Integrating Local Precision With Global Consistency for Unsupervised Magnetic Resonance Image Registration

View at publisher Summarise with VIRAT
Authors: He Deng, Jiangfeng Wang, Xi Yin, Xiangde Min
Cited by: 0
References: 27

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

ABSTRACT Purpose To address the issues of interpretability and learning efficiency in traditional single‐stream frameworks, as well as the limitations in capturing long‐range dependencies and semantic relationships caused by the dependence of two‐stream architectures. Methods This paper proposes GLACF, a triple‐stream global‐to‐local attention framework for deformable MR image registration, integrating CNNs, Transformers, and coarse‐to‐fine strategies to enhance alignment accuracy. Its key innovations include: a triple‐stream feature extraction based on Transformers for enriched feature representation; multi‐scale decoupling blocks (MSDBs) that leverage low‐resolution features to generate coarse displacement fields; and a voxel‐wise local attention module (VLFM) that refines high‐resolution features to produce precise displacement fields. Results Experimental results on three public 3D brain MRI datasets (e.g., LONI LBPA40, IXI, and OASIS) demonstrate that GLACF consistently outperforms state‐of‐the‐art methods in registration similarity, smoothness, and invertibility. Specifically, on LONI LBPA40, GLACF achieves a Dice similarity coefficient (DSC) of 72.7%, structural similarity index measure (SSIM) of 0.973, percentage of negative Jacobian determinants (% of | J ϕ | ≤ 0) of 0.15, and 95th percentile Hausdorff distance (HD95) of 6.088. On IXI, it attains 76.8% DSC, 0.952 SSIM, 0.48% of | J ϕ | ≤ 0, and 3.284 HD95. On OASIS, it reaches 89.1% DSC, 0.973 SSIM, 0.55% of | J ϕ | ≤ 0, and 1.328 HD95. Conclusion These results confirm the robustness and accuracy of GLACF across diverse datasets, highlighting its strong potential for clinical translation in high‐fidelity image registration scenarios.

Fields of Study & Subjects

Medical Image Segmentation Techniques Advanced MRI Techniques and Applications Brain Tumor Detection and Classification

Publication details

Journal / source
Magnetic Resonance in Medicine
Volume
96
Issue
2
Pages
908–917
Publication date
26 March 2026
Language
EN