NeuroFLAME: A Scalable, Privacy-Preserving Federated Framework for Secure, Reproducible, and Multi-Site Neuroimaging Analysis

Federated analysis offers a transformative approach to neuroimaging research, enabling multi-site collaboration without the exchange of sensitive raw data. However, a significant implementation gap exists, as the majority of federated healthcare studies remain technical proofs-of-concept, struggling to fully navigate the rigorous data-sharing regulations and security constraints of real-world clinical and research environments. To address these barriers, we present NeuroFLAME, an enterprise-grade, open-source federated neuroimaging platform built upon the NVIDIA FLARE (NVFlare) framework. NeuroFLAME couples a framework restricted to outbound communication with a graphical user interface specifically tailored for neuroscientists. Using certificate-based trust and containerized execution, the platform ensures reproducible, privacy-preserving analyses. We demonstrate the platforms utility through two federated analyses: decentralized guided joint ICA and federated label-based dimensional prediction. Empirical validation of both analyses shows that federated analysis via NeuroFLAME achieves high consistency with established centralized approaches, effectively bridging the gap between experimental FL prototypes and production-ready collaborative tools for large-scale neuroimaging research.