A highly generalized federated learning algorithm for brain tumor segmentation

Abstract Brain image segmentation plays a pivotal role in modern healthcare by enabling precise diagnosis and treatment planning. Federated Learning (FL) enables collaborative model training across institutions while safeguarding sensitive patient data. The integration of these technologies holds si...

Full description

Saved in:
Bibliographic Details
Main Authors: Jun Wen, Xiusheng Li, Xin Ye, Xiaoli Li, Hang Mao
Format: Article
Language:English
Published: Nature Portfolio 2025-07-01
Series:Scientific Reports
Subjects:
Online Access:https://doi.org/10.1038/s41598-025-05297-2
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849334762038099968
author Jun Wen
Xiusheng Li
Xin Ye
Xiaoli Li
Hang Mao
author_facet Jun Wen
Xiusheng Li
Xin Ye
Xiaoli Li
Hang Mao
author_sort Jun Wen
collection DOAJ
description Abstract Brain image segmentation plays a pivotal role in modern healthcare by enabling precise diagnosis and treatment planning. Federated Learning (FL) enables collaborative model training across institutions while safeguarding sensitive patient data. The integration of these technologies holds significant potential for advancing artificial intelligence (AI) in healthcare. However, medical institutions frequently encounter data imbalances, where some have limited annotated brain imaging data, whereas others possess larger datasets and more diverse cases. Such data exhibit non-independent, non-identically distributed characteristics, which adversely affect segmentation accuracy and generalizability. To address these issues, this paper proposes a client-side brain tumor image segmentation model utilizing Virtual Adversarial Training (VAT) integrated into a 3D U-Net to improve model performance under conditions of limited datasets, effectively addressing data scarcity and imbalance within the federated learning environment by optimizing the use of brain tumor image data held by each client. FedHG introduces an effective federated model aggregation strategy that leverages key parameters, specifically the ‘weights’ derived from a public validation dataset. Additionally, instance normalization parameters are incorporated into client models during training. These strategies collectively enhance the generalizability of the federated model. Empirical experiments validate the proposed algorithm, showing a 2.2% improvement in the Dice Similarity Coefficient (DSC) for brain tumor segmentation over the baseline federated learning algorithm, with a marginal 3% reduction in performance compared to centralized training, highlighting its practical applicability.
format Article
id doaj-art-5d111b7e3478461d99fb0793a3acda84
institution Kabale University
issn 2045-2322
language English
publishDate 2025-07-01
publisher Nature Portfolio
record_format Article
series Scientific Reports
spelling doaj-art-5d111b7e3478461d99fb0793a3acda842025-08-20T03:45:28ZengNature PortfolioScientific Reports2045-23222025-07-0115111510.1038/s41598-025-05297-2A highly generalized federated learning algorithm for brain tumor segmentationJun Wen0Xiusheng Li1Xin Ye2Xiaoli Li3Hang Mao4School of Information and Software Engineering, University of Electronic Science and Technology of ChinaSichuan Xinwang Bank, ChinaSchool of Information and Software Engineering, University of Electronic Science and Technology of ChinaComputer School, HuBei University of Arts and ScienceSichuan Xinwang Bank, ChinaAbstract Brain image segmentation plays a pivotal role in modern healthcare by enabling precise diagnosis and treatment planning. Federated Learning (FL) enables collaborative model training across institutions while safeguarding sensitive patient data. The integration of these technologies holds significant potential for advancing artificial intelligence (AI) in healthcare. However, medical institutions frequently encounter data imbalances, where some have limited annotated brain imaging data, whereas others possess larger datasets and more diverse cases. Such data exhibit non-independent, non-identically distributed characteristics, which adversely affect segmentation accuracy and generalizability. To address these issues, this paper proposes a client-side brain tumor image segmentation model utilizing Virtual Adversarial Training (VAT) integrated into a 3D U-Net to improve model performance under conditions of limited datasets, effectively addressing data scarcity and imbalance within the federated learning environment by optimizing the use of brain tumor image data held by each client. FedHG introduces an effective federated model aggregation strategy that leverages key parameters, specifically the ‘weights’ derived from a public validation dataset. Additionally, instance normalization parameters are incorporated into client models during training. These strategies collectively enhance the generalizability of the federated model. Empirical experiments validate the proposed algorithm, showing a 2.2% improvement in the Dice Similarity Coefficient (DSC) for brain tumor segmentation over the baseline federated learning algorithm, with a marginal 3% reduction in performance compared to centralized training, highlighting its practical applicability.https://doi.org/10.1038/s41598-025-05297-2Federated learningBrain tumor segmentationMachine learningVirtual adversarial trainingModel aggregation
spellingShingle Jun Wen
Xiusheng Li
Xin Ye
Xiaoli Li
Hang Mao
A highly generalized federated learning algorithm for brain tumor segmentation
Scientific Reports
Federated learning
Brain tumor segmentation
Machine learning
Virtual adversarial training
Model aggregation
title A highly generalized federated learning algorithm for brain tumor segmentation
title_full A highly generalized federated learning algorithm for brain tumor segmentation
title_fullStr A highly generalized federated learning algorithm for brain tumor segmentation
title_full_unstemmed A highly generalized federated learning algorithm for brain tumor segmentation
title_short A highly generalized federated learning algorithm for brain tumor segmentation
title_sort highly generalized federated learning algorithm for brain tumor segmentation
topic Federated learning
Brain tumor segmentation
Machine learning
Virtual adversarial training
Model aggregation
url https://doi.org/10.1038/s41598-025-05297-2
work_keys_str_mv AT junwen ahighlygeneralizedfederatedlearningalgorithmforbraintumorsegmentation
AT xiushengli ahighlygeneralizedfederatedlearningalgorithmforbraintumorsegmentation
AT xinye ahighlygeneralizedfederatedlearningalgorithmforbraintumorsegmentation
AT xiaolili ahighlygeneralizedfederatedlearningalgorithmforbraintumorsegmentation
AT hangmao ahighlygeneralizedfederatedlearningalgorithmforbraintumorsegmentation
AT junwen highlygeneralizedfederatedlearningalgorithmforbraintumorsegmentation
AT xiushengli highlygeneralizedfederatedlearningalgorithmforbraintumorsegmentation
AT xinye highlygeneralizedfederatedlearningalgorithmforbraintumorsegmentation
AT xiaolili highlygeneralizedfederatedlearningalgorithmforbraintumorsegmentation
AT hangmao highlygeneralizedfederatedlearningalgorithmforbraintumorsegmentation