Machine Learning and Other Artificial Intelligence Applications, An Issue of Neuroimaging Clinics of North America

1st Edition, Volume 30-4 - October 20, 2020
Editor: Reza Forghani
Language: English
Hardback ISBN:
9 7 8 - 0 - 3 2 3 - 7 1 2 4 4 - 6
eBook ISBN:
9 7 8 - 0 - 3 2 3 - 7 1 2 4 5 - 3

This issue of Neuroimaging Clinics of North America focuses on Artificial Intelligence and Machine Learning and is edited by Dr. Reza Forghani. Articles will include: A Brief… Read more

Machine Learning and Other Artificial Intelligence Applications, An Issue of Neuroimaging Clinics of North America

Purchase options

Info / Buy

LIMITED OFFER

Save 50% on book bundles

Immediately download your ebook while waiting for your print delivery. No promo code is needed.

Institutional subscription on ScienceDirect

Request a sales quote

This issue of Neuroimaging Clinics of North America focuses on Artificial Intelligence and Machine Learning and is edited by Dr. Reza Forghani. Articles will include: A Brief History of Artificial Intelligence; Evolution of Approaches for Computerized Image Analysis; Overview of Machine Learning Part 1: Classic Approaches; Overview of Machine Learning Part 2: Artificial Neural Networks & Deep Learning; Overview of Natural Language Processing; Artificial Intelligence & Stroke Imaging: An East Coast Perspective; Artificial Intelligence & Stroke Imaging: A West Coast Perspective; Artificial Intelligence Applications for Brain Tumor Imaging; Diverse Applications of Artificial Intelligence in Neuroradiology; Artificial Intelligence Applications for Head and Neck Imaging; Artificial Intelligence Applications for Predictive Analytics and Workflow Optimization; Artificial Intelligence, Advanced Visualization, and 3D Printing; Ethical & Legal Considerations for Artificial Intelligence; Comprehensive (or 360) Artificial Intelligence: Beyond Image Interpretation Alone, and more!

Cover image
Title page
Table of Contents
Copyright
CME Accreditation Page
Neuroimaging Clinics of North America
Contributors
Foreword
Preface
Brief History of Artificial Intelligence
Key points
Introduction
Earliest attempts at artificial intelligence
Cycles of interest in artificial intelligence and the first and second artificial intelligence winters
Resurgence of interest in artificial intelligence: the third wave
Summary
Knowledge Based Versus Data Based: A Historical Perspective on a Continuum of Methodologies for Medical Image Analysis
Key points
Introduction
The knowledge-driven versus data-driven continuum
The knowledge-driven versus data-driven continuum: a historical perspective
Summary
Overview of Machine Learning: Part 2: Deep Learning for Medical Image Analysis
Key points
Introduction
Deep learning architectures
Training and validation of deep learning models
Limitations and future directions
Summary
Machine Learning Algorithm Validation: From Essentials to Advanced Applications and Implications for Regulatory Certification and Deployment
Key points
Introduction
Estimating error in model evaluation
Evaluation of machine learning models: terminology
Model evaluation workflow
Data used for model evaluation
Implication of robust experimental design for regulatory approval and certification
Summary
Review of Natural Language Processing in Radiology
Key points
Introduction
What is natural language processing?
Word embeddings
Rules-based and classic machine learning techniques
Clinical applications
Limitations
Summary
An East Coast Perspective on Artificial Intelligence and Machine Learning: Part 1: Hemorrhagic Stroke Imaging and Triage
Key points
Introduction
Automatic detection of hemorrhagic stroke
Hemorrhage segmentation and quantitation
Prediction of hemorrhage expansion
Summary
An East Coast Perspective on Artificial Intelligence and Machine Learning: Part 2: Ischemic Stroke Imaging and Triage
Key points
Introduction
Infarct localization on computed tomography scans
Infarct volume estimation using MR imaging
Automatic computed tomography-based stroke triage
Detection of large vessel occlusions
Core and penumbra estimation using computed tomography perfusion
Challenges and future directions
Artificial Intelligence and Stroke Imaging: A West Coast Perspective
Key points
Introduction
Artificial intelligence applications for the acquisition and postprocessing of stroke imaging data
Diagnosis approach: automatic lesion identification and/or segmentation
Prognosis approach: prediction of treatment complications and clinical outcomes
Summary: perspectives of artificial intelligence and stroke imaging
Updates on Deep Learning and Glioma: Use of Convolutional Neural Networks to Image Glioma Heterogeneity
Key points
Background
Isocitrate dehydrogenase mutations
1p19q codeletion
O-6-methylguanine-DNA-methyltransferease promoter
Epidermal growth factor receptor variant III amplification
Pseudoprogression
Overall survival after diagnosis with glioblastoma multiforme
Challenges and the future
Diverse Applications of Artificial Intelligence in Neuroradiology
Key points
Introduction
Diverse applications for artificial intelligence in neuroradiology
Discussion
Machine Learning Applications for Head and Neck Imaging
Key points
Introduction
Radiomics and machine learning
Application of machine learning in head and neck imaging
Barriers and challenges for deep learning applications in head and neck imaging
Summary
Online Only Articles, available at www.neuroimaging.theclinics.com, ScienceDirect, and ClinicalKey
Artificial Intelligence Applications for Workflow, Process Optimization and Predictive Analytics
Key points
Introduction
Natural language processing
Pre-image acquisition workflow enhancement: Scan ordering, protocoling, and scheduling
Artificial Intelligence AI applications during image acquisition: smart devices
Post–image acquisition workflow enhancement: before and during image interpretation
Other artificial intelligence applications for diagnostic and workflow enhancement
Summary and future directions
Overview of Machine Learning Part 1: Fundamentals and Classic Approaches
Key points
Introduction
Terminology
Predictive modeling workflow in machine learning
Supervised learning
Concluding remarks