文献速递妇科

人工智能辅助细胞学检测宫颈上皮内瘤变或浸润性癌:一项多中心、基于临床的观察性研究

Artificial intelligence-assisted cytology for detection of cervical intraepithelial neoplasia or invasive cancer: A multicenter, clinical-based, observational study.
PubMed 文献 · Gynecol Oncol · 2020-08-16

该多中心观察性研究基于188,542张数字细胞学图像训练监督深度学习算法,纳入2145例转诊女性,比较AI辅助阅片与人工阅片对CIN2+的相对敏感度和特异度。AI辅助阅片对CIN2+的敏感度与资深细胞学家等效(相对敏感度1.01,95%CI 0.97-1.05),特异度更高(相对特异度1.26,95%CI 1.20-1.32),对基层细胞学医生的敏感度和特异度均更高。作者认为AI辅助细胞学可能有助于初级细胞学筛查或分流,但需在一般人群中进一步研究。

要点

  • AI辅助阅片对CIN2+的相对敏感度1.01(95%CI 0.97-1.05),与资深细胞学家等效。
  • AI辅助阅片相对资深细胞学家的相对特异度1.26(95%CI 1.20-1.32),特异度更高。
  • AI辅助阅片相对基层细胞学医生的相对敏感度1.12(95%CI 1.05-1.20)、相对特异度1.36(95%CI 1.25-1.48)。

核心结论

  • AI辅助细胞学可能有助于初级细胞学筛查或分流,但需在一般人群中进一步研究。

研究设计与样本

  • 基于188,542张数字细胞学图像训练监督深度学习算法。
  • 2017年3月13日至2018年10月20日纳入2145例来自有组织筛查的转诊女性,进行多中心、基于临床的观察性研究。
  • 宫颈标本生成两张液基玻片,随机分配一张行AI辅助阅片,另一张由资深医院细胞学家和基层医院细胞学医生行人工阅片。
  • 行HPV检测和阴道镜下定向活检,以组织学结果为参照。
  • 计算AI辅助阅片相比人工阅片对CIN2+的相对敏感度和相对特异度。

主要发现

  • 在转诊人群中,AI辅助阅片检出92.6%的CIN2和96.1%的CIN3+,显著高于或相似于人工阅片。
  • AI辅助阅片相比资深细胞学家:相对敏感度1.01(95%CI 0.97-1.05),相对特异度1.26(95%CI 1.20-1.32)。
  • AI辅助阅片相比基层细胞学医生:相对敏感度1.12(95%CI 1.05-1.20),相对特异度1.36(95%CI 1.25-1.48)。
  • 在HPV阳性女性中,AI辅助阅片相比人工阅片提高了对CIN1或以下的特异度,且未以降低敏感度为代价。

临床怎么用

  • 原文未据此给出推荐。

局限性

  • 原文结论指出需在一般人群中进一步研究。

以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。

原文

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.

来源:Gynecol Oncol,查看原文。版权归原作者所有。

引用

  1. Bao H, Bi H, Zhang X, et al. Artificial intelligence-assisted cytology for detection of cervical intraepithelial neoplasia or invasive cancer: A multicenter, clinical-based, observational study. Gynecol Oncol. 2020. PMID: 32814641. doi:10.1016/j.ygyno.2020.07.099

供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。