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

2026-01-24

AI Summary

This work addresses the limited out-of-domain generalization and data scarcity challenges in medical image registration by introducing foundation models to this task for the first time. The authors propose a novel framework that integrates a foundation model-based feature encoder with a universal registration head, along with a channel-wise regularization training strategy. Trained exclusively on a single dataset, the method achieves state-of-the-art performance within the training domain and significantly outperforms existing approaches across multiple out-of-domain datasets, demonstrating exceptional cross-domain robustness. This study thus establishes a promising new direction toward building generalizable foundation models for medical image analysis.

Technology Category

• Machine Learning: Deep Neural Architectures and Foundation Models
• Computer Vision: Other Foundations of Computer Vision
• Cognitive Modeling & Cognitive Systems: Other Foundations of Cognitive Modeling & Systems

Application Category

• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• User Modeling, Personalization and Recommendation: Federated recommendation systems and personalization
• Search and Retrieval-Augmented AI: Vertical and domain-specific search

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.

Problem

• medical image registration
• generalization
• foundation model
• domain shift
• limited data

Innovation

• foundation model
• image registration
• domain generalization
• channel regularization
• medical imaging