{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,4]],"date-time":"2026-11-04T17:39:19Z","timestamp":1793813959348,"version":"4.6.1"},"reference-count":24,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2025,9,10]],"date-time":"2025-09-10T00:00:00Z","timestamp":1757462400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Neurol."],"abstract":"<jats:p>Multiple sclerosis (MS) is a chronic neuroinflammatory disease driven by immune-mediated central nervous system damage, often leading to progressive disability. Accurate segmentation of MS lesions on MRI is crucial for monitoring disease and treatment efficacy; however, manual segmentation remains time-consuming and prone to variability. While deep learning has advanced automated segmentation, robust performance benefits from large-scale, diverse datasets, yet data pooling is restricted by privacy regulations and clinical performance remains challenged by inter-site heterogeneity. In this proof-of-concept work, we aim to apply and adopt Federated Learning (FL) in a real-world hospital setting. We assessed FL for MS lesion segmentation using the self-configuring nnU-Net model, leveraging 512 MRI cases from three sites without sharing raw patient data. The federated model achieved Dice scores ranging from 0.66 to 0.80 across held-out test sets. While performance varied across sites, reflecting data heterogeneity, the study demonstrates the potential of FL as a scalable and secure paradigm for advancing automated MS analysis in distributed clinical environments. This work supports adopting secure, collaborative AI in neuroimaging, offering utility for privacy-sensitive clinical research and a starting point for medical AI development, bridging the gap between model generalizability and regulatory compliance.<\/jats:p>","DOI":"10.3389\/fneur.2025.1620469","type":"journal-article","created":{"date-parts":[[2025,9,10]],"date-time":"2025-09-10T04:17:50Z","timestamp":1757477870000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":14,"title":["Federated learning for lesion segmentation in multiple sclerosis: a real-world multi-center feasibility study"],"prefix":"10.3389","volume":"16","author":[{"given":"Sarah","family":"Hindawi","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bartlomiej","family":"Szubstarski","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Eric","family":"Boernert","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bj\u00f6rn","family":"Tackenberg","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jens","family":"Wuerfel","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2025,9,10]]},"reference":[{"key":"ref1","doi-asserted-by":"publisher","first-page":"612","DOI":"10.3399\/bjgp14X682609","article-title":"What\u2019s new in multiple sclerosis?","volume":"64","author":"Dimitrov","year":"2014","journal-title":"Br J Gen Pract"},{"key":"ref2","doi-asserted-by":"publisher","first-page":"1816","DOI":"10.1177\/1352458520970841","article-title":"Rising prevalence of multiple sclerosis worldwide: insights from the atlas of MS, third edition","volume":"26","author":"Walton","year":"2020","journal-title":"Mult Scler"},{"key":"ref3","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-030-38490-6_13","article-title":"Demyelinating diseases of the CNS (brain and spine)","volume-title":"Diseases of the brain, head and neck, spine 2020\u20132023: Diagnostic imaging","author":"Barkhof","year":"2020"},{"key":"ref4","doi-asserted-by":"publisher","first-page":"24","DOI":"10.1016\/j.neurad.2023.11.007","article-title":"MRI features and disability in multiple sclerosis: a systematic review and meta-analysis","volume":"51","author":"Nabizadeh","year":"2024","journal-title":"J Neuroradiol"},{"key":"ref5","doi-asserted-by":"publisher","first-page":"610967","DOI":"10.3389\/fninf.2020.610967","article-title":"Review of deep learning approaches for the segmentation of multiple sclerosis lesions on brain MRI","volume":"14","author":"Zeng","year":"2020","journal-title":"Front Neuroinform"},{"key":"ref6","doi-asserted-by":"publisher","first-page":"203","DOI":"10.1038\/s41592-020-01008-z","article-title":"Nn U-net: a self-configuring method for deep learning-based biomedical image segmentation","volume":"18","author":"Isensee","year":"2021","journal-title":"Nat Methods"},{"key":"ref7","doi-asserted-by":"publisher","first-page":"e210064","DOI":"10.1148\/ryai.210064","article-title":"External validation of deep learning algorithms for radiologic diagnosis: a systematic review","volume":"4","author":"Yu","year":"2022","journal-title":"Radiol Artif Intell"},{"key":"ref8","doi-asserted-by":"publisher","first-page":"119","DOI":"10.1038\/s41746-020-00323-1","article-title":"The future of digital health with federated learning","volume":"3","author":"Rieke","year":"2020","journal-title":"NPJ Digit Med"},{"key":"ref9","doi-asserted-by":"publisher","first-page":"20220890","DOI":"10.1259\/bjr.20220890","article-title":"Federated learning for medical imaging radiology","volume":"96","author":"Rehman","year":"2023","journal-title":"Br J Radiol"},{"key":"ref10","doi-asserted-by":"publisher","first-page":"1167612","DOI":"10.3389\/fnins.2023.1167612","article-title":"Multiple sclerosis lesion segmentation: revisiting weighting mechanisms for federated learning","volume":"17","author":"Liu","year":"2023","journal-title":"Front Neurosci"},{"key":"ref11","doi-asserted-by":"publisher","first-page":"102872","DOI":"10.1016\/j.artmed.2024.102872","article-title":"Improving multiple sclerosis lesion segmentation across clinical sites: a federated learning approach with noise-resilient training","volume":"152","author":"Bai","year":"2024","journal-title":"Artif Intell Med"},{"key":"ref12","author":"Wagner","year":"2024"},{"key":"ref13","doi-asserted-by":"publisher","first-page":"13650","DOI":"10.1038\/s41598-018-31911-7","article-title":"Objective evaluation of multiple sclerosis lesion segmentation using a data management and processing infrastructure","volume":"8","author":"Commowick","year":"2018","journal-title":"Sci Rep"},{"key":"ref14","first-page":"130","article-title":"Towards real-world federated learning in medical image analysis using Kaapana","volume-title":"Distributed, collaborative, and federated learning, and affordable AI and healthcare for resource diverse Global Health","author":"Kades","year":"2022"},{"key":"ref15","doi-asserted-by":"publisher","first-page":"1027","DOI":"10.1200\/CCI.20.00045","article-title":"Joint imaging platform for federated clinical data analytics","volume":"4","author":"Scherer","year":"2020","journal-title":"JCO Clin Cancer Inform"},{"key":"ref16","volume-title":"Communication-efficient learning of deep networks from decentralized data","author":"McMahan","year":"2016"},{"key":"ref17","doi-asserted-by":"publisher","first-page":"124","DOI":"10.1007\/s10916-023-02017-z","article-title":"A lightweight deep learning framework for automatic MRI data sorting and artifacts detection","volume":"47","author":"Gao","year":"2023","journal-title":"J Med Syst"},{"key":"ref18","doi-asserted-by":"publisher","first-page":"371","DOI":"10.1016\/j.neucom.2021.07.098","article-title":"Federated learning on non-IID data: a survey","volume":"465","author":"Zhu","year":"2021","journal-title":"Neurocomputing"},{"key":"ref19","article-title":"Tackling the objective inconsistency problem in heterogeneous federated optimization","author":"Wang","year":""},{"key":"ref20","doi-asserted-by":"publisher","first-page":"1217","DOI":"10.1177\/1352458519856843","article-title":"Brain and lesion segmentation in multiple sclerosis using fully convolutional neural networks: a large-scale study","volume":"26","author":"Gabr","year":"2020","journal-title":"Mult Scler"},{"key":"ref21","doi-asserted-by":"publisher","first-page":"117002","DOI":"10.1016\/j.neuroimage.2020.117002","article-title":"Confound modelling in UK biobank brain imaging","volume":"224","author":"Alfaro-Almagro","year":"2021","journal-title":"NeuroImage"},{"key":"ref22","first-page":"754","article-title":"Fed BN: a communication-efficient federated learning strategy based on blockchain","author":"Peng","year":"2024"},{"key":"ref23","author":"Li","year":"2020"},{"key":"ref24","author":"Li","year":"2020"}],"container-title":["Frontiers in Neurology"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fneur.2025.1620469\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,10]],"date-time":"2025-09-10T04:17:51Z","timestamp":1757477871000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fneur.2025.1620469\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,10]]},"references-count":24,"alternative-id":["10.3389\/fneur.2025.1620469"],"URL":"https:\/\/doi.org\/10.3389\/fneur.2025.1620469","relation":{},"ISSN":["1664-2295"],"issn-type":[{"value":"1664-2295","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,9,10]]},"article-number":"1620469"}}