中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
首页 机构 成果 学者
  
  1. CAS IR Grid
  2. 自动化研究所
  3. 中国科学院自动化研究所
  4. 智能感知与计算研究中心
FedBrain: A robust multi-site brain network analysis framework based on federated learning for brain disease diagnosis

文献类型：期刊论文

作者Zhang, Chang1; Meng, Xiangzhu2; Liu, Qiang2; Wu, Shu2; Wang, Liang2; Ning, Huansheng1
刊名NEUROCOMPUTING
出版日期2023-11-28
卷号559页码:13
ISSN号0925-2312
关键词Functional magnetic resonance image Brain network Federated learning Deep neural networks Brain disease diagnosis
DOI10.1016/j.neucom.2023.126791
通讯作者Meng, Xiangzhu(xiangzhu.meng@cripac.ia.ac.cn)
英文摘要In recent years, deep learning models have shown their advantages in neuroimage analysis, such as brain disease diagnosis. Unfortunately, it is usually difficult to acquire numerous brain networks at a single centralized site to effectively train a high-quality deep learning model. To address this issue, federated learning (FL) has gained popularity in brain disease diagnosis, which allows deep learning models to be trained without centralizing data. However, most FL-based works might still face two following challenges. Firstly, the high -dimensional features of brain networks are often far larger than sample size, which might lead to poor performance due to the curse of dimensionality. Secondly, differences in data distributions across different sites can impact the communication efficiency and performance of FL models. To overcome these challenges, we design a novel FL framework for diagnosing brain disorders, named FedBrain. Firstly, FedBrain proposes data augmentation based on L1 regularization to select significant features shared by all clients. The domain alignment loss based on the maximum mean discrepancy criterion is introduced to minimize differences in the marginal and conditional distributions between local clients. Furthermore, FedBrain proposes a personalized predictor based on mixture of experts to adapt to different clients, using a global and private predictor as two experts. Eventually, FedBrain integrates the above modules with differential privacy and homomorphic encryption into a unified FL framework. Experimental results on the Autism Brain Imaging Data Exchange (ABIDE) dataset demonstrate its effectiveness and robustness, which shows that FedBrain can reduce the communication burden of FL and achieve the highest average accuracy of 79% against other counterparts.
WOS关键词FMRI ; CONNECTIVITY ; IDENTIFICATION ; MRI ; EEG
资助项目National Natural Science Foundation of China[62141608] ; National Natural Science Foundation of China[62206291] ; National Natural Science Foundation of China[62372454]
WOS研究方向Computer Science
语种英语
出版者ELSEVIER
WOS记录号WOS:001079155400001
资助机构National Natural Science Foundation of China
源URL[http://ir.ia.ac.cn/handle/173211/53065]  
专题自动化研究所_智能感知与计算研究中心
多模态人工智能系统全国重点实验室
通讯作者Meng, Xiangzhu
作者单位1.Univ Sci & Technol Beijing, Sch Comp & Commun Engn, Beijing 100083, Peoples R China
2.Chinese Acad Sci, Inst Automat, Ctr Res Intelligent Percept & Comp, Beijing, Peoples R China
推荐引用方式
GB/T 7714		 Zhang, Chang,Meng, Xiangzhu,Liu, Qiang,et al. FedBrain: A robust multi-site brain network analysis framework based on federated learning for brain disease diagnosis[J]. NEUROCOMPUTING,2023,559:13.
APA Zhang, Chang,Meng, Xiangzhu,Liu, Qiang,Wu, Shu,Wang, Liang,&Ning, Huansheng.(2023).FedBrain: A robust multi-site brain network analysis framework based on federated learning for brain disease diagnosis.NEUROCOMPUTING,559,13.
MLA Zhang, Chang,et al."FedBrain: A robust multi-site brain network analysis framework based on federated learning for brain disease diagnosis".NEUROCOMPUTING 559(2023):13.

入库方式： OAI收割

来源：自动化研究所

浏览0
下载0
收藏0
其他版本

除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。