PCRFed: personalized federated learning with contrastive representation for non-independently and identically distributed medical image segmentation.

IF 3.2 4区 计算机科学 Q2 COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS
Shengyuan Liu, Ruofan Zhang, Mengjie Fang, Hailin Li, Tianwang Xun, Zipei Wang, Wenting Shang, Jie Tian, Di Dong
{"title":"PCRFed: personalized federated learning with contrastive representation for non-independently and identically distributed medical image segmentation.","authors":"Shengyuan Liu, Ruofan Zhang, Mengjie Fang, Hailin Li, Tianwang Xun, Zipei Wang, Wenting Shang, Jie Tian, Di Dong","doi":"10.1186/s42492-025-00191-0","DOIUrl":null,"url":null,"abstract":"<p><p>Federated learning (FL) has shown great potential in addressing data privacy issues in medical image analysis. However, varying data distributions across different sites can create challenges in aggregating client models and achieving good global model performance. In this study, we propose a novel personalized contrastive representation FL framework, named PCRFed, which leverages contrastive representation learning to address the non-independent and identically distributed (non-IID) challenge and dynamically adjusts the distance between local clients and the global model to improve each client's performance without incurring additional communication costs. The proposed weighted model-contrastive loss provides additional regularization for local models, optimizing their respective distributions while effectively utilizing information from all clients to mitigate performance challenges caused by insufficient local data. The PCRFed approach was evaluated on two non-IID medical image segmentation datasets, and the results show that it outperforms several state-of-the-art FL frameworks, achieving higher single-client performance while ensuring privacy preservation and minimal communication costs. Our PCRFed framework can be adapted to various encoder-decoder segmentation network architectures and holds significant potential for advancing the use of FL in real-world medical applications. Based on a multi-center dataset, our framework demonstrates superior overall performance and higher single-client performance, achieving a 2.63% increase in the average Dice score for prostate segmentation.</p>","PeriodicalId":29931,"journal":{"name":"Visual Computing for Industry Biomedicine and Art","volume":"8 1","pages":"6"},"PeriodicalIF":3.2000,"publicationDate":"2025-03-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11953490/pdf/","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Visual Computing for Industry Biomedicine and Art","FirstCategoryId":"94","ListUrlMain":"https://doi.org/10.1186/s42492-025-00191-0","RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS","Score":null,"Total":0}
引用次数: 0

Abstract

Federated learning (FL) has shown great potential in addressing data privacy issues in medical image analysis. However, varying data distributions across different sites can create challenges in aggregating client models and achieving good global model performance. In this study, we propose a novel personalized contrastive representation FL framework, named PCRFed, which leverages contrastive representation learning to address the non-independent and identically distributed (non-IID) challenge and dynamically adjusts the distance between local clients and the global model to improve each client's performance without incurring additional communication costs. The proposed weighted model-contrastive loss provides additional regularization for local models, optimizing their respective distributions while effectively utilizing information from all clients to mitigate performance challenges caused by insufficient local data. The PCRFed approach was evaluated on two non-IID medical image segmentation datasets, and the results show that it outperforms several state-of-the-art FL frameworks, achieving higher single-client performance while ensuring privacy preservation and minimal communication costs. Our PCRFed framework can be adapted to various encoder-decoder segmentation network architectures and holds significant potential for advancing the use of FL in real-world medical applications. Based on a multi-center dataset, our framework demonstrates superior overall performance and higher single-client performance, achieving a 2.63% increase in the average Dice score for prostate segmentation.

联合学习(FL)在解决医学图像分析中的数据隐私问题方面显示出巨大的潜力。然而,不同地点的数据分布各不相同,这给聚合客户端模型和实现良好的全局模型性能带来了挑战。在本研究中,我们提出了一种名为 PCRFed 的新型个性化对比表示 FL 框架,它利用对比表示学习来解决非独立和同分布(non-IID)挑战,并动态调整本地客户端与全局模型之间的距离,以提高每个客户端的性能,而不会产生额外的通信成本。所提出的加权模型对比损失为本地模型提供了额外的正则化,优化了它们各自的分布,同时有效地利用了来自所有客户端的信息,减轻了因本地数据不足而带来的性能挑战。我们在两个非 IID 医学影像分割数据集上对 PCRFed 方法进行了评估,结果表明它优于几种最先进的 FL 框架,在确保隐私保护和最低通信成本的同时,实现了更高的单客户端性能。我们的 PCRFed 框架可适用于各种编码器-解码器分割网络架构,在推动 FL 在实际医疗应用中的使用方面具有巨大潜力。基于多中心数据集,我们的框架展示了卓越的整体性能和更高的单客户端性能,使前列腺分割的平均 Dice 分数提高了 2.63%。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
来源期刊
CiteScore
5.60
自引率
0.00%
发文量
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信