AttmNet: a hybrid Transformer integrating self-attention, Mamba, and multi-layer convolution for enhanced lesion segmentation
AttmNet is a powerful and efficient tool for medical image segmentation, addressing the limitations of existing methods through its advanced design. The MAM block significantly enhances segmentation accuracy while maintaining computational efficiency, making AttmNet highly suitable for clinical applications. The code is available at https://github.com/hyb2840/AttmNet.
Authors
- Hancan Zhu (ORCID: https://orcid.org/0000-0002-5236-686X)
- Kangfei Yao
- Keli Hu
- Guanghua He (ORCID: https://orcid.org/0000-0002-7597-987X)
- Zhong Li (ORCID: https://orcid.org/0000-0002-3443-0557)
- Yibing Huang
- Jin Shang (ORCID: https://orcid.org/0000-0002-2028-3787)
Institutions
- Huzhou Normal University (CN)
Publication Details
- Journal
- Quantitative Imaging in Medicine and Surgery
- Published
- 2025-04-30
- DOI
- https://doi.org/10.21037/qims-2024-2561
- Citations
- 3
- Primary Topic
- AI in cancer detection
- Type
- article
- Field-Weighted Citation Impact
- 7.44