Federated training performs as well as centralized for 3D Latent Diffusion for Diagnosis-Conditioned Brain MRI Synthesis

A 3D conditional latent diffusion model trained federatedly on multi-site brain MRI data performed similarly to centralized training, according to arXiv paper 2611.08771v1. The authors evaluated conditional fidelity (how well generated MRIs perform in classification), diversity (MultiScale-SSIM match to the real data distribution), and realism (Fréchet Inception Distance), and concluded that federated learning is a viable route to develop multi-site generative models of brain MRI while keeping data private at each site.

arXiv:2611.08771v1 Announce Type: new Abstract: Generative models of brain MRI are useful to understand brain conditions, and to enrich scarce and imbalanced neuroimaging data. However, training these models requires large, multi-site training sets, which is challenging. Federated learning FL allows for training deep learning models without sharing data. We show that training a 3D conditional latent model federatedly where data is kept private at each site performs similarly to centralized training where all the data have been copied to a single site . We evaluate three metrics: conditional fidelity how well generated MRIs perform in classification , diversity how the generated images match the real data distribution, using MultiScale-SSIM , and realism how close generated images are to real images, using Fr\'{e}chet Inception Distance . Our results show that federated training is a viable route to develop multi-site generative models of brain MRI.