cs.CVNov 5, 2026

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

Authors: Abhijith Shaji, Paul Kurian, Greg Ver Steeg, Paul M. Thompson, Jose-Luis Ambite

Organizations: Information Sciences Institute, University of Southern California, Marina del Rey, CA, USA · University of California, Riverside, CA, USA · Imaging Genetics Center, Mark and Mary Stevens Neuroimaging and Informatics Institute, Keck School of Medicine, University of Southern California, Marina del Rey, CA, USA

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 Fréchet Inception Distance). Our results show that federated training is a viable route to develop multi-site generative models of brain MRI.

Figures & tables

Explore similar work

CardsList
  1. A generalizable structural brain MRI foundation model via dual-priority federated pretraining

    Sep 23, 2026Zhen Yu, Yang Liu, Jianfeng Feng +2Medical Imaging Foundation ModelsFederated Learning Aggregation

  2. Data Amount Heterogeneity Improves Performance in Federated Learning for Neuroimaging

    Oct 28, 2026Paul Kurian, Tamoghna Chattopadhyay, Abhijith Shaji +3Federated LearningHeterogeneous Federated Learning

  3. Lesion-DDPM: Lesion-Enhanced 3D Diffusion for MS MRI Synthesis

    Jun 13, 2026Weidong Zhang, Yongchan Jung, Shafayat Mowla Anik +6Medical Image SynthesisDiffusion MRI