CCVA-FL: Cross-Client Variations Adaptive Federated Learning for Medical Imaging

TL;DR

CCVA-FL introduces a novel federated learning approach for medical imaging that reduces cross-client variations by transforming images into a common feature space using synthetic data, enhancing model performance across decentralized datasets.

Contribution

The paper proposes CCVA-FL, a method that uses synthetic images generated via diffusion models to align data distributions across clients in federated learning for healthcare.

Findings

CCVA-FL outperforms vanilla federated averaging in accuracy.

Synthetic images effectively reduce data heterogeneity.

Method preserves privacy while improving model robustness.

Abstract

Federated Learning (FL) offers a privacy-preserving approach to train models on decentralized data. Its potential in healthcare is significant, but challenges arise due to cross-client variations in medical image data, exacerbated by limited annotations. This paper introduces Cross-Client Variations Adaptive Federated Learning (CCVA-FL) to address these issues. CCVA-FL aims to minimize cross-client variations by transforming images into a common feature space. It involves expert annotation of a subset of images from each client, followed by the selection of a client with the least data complexity as the target. Synthetic medical images are then generated using Scalable Diffusion Models with Transformers (DiT) based on the target client's annotated images. These synthetic images, capturing diversity and representing the original data, are shared with other clients. Each client then translates its local images into the target image space using image-to-image translation. The translated images are subsequently used in a federated learning setting to develop a server model. Our results demonstrate that CCVA-FL outperforms Vanilla Federated Averaging by effectively addressing data distribution differences across clients without compromising privacy.