Deep learning enabled liquid-based cytology model for cervical precancer and cancer detection
Deep learning (DL) enabled liquid-based cytology has potential for cervical cancer screening or triage. Here, we develop a DL model using whole cytology slides from 17,397 women and test it on 10,826 additional cases through a three-stage process. The DL model achieves robust performance across nine hospitals. In a multi-reader, multi-case study, it outperforms cytopathologists' sensitivity by 9%. Reading time significantly decreases with DL assistance (218s vs 30s; p < 0.0001). In community-based organized screening, the DL model's sensitivity matches that of senior cytopathologists (0.878 vs 0.854; p > 0.999), yet it has reduced specificity (0.831 vs 0.901; p < 0.0001). Notably, hospital-based opportunistic screening shows that junior cytopathologists with DL assistance significantly improve both their sensitivity and specificity (0.857 vs 0.657, 0.840 vs 0.737; both p < 0.0001). When triaging human papillomavirus-positive cases, DL assistance exhibits better performance than junior cytopathologists alone. These findings support using the DL model as an assistance tool in cervical screening and case triage.
Authors
- Zhi-Fang Li (ORCID: https://orcid.org/0000-0002-1586-7606)
- Wen Chen (ORCID: https://orcid.org/0000-0002-6603-0056)
- Remila Rezhake (ORCID: https://orcid.org/0000-0003-1842-6205)
- You‐Lin Qiao (ORCID: https://orcid.org/0000-0001-6380-0871)
- Haiyan Niu
- Peng Xue (ORCID: https://orcid.org/0000-0003-3002-8146)
- Fanghui Zhao (ORCID: https://orcid.org/0000-0001-9294-0005)
- Haimiao Xu (ORCID: https://orcid.org/0000-0003-1060-0512)
- Linghua Kong (ORCID: https://orcid.org/0000-0003-0863-9979)
- Haiyan Weng
- Lan Zhu (ORCID: https://orcid.org/0000-0001-5753-5426)
- Mingjuan Wang
- Hongping Tang (ORCID: https://orcid.org/0000-0001-8263-8996)
- Le Dang (ORCID: https://orcid.org/0000-0001-8319-0708)
- Qinjing Pan (ORCID: https://orcid.org/0000-0001-7729-0868)
- Rong Wei
- Hongxia Li (ORCID: https://orcid.org/0000-0001-5940-2264)
- Zhe Wang (ORCID: https://orcid.org/0000-0002-4338-2630)
- Li Zhang (ORCID: https://orcid.org/0000-0002-3617-2627)
- Zichen Ye (ORCID: https://orcid.org/0000-0003-4841-1303)
- Yu Jiang (ORCID: https://orcid.org/0000-0002-2443-911X)
- Lian Xu
- Xun Zhang (ORCID: https://orcid.org/0009-0003-7693-1805)
Institutions
- University of Science and Technology of China (CN)
- Xinjiang Medical University (CN)
- Changzhi Medical College (CN)
- Chinese Academy of Medical Sciences & Peking Union Medical College (CN)
- Sichuan University (CN)
- Peking Union Medical College Hospital (CN)
- Chinese PLA General Hospital (CN)
- National Cancer Center (US)
- Zhejiang Cancer Hospital (CN)
- Northwest Women's and Children's Hospital (CN)
- Tumor Hospital of Xinjiang Medical University (CN)
- Shenzhen Maternity and Child Healthcare Hospital (CN)
- The People's Hospital of Guangxi Zhuang Autonomous Region (CN)
- Xijing Hospital (CN)
- Hainan Medical University (CN)
- Air Force Medical University (CN)
Publication Details
- Journal
- Nature Communications
- Published
- 2025-04-13
- DOI
- https://doi.org/10.1038/s41467-025-58883-3
- Citations
- 15
- Primary Topic
- Cervical Cancer and HPV Research
- Type
- article
- Field-Weighted Citation Impact
- 20.31
Funders
- China Postdoctoral Science Foundation
- Chinese Academy of Medical Sciences
- Peking Union Medical College Hospital
- Sanming Project of Medicine in Shenzhen