联邦学习在医学图像处理任务中的研究综述

doi:10.11896/jsjkx.231200057

摘要/Abstract

摘要： 在医学领域,由于患者隐私问题,图像很难集中收集和标注,这给深度学习模型的训练和部署带来了较大困难。联邦学习作为一种能有效保护数据隐私的分布式学习框架,能够在参与方不共享数据的基础上进行联合建模,从技术上打破数据孤岛,其凭借这些优势在许多行业已经得到广泛应用。由于与医学图像处理的需求高度契合,近年来也涌现出许多应用于医学图像处理的联邦学习研究,然而大部分新的方法仍未被归纳分析,不利于后续的进一步探索。文中对联邦学习进行了简单的介绍,列举了其在医学图像处理方面的部分应用,并根据改进的方向对目前已有的研究进行了分类总结。最后,讨论了目前医学图像方向联邦学习所面临的问题和挑战,并对未来的研究方向进行了展望,希望给后续研究提供一定的帮助。

关键词: 联邦学习, 医学图像, 深度学习, 图像处理, 分布式学习, 隐私保护

Abstract: In the medical field,due to patient privacy concerns,it is difficult to collect and label images,which brings great difficulties to the training and deployment of deep learning models.As a distributed learning framework that can effectively protect data privacy,federated learning can conduct joint modeling on the basis that participants do not share data,and technically break the data island.With these advantages,it has been widely used in many industries.Due to the high degree of compliance with the needs of medical image processing,many federated learning research works applied to medical image processing have emerged in recent years.However,most of the new methods have not been summarized and analyzed,which is not conducive to further exploration.This paper gives a brief introduction to federated learning,lists some of its applications in medical image processing,and classifies and summarizes the existing research according to the improvement direction.Finally,the problems and challenges of federated learning in medical image are discussed,and future research directions are prospected,hoping to provide some help for subsequent research.

Key words: Federated learning, Medical image, Deep learning, Image processing, Distributed learning, Privacy protection

中图分类号:

TP391

刘育铭, 代煜, 陈公平. 联邦学习在医学图像处理任务中的研究综述[J]. 计算机科学, 2025, 52(1): 183-193. https://doi.org/10.11896/jsjkx.231200057

LIU Yuming, DAI Yu, CHEN Gongping. Review of Federated Learning in Medical Image Processing[J]. Computer Science, 2025, 52(1): 183-193. https://doi.org/10.11896/jsjkx.231200057

参考文献

[1]KRIZHEVSKY A,SUTSKEVER I,HINTON G.ImageNetClassification with Deep Convolutional Neural Networks [J].Communications of the ACM,2017,60(6):84-90.
[2]SIMONYAN K,ZISSERMAN A.Very Deep Convolutional Networks for Large-Scale Image Recognition [J].arXiv:1409.1556,2014.
[3]HE K,ZHANG X,REN S,et al.Deep Residual Learning forImage Recognition [C]//2016 IEEE Conference on Computer Vision and Pattern Recognition.2016.
[4]VASWANI A,SHAZEER N,PARMAR N,et al.Attention IsAll You Need[C]//Proceedings of the 31st International Conference on Neural Information Processing Systems.2017:6000-6010.
[5]DOSOVITSKIY A,BEYER L,KOLESNIKOV A,et al.AnImage is Worth 16x16 Words:Transformers for Image Recognition at Scale [J].arXiv:2010.11929,2020.
[6]DENG J,DONG W,SOCHER R,et al.ImageNet:A large-scale hierarchical image database [C]//2009 IEEE Conference on Computer Vision and Pattern Recognition.2009:248-255.
[7]KRIZHEVSKY A.Learning Multiple Layers of Features fromTiny Images[J/OL].https://www.cs.toronto.edu/~kriz/lear-ning-features-2009-TR.pdf.
[8]ZHOU B,ZHAO H,PUIG X,et al.Semantic Understanding of Scenes Through the ADE20K Dataset [J].International Journal of Computer Vision,2016,127:302-321.
[9]LIU T,SIEGEL E,SHEN D.Deep Learning and Medical Image Analysis for COVID-19 Diagnosis and Prediction [J].Annual review of biomedical engineering,2022,24:179-201.
[10]QIU Z,XU T,LANGERMAN J,et al.A Deep Learning Ap-proach for Segmentation,Classification,and Visualization of 3-D High-Frequency Ultrasound Images of Mouse Embryos [J].IEEE Transactions on Ultrasonics,Ferroelectrics,and Frequency Control,2021,68:2460-2471.
[11]TALEB A,LIPPERT C,KLEIN T,et al.Multimodal Self-Supervised Learning for Medical Image Analysis [C]//Information Processing in Medical Imaging.2019.
[12]ZHU W,LIAO H,LI W,et al.Alleviating the Incompatibility between Cross Entropy Loss and Episode Training for Few-shot Skin Disease Classification [C]//International Conference on Medical Image Computing and Computer-Assisted Intervention.2020.
[13]KIRILLOV A,MINTUN E,RAVI N,et al.Segment Anything [J].arXiv:2304.02643,2023.
[14]MCMAHAN H B,MOORE E,RAMAGE D,et al.Communication-Efficient Learning of Deep Networks from Decentralized Data [C]//International Conference on Artificial Intelligence and Statistics.2016.
[15]LIU Y,FAN T,CHEN T,et al.FATE:An Industrial Grade Platform for Collaborative Learning With Data Protection [J].The Journal of Machine Learning Research,2021,22(1):10320-10325.
[16]ZILLER A,TRASK A,LOPARDO A,et al.PySyft:A Library for Easy Federated Learning [M]//Federated Learning Systems.2021:111-139.
[17]ROTH H R,CHANG K,SINGH P,et al.Federated Learning for Breast Density Classification:A Real-World Implementation [C]//DART/DCL@MICCAI.2020.
[18]JU C,ZHAO R,SUN J,et al.Privacy-Preserving Technology to Help Millions of People:Federated Prediction Model for Stroke Prevention [J].arXiv:2006.10517,2020.
[19]WEI Z Y,TANG Y,TENG Z,et al.Artificial intelligence fede-rated learning system based on chest X-ray films for pathogen diagnosis of community-acquired pneumonia in children[J].Chinese Journal of Interventional Imaging and Therapy,2024,21(6):368-373.
[20]BANERJEE S,MISRA R,PRASAD M,et al.Multi-diseasesClassification from Chest-X-ray:A Federated Deep Learning Approach [C]//Australasian Conference on Artificial Intelligence.2020.
[21]PRIYA K V,PETER J D.A federated approach for detecting the chest diseases using DenseNet for multi-label classification [J].Complex & Intelligent Systems,2021,8:3121-3129.
[22]YANG Y,JIN Z,SUZUKI K.Federated Tumor Segmentation with Patch-Wise Deep Learning Model [C]//MLMI@MICCAI.2022.
[23]PATI S,BAID U,EDWARDS B,et al.Federated learning enables big data for rare cancer boundary detection [J].arXiv:2204.10836,2022.
[24]LI D,KAR A,RAVIKUMAR N,et al.Fed-Sim:Federated Si-mulation for Medical Imaging [J].arXiv:2009.00668,2020.
[25]ZHU W,LUO J.Federated Medical Image Analysis with Virtual Sample Synthesis [C]//International Conference on Medical Image Computing and Computer-Assisted Intervention.2022.
[26]WANG P,SHEN C,ROTH H R,et al.Automated PancreasSegmentation Using Multi-institutional Collaborative Deep Learning [J].arXiv:2009.13148,2020.
[27]KADES K,SCHERER J,ZENK M,et al.Towards Real-World Federated Learning in Medical Image Analysis Using Kaapana [C]//DeCaF/FAIR@MICCAI.2022.
[28]NALAWADE S,GANESH C,WAGNER B C,et al.Federated Learning for Brain Tumor Segmentation Using MRI and Transformers [C]//BrainLes@MICCAI.2021.
[29]PAN E Y,ZHONG Y,LI P.Semi-Supervised Cervical SpineMRI Segmentation Model in Federated Heterogeneous Data[J].Computer Engineering,2024,50(9):367-376.
[30]SHELLER M J,EDWARDS B,REINA G A,et al.Federated learning in medicine:facilitating multi-institutional collaborations without sharing patient data[J/OL].https://www.nature.com/articles/s41598-020-69250-1.pdf.
[31]BAID U,PATI S,KURÇ T M,et al.Federated Learning for the Classification of Tumor Infiltrating Lymphocytes [J].arXiv:2203.16622,2022.
[32]TULADHAR A,TYAGI L,SOUZA R,et al.Federated Lear-ning Using Variable Local Training for Brain Tumor Segmentation [C]//BrainLes@MICCAI.2021.
[33]JI C,CHENG B,GAO Z,et al.COVID-19 Classification Algorithm Based on Privacy Preserving Federated Learning [C]//International Conference on Pervasive Computing Technologies for Healthcare.2022.
[34]YIN Y,YANG H,LIU Q,et al.Efficient Federated Tumor Segmentation via Normalized Tensor Aggregation and Client Pru-ning [C]//BrainLes@MICCAI.2021.
[35]GU Y,HU Q,WANG X,et al.FedACS:an Efficient Federated Learning Method Among Multiple Medical Institutions with Adaptive Client Sampling [C]//2021 14th International Congress on Image and Signal Processing,BioMedical Engineering and Informatics(CISP-BMEI).2021:1-6.
[36]LI X,GU Y,DVORNEK N C,et al.Multi-site fMRI Analysis Using Privacy-preserving Federated Learning and Domain Adaptation:ABIDE Results [J].Medical image analysis,2020,65:101765.
[37] GOODFELLOW I,POUGET-ABADIE J,MIRZA M,et al.Ge-nerative adversarial networks [J].Commun ACM,2020,63(11):139-144.
[38]GUO P,WANG P,ZHOU J,et al.Multi-institutional Collaborations for Improving Deep Learning-based Magnetic Resonance Image Reconstruction Using Federated Learning [C]//2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition(CVPR).2021:2423-2432.
[39]DONG N,VOICULESCU I.Federated Contrastive Learning for Decentralized Unlabeled Medical Images [J].arXiv:2109.07504,2021.
[40]WU Y,ZENG D,WANG Z,et al.Federated Contrastive Lear-ning for Dermatological Disease Diagnosis via On-device Lear-ning [J].arXiv:2202.07470,2022.
[41]WU Y,ZENG D,WANG Z,et al.Federated Contrastive Lear-ning for Volumetric Medical Image Segmentation [C]//International Conference on Medical Image Computing and Computer-Assisted Intervention.2022.
[42]LIU Z,WU F,WANG Y,et al.FedCL:Federated contrastive learning for multi-center medical image classification [J].Pattern Recognition,2023,143:109739.
[43]GUNESLI G N,BILAL M,RAZA S E A,et al.A Federated Learning Approach to Tumor Detection in Colon Histology Images [J].Journal of Medical Systems,2023,47:1-15.
[44]JIANG M,ROTH H R,LI W,et al.Fair Federated MedicalImage Segmentation via Client Contribution Estimation [C]//2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition(CVPR).2023:16302-16311.
[45]YAN Z,WICAKSANA J,WANG Z,et al.Variation-AwareFederated Learning With Multi-Source Decentralized Medical Image Data [J].IEEE Journal of Biomedical and Health Informatics,2020,25:2615-2628.
[46]JIANG M,WANG Z,DOU Q.HarmoFL:Harmonizing Localand Global Drifts in Federated Learning on Heterogeneous Me-dical Images [C]//AAAI Conference on Artificial Intelligence.2021.
[47]JIANG M,YANG H,CHENG C,et al.IOP-FL:Inside-Outside Personalization for Federated Medical Image Segmentation [J].IEEE Transactions on Medical Imaging,2022,42:2106-2117.
[48]WANG J,JIN Y,WANG L.Personalizing Federated MedicalImage Segmentation via Local Calibration [C]//European Conference on Computer Vision.2022.
[49]CHEN Z,ZHU M,YANG C,et al.Personalized Retrogress-Resilient Framework for Real-World Medical Federated Learning [C]//International Conference on Medical Image Computing and Computer-Assisted Intervention.2021.
[50]ROY A G,SIDDIQUI S,PöLSTERL S,et al.BrainTorrent:A Peer-to-Peer Environment for Decentralized Federated Learning [J].arXiv:1905.06731,2019.
[51]SILVA S,ALTMANN A,GUTMAN B,et al.Fed-BioMed:A General Open-Source Frontend Framework for Federated Lear-ning in Healthcare [C]//DART/DCL@MICCAI.2020.
[52]ELAYAN H,ALOQAILY M,GUIZANI M.Deep FederatedLearning for IoT-based Decentralized Healthcare Systems [C]//2021 International Wireless Communications and Mobile Computing(IWCMC).2021:105-109.
[53]ELAYAN H,ALOQAILY M,GUIZANI M.Sustainability ofHealthcare Data Analysis IoT-Based Systems Using Deep Fe-derated Learning [J].IEEE Internet of Things Journal,2021,9:7338-7346.
[54]SINGH S,RATHORE S,ALFARRAJ O,et al.A framework for privacy-preservation of IoT healthcare data using Federated Learning and blockchain technology [J].Future Generation Computer Systems,2021,129:380-388.
[55]BÉGUIER C,TERRAIL J O D,MEAH I,et al.Differentially Private Federated Learning for Cancer Prediction [J].arXiv:2101.02997,2021.
[56]WU B,ZHAO S,SUN G,et al.P3SGD:Patient Privacy Preserving SGD for Regularizing Deep CNNs in Pathological Image Classification [C]//2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition(CVPR).2019:2094-2103.
[57]ZILLER A,USYNIN D,BRAREN R F,et al.Medical imaging deep learning with differential privacy [J].Scientific Reports,2021,11:13524.
[58]LI W,MILLETARì F,XU D,et al.Privacy-preserving Federated Brain Tumour Segmentation [C]//MLMI@MICCAI.2019.
[59]CHENG W H,OU W,YIN X D,et al.A Privacy-Protection Model for Patients [J].Security and Communication Networks,2020,2020:1-12.
[60]FROELICHER D,TRONCOSO-PASTORIZA J R,RAISARO J L,et al.Truly privacy-preserving federated analytics for precision medicine with multiparty homomorphic encryption [J].Nature Communications,2021,12:5910.
[61]LIU Q,CHEN C,QIN J,et al.FedDG:Federated Domain Ge-neralization on Medical Image Segmentation via Episodic Lear-ning in Continuous Frequency Space [C]//2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition(CVPR).2021:1013-1023.
[62]KUMAR A,PUROHIT V,BHARTI V,et al.MediSecFed:Private and Secure Medical Image Classification in the Presence of Malicious Clients [J].IEEE Transactions on Industrial Informatics,2022,18:5648-5657.
[63]LAI W L,YAN Q.Federated Learning for Detecting COVID-19 in Chest CT Images:A Lightweight Federated Learning Approach [C]//2022 4th International Conference on Frontiers Technology of Information and Computer(ICFTIC).2022:146-149.

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed