Deep learning has revolutionized medical image registration by achieving unprecedented speeds, yet its clinical application is hindered by a limited ability to generalize beyond the training domain, a critical weakness given the typically small scale of medical datasets. In this paper, we introduce FMIR, a foundation model-based registration framework that overcomes this limitation.Combining a foundation model-based feature encoder for extracting anatomical structures with a general registration head, and trained with a channel regularization strategy on just a single dataset, FMIR achieves state-of-the-art(SOTA) in-domain performance while maintaining robust registration on out-of-domain images.Our approach demonstrates a viable path toward building generalizable medical imaging foundation models with limited resources. The code is available at https://github.com/Monday0328/FMIR.git.
@article{arxiv.2601.17529,
title = {FMIR, a foundation model-based Image Registration Framework for Robust Image Registration},
author = {Fengting Zhang and Yue He and Qinghao Liu and Yaonan Wang and Xiang Chen and Hang Zhang},
journal= {arXiv preprint arXiv:2601.17529},
year = {2026}
}
Comments
Accepted to the International Symposium on Biomedical Imaging (ISBI 2026)