arXiv Open Access 2025

MDN: Mamba-Driven Dualstream Network For Medical Hyperspectral Image Segmentation

Shijie Lin Boxiang Yun Wei Shen Qingli Li Anqiang Yang +1 lainnya
Lihat Sumber

Abstrak

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.

Topik & Kata Kunci

Penulis (6)

S

Shijie Lin

B

Boxiang Yun

W

Wei Shen

Q

Qingli Li

A

Anqiang Yang

Y

Yan Wang

Format Sitasi

Lin, S., Yun, B., Shen, W., Li, Q., Yang, A., Wang, Y. (2025). MDN: Mamba-Driven Dualstream Network For Medical Hyperspectral Image Segmentation. https://arxiv.org/abs/2502.17255

Akses Cepat

Lihat di Sumber
Informasi Jurnal
Tahun Terbit
2025
Bahasa
en
Sumber Database
arXiv
Akses
Open Access ✓