_version_ 1866915750760939520
author Chen, Junyu
Wei, Shuwen
Honkamaa, Joel
Marttinen, Pekka
Zhang, Hang
Liu, Min
Zhou, Yichao
Tan, Zuopeng
Wang, Zhuoyuan
Wang, Yi
Zhou, Hongchao
Hu, Shunbo
Zhang, Yi
Tao, Qian
Förner, Lukas
Wendler, Thomas
Jian, Bailiang
Wiestler, Benedikt
Hable, Tim
Kim, Jin
Ruan, Dan
Madesta, Frederic
Sentker, Thilo
Heyer, Wiebke
Zuo, Lianrui
Dai, Yuwei
Wu, Jing
Prince, Jerry L.
Bai, Harrison
Du, Yong
Liu, Yihao
Hering, Alessa
Dorent, Reuben
Hansen, Lasse
Heinrich, Mattias P.
Carass, Aaron
author_facet Chen, Junyu
Wei, Shuwen
Honkamaa, Joel
Marttinen, Pekka
Zhang, Hang
Liu, Min
Zhou, Yichao
Tan, Zuopeng
Wang, Zhuoyuan
Wang, Yi
Zhou, Hongchao
Hu, Shunbo
Zhang, Yi
Tao, Qian
Förner, Lukas
Wendler, Thomas
Jian, Bailiang
Wiestler, Benedikt
Hable, Tim
Kim, Jin
Ruan, Dan
Madesta, Frederic
Sentker, Thilo
Heyer, Wiebke
Zuo, Lianrui
Dai, Yuwei
Wu, Jing
Prince, Jerry L.
Bai, Harrison
Du, Yong
Liu, Yihao
Hering, Alessa
Dorent, Reuben
Hansen, Lasse
Heinrich, Mattias P.
Carass, Aaron
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2505_24160
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Beyond the LUMIR challenge: The pathway to foundational registration models
Chen, Junyu
Wei, Shuwen
Honkamaa, Joel
Marttinen, Pekka
Zhang, Hang
Liu, Min
Zhou, Yichao
Tan, Zuopeng
Wang, Zhuoyuan
Wang, Yi
Zhou, Hongchao
Hu, Shunbo
Zhang, Yi
Tao, Qian
Förner, Lukas
Wendler, Thomas
Jian, Bailiang
Wiestler, Benedikt
Hable, Tim
Kim, Jin
Ruan, Dan
Madesta, Frederic
Sentker, Thilo
Heyer, Wiebke
Zuo, Lianrui
Dai, Yuwei
Wu, Jing
Prince, Jerry L.
Bai, Harrison
Du, Yong
Liu, Yihao
Hering, Alessa
Dorent, Reuben
Hansen, Lasse
Heinrich, Mattias P.
Carass, Aaron
Image and Video Processing
Computer Vision and Pattern Recognition
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.
title Beyond the LUMIR challenge: The pathway to foundational registration models
topic Image and Video Processing
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2505.24160