FedGS: Federated Gradient Scaling for Heterogeneous Medical Image Segmentation

Philip Schutte, Valentina Corbetta, Regina Beets-Tan, Wilson Silva
8/21/2024
eess.IVcs.CV

Official code: Trustworthy-AI-UU-NKI/Federated-Learning-Disentanglement (7 stars, last commit 2024-07-19).

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

View on arXivView PDF

Code Implementations(1)

Trustworthy-AI-UU-NKI/Federated-Learning-DisentanglementOfficial100%
72PythonJul 19, 20242 years ago

Similar Papers

FedLPPA: Learning Personalized Prompt and Aggregation for Federated Weakly-supervised Medical Image Segmentation

88% match1 repo192024

Continual Alignment for SAM: Rethinking Foundation Models for Medical Image Segmentation in Continual Learning

88% match2025

MCP-MedSAM: A Powerful Lightweight Medical Segment Anything Model Trained with a Single GPU in Just One Day

87% match1 repo132024

Adversarial Versus Federated: An Adversarial Learning based Multi-Modality Cross-Domain Federated Medical Segmentation

87% match1 repo22025

Adaptive Aggregation Weights for Federated Segmentation of Pancreas MRI

87% match2024

MedicoSAM: Robust Improvement of SAM for Medical Imaging

86% match1 repo322025

Cite this paper

@article{schutte2024fedgs,
  title  = {FedGS: Federated Gradient Scaling for Heterogeneous Medical Image Segmentation},
  author = {Philip Schutte and Valentina Corbetta and Regina Beets-Tan and Wilson Silva},
  year   = {2024},
  eprint = {2408.11701},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2408.11701v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2408.11701.svg)](https://codeofpaper.com/paper/2408.11701)

Discussion