Deep learning enabled liquid-based cytology model for cervical precancer and cancer detection.

Journal: Nature communications
PMID: 40222978

Abstract

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

  • Peng Xue
    National Cancer Center/National Clinical Research Center for Cancer, Cancer Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing, China.
  • Le Dang
    Peking Union Medical College Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing, China.
  • Ling-Hua Kong
    Department of Obstetrics and Gynecology, National Clinical Research Center for Obstetric and Gynaecological Diseases, State Key Laboratory of Common Mechanism Research for Major Diseases, Peking Union Medical College Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing, China.
  • Hong-Ping Tang
    Department of Pathology, Shenzhen Maternity and Child Healthcare Hospital, Shenzhen, China.
  • Hai-Miao Xu
    Department of Pathology, Zhejiang Cancer Hospital, Zhejiang Cancer Center, Hangzhou, China.
  • Hai-Yan Weng
    Department of Pathology, The First Affiliated Hospital of USTC, Division of Life Sciences and Medicine, University of Science and Technology of China, Hefei, China.
  • Zhe Wang
    Department of Pathology, The Eighth Affiliated Hospital, Sun Yat-sen University, Shenzhen 518033, China.
  • Rong-Gan Wei
    Department of Pathology, Guangxi Zhuang Autonomous Region People's Hospital, Nanning, China.
  • Lian Xu
    State Key Laboratory of Natural Medicines and National R&D Center for Chinese Herbal Medicine Processing, College of Engineering, China Pharmaceutical University, Nanjing 211109, China.
  • Hong-Xia Li
    Department of Pathology, The Seventh Medical Center of Chinese PLA General Hospital, Beijing, China.
  • Hai-Yan Niu
    Department of Pathology, The First Affiliated Hospital/School of Basic Medicine and Life Sciences, Hainan Medical University, Haikou, China.
  • Ming-Juan Wang
    Department of Pathology, Northwest Women's and Children's Hospital, Xi'an, China.
  • Zi-Chen Ye
    School of Population Medicine and Public Health, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing, China.
  • Zhi-Fang Li
    Department of Public Health and Preventive Medicine, Changzhi Medical College, Changzhi, China.
  • Wen Chen
    School of Cyber Science and Engineering, Sichuan University, Chengdu, Sichuan, China.
  • Qin-Jing Pan
    National Cancer Center/National Clinical Research Center for Cancer/Cancer Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing, China.
  • Xun Zhang
    Department of Neurosurgery, Xiangya Hospital, Central South University, Changsha, China.
  • Remila Rezhake
    Affiliated Cancer Hospital, The 3rd Affiliated Teaching Hospital of Xinjiang Medical University, Xinjiang, China.
  • Li Zhang
    Department of Animal Nutrition and Feed Science, College of Animal Science and Technology, Huazhong Agricultural University, Wuhan 430070, China.
  • Yu Jiang
    School of Pharmacy and Food Engineering, Wuyi University, Jiangmen, China.
  • You-Lin Qiao
    School of Population Medicine and Public Health, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing, China.
  • Lan Zhu
    Department of General Practice, Zhongshan Hospital, Fudan University, Shanghai, China.
  • Fang-Hui Zhao
    National Cancer Center/National Clinical Research Center for Cancer/Cancer Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing, China. zhaofangh@cicams.ac.cn.

Keywords

External Resources

Popular Topics
Recent Journals