[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-85062-en":3,"doc-seo-85062-105":30,"detail-sidebar-cat-0-en-105":92},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":20,"is_deleted":4,"is_public":21,"is_downloadable":21,"audit_status":21,"page_count":22,"language":23,"language_code":24,"site_id":25,"html_lang":24,"table_of_contents":26,"faqs":27,"seo_title":13,"seo_description":14,"update_tm":28,"read_time":29},85062,1099514067415,"Rowan","https://ap-avatar.wpscdn.com/avatar/100002539d78ffe74a7?x-image-process=image/resize,m_fixed,w_180,h_180&k=1779092875211072502",8,"Research & Report","Benchmark Evaluation of Feredated Learning on Multi-organ Images","Medical data privacy constraints and substantial organ- and modality-specific variations prevent broad clinical deployment of medical AI. Federated learning (FL) offers a practical path to coordinate multi-center learning without pooling raw data, but the rapid growth of FL methods and strong clinical heterogeneity make real-world evaluation difficult. A unified, comprehensive benchmark is needed. MobenFL is proposed, integrating 20 state-of-the-art FL algorithms and 22 medical imaging datasets across 12 key organs, evaluating performance alongside efficiency and privacy protection, with scenario-specific testing.","Benchmark Evaluation of Feredated Learning on Multi-organ Images  \nJunbin Maoa , Xu Tiana , Jianchun Zhua , Ludi Lib and Jin Liu a,b,∗  \na Hunan Provincial Key Laboratory on Bioinformatics, School of Computer Science and Engineering, Central South University, Changsha 410083, China b Xinjiang Engineering Research Center of Big Data and Intelligent Software, School of software, Xinjiang University, Urumqi, 830008, China  \narXiv :2607 .082 19v 1 [ cs .CV] 9 Jul 2026  \nARTICLE INFO  \nKeywords:  \nFederated Learning  \nMulti-Center Learning Medical Image Classification Multi-organ data  \nAB STRACT  \nThe privacy requirements of medical data and its substantial variations across organs and modalities hinder the clinical implementation of medical AI. Federated learning (FL) is a feasible approach to overcome these challenges. Due to the continuous emergence of FL algorithms and the highly heterogeneous nature of medical data, objectively evaluating their performance in real-world clinical settings remains difficult. Therefore, a comprehensive federated medical imaging benchmark, serving as a unified evaluation standard, is crucial for advancing the technology toward reliable clinical application. Existing federated medical imaging benchmarks have not yet adequately incorporated state-of-the-art algorithms, are limited to data from single organs or modalities, and overly emphasize model accuracy, making it difficult to comprehensively assess the overall efficacy of FL in realworld medical environments. To address these challenges, we developed the MobenFL benchmark. This benchmark integrates 20 cutting-edge FL algorithms and 22 medical imaging datasets, covering 12 critical organs across the human body, surpassing existing benchmark in breadth. In terms of evaluation dimensions, MobenFL not only assesses performance but also systematically incorporates key metrics such as algorithmic efficiency and privacy protection capabilities. Additionally, it conducts specialized evaluations for complex real-world clinical scenarios involving different diseases, devices, and imaging modalities, thereby providing a comprehensive and in-depth evaluation framework for the clinical application of FL in the medical field. Our code is published at [https://github.com/](https://github.com/)[ ](https://github.com/)yutian0315/MobenFL.  \n1. Introduction  \nCurrently, AI-based medical image analysis has maturedin competitive research scenarios, but a significant gap remains between its technical maturity and large-scale clinical implementation. This gap stems primarily from the inherent characteristics of medical data: data accumulated by hospitals in different regions and specialties vary greatly in organ types and imaging modalities. For instance, one hospital may possess abundant lung CT data, while another specializes in brain MRI data. As a result, diagnostic models trained on single-center data suffer a sharp decline in generalization performance when applied across institutions (Dayan et al., 2021) . Additionally, medical imaging data involve sensitive patient information and are strictly regulated by privacy protection laws such as HIPAA and GDPR (Pati et al., 2022), making the traditional approach of consolidating multi-center data to enhance model generalization nearly unfeasible both legally and compliantly.  \nIt is for these reasons that federated learning (McMahanet al., 2017), with its distributed collaborative paradigm of\"moving models, not data\" (shown in Fig. 1) demonstrates critical value. FL can effectively coordinate data resources from various centers without the need to aggregate raw data (Karargyris et al., 2023). By encrypting and aggregating locally trained model parameters, it enables the collaborative training of a global model with broader knowledge and stronger adaptability. FL is developing rapidly, with new algorithms emerging continuously. Meanwhile, the medical data environment is inherently highly heterogeneous, with  \n∗Corres","cbCaijzyu24gNEL4","https://ap.wps.com/l/cbCaijzyu24gNEL4","pdf",5801095,6,1,29,"English","en",105,"# Introduction\n## Motivation: clinical deployment challenges\n## Federated learning as a solution\n## Need for unified evaluation benchmarks\n## Contributions of the MobenFL benchmark","[{\"question\":\"Why is evaluating federated learning for medical imaging difficult in real clinical settings?\",\"answer\":\"Medical data varies greatly across organs and modalities and is highly heterogeneous across institutions. Meanwhile, FL algorithms evolve rapidly, so objective, fair comparison under real clinical constraints is hard.\"},{\"question\":\"What is MobenFL and what does it include?\",\"answer\":\"MobenFL is a federated medical imaging benchmark that combines 20 cutting-edge FL algorithms and 22 medical imaging datasets. It covers 12 critical organs across the human body.\"},{\"question\":\"How does MobenFL evaluate federated learning beyond model accuracy?\",\"answer\":\"It assesses multiple evaluation dimensions, explicitly incorporating algorithmic efficiency and privacy protection capabilities. It also performs specialized evaluations for complex clinical scenarios involving different diseases, devices, and imaging modalities.\"}]",1784200726,73,{"code":4,"msg":31,"data":32},"ok",{"site_id":25,"language":24,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":87,"head_meta":89,"extra_data":91,"updated_unix":28},"benchmark-evaluation-of-feredated-learning-on-multi-organ-images","",{"@graph":36,"@context":86},[37,54,69],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":21},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/benchmark-evaluation-of-feredated-learning-on-multi-organ-images/85062/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":24,"description":14,"dateModified":62,"datePublished":63,"encodingFormat":61,"isAccessibleForFree":64,"interactionStatistic":65},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-07-23","2026-07-16",true,{"@type":66,"interactionType":67,"userInteractionCount":20},"InteractionCounter",{"@type":68},"ViewAction",{"@type":70,"mainEntity":71},"FAQPage",[72,78,82],{"name":73,"@type":74,"acceptedAnswer":75},"Why is evaluating federated learning for medical imaging difficult in real clinical settings?","Question",{"text":76,"@type":77},"Medical data varies greatly across organs and modalities and is highly heterogeneous across institutions. Meanwhile, FL algorithms evolve rapidly, so objective, fair comparison under real clinical constraints is hard.","Answer",{"name":79,"@type":74,"acceptedAnswer":80},"What is MobenFL and what does it include?",{"text":81,"@type":77},"MobenFL is a federated medical imaging benchmark that combines 20 cutting-edge FL algorithms and 22 medical imaging datasets. It covers 12 critical organs across the human body.",{"name":83,"@type":74,"acceptedAnswer":84},"How does MobenFL evaluate federated learning beyond model accuracy?",{"text":85,"@type":77},"It assesses multiple evaluation dimensions, explicitly incorporating algorithmic efficiency and privacy protection capabilities. It also performs specialized evaluations for complex clinical scenarios involving different diseases, devices, and imaging modalities.","https://schema.org",{"og:url":52,"og:type":88,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":90,"canonical":52},"index,follow",{"doc_id":7,"site_id":25},{"code":4,"msg":5,"data":93},[94,98,102,106,111,115,120,123,128,131,135],{"id":21,"doc_module":4,"doc_module_name":46,"category_name":95,"show_sort_weight":96,"slug":97},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":99,"show_sort_weight":100,"slug":101},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":103,"show_sort_weight":104,"slug":105},"Exam",70,"exam",{"id":107,"doc_module":4,"doc_module_name":46,"category_name":108,"show_sort_weight":109,"slug":110},5,"Comic",60,"comic",{"id":20,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":124,"doc_module":4,"doc_module_name":46,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":46,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":46,"category_name":137,"show_sort_weight":107,"slug":138},19,"General","general"]