1 k-Nearest Neighbours
3.3.2.2 Principal Component Analysis
3.3.2.3 k-Means Clustering
3.3.3 Artificial Neural Networks
3.3.4 Reinforcement Learning
3.4 Issues and Challenges
3.4.1 Data Management
3.4.2 Machine Learning Model Evaluation Metrics
3.4.3 Explainability, Interpretability, and Ethical and Legal Issues
3.4.4 Perspectives in Personalized Medicine
3.5 Conclusions
References
4 Machine Learning Methods for Radiomics Analysis: Algorithms Made Easy
4.1 Introduction
4.2 Methods for Region of Interest Segmentation
4.2.1 R-CNN
4.2.2 U-Net and V-Net
4.2.3 DeepLab
4.3 Methods for Exploratory Data Analysis
4.3.1 Correlation Analysis
4.3.2 Clustering
4.3.3 Principal Component Analysis
4.4 Methods for Feature Selection
4.4.1 Boruta
4.4.2 Recursive Feature Elimination
4.4.3 Maximum Relevance: Minimum Redundancy
4.5 Methods for Predictive Model Construction
4.5.1 Decision Trees
4.5.2 Random Forests
4.5.3 Gradient Boosting Algorithms
4.5.4 Support Vector Machines
4.5.5 Neural Networks
4.6 Conclusion
References
5 Natural Language Processing
5.1 Brief History of NLP
5.2 Basic of Natural Language Processing
5.3 Current Applications of Natural Language Processing
References
6 Deep Learning Fundamentals
Abbreviations
6.1 Deep Learning in Medical Imaging
6.1.1 Key Concepts
6.1.2 DL Architectures for Medical Image Analysis*-9pt
6.1.3 Cloud Computing for Deep Learning
6.1.4 DL-Based Computer-Aided Diagnosis
6.2 Quality and Biases of Medical Databases
6.3 Pre-processing for Deep Learning
6.3.1 CT Radiation Absorption Map to Grayscale
6.3.2 MRI Bias Field Correction
6.3.3 Tissue-Based Standardization
6.3.4 Pixel Intensities Normalization
6.3.5 Harmonization
6.3.6 Spacing Resampling
6.3.7 Image Enhancement
6.3.8 Image Denoising
6.3.9 Lowering Dimensionality at the Imaging Level for Deep Learning
6.4 Learning Strategies
6.4.1 Transfer Learning
6.4.2 Multi-task Learning
6.4.3 Ensemble Learning
6.4.4 Multimodal Learning
6.4.5 Federated Learning
6.5 Interpretability and Trustworthiness of Artificial Intelligence
6.5.1 Reproducibility
6.5.2 Traceability
6.5.3 Explainability
6.5.4 Trustworthiness
References
7 Data Preparation for AI Analysis
7.1 Introduction
7.2 Data Quality and Numerosity
7.2.1 Intrinsic Image Quality
7.2.2 Image Diagnostic Quality
7.2.3 Image Quality for AI Analyses
7.3 Data Preprocessing for Machine Learning Analyses
7.3.1 The Machine Learning Pipeline
7.3.2 The Machine Learning Pipeline: A Case Study
References
8 Current Applications of AI in Medical Imaging
8.1 Introduction
8.2 Detection
8.3 Classification
8.4 Segmentation
8.4.1 Monitoring
8.4.2 Prediction
8.4.3 Additional Applications
8.4.3.1 Image Enhancement and Reconstruction
8.4.4 Workload Reduction?
8.5 Conclusions
References
