A contrastive learning method integrating pathological prior information for effective differentiation of histological categories in lung squamous cell carcinoma
Overall, combining the SP technique with contrastive learning shows significant improvements in distinguishing histological categories in LSCC, making it effective for WSIs of non-diffuse cancers.
Authors
- Gen Lin (ORCID: https://orcid.org/0000-0001-9411-5519)
- Haipeng Xu (ORCID: https://orcid.org/0000-0001-7511-4991)
- Yunjian Huang (ORCID: https://orcid.org/0000-0003-3064-6067)
- Chao Li (ORCID: https://orcid.org/0000-0002-0240-5170)
- Chuanben Chen (ORCID: https://orcid.org/0000-0002-2225-7865)
- Yang Sun (ORCID: https://orcid.org/0000-0003-3751-2790)
- Qiaofeng Zhong
- Shengjia Chen (ORCID: https://orcid.org/0000-0003-1556-0679)
- Mingci Huang
- Weijin Xiao
Institutions
- Fujian Medical University (CN)
- Karolinska Institutet (SE)
- Fujian Provincial Cancer Hospital (CN)
Publication Details
- Journal
- BMC Cancer
- Published
- 2025-12-17
- DOI
- https://doi.org/10.1186/s12885-025-15459-0
- Primary Topic
- AI in cancer detection
- Type
- article
- Field-Weighted Citation Impact
- 0.00