Bao Heling, Bi Hui, Zhang Xiaosong, Zhao Yun, Dong Yan, Luo Xiping, Zhou Deping, You Zhixue, Wu Yinglan, Liu Zhaoyang, Zhang Yuping, Liu Juan, Fang Liwen, Wang Linhong
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.
Department of Obstetrics and Gynecology, Peking University First Hospital, Beijing, China.
Gynecol Oncol. 2020 Oct;159(1):171-178. doi: 10.1016/j.ygyno.2020.07.099. Epub 2020 Aug 16.
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.
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.
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.
AI-assisted cytology may contribute to the primary cytology screening or triage. Further studies are needed in general population.
人工智能（AI）能够自动检测数字细胞学图像中的异常情况，然而，其在宫颈癌筛查中的效果尚无定论。我们旨在评估AI辅助细胞学检测组织学宫颈上皮内瘤变（CIN）或癌症的性能。
我们基于188,542张数字细胞学图像训练了一种监督深度学习算法。在2017年3月13日至2018年10月20日期间，来自组织性筛查的2145名转诊女性参加了一项多中心、基于临床的观察性研究。采集宫颈标本制成两张液基涂片：一张随机涂片用于AI辅助阅片，另一张用于由上级医院的熟练细胞病理学家和基层医院的细胞学医生进行的人工阅片。进行HPV检测和阴道镜引导下活检，组织学结果作为参考。我们计算了AI辅助阅片与人工阅片相比对CIN2+的相对敏感性和相对特异性。该试验已注册，注册号为ChiCTR2000034131。
在转诊人群中，AI辅助阅片检测出92.6%的CIN 2和96.1%的CIN 3+，显著高于或类似于人工阅片。与熟练的细胞病理学家相比，AI辅助阅片具有相当的敏感性（相对敏感性1.01，95%CI，0.97 - 1.05）和更高的特异性（相对特异性1.26，1.20 - 1.32）；与细胞学医生相比，具有更高的敏感性（1.12，1.05 - 1.20）和特异性（1.36，1.25 - 1.48）。在HPV阳性女性中，与人工阅片相比，AI辅助阅片提高了对CIN1或更低病变的特异性，且不降低敏感性。
AI辅助细胞学可能有助于初级细胞学筛查或分流。一般人群中还需要进一步研究。
