arXiv 2601.175292026-01-30cs.CV

FMIR：一种基于基础模型的图像配准框架，用于稳健的图像配准

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

School of Artificial Intelligence and Robotics（人工智能与机器人学院）；Hunan University（湖南大学）；Department of Electrical and Computer Engineering（电气与计算机工程系）；Cornell University（康奈尔大学）

Fengting Zhang, Yue He, Qinghao Liu, Yaonan Wang, Xiang Chen, Hang Zhang

备注：: Accepted to the International Symposium on Biomedical Imaging (ISBI 2026)

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

FMIR通过基于基础模型的特征编码器和通道正则化策略，在单一数据集上实现域内最佳性能并保持域外配准的鲁棒性。

摘要：

深度学习通过实现前所未有的速度革新了医学图像配准，但其临床应用受到其在训练域外泛化能力有限的限制，这在通常医学数据集规模较小的情况下尤为关键。在本文中，我们介绍了FMIR，一种基于基础模型的配准框架，克服了这一限制。结合基于基础模型的特征编码器提取解剖结构与通用配准头，并仅在单一数据集上训练，采用通道正则化策略，FMIR在域内实现了最先进的性能，同时在域外图像上保持稳健的配准。我们的方法展示了在有限资源下构建可泛化医学成像基础模型的可行路径。代码可在https://github.com/Monday0328/FMIR.git获取。

英文摘要：

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.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。