The artificial intelligence-assisted cytology diagnostic system in large-scale cervical cancer screening: A population-based cohort study of 0.7 million women.
The artificial intelligence-assisted cytology diagnostic system in large-scale cervical cancer screening: A population-based cohort study of 0.7 million women.
复制标题
人工智能辅助细胞学诊断系统在大规模宫颈癌筛查中的应用：70万女性人群队列研究
DOI：
10.1002/cam4.3296
复制
发表时间：
2020-09
期刊：
影响因子：
4
通讯作者：
Wang L
中科院分区：
文献类型：
--
作者：
Bao H;Sun X;Zhang Y;Pang B;Li H;Zhou L;Wu F;Cao D;Wang J;Turic B;Wang L
在大规模宫颈癌筛查中，细胞学家不足限制了适当的细胞学检查。我们的目标是在宫颈癌筛查项目中开发一种人工智能（AI）辅助细胞学系统。我们在基于人群的宫颈癌筛查项目中使用经验证的AI辅助细胞学系统对70万名女性进行了前瞻性队列研究。为了进行比较，细胞学家检查了AI分类为异常的所有载玻片和随机选择的10%正常载玻片。通过阴道镜检查和活检对AI辅助或手动阅读分类为切片异常的每位女性进行诊断。结果经组织学证实为宫颈上皮内瘤变2级或更严重（CIN 2+）。最后，我们招募了703103名女性，其中98549人通过人工智能和手动阅读进行独立筛选。AI和手动阅读之间的总体一致率为94.7%（95%置信区间[CI]，94.5%-94.8%），kappa为0.92（0.91 - 0.92）。AI和手工阅读检查的CIN 2+检出率均随细胞学异常程度的增加而增加（P趋势< 0.001）。一般估计方程显示，通过AI检测的ASC-H或HSIL女性的CIN 2+检出率显著高于细胞学家分类的相应组（对于ASC-H：比值比[OR] = 1.22，95%CI 1.11 - 1.34，P < .001;对于HSIL：OR = 1.41，1.28 - 1.55，P < .001）。AI辅助细胞学检测CIN 2+的灵敏度比手动阅读高5.8%（3.0%-8.6%），特异性略有降低。AI辅助细胞学系统可以排除大部分正常细胞学，与手动细胞学阅读相比，提高了CIN 2+检测的灵敏度，具有临床等效的特异性。总体而言，结果支持基于AI的细胞学系统用于大规模人群的原发性宫颈癌筛查。本研究旨在评估人工智能（AI）在低资源环境下检测早期宫颈癌中的作用。我们的研究结果表明，AI辅助细胞学可以识别大多数阴性细胞学，并且与细胞学家相比，对CIN 2或更差的阳性预测值更高。这项研究表明，AI辅助细胞学可能是一个非常有用的工具，作为大规模宫颈癌筛查计划的主要筛查方法，以提高其有效性。
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. 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+). 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 (P trend < 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 sensitive for detection of CIN2+ than manual reading with a slight reduction in specificity. AI‐assisted cytology system could exclude most of normal cytology, and improve sensitivity with clinically equivalent specificity for detection of CIN2+ compared with manual cytology reading. Overall, the results support AI‐based cytology system for the primary cervical cancer screening in large‐scale population. This study aims to assess the role of Artificial Intelligence (AI) in the detection of early cervical cancer in a low resource setting. Our results showed that AI‐assisted cytology could identify most of negative cytology, and showed higher positive predictive value for CIN2 or worse when compared with cytologists. This study indicates that AI‐assisted cytology could be very useful tool as a primary screening method in a large‐scale cervical cancer screening program to improve its effectiveness.
登录
查看更多内容
影响因子：
2.9
作者：
Sato M;Horie K;Hara A;Miyamoto Y;Kurihara K;Tomio K;Yokota H
通讯作者：
Yokota H
影响因子：
3.4
作者：
Renshaw, AA;Holladay, EB;Geils, KB
通讯作者：
Geils, KB
影响因子：
28.4
作者：
Cuzick, Jack;Myers, Orrin;Wheeler, Cosette M.
通讯作者：
Wheeler, Cosette M.
DOI：
10.1136/bmj.j504
发表时间：
2017-02-14
期刊：
BMJ (Clinical research ed.)
影响因子：
--
作者：
Rozemeijer K;Naber SK;Penning C;Overbeek LI;Looman CW;de Kok IM;Matthijsse SM;Rebolj M;van Kemenade FJ;van Ballegooijen M
通讯作者：
van Ballegooijen M
影响因子：
3.7
作者：
Doornewaard, H;van den Tweel, J G;Jones, H W 3rd
通讯作者：
Jones, H W 3rd