FedGS: Federated Gradient Scaling for Heterogeneous Medical Image Segmentation

TL;DR

FedGS introduces a federated learning aggregation method that enhances medical image segmentation, especially for small lesions, by addressing data heterogeneity and leveraging disentangled representation learning.

Contribution

The paper presents FedGS, a novel federated learning aggregation technique that improves segmentation of small, under-represented targets by incorporating disentangled representation learning.

Findings

FedGS outperforms FedAvg in segmentation accuracy for small lesions.

FedGS maintains overall model performance across heterogeneous datasets.

The method demonstrates robustness on PolypGen and LiTS datasets.

Abstract

Federated Learning (FL) in Deep Learning (DL)-automated medical image segmentation helps preserving privacy by enabling collaborative model training without sharing patient data. However, FL faces challenges with data heterogeneity among institutions, leading to suboptimal global models. Integrating Disentangled Representation Learning (DRL) in FL can enhance robustness by separating data into distinct representations. Existing DRL methods assume heterogeneity lies solely in style features, overlooking content-based variability like lesion size and shape. We propose FedGS, a novel FL aggregation method, to improve segmentation performance on small, under-represented targets while maintaining overall efficacy. FedGS demonstrates superior performance over FedAvg, particularly for small lesions, across PolypGen and LiTS datasets. The code and pre-trained checkpoints are available at the following link: https://github.com/Trustworthy-AI-UU-NKI/Federated-Learning-Disentanglement