FedCLAM: Client Adaptive Momentum with Foreground Intensity Matching for Federated Medical Image Segmentation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Siomos, Vasilis, Passerat-Palmbach, Jonathan, Tarroni, Giacomo
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916814382956544
author Siomos, Vasilis
Passerat-Palmbach, Jonathan
Tarroni, Giacomo
author_facet Siomos, Vasilis
Passerat-Palmbach, Jonathan
Tarroni, Giacomo
contents Federated learning is a decentralized training approach that keeps data under stakeholder control while achieving superior performance over isolated training. While inter-institutional feature discrepancies pose a challenge in all federated settings, medical imaging is particularly affected due to diverse imaging devices and population variances, which can diminish the global model's effectiveness. Existing aggregation methods generally fail to adapt across varied circumstances. To address this, we propose FedCLAM, which integrates \textit{client-adaptive momentum} terms derived from each client's loss reduction during local training, as well as a \textit{personalized dampening factor} to curb overfitting. We further introduce a novel \textit{intensity alignment} loss that matches predicted and ground-truth foreground distributions to handle heterogeneous image intensity profiles across institutions and devices. Extensive evaluations on two datasets show that FedCLAM surpasses eight cutting-edge methods in medical segmentation tasks, underscoring its efficacy. The code is available at https://github.com/siomvas/FedCLAM.
format Preprint
id arxiv_https___arxiv_org_abs_2506_22580
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle FedCLAM: Client Adaptive Momentum with Foreground Intensity Matching for Federated Medical Image Segmentation
Siomos, Vasilis
Passerat-Palmbach, Jonathan
Tarroni, Giacomo
Image and Video Processing
Artificial Intelligence
Computer Vision and Pattern Recognition
Federated learning is a decentralized training approach that keeps data under stakeholder control while achieving superior performance over isolated training. While inter-institutional feature discrepancies pose a challenge in all federated settings, medical imaging is particularly affected due to diverse imaging devices and population variances, which can diminish the global model's effectiveness. Existing aggregation methods generally fail to adapt across varied circumstances. To address this, we propose FedCLAM, which integrates \textit{client-adaptive momentum} terms derived from each client's loss reduction during local training, as well as a \textit{personalized dampening factor} to curb overfitting. We further introduce a novel \textit{intensity alignment} loss that matches predicted and ground-truth foreground distributions to handle heterogeneous image intensity profiles across institutions and devices. Extensive evaluations on two datasets show that FedCLAM surpasses eight cutting-edge methods in medical segmentation tasks, underscoring its efficacy. The code is available at https://github.com/siomvas/FedCLAM.
title FedCLAM: Client Adaptive Momentum with Foreground Intensity Matching for Federated Medical Image Segmentation
topic Image and Video Processing
Artificial Intelligence
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2506.22580