The artificial intelligence‐assisted cytology diagnostic system in large‐scale cervical cancer screening: A population‐based cohort study of 0.7 million women

作者：Heling Bao, Xiaorong Sun, Yi Sheng Zhang, Baochuan Pang, Hua Li, Liang Zhou, Fengpin Wu, Dehua Cao, Jian Wang, Bojana Turic, Lınhong Wang · 发表于：Cancer Medicine · 年份：2020 · DOI：10.1002/cam4.3296 · 被引用次数：104 · 研究领域：Cervical Cancer and HPV Research、AI in cancer detection、Endometrial and Cervical Cancer Treatments

Abstract Background Adequate cytology is limited by insufficient cytologists in a large‐scale cervical cancer screening. We aimed to develop an artificial intelligence (AI)‐assisted cytology system in cervical cancer screening program. Methods We conducted a perspective cohort study within a population‐based cervical cancer screening program for 0.7 million women, using a validated AI‐assisted cytology system. For comparison, cytologists examined all slides classified by AI as abnormal and a randomly selected 10% of normal slides. Each woman with slides classified as abnormal by either AI‐assisted or manual reading was diagnosed by colposcopy and biopsy. The outcomes were histologically confirmed cervical intraepithelial neoplasia grade 2 or worse (CIN2+). Results Finally, we recruited 703 103 women, of whom 98 549 were independently screened by AI and manual reading. The overall agreement rate between AI and manual reading was 94.7% (95% confidential interval [CI], 94.5%‐94.8%), and kappa was 0.92 (0.91‐0.92). The detection rates of CIN2+ increased with the severity of cytology abnormality performed by both AI and manual reading (Ptrend < 0.001). General estimated equations showed that detection of CIN2+ among women with ASC‐H or HSIL by AI were significantly higher than corresponding groups classified by cytologists (for ASC‐H: odds ratio [OR] = 1.22, 95%CI 1.11‐1.34, P < .001; for HSIL: OR = 1.41, 1.28‐1.55, P < .001). AI‐assisted cytology was 5.8% (3.0%‐8.6%) more sensiti...