Heling Bao1, Hui Bi2, Xiaosong Zhang2, Yun Zhao3, Yan Dong4, Xiping Luo5, Deping Zhou6, Zhixue You7, Yinglan Wu8, Zhaoyang Liu9, Yuping Zhang4, Juan Liu10, Liwen Fang11, Linhong Wang12. 1. Department of Maternal and Child Health, School of Public Health, Peking University, Beijing, China; National Center for Chronic and Non-communicable Disease Control and Prevention, Chinese Center for Disease Control and Prevention, Beijing, China. 2. Department of Obstetrics and Gynecology, Peking University First Hospital, Beijing, China. 3. Department of Obstetrics and Gynecology, Peking University People's Hospital, Beijing, China. 4. Shanxi Maternal and Child Health Care Hospital, Taiyuan, China. 5. Guangdong Maternal and Child Health Care Hospital, Guangzhou, China. 6. Chongqing Health Center for Women and Children, Chongqing, China. 7. The First Affiliated Hospital With Nanjing Medical University, Nanjing, China. 8. Hunan Provincial Maternal and Child Health Care Hospital, Changsha, China. 9. Northwest Women and Children Hospital, Xi'an, China. 10. Key State Laboratory of Software Engineering, School of Computer, Wuhan University, Wuhan, China; Landing Artificial Intelligence Center for Pathological Diagnosis, Wuhan University, Wuhan, China. 11. National Center for Chronic and Non-communicable Disease Control and Prevention, Chinese Center for Disease Control and Prevention, Beijing, China. 12. National Center for Chronic and Non-communicable Disease Control and Prevention, Chinese Center for Disease Control and Prevention, Beijing, China. Electronic address: linhong@chinawch.org.cn.
Abstract
OBJECTIVE: Artificial intelligence (AI) could automatedly detect abnormalities in digital cytological images, however, the effect in cervical cancer screening is inconclusive. We aim to evaluate the performance of AI-assisted cytology for the detection of histologically cervical intraepithelial lesions (CIN) or cancer. METHODS: We trained a supervised deep learning algorithm based on 188,542 digital cytological images. Between Mar 13, 2017, and Oct 20, 2018, 2145 referral women from organized screening were enrolled in a multicenter, clinical-based, observational study. Cervical specimen was sampled to generate two liquid-based slides: one random slide was allocated to AI-assisted reading, and the other to manual reading conducted by skilled cytologists from senior hospital and cytology doctors from primary hospitals. HPV testing and colposcopy-directed biopsy was performed, and histological result was regarded as reference. We calculated the relative sensitivity and relative specificity of AI-assisted reading compared to manual reading for CIN2+. This trial was registered, number ChiCTR2000034131. RESULTS: In the referral population, AI-assisted reading detected 92.6% of CIN 2 and 96.1% of CIN 3+, significantly higher than or similar to manual reading. AI-assisted reading had equivalent sensitivity (relative sensitivity 1.01, 95%CI, 0.97-1.05) and higher specificity (relative specificity 1.26, 1.20-1.32) compared to skilled cytologists; whereas higher sensitivity (1.12, 1.05-1.20) and specificity (1.36, 1.25-1.48) compared to cytology doctors. In HPV-positive women, AI-assisted reading improved specificity for CIN1 or less at no expense of reduction of sensitivity compared to manual reading. CONCLUSIONS: AI-assisted cytology may contribute to the primary cytology screening or triage. Further studies are needed in general population.
OBJECTIVE: Artificial intelligence (AI) could automatedly detect abnormalities in digital cytological images, however, the effect in cervical cancer screening is inconclusive. We aim to evaluate the performance of AI-assisted cytology for the detection of histologically cervical intraepithelial lesions (CIN) or cancer. METHODS: We trained a supervised deep learning algorithm based on 188,542 digital cytological images. Between Mar 13, 2017, and Oct 20, 2018, 2145 referral women from organized screening were enrolled in a multicenter, clinical-based, observational study. Cervical specimen was sampled to generate two liquid-based slides: one random slide was allocated to AI-assisted reading, and the other to manual reading conducted by skilled cytologists from senior hospital and cytology doctors from primary hospitals. HPV testing and colposcopy-directed biopsy was performed, and histological result was regarded as reference. We calculated the relative sensitivity and relative specificity of AI-assisted reading compared to manual reading for CIN2+. This trial was registered, number ChiCTR2000034131. RESULTS: In the referral population, AI-assisted reading detected 92.6% of CIN 2 and 96.1% of CIN 3+, significantly higher than or similar to manual reading. AI-assisted reading had equivalent sensitivity (relative sensitivity 1.01, 95%CI, 0.97-1.05) and higher specificity (relative specificity 1.26, 1.20-1.32) compared to skilled cytologists; whereas higher sensitivity (1.12, 1.05-1.20) and specificity (1.36, 1.25-1.48) compared to cytology doctors. In HPV-positive women, AI-assisted reading improved specificity for CIN1 or less at no expense of reduction of sensitivity compared to manual reading. CONCLUSIONS: AI-assisted cytology may contribute to the primary cytology screening or triage. Further studies are needed in general population.