People-Centred Medical Image Analysis

TL;DR

This paper introduces PecMan, a human-AI framework that jointly optimizes fairness, accuracy, and workflow efficiency in medical image analysis, addressing clinical adoption barriers.

Contribution

It proposes a novel dynamic gating mechanism for balanced case assignment and introduces the FairHAI benchmark for evaluating trade-offs in clinical AI systems.

Findings

PecMan outperforms existing methods in balancing accuracy, fairness, and workload.

The benchmark effectively evaluates trade-offs in clinical AI deployment.

Code will be available upon acceptance.

Abstract

Recent advances in data-centric medical AI have produced highly accurate diagnostic systems, but the emphasis on data curation and performance metrics has not translated into widespread clinical adoption. We conjecture that this limited uptake stems from insufficient attention dedicated to the optimisation of fair performance across diverse patient populations and to workflow integration: performance biases can create regulatory barriers, and poorly integrated automation can disrupt clinical routines, degrade the quality of human-AI collaboration, and reduce clinicians' willingness to adopt AI tools. Prior work on workflow integration (e.g., Learning to Defer (L2D) and Learning to Complement (L2C)) and AI fairness has typically examined these challenges in isolation, overlooking their natural interdependence and the practical constraints of clinical environments, such as restricted clinician availability. We propose People-Centred Medical Image Analysis (PecMan), a human-AI framework that jointly optimises fairness, diagnostic accuracy, and workflow effectiveness through a dynamic gating mechanism that assigns cases to AI, clinicians, or both under clinician workload constraints. We also introduce the Fairness and Human-Centred AI (FairHAI) benchmark for evaluating trade-offs between accuracy, fairness, and clinician workload. Experiments using this benchmark show that PecMan consistently outperforms existing methods, paving the way for more trustworthy and clinically viable AI systems. Code will be available upon paper acceptance.