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 +2 more
1/19/2026
cs.CVcs.AIcs.LG

Official code: jbanusco/BrainFM4Challenges (11 stars, Apache-2.0, last commit 2026-02-09).

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.

View on arXivView PDF

Code Implementations(1)

jbanusco/BrainFM4ChallengesOfficial100%
Apache-2.0
111Python, DockerfileNov 25, 20258 months agoApache-2.0

Similar Papers

MRI-CORE: A Foundation Model for Magnetic Resonance Imaging

84% match2025

BrainSegFounder: Towards 3D Foundation Models for Neuroimage Segmentation

82% match1 repo152024

Towards Generalisable Foundation Models for Brain MRI

82% match2025

Building a General SimCLR Self-Supervised Foundation Model Across Neurological Diseases to Advance 3D Brain MRI Diagnoses

82% match1 repo112025

Revisiting MAE pre-training for 3D medical image segmentation

81% match2024

Brain Foundation Models: A Survey on Advancements in Neural Signal Processing and Brain Discovery

81% match2025

Cite this paper

@article{gordaliza2026from,
  title  = {From 100,000+ images to winning the first brain MRI foundation model challenges: Sharing lessons and models},
  author = {Pedro M. Gordaliza and Jaume Banus and Benoît Gérin and Maxence Wynen and Nataliia Molchanova and Jonas Richiardi and Meritxell Bach Cuadra},
  year   = {2026},
  eprint = {2601.13166},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2601.13166v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2601.13166.svg)](https://codeofpaper.com/paper/2601.13166)

Discussion