Beyond the LUMIR challenge: The pathway to foundational registration models
Abstract
Medical image challenges have played a transformative role in advancing the field, catalyzing innovation and establishing new performance benchmarks. Image registration, a foundational task in neuroimaging, has similarly advanced through the Learn2Reg initiative. Building on this, we introduce the Large-scale Unsupervised Brain MRI Image Registration (LUMIR) challenge, a next-generation benchmark for unsupervised brain MRI registration. Previous challenges relied upon anatomical label maps, however LUMIR provides 4,014 unlabeled T1-weighted MRIs for training, encouraging biologically plausible deformation modeling through self-supervision. Evaluation includes 590 in-domain test subjects and extensive zero-shot tasks across disease populations, imaging protocols, and species. Deep learning methods consistently achieved state-of-the-art performance and produced anatomically plausible, diffeomorphic deformation fields. They outperformed several leading optimization-based methods and remained robust to most domain shifts. These findings highlight the growing maturity of deep learning in neuroimaging registration and its potential to serve as a foundation model for general-purpose medical image registration.
Keywords
Cite
@article{arxiv.2505.24160,
title = {Beyond the LUMIR challenge: The pathway to foundational registration models},
author = {Junyu Chen and Shuwen Wei and Joel Honkamaa and Pekka Marttinen and Hang Zhang and Min Liu and Yichao Zhou and Zuopeng Tan and Zhuoyuan Wang and Yi Wang and Hongchao Zhou and Shunbo Hu and Yi Zhang and Qian Tao and Lukas Förner and Thomas Wendler and Bailiang Jian and Benedikt Wiestler and Tim Hable and Jin Kim and Dan Ruan and Frederic Madesta and Thilo Sentker and Wiebke Heyer and Lianrui Zuo and Yuwei Dai and Jing Wu and Jerry L. Prince and Harrison Bai and Yong Du and Yihao Liu and Alessa Hering and Reuben Dorent and Lasse Hansen and Mattias P. Heinrich and Aaron Carass},
journal= {arXiv preprint arXiv:2505.24160},
year = {2026}
}