MDN: Mamba-Driven Dualstream Network For Medical Hyperspectral Image Segmentation
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866915170133999616 |
|---|---|
| author | Lin, Shijie Yun, Boxiang Shen, Wei Li, Qingli Yang, Anqiang Wang, Yan |
| author_facet | Lin, Shijie Yun, Boxiang Shen, Wei Li, Qingli Yang, Anqiang Wang, Yan |
| contents | Medical Hyperspectral Imaging (MHSI) offers potential for computational pathology and precision medicine. However, existing CNN and Transformer struggle to balance segmentation accuracy and speed due to high spatial-spectral dimensionality. In this study, we leverage Mamba's global context modeling to propose a dual-stream architecture for joint spatial-spectral feature extraction. To address the limitation of Mamba's unidirectional aggregation, we introduce a recurrent spectral sequence representation to capture low-redundancy global spectral features. Experiments on a public Multi-Dimensional Choledoch dataset and a private Cervical Cancer dataset show that our method outperforms state-of-the-art approaches in segmentation accuracy while minimizing resource usage and achieving the fastest inference speed. Our code will be available at https://github.com/DeepMed-Lab-ECNU/MDN. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_17255 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | MDN: Mamba-Driven Dualstream Network For Medical Hyperspectral Image Segmentation Lin, Shijie Yun, Boxiang Shen, Wei Li, Qingli Yang, Anqiang Wang, Yan Image and Video Processing Medical Hyperspectral Imaging (MHSI) offers potential for computational pathology and precision medicine. However, existing CNN and Transformer struggle to balance segmentation accuracy and speed due to high spatial-spectral dimensionality. In this study, we leverage Mamba's global context modeling to propose a dual-stream architecture for joint spatial-spectral feature extraction. To address the limitation of Mamba's unidirectional aggregation, we introduce a recurrent spectral sequence representation to capture low-redundancy global spectral features. Experiments on a public Multi-Dimensional Choledoch dataset and a private Cervical Cancer dataset show that our method outperforms state-of-the-art approaches in segmentation accuracy while minimizing resource usage and achieving the fastest inference speed. Our code will be available at https://github.com/DeepMed-Lab-ECNU/MDN. |
| title | MDN: Mamba-Driven Dualstream Network For Medical Hyperspectral Image Segmentation |
| topic | Image and Video Processing |
| url | https://arxiv.org/abs/2502.17255 |