TopoMamba: Topology-Aware Scanning and Fusion for Segmenting Heterogeneous Medical Visual Media
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866913070625849344 |
|---|---|
| author | Zheng, Fuchen Xu, Chengpei Ma, Long Li, Weixuan Zhou, Junhua Chen, Xuhang Liu, Weihuang Li, Haolun Li, Quanjun Zhang, Zhenxi Zhao, Lei Pun, Chi-Man Zhou, Shoujun |
| author_facet | Zheng, Fuchen Xu, Chengpei Ma, Long Li, Weixuan Zhou, Junhua Chen, Xuhang Liu, Weihuang Li, Haolun Li, Quanjun Zhang, Zhenxi Zhao, Lei Pun, Chi-Man Zhou, Shoujun |
| contents | Visual state-space models (SSMs) have shown strong potential for medical image segmentation, yet their effectiveness is often limited by two practical issues: axis-biased scan ordering weakens the modeling of oblique and curved structures, and naive multi-branch fusion tends to amplify redundant responses. We present TopoMamba, a topology-aware scan-and-fuse framework for segmenting heterogeneous medical visual media. The method combines a diagonal/anti-diagonal TopoA-Scan branch with the standard Cross-Scan branch to provide complementary structural priors, and introduces ScanCache, a device-aware caching mechanism that amortizes explicit scan-index construction across recurring resolutions. To fuse heterogeneous scan features efficiently, we further propose a lightweight HSIC Gate that regulates branch interaction using a dependence-aware scalar gating rule. We also instantiate a volumetric TopoMamba-3D for practical 3D clinical segmentation. Experiments on Synapse CT, ISIC 2017 dermoscopy, and CVC-ClinicDB endoscopy show that TopoMamba consistently improves segmentation quality over strong CNN, Transformer, and SSM baselines, with particularly clear gains on thin or curved targets such as the pancreas and gallbladder, while maintaining favorable deployment efficiency under dynamic input resolutions. These results suggest that topology-aware scan ordering and lightweight dependence-aware fusion form an effective and practical design for medical multimedia segmentation. The code will be made publicly available. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_25545 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | TopoMamba: Topology-Aware Scanning and Fusion for Segmenting Heterogeneous Medical Visual Media Zheng, Fuchen Xu, Chengpei Ma, Long Li, Weixuan Zhou, Junhua Chen, Xuhang Liu, Weihuang Li, Haolun Li, Quanjun Zhang, Zhenxi Zhao, Lei Pun, Chi-Man Zhou, Shoujun Computer Vision and Pattern Recognition Visual state-space models (SSMs) have shown strong potential for medical image segmentation, yet their effectiveness is often limited by two practical issues: axis-biased scan ordering weakens the modeling of oblique and curved structures, and naive multi-branch fusion tends to amplify redundant responses. We present TopoMamba, a topology-aware scan-and-fuse framework for segmenting heterogeneous medical visual media. The method combines a diagonal/anti-diagonal TopoA-Scan branch with the standard Cross-Scan branch to provide complementary structural priors, and introduces ScanCache, a device-aware caching mechanism that amortizes explicit scan-index construction across recurring resolutions. To fuse heterogeneous scan features efficiently, we further propose a lightweight HSIC Gate that regulates branch interaction using a dependence-aware scalar gating rule. We also instantiate a volumetric TopoMamba-3D for practical 3D clinical segmentation. Experiments on Synapse CT, ISIC 2017 dermoscopy, and CVC-ClinicDB endoscopy show that TopoMamba consistently improves segmentation quality over strong CNN, Transformer, and SSM baselines, with particularly clear gains on thin or curved targets such as the pancreas and gallbladder, while maintaining favorable deployment efficiency under dynamic input resolutions. These results suggest that topology-aware scan ordering and lightweight dependence-aware fusion form an effective and practical design for medical multimedia segmentation. The code will be made publicly available. |
| title | TopoMamba: Topology-Aware Scanning and Fusion for Segmenting Heterogeneous Medical Visual Media |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2604.25545 |