FairFedMed: Benchmarking Group Fairness in Federated Medical Imaging with FairLoRA

TL;DR

This paper introduces FairFedMed, a comprehensive benchmark and dataset for evaluating fairness in federated medical imaging, and proposes FairLoRA, a fairness-aware federated learning framework that improves both accuracy and fairness across demographic groups.

Contribution

It establishes the first benchmark and dataset for fairness in medical federated learning and proposes FairLoRA, a novel low-rank approximation method that enhances fairness and efficiency.

Findings

FairLoRA achieves state-of-the-art accuracy in medical image classification.

FairLoRA significantly improves fairness across demographic groups.

The benchmark supports diverse medical modalities and demographic attributes.

Abstract

Fairness remains a critical concern in healthcare, where unequal access to services and treatment outcomes can adversely affect patient health. While Federated Learning (FL) presents a collaborative and privacy-preserving approach to model training, ensuring fairness is challenging due to heterogeneous data across institutions, and current research primarily addresses non-medical applications. To fill this gap, we establish the first experimental benchmark for fairness in medical FL, evaluating six representative FL methods across diverse demographic attributes and imaging modalities. We introduce FairFedMed, the first medical FL dataset specifically designed to study group fairness (i.e., demographics). It comprises two parts: FairFedMed-Oph, featuring 2D fundus and 3D OCT ophthalmology samples with six demographic attributes; and FairFedMed-Chest, which simulates real cross-institutional FL using subsets of CheXpert and MIMIC-CXR. Together, they support both simulated and real-world FL across diverse medical modalities and demographic groups. Existing FL models often underperform on medical images and overlook fairness across demographic groups. To address this, we propose FairLoRA, a fairness-aware FL framework based on SVD-based low-rank approximation. It customizes singular value matrices per demographic group while sharing singular vectors, ensuring both fairness and efficiency. Experimental results on the FairFedMed dataset demonstrate that FairLoRA not only achieves state-of-the-art performance in medical image classification but also significantly improves fairness across diverse populations. Our code and dataset can be accessible via link: https://wang.hms.harvard.edu/fairfedmed/.