Beyond the LUMIR challenge: The pathway to foundational registration models.
Authors
Affiliations (20)
Affiliations (20)
- The Russell H. Morgan Department of Radiology and Radiological Science, Johns Hopkins Medical School, Baltimore, MD, USA. Electronic address: [email protected].
- Image Analysis and Communications Laboratory, Department of Electrical and Computer Engineering, Johns Hopkins University, Baltimore, MD, USA.
- Department of Computer Science, Aalto University, Espoo, Uusimaa, Finland.
- Cornell University, New York, NY, USA.
- College of Electrical and Information Engineering, Hunan University, Changsha, Hunan, China.
- Canon Medical Systems (China) Co. Ltd., Beijing, China.
- School of Biomedical Engineering, Shenzhen University Medical School, Shenzhen, Guangdong, China.
- School of Information Science and Engineering, Linyi University, Linyi, Shandong, China.
- Department of Imaging Physics, Delft University of Technology, Delft, South Holland, Netherlands.
- Department of Diagnostic and Interventional Radiology and Neuroradiology, University Hospital Augsburg and Institute of Digital Medicine, Augsburg, Bavaria, Germany.
- Technical University of Munich and Klinikum Rechts der Isar, Munich, Bavaria, Germany.
- Institute of Medical Informatics, University of Lübeck, Lübeck, Schleswig-Holstein, Germany.
- Department of Radiology and Center for Computer Vision and Imaging Biomarkers, University of California Los Angeles, Los Angeles, CA, USA.
- Institute for Applied Medical Informatics and Institute of Computational Neuroscience, University Medical Center Hamburg, Hamburg, Germany.
- Department of Electrical and Computer Engineering, Vanderbilt University, Nashville, TN, USA.
- Radboud University Medical Center, Nijmegen, Gelderland, Netherlands.
- Department of Radiology and Radiological Science, Johns Hopkins Medical Institutions, Baltimore, MD, USA.
- The Russell H. Morgan Department of Radiology and Radiological Science, Johns Hopkins Medical School, Baltimore, MD, USA.
- Inria, Paris, France; Department of Neurosurgery, Brigham & Women's Hospital and Harvard Medical School, Boston, MA, USA.
- EchoScout GmbH, Lübeck, Schleswig-Holstein, Germany.
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.