From 100,000+ images to winning the first brain MRI foundation model challenges: Sharing lessons and models
Pedro M. Gordaliza, Jaume Banus, Benoît Gérin, Maxence Wynen, Nataliia Molchanova, Jonas Richiardi, Meritxell Bach Cuadra
Code Available — Be the first to reproduce this paper.
ReproduceCode
- github.com/jbanusco/brainfm4challengesOfficialIn paper★ 6
Abstract
Developing Foundation Models for medical image analysis is essential to overcome the unique challenges of radiological tasks. The first challenges of this kind for 3D brain MRI, SSL3D and FOMO25, were held at MICCAI 2025. Our solution ranked first in tracks of both contests. It relies on a U-Net CNN architecture combined with strategies leveraging anatomical priors and neuroimaging domain knowledge. Notably, our models trained 1-2 orders of magnitude faster and were 10 times smaller than competing transformer-based approaches. Models are available here: https://github.com/jbanusco/BrainFM4Challenges.