FMIR, a foundation model-based Image Registration Framework for Robust Image Registration

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhang, Fengting, He, Yue, Liu, Qinghao, Wang, Yaonan, Chen, Xiang, Zhang, Hang
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914292812480512
author Zhang, Fengting
He, Yue
Liu, Qinghao
Wang, Yaonan
Chen, Xiang
Zhang, Hang
author_facet Zhang, Fengting
He, Yue
Liu, Qinghao
Wang, Yaonan
Chen, Xiang
Zhang, Hang
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2601_17529
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle FMIR, a foundation model-based Image Registration Framework for Robust Image Registration
Zhang, Fengting
He, Yue
Liu, Qinghao
Wang, Yaonan
Chen, Xiang
Zhang, Hang
Computer Vision and Pattern Recognition
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.
title FMIR, a foundation model-based Image Registration Framework for Robust Image Registration
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2601.17529