Multi-Scale Dual-Stream CNN–Mamba Hybrid Framework for Accurate Nuclei Segmentation in H&E Images
Pakistan Journal of Scientific Research · 2025
DOI: 10.57041/eb60k036 ↗Kurz gefasst
Fachartikel in der Zeitschrift Pakistan Journal of Scientific Research, 2025. Verfasst von Nimra Bukhari und 7 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY-SA 4.0).
Abstract (Originalsprache)
Accurate nuclei segmentation in H&E-stained histopathology images is critical for quantitative tissue analysis and downstream computational pathology tasks. We propose MS-DS Mamba-Seg, a multi-scale dual-stream framework that integrates CNN-based local feature extraction with Mamba-based global context modeling to enhance nuclei segmentation. The Local Stream captures fine-grained morphological details such as nuclear boundaries and texture, while the Global Stream models long-range spatial dependencies across tissue regions. A novel Fusion Gate adaptively combines these complementary features, producing high-resolution and morphologically precise segmentation masks. Evaluated on the NuInsSeg dataset, MS-DS Mamba-Seg achieves a Dice score of 95.41%, outperforming baseline methods including Attention U-Net, UNETR, and SegMamba, while maintaining structural consistency and boundary accuracy. These results demonstrate the framework’s effectiveness in leveraging complementary local and global features for robust nuclei segmentation.
Zitieren
APA
Bukhari, N., Hussain, S., Shahzada, H. M. A., Haider, R., Munir, H., Mudassar, I. A., Yu, Y., & Khan, A. (2025). Multi-Scale Dual-Stream CNN–Mamba Hybrid Framework for Accurate Nuclei Segmentation in H&E Images. Pakistan Journal of Scientific Research. https://doi.org/10.57041/eb60k036
Vancouver
Bukhari N, Hussain S, Shahzada HMA, Haider R, Munir H, Mudassar IA, et al. Multi-Scale Dual-Stream CNN–Mamba Hybrid Framework for Accurate Nuclei Segmentation in H&E Images. Pakistan Journal of Scientific Research. 2025. doi:10.57041/eb60k036
BibTeX
@article{Bukhari2025,
author = {Bukhari, Nimra and Hussain, Shabir and Shahzada, Hafiz Muhammad Anwar and Haider, Rafique and Munir, Hassan and Mudassar, Imran Ali and Yu, Yang and Khan, Akmal},
title = {Multi-Scale Dual-Stream CNN–Mamba Hybrid Framework for Accurate Nuclei Segmentation in H&E Images},
journal = {Pakistan Journal of Scientific Research},
year = {2025},
doi = {10.57041/eb60k036}
}
EUVIMED