Federated Vision Transformer with Adaptive Focal Loss for Medical Image Classification
School of Artificial Intelligence, Guilin University of Electronic Technology, Guilin, China, 541004（桂林电子科技大学人工智能学院）；The Laboratory for Imagery, Vision and Artificial Intelligence, École de Technologie Supérieure, Montreal, Canada, H3C 1K3（影像、视觉与人工智能实验室）；College of Medicine, Taibah University, Al Madinah, Saudi Arabia, 42353（塔布大学医学院）；Department of Radiology, Prince Mohammed Bin Abdulaziz Hospital, Ministry of National Guard Health Affairs, Al Madinah, Saudi Arabia, 42324（王子穆罕默德·本·阿卜杜勒阿齐兹医院放射科）；College of Computer Science and Engineering, Taibah University, Madinah, Saudi Arabia, 42353（塔布大学计算机科学与工程学院）；Engineering, Jeddah University, Jeddah, Saudi Arabia, 23445（吉达大学工程学院）
Xinyuan Zhao, Yihang Wu, Ahmad Chaddad, Tareef Daqqaq, Reem Kateb
While deep learning models like Vision Transformer (ViT) have achieved significant advances, they typically require large datasets. With data privacy regulations, access to many original datasets is restricted, especially medical images. Federated learning (FL) addresses this challenge by enabling global model aggregation without data exchange. However, the heterogeneity of the data and the class imbalance that exist in local clients pose challenges for the generalization of the model. This study proposes a FL framework leveraging a dynamic adaptive focal loss (DAFL) and a client-aware aggregation strategy for local training. Specifically, we design a dynamic class imbalance coefficient that adjusts based on each client's sample distribution and class data distribution, ensuring minority classes receive sufficient attention and preventing sparse data from being ignored. To address client heterogeneity, a weighted aggregation strategy is adopted, which adapts to data size and characteristics to better capture inter-client variations. The classification results on three public datasets (ISIC, Ocular Disease and RSNA-ICH) show that the proposed framework outperforms DenseNet121, ResNet50, ViT-S/16, ViT-L/32, FedCLIP, Swin Transformer, CoAtNet, and MixNet in most cases, with accuracy improvements ranging from 0.98\% to 41.69\%. Ablation studies on the imbalanced ISIC dataset validate the effectiveness of the proposed loss function and aggregation strategy compared to traditional loss functions and other FL approaches. The codes can be found at: https://github.com/AIPMLab/ViT-FLDAF.
FeTTL: Federated Template and Task Learning for Multi-Institutional Medical Imaging
Sheikh Zayed Institute for Pediatric Surgical Innovation, Children’s National Hospital, Washington, DC, USA（Sheikh Zayed儿童外科创新研究所，儿童医院，华盛顿特区，美国）；Universidad Politécnica de Madrid（马德里理工大学）；Universitat Pompeu Fabra（庞培法布拉大学）；NVIDIA Corporation（英伟达公司）；Departments of Radiology and Pediatrics, George Washington University（放射学和儿科学系，乔治华盛顿大学）
Federated Semi-supervised Medical Image Classification via Inter-client Relation Matching
The Chinese University of Hong Kong（香港中文大学）；Beihang University（北京航空航天大学）；Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences（中国科学院深圳先进技术研究院）
联邦学习（FL）已经越来越流行，以协作分布式医疗机构来训练深度网络。然而，尽管现有的FL算法只允许监督训练设置，但由于缺乏预算或专业知识，现实中大多数医院通常无法负担复杂的数据标记。本文研究了一个实际但具有挑战性的FL问题，称为\textit{Federated Semi-supervised Learning}（FSSL），其目的是通过联合利用来自标记和未标记客户端的数据（即，医院）。我们提出了一种新的方法来解决这个问题，它改进了传统的一致性正则化机制与一个新的客户端之间的关系匹配计划。所提出的学习方案通过对齐提取的疾病关系来明确地连接标记和未标记客户端之间的学习，从而减轻未标记客户端的任务知识的不足，并促进来自未标记样本的判别信息。我们验证了我们的方法在两个大规模的医学图像分类数据集。我们的方法的有效性已被证明与国家的最先进的明确改进，以及彻底的消融分析上的两个任务\footnote{Code will be made available at \url{https://github.com/liuquande/FedIRM}}。
Federated Learning for Medical Image Classification: A Comprehensive Benchmark
School of Electronic and Computer Engineering, Peking University（北京大学电子与计算机工程学院）；Shien-Ming Wu School of Intelligent Engineering, South China University of Technology（华南理工大学吴贤铭智能工程学院）
Federated Distillation for Medical Image Classification: Towards Trustworthy Computer-Aided Diagnosis
School of Information and Communication Engineering, Hainan University（海南大学信息与通信工程学院）；College of Mathematical Sciences, BoHai University（渤海大学数学科学学院）；Australian AI Institute, University of Technology Sydney（悉尼科技大学澳大利亚人工智能研究所）；School of Electronic Science and Technology, Hainan University（海南大学电子科学与技术学院）
Think Twice Before Selection: Federated Evidential Active Learning for Medical Image Analysis with Domain Shifts
School of Computer Science and Engineering, Northwestern Polytechnical University（西北工业大学计算机科学与工程学院）；Hong Kong University of Science and Technology（香港科技大学）；Research & Development Institute of Northwestern Polytechnical University in Shenzhen（西北工业大学深圳研究院）
FedSemiDG: Domain Generalized Federated Semi-supervised Medical Image Segmentation
Medical Artificial Intelligence Lab, Westlake University（西交大学医学人工智能实验室）；Department of Information and Communication Engineering, School of Engineering, Institute of Science Tokyo（东京科学大学工程学院信息与通信工程系）；Department of Biomedical Engineering, The Chinese University of Hong Kong（香港中文大学生物医学工程系）
Focal Modulation and Bidirectional Feature Fusion Network for Medical Image Segmentation
Department of Computing, Abasyn University Islamabad Campus (AUIC)（阿巴斯扬大学伊斯兰堡校区计算机系）；School of Computer Science and Informatics, De Montfort University（德蒙福特大学计算机科学与信息学学院）；Naif Arab University for Security Sciences（纳夫阿拉伯安全科学大学）；School of Computer Science and Engineering, University of New South Wales（新南威尔士大学计算机科学与工程学院）；Center of Excellence in Precision Medicine and Digital Health, Chulalongkorn University（朱拉隆功大学精准医学与数字健康卓越中心）；School of Biomedical Engineering, UNSW Sydney（新南威尔士大学悉尼分校生物医学工程学院）
Which Client is Reliable?: A Reliable and Personalized Prompt-based Federated Learning for Medical Image Question Answering
Graduate School of Information Science and Technology, Hokkaido University（北海道大学信息科学与技术研究院）；Faculty of Information Science and Technology, Hokkaido University（北海道大学信息科学与技术学院）
Cross-Domain Federated Learning in Medical Imaging
The Johns Hopkins University（约翰斯·霍普金斯大学）；The Johns Hopkins University School of Medicine（约翰斯·霍普金斯大学医学院）；Sidney Kimmel Comprehensive Center（西德尼·金梅尔综合中心）
Med-MMFL: A Multimodal Federated Learning Benchmark in Healthcare
University of Aberdeen（阿伯丁大学）；NepAl Applied Mathematics and Informatics Institute for research, Nepal（尼泊尔应用数学与信息学研究所）；University of Lausanne（洛桑大学）；West Virginia University（西弗吉尼亚大学）；University of Verona（威尼斯大学）；University College London（伦敦大学学院）
Analysing the Influence of Attack Configurations on the Reconstruction of Medical Images in Federated Learning
Technical University of Denmark（丹麦技术大学）
联邦学习的思想是协同训练深度神经网络模型，并与多个参与者共享它们，而不会相互暴露他们的私人训练数据。由于患者的隐私记录，这在医疗领域非常有吸引力。然而，最近提出的一种名为Deep Leakage from Concentrants的方法使攻击者能够从共享梯度中重建数据。这项研究表明，它是多么容易重建不同的数据初始化方案和距离措施的图像。我们展示了数据和模型架构如何影响初始化方案和距离测量配置的最佳选择时，与单图像。我们证明了初始化方案和距离测量的选择可以显着提高收敛速度和质量。此外，我们发现，最佳的攻击配置在很大程度上取决于目标图像分布的性质和模型架构的复杂性。
FedProIn: Mitigating Client Drift for Learnable Prototypes in Federated Medical Imaging
Department of Computational and Data Sciences, Indian Institute of Science（印度科学研究院计算与数据科学系）；Department of IISc Mathematics Initiative, Indian Institute of Science（印度科学研究院数学倡议系）；Equally contributed to the work（共同完成工作）；Corresponding author（通讯作者）
FedGSCA: Medical Federated Learning with Global Sample Selector and Client Adaptive Adjuster under Label Noise
Academy for Engineering and Technology, Fudan University（复旦大学工程学院）；School of Computer Science, China University of Geosciences（中国地质大学（武汉）计算机学院）；College of Science, Beijing Forestry University（北京林业大学理学院）
CoM$^3$eT: A foundation model for medical image analysis through federated, multidimensional context integration
Fraunhofer Institute for Digital Medicine MEVIS（弗劳恩霍夫数字医学MEVIS研究所）；RWTH Aachen University（亚琛工业大学）；Medizinische Hochschule Hannover（汉诺威医学院）；Massachusetts General Hospital（麻省总医院）；Harvard Medical School（哈佛医学院）；Charité – Universitätsmedizin Berlin（柏林夏里特医学院）；Freie Universität Berlin（柏林自由大学）；Humboldt-Universität zu Berlin（柏林洪堡大学）
Federated Learning for Large Models in Medical Imaging: A Comprehensive Review
School of Cyber Science and Engineering, Sichuan University（四川大学网络科学与工程学院）；Sichuan Institute of Computer Sciences（四川省计算机科学研究院）；College of Computer Science, Sichuan University（四川大学计算机学院）；Department of Mathematics, The Chinese University of Hong Kong（香港中文大学数学系）；School of Electrical and Electronic Engineering, College of Engineering, Yonsei University（延世大学工程学院电子与电气工程系）
