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

TL;DR

FMIR is a novel medical image registration framework that leverages foundation models to achieve high accuracy and robustness across different datasets, addressing generalization issues in deep learning-based registration.

Contribution

Introduces FMIR, a foundation model-based registration framework that generalizes well across domains with limited training data, a significant advancement over existing methods.

Findings

Achieves state-of-the-art in-domain registration performance.

Maintains robust registration on out-of-domain images.

Demonstrates effectiveness with limited training resources.

Abstract

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.