<scp>WSSM</scp> : A Weakly Supervised Oral Mucosal Disease Segmentation Model Based on Multi‐Task Collaboration
Our model, with Mamba as the backbone (balancing local texture feature extraction and long-range semantic dependency modeling of OMD lesions), enables deeper supervision via dual-branch collaboration, significantly improving boundary segmentation accuracy in scenarios with insufficient OMD supervision and unclear boundaries. PAPER CODE: https://github.com/XJ156/WSSM3.git.
Authors
- Xinhao Zeng
- Jianguo Ju (ORCID: https://orcid.org/0000-0002-9682-2679)
- Ziyu Guan
- Pengfei Xu
- Xuemin Shen
- Zhengyu Shen
- Qian Zhang
- Jing Xu
- Cao Li Nurmanbai
Institutions
- Xi'an University of Science and Technology (CN)
- Shanghai Medical College of Fudan University (CN)
- Shanghai Jiao Tong University (CN)
- Northwest University (CN)
- Shanghai Ninth People's Hospital (CN)
- Xi’an University (CN)
- Urumqi General Hospital of PLA (CN)
Publication Details
- Journal
- Oral Diseases
- Published
- 2026-01-12
- DOI
- https://doi.org/10.1111/odi.70204
- Primary Topic
- Cutaneous Melanoma Detection and Management
- Type
- article
- Field-Weighted Citation Impact
- 0.00
Funders
- National Natural Science Foundation of China
- Key Research and Development Projects of Shaanxi Province