Medical Imaging AI Competitions Lack Fairness

TL;DR

This study reveals significant fairness issues in medical imaging AI competitions, showing that datasets often lack representativeness and accessibility, which hampers clinical relevance and reproducibility.

Contribution

The paper provides a comprehensive systematic analysis of 241 challenges, highlighting biases and access issues that undermine the fairness and utility of current benchmarks.

Findings

Datasets show geographic and modality biases.

Access restrictions limit dataset reuse.

Benchmark datasets often lack comprehensive documentation.

Abstract

Benchmarking competitions are central to the development of artificial intelligence (AI) in medical imaging, defining performance standards and shaping methodological progress. However, it remains unclear whether these benchmarks provide data that are sufficiently representative, accessible, and reusable to support clinically meaningful AI. In this work, we assess fairness along two complementary dimensions: (1) whether challenge datasets are representative of real-world clinical diversity, and (2) whether they are accessible and legally reusable in line with the FAIR principles. To address this question, we conducted a large-scale systematic study of 241 biomedical image analysis challenges comprising 458 tasks across 19 imaging modalities. Our findings show substantial biases in dataset composition, including geographic location, modality-, and problem type-related biases, indicating that current benchmarks do not adequately reflect real-world clinical diversity. Despite their widespread influence, challenge datasets were frequently constrained by restrictive or ambiguous access conditions, inconsistent or non-compliant licensing practices, and incomplete documentation, limiting reproducibility and long-term reuse. Together, these shortcomings expose foundational fairness limitations in our benchmarking ecosystem and highlight a disconnect between leaderboard success and clinical relevance.