A Review of Causality for Learning Algorithms in Medical Image Analysis

Abstract

Medical image analysis is a vibrant research area that offers doctors and medical practitioners invaluable 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. In this paper we analyze machine learning for medical image analysis within the framework of Technology Readiness Levels and review how causal analysis methods can fill a gap when creating robust and adaptable medical image analysis algorithms. We review methods using causality in medical imaging AI/ML and find that causal analysis has the potential to mitigate critical problems for clinical translation but that uptake and clinical downstream research has been limited so far.

A Review of the Role of Causality in Developing Trustworthy AI Systems

“…The literature provides many reviews which focus on the usage of SCMs in healthcare and personalized medicine [231,275,306]. Zhang et al [306] provided an introduction to causality using different medical examples like lung cancer causal graphs and shed light on the different challenges and issues encountered when dealing with causal inference, such as missing data, biased data, and transferability of models.…”

“…Zhang et al [306] provided an introduction to causality using different medical examples like lung cancer causal graphs and shed light on the different challenges and issues encountered when dealing with causal inference, such as missing data, biased data, and transferability of models. Vlontzos et al [275] present the benefits of introducing causality and its use in the field of medical imaging. Their survey reviews several applications that incorporate Causality in Healthcare Structural Causal Model Analysing Diseases [157,231,242] Drugs Repurposing [23] Improving Diagnosis [219,271] Potential Outcome Framework Analysing Drugs Outcome [73,86,190,243,244,314] Fig.…”

Overcoming the Challenges in the Development and Implementation of Artificial Intelligence in Radiology: A Comprehensive Review of Solutions Beyond Supervised Learning

“…Causal learning is an emerging field of machine learning that focuses on the causal relationships between variables in a system [ 164 165 ]. The goal of causal learning is to understand the underlying mechanisms governing a system and predict how changes in one variable affect another.…”