SAMReg: SAM-enabled Image Registration with ROI-based Correspondence

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Huang, Shiqi, Xu, Tingfa, Shen, Ziyi, Saeed, Shaheer Ullah, Yan, Wen, Barratt, Dean, Hu, Yipeng
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913552938303488
author Huang, Shiqi
Xu, Tingfa
Shen, Ziyi
Saeed, Shaheer Ullah
Yan, Wen
Barratt, Dean
Hu, Yipeng
author_facet Huang, Shiqi
Xu, Tingfa
Shen, Ziyi
Saeed, Shaheer Ullah
Yan, Wen
Barratt, Dean
Hu, Yipeng
contents This paper describes a new spatial correspondence representation based on paired regions-of-interest (ROIs), for medical image registration. The distinct properties of the proposed ROI-based correspondence are discussed, in the context of potential benefits in clinical applications following image registration, compared with alternative correspondence-representing approaches, such as those based on sampled displacements and spatial transformation functions. These benefits include a clear connection between learning-based image registration and segmentation, which in turn motivates two cases of image registration approaches using (pre-)trained segmentation networks. Based on the segment anything model (SAM), a vision foundation model for segmentation, we develop a new registration algorithm SAMReg, which does not require any training (or training data), gradient-based fine-tuning or prompt engineering. The proposed SAMReg models are evaluated across five real-world applications, including intra-subject registration tasks with cardiac MR and lung CT, challenging inter-subject registration scenarios with prostate MR and retinal imaging, and an additional evaluation with a non-clinical example with aerial image registration. The proposed methods outperform both intensity-based iterative algorithms and DDF-predicting learning-based networks across tested metrics including Dice and target registration errors on anatomical structures, and further demonstrates competitive performance compared to weakly-supervised registration approaches that rely on fully-segmented training data. Open source code and examples are available at: https://github.com/sqhuang0103/SAMReg.git.
format Preprint
id arxiv_https___arxiv_org_abs_2410_14083
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle SAMReg: SAM-enabled Image Registration with ROI-based Correspondence
Huang, Shiqi
Xu, Tingfa
Shen, Ziyi
Saeed, Shaheer Ullah
Yan, Wen
Barratt, Dean
Hu, Yipeng
Computer Vision and Pattern Recognition
This paper describes a new spatial correspondence representation based on paired regions-of-interest (ROIs), for medical image registration. The distinct properties of the proposed ROI-based correspondence are discussed, in the context of potential benefits in clinical applications following image registration, compared with alternative correspondence-representing approaches, such as those based on sampled displacements and spatial transformation functions. These benefits include a clear connection between learning-based image registration and segmentation, which in turn motivates two cases of image registration approaches using (pre-)trained segmentation networks. Based on the segment anything model (SAM), a vision foundation model for segmentation, we develop a new registration algorithm SAMReg, which does not require any training (or training data), gradient-based fine-tuning or prompt engineering. The proposed SAMReg models are evaluated across five real-world applications, including intra-subject registration tasks with cardiac MR and lung CT, challenging inter-subject registration scenarios with prostate MR and retinal imaging, and an additional evaluation with a non-clinical example with aerial image registration. The proposed methods outperform both intensity-based iterative algorithms and DDF-predicting learning-based networks across tested metrics including Dice and target registration errors on anatomical structures, and further demonstrates competitive performance compared to weakly-supervised registration approaches that rely on fully-segmented training data. Open source code and examples are available at: https://github.com/sqhuang0103/SAMReg.git.
title SAMReg: SAM-enabled Image Registration with ROI-based Correspondence
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2410.14083