V — Systems & The Road Ahead
22
Ethics, Bias, Safety & The Future
AI in Medical Imaging
Preface
I — The Landscape of Medical Imaging
1
Introduction: Why AI in Medical Imaging
2
The Universe of Medical Images
3
How Images Live in a Hospital
4
Medical Image Viewers
II — Foundations: Machine Learning & Computer Vision
5
Machine Learning: The Concepts
6
What Computer Vision Can Do
7
Deep Learning Architectures
8
Generative & Frontier Models
9
Agentic AI in Medical Imaging
10
From Model to Product: Evaluation, Regulation, Deployment
III — Diagnostic Imaging, Modality by Modality
11
Chest X-ray
12
Computed Tomography (CT)
13
Magnetic Resonance Imaging (MRI)
14
Ultrasound & Echocardiography
15
Mammography & Breast Imaging
16
Nuclear Medicine: PET & SPECT
17
Ophthalmic Imaging: Fundus & OCT
IV — Interventional, Lab-Based & Video
18
Surgical & Endoscopic Video
19
Digital Pathology & Histology
20
The Remaining Map
V — Systems & The Road Ahead
21
Building an Imaging AI Platform
22
Ethics, Bias, Safety & The Future
Appendices
The Dataset Directory
The Model Zoo
FDA-Cleared AI Product Index
DICOM Quick Reference for ML Engineers
Dual Glossary
Table of contents
22.1
Fairness across populations
22.2
Automation bias and human–AI teaming
22.3
Liability and accountability
22.4
The economics and sustainability of imaging AI
22.5
Foundation-model consolidation and agentic radiology
22.6
What to watch next
Edit this page
Report an issue
V — Systems & The Road Ahead
22
Ethics, Bias, Safety & The Future
22
Ethics, Bias, Safety & The Future
Note
Draft chapter — outline only. Content coming soon.
22.1
Fairness across populations
22.2
Automation bias and human–AI teaming
22.3
Liability and accountability
22.4
The economics and sustainability of imaging AI
22.5
Foundation-model consolidation and agentic radiology
22.6
What to watch next
21
Building an Imaging AI Platform
The Dataset Directory