English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Zendy Plus

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Zendy Tools

Zendy Open

Capturing voxel-wise spatial correspondence across distinct modalities iscrucial for medical image analysis. However, current registration approachesare not practical enough in terms of registration accuracy and clinicalapplicability. In this paper, we introduce MambaMorph, a novel multi-modalitydeformable registration framework. Specifically, MambaMorph utilizes aMamba-based registration module and a fine-grained, yet simple, featureextractor for efficient long-range correspondence modeling and high-dimensionalfeature learning, respectively. Additionally, we develop a well-annotated brainMR-CT registration dataset, SR-Reg, to address the scarcity of data inmulti-modality registration. To validate MambaMorph's multi-modalityregistration capabilities, we conduct quantitative experiments on both ourSR-Reg dataset and a public T1-T2 dataset. The experimental results on bothdatasets demonstrate that MambaMorph significantly outperforms the currentstate-of-the-art learning-based registration methods in terms of registrationaccuracy. Further study underscores the efficiency of the Mamba-basedregistration module and the lightweight feature extractor, which achievenotable registration quality while maintaining reasonable computational costsand speeds. We believe that MambaMorph holds significant potential forpractical applications in medical image registration. The code for MambaMorphis available at: https://github.com/Guo-Stone/MambaMorph.

MambaMorph: a Mamba-based Framework for Medical MR-CT Deformable Registration