pFLFE: Cross-silo Personalized Federated Learning via Feature Enhancement on Medical Image Segmentation

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Xie, Luyuan, Lin, Manqing, Liu, Siyuan, Xu, ChenMing, Luan, Tianyu, Li, Cong, Fang, Yuejian, Shen, Qingni, Wu, Zhonghai
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866929404372844544
author Xie, Luyuan
Lin, Manqing
Liu, Siyuan
Xu, ChenMing
Luan, Tianyu
Li, Cong
Fang, Yuejian
Shen, Qingni
Wu, Zhonghai
author_facet Xie, Luyuan
Lin, Manqing
Liu, Siyuan
Xu, ChenMing
Luan, Tianyu
Li, Cong
Fang, Yuejian
Shen, Qingni
Wu, Zhonghai
contents In medical image segmentation, personalized cross-silo federated learning (FL) is becoming popular for utilizing varied data across healthcare settings to overcome data scarcity and privacy concerns. However, existing methods often suffer from client drift, leading to inconsistent performance and delayed training. We propose a new framework, Personalized Federated Learning via Feature Enhancement (pFLFE), designed to mitigate these challenges. pFLFE consists of two main stages: feature enhancement and supervised learning. The first stage improves differentiation between foreground and background features, and the second uses these enhanced features for learning from segmentation masks. We also design an alternative training approach that requires fewer communication rounds without compromising segmentation quality, even with limited communication resources. Through experiments on three medical segmentation tasks, we demonstrate that pFLFE outperforms the state-of-the-art methods.
format Preprint
id arxiv_https___arxiv_org_abs_2407_00462
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle pFLFE: Cross-silo Personalized Federated Learning via Feature Enhancement on Medical Image Segmentation
Xie, Luyuan
Lin, Manqing
Liu, Siyuan
Xu, ChenMing
Luan, Tianyu
Li, Cong
Fang, Yuejian
Shen, Qingni
Wu, Zhonghai
Computer Vision and Pattern Recognition
Artificial Intelligence
In medical image segmentation, personalized cross-silo federated learning (FL) is becoming popular for utilizing varied data across healthcare settings to overcome data scarcity and privacy concerns. However, existing methods often suffer from client drift, leading to inconsistent performance and delayed training. We propose a new framework, Personalized Federated Learning via Feature Enhancement (pFLFE), designed to mitigate these challenges. pFLFE consists of two main stages: feature enhancement and supervised learning. The first stage improves differentiation between foreground and background features, and the second uses these enhanced features for learning from segmentation masks. We also design an alternative training approach that requires fewer communication rounds without compromising segmentation quality, even with limited communication resources. Through experiments on three medical segmentation tasks, we demonstrate that pFLFE outperforms the state-of-the-art methods.
title pFLFE: Cross-silo Personalized Federated Learning via Feature Enhancement on Medical Image Segmentation
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2407.00462