Development and validation of an artificial intelligence system for grading colposcopic impressions and guiding biopsies
Peng Xue,
Chao Tang,
Qing Li,
Yuexiang Li,
Yu Shen,
Yuqian Zhao,
Jiawei Chen,
Jianrong Wu,
Longyu Li,
Wei Wang,
Yucong Li,
Xiaoli Cui,
Shaokai Zhang,
Wenhua Zhang,
Xun Zhang,
Kai Ma,
Yefeng Zheng,
Tianyi Qian,
Man Tat Alexander Ng,
Zhihua Liu,
Youlin Qiao,
Yu Jiang,
Fanghui Zhao
Affiliations
Peng Xue
Department of Epidemiology and Biostatistics, School of Population Medicine and Public Health, Chinese Academy of Medical Sciences and Peking Union Medical College
Chao Tang
School of Public Health, Dalian Medical University
Qing Li
Diagnosis and Treatment for Cervical Lesions Center, Shenzhen Maternity & Child Healthcare Hospital
Yuexiang Li
Tencent Jarvis Lab
Yu Shen
Zonsun Healthcare
Yuqian Zhao
Center for Cancer Prevention Research, Sichuan Cancer Hospital & Institute, Sichuan Cancer Center, School of Medicine, University of Electronic Science and Technology of China
Jiawei Chen
Tencent Jarvis Lab
Jianrong Wu
Tencent Healthcare
Longyu Li
Jiangxi Maternal and Child Health Hospital
Wei Wang
Chengdu Women’s and Children’s Central Hospital, School of Medicine, University of Electronic Science and Technology of China
Yucong Li
Chongqing University Cancer Hospital
Xiaoli Cui
Cancer Hospital of China Medical University, Liaoning Cancer Hospital & Institute
Shaokai Zhang
Affiliated Cancer Hospital of Zhengzhou University/Henan Cancer Hospital
Wenhua Zhang
Department of Cancer Epidemiology, National Cancer Center/National Clinical Research Center for Cancer/Cancer Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College
Xun Zhang
Department of Pathology, National Cancer Center/National Clinical Research Center for Cancer/Cancer Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College
Kai Ma
Tencent Jarvis Lab
Yefeng Zheng
Tencent Jarvis Lab
Tianyi Qian
Tencent Healthcare
Man Tat Alexander Ng
Tencent Healthcare
Zhihua Liu
Department of Gynecology, Shenzhen Maternity & Child Healthcare Hospital
Youlin Qiao
Department of Epidemiology and Biostatistics, School of Population Medicine and Public Health, Chinese Academy of Medical Sciences and Peking Union Medical College
Yu Jiang
Department of Epidemiology and Biostatistics, School of Population Medicine and Public Health, Chinese Academy of Medical Sciences and Peking Union Medical College
Fanghui Zhao
Department of Cancer Epidemiology, National Cancer Center/National Clinical Research Center for Cancer/Cancer Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College
Abstract Background Colposcopy diagnosis and directed biopsy are the key components in cervical cancer screening programs. However, their performance is limited by the requirement for experienced colposcopists. This study aimed to develop and validate a Colposcopic Artificial Intelligence Auxiliary Diagnostic System (CAIADS) for grading colposcopic impressions and guiding biopsies. Methods Anonymized digital records of 19,435 patients were obtained from six hospitals across China. These records included colposcopic images, clinical information, and pathological results (gold standard). The data were randomly assigned (7:1:2) to a training and a tuning set for developing CAIADS and to a validation set for evaluating performance. Results The agreement between CAIADS-graded colposcopic impressions and pathology findings was higher than that of colposcopies interpreted by colposcopists (82.2% versus 65.9%, kappa 0.750 versus 0.516, p 0.05). The CAIADS also demonstrated a superior ability in predicting biopsy sites, with a median mean-intersection-over-union (mIoU) of 0.758. Conclusions The CAIADS has potential in assisting beginners and for improving the diagnostic quality of colposcopy and biopsy in the detection of cervical precancer/cancer.
