Lightweight hybrid Mamba2 for unsupervised medical image registration
HybridMorph brings significant performance improvements and lower computational overhead compared to baseline methods, demonstrating the potential of our model in promoting the lightweight design of medical image registration models.
Authors
- Wenkang Chen
- Ao‐Bo Xu (ORCID: https://orcid.org/0009-0003-2833-7561)
- Shaofei Shen (ORCID: https://orcid.org/0000-0002-4350-5696)
- Xuejun Zhang (ORCID: https://orcid.org/0000-0002-0648-2528)
Institutions
- Guangxi University (CN)
- Guangxi Science and Technology Department (CN)
Publication Details
- Journal
- Medical Physics
- Published
- 2025-09-01
- DOI
- https://doi.org/10.1002/mp.18104
- Primary Topic
- Medical Image Segmentation Techniques
- Type
- article
- Field-Weighted Citation Impact
- 0.00