Explainable AI for medical imaging: Explaining pneumothorax diagnoses with Bayesian Teaching

TL;DR

This paper explores using Bayesian Teaching to generate explanations in AI systems for medical imaging, aiming to enhance radiologist trust and collaboration in pneumothorax diagnosis.

Contribution

It introduces a novel explanation method based on Bayesian Teaching and evaluates its effectiveness in building appropriate trust among medical experts.

Findings

Experts successfully predicted AI decisions using Bayesian Teaching explanations.

Explanations increased trust when AI was correct, reducing over-reliance on incorrect AI judgments.

The approach supports effective human-AI collaboration in medical diagnostics.

Abstract

Limited expert time is a key bottleneck in medical imaging. Due to advances in image classification, AI can now serve as decision-support for medical experts, with the potential for great gains in radiologist productivity and, by extension, public health. However, these gains are contingent on building and maintaining experts' trust in the AI agents. Explainable AI may build such trust by helping medical experts to understand the AI decision processes behind diagnostic judgements. Here we introduce and evaluate explanations based on Bayesian Teaching, a formal account of explanation rooted in the cognitive science of human learning. We find that medical experts exposed to explanations generated by Bayesian Teaching successfully predict the AI's diagnostic decisions and are more likely to certify the AI for cases when the AI is correct than when it is wrong, indicating appropriate trust. These results show that Explainable AI can be used to support human-AI collaboration in medical imaging.