Federated learning for lesion segmentation in multiple sclerosis: a real-world multi-center feasibility study.

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.