Causal reasoning in medical imaging

Vlontzos A, Müller C, Kainz B (2025)

Publication Type: Book chapter / Article in edited volumes

Publication year: 2025

Publisher: Academic Press

Edited Volumes: Trustworthy AI in Medical Imaging

Series: The MICCAI Society

Pages Range: 367-381

ISBN: 9780443237614

DOI: 10.1016/B978-0-44-323761-4.00029-8

Open Access Link: https://www.sciencedirect.com/science/article/abs/pii/B9780443237614000298

Abstract

Medical image analysis is a vibrant research area that offers doctors and medical practitioners valuable insight and the ability to accurately diagnose and monitor disease. Machine learning provides an additional boost for this area. However, machine learning for medical image analysis is particularly vulnerable to natural biases like domain shifts that affect algorithmic performance and robustness.

This chapter analyzes machine learning for medical image analysis within the framework of Technology Readiness Levels and reviews how causal analysis methods can fill a gap when creating robust and adaptable medical image analysis algorithms. This work provides a review of the methods using causality in medical imaging AI/ML, and highlights the potential of causal analysis to mitigate critical problems for clinical translation.

Authors with CRIS profile

Christine Müller Professur für Image Data Exploration and Analysis Bernhard Kainz Professur für Image Data Exploration and Analysis

Involved external institutions

Imperial College London / The Imperial College of Science, Technology and Medicine GB United Kingdom (GB)

How to cite

APA:

Vlontzos, A., Müller, C., & Kainz, B. (2025). Causal reasoning in medical imaging. In Trustworthy AI in Medical Imaging. (pp. 367-381). Academic Press.

MLA:

Vlontzos, Athanasios, Christine Müller, and Bernhard Kainz. "Causal reasoning in medical imaging." Trustworthy AI in Medical Imaging. Academic Press, 2025. 367-381.

BibTeX: Download