深度学习优化肺癌CT筛查候选者选择:推进2021年USPSTF推荐
本研究在健康体检样本中外部验证了一种基于胸部X线的深度学习模型,用于识别肺癌筛查候选者。研究纳入2004年1月至2018年6月间50-80岁现吸烟或既往吸烟者,模型对肺癌的AUC在总体人群为0.68,在USPSTF符合条件人群中为0.75。在排除低风险及不确定风险类别后,CT筛查候选者比例从45.1%降至35.8%(P<.001),肺癌纳入率(0.3% vs 0.3%,P=.85)和阳性预测值(0.9% vs 0.7%,P=.42)未受影响,但遗漏3例肺癌(0.2%)。
要点
- 深度学习模型基于胸部X线可辅助筛选肺癌CT筛查候选者,在USPSTF符合条件人群中AUC为0.75。
- 排除低风险及不确定风险类别后,筛查候选者比例从45.1%降至35.8%,肺癌纳入率和阳性预测值无显著变化。
- 该策略遗漏3例肺癌(0.2%),需在减少筛查人数的同时关注漏诊风险。
核心结论
- 外部验证的深度学习模型对2021年USPSTF低剂量CT肺癌筛查推荐有附加价值,可在保持肺癌纳入率和阳性预测值的情况下减少筛查候选者数量。
研究设计与样本
- 单中心回顾性研究,纳入2004年1月至2018年6月健康体检中接受胸部X线的连续现吸烟或既往吸烟者,年龄50-80岁;共评估19 488人(平均年龄58岁±6,18 467人[95%]为男性),其中USPSTF符合条件者7 835人(平均年龄57岁±6,7 699人[98%]为男性);以胸部X线为基础验证深度学习模型对肺癌的判别性能,并评估其对2021年USPSTF推荐的附加价值。
诊断标准与关键数值
- 模型对肺癌的AUC在总体验证人群为0.68(95%CI:0.62,0.73),在USPSTF符合条件人群中为0.75(95%CI:0.68,0.81);在有包年信息者(n=17 390)中,从USPSTF符合条件样本排除低风险及不确定风险类别后,CT筛查候选者比例从45.1%(7 835/17 390)降至35.8%(6 233/17 390),P<.001;肺癌纳入率0.3%(53/17 390)vs 0.3%(56/17 390),P=.85;阳性预测值0.9%(53/6 233)vs 0.7%(56/7 835),P=.42;遗漏肺癌3例(0.2%)。
临床应用与阅片要点
- 作者结论认为,该深度学习模型对2021年USPSTF低剂量CT肺癌筛查推荐有附加价值,可在保持肺癌纳入率和阳性预测值的情况下减少筛查候选者数量。
局限性
- 原文未报告局限性。
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)。
英文原文(摘要)· 点击展开
Background A deep learning (DL) model to identify lung cancer screening candidates based on their chest radiographs requires external validation with a recent real-world non-U.S. sample. Purpose To validate the DL model and identify added benefits to the 2021 U.S. Preventive Services Task Force (USPSTF) recommendations in a health check-up sample. Materials and Methods This single-center retrospective study included consecutive current and former smokers aged 50-80 years who underwent chest radiography during a health check-up between January 2004 and June 2018. Discrimination performance, including receiver operating characteristic curve analysis and area under the receiver operating characteristic curve (AUC) calculation, of the model for incident lung cancers was evaluated. The added value of the model to the 2021 USPSTF recommendations was investigated for lung cancer inclusion rate, proportion of selected CT screening candidates, and positive predictive value (PPV). Results For model validation, a total of 19 488 individuals (mean age, 58 years ± 6 [SD]; 18 467 [95%] men) and the subset of USPSTF-eligible individuals (n = 7835; mean age, 57 years ± 6; 7699 [98%] men) were assessed, and the AUCs for incident lung cancers were 0.68 (95% CI: 0.62, 0.73) and 0.75 (95% CI: 0.68, 0.81), respectively. In individuals with pack-year information (n = 17 390), when excluding low- and indeterminate-risk categories from the USPSTF-eligible sample, the proportion of selected CT screening candidates was reduced to 35.8% (6233 of 17 390) from 45.1% (7835 of 17 390, P < .001), with three missed lung cancers (0.2%). The cancer inclusion rate (0.3% [53 of 17 390] vs 0.3% [56 of 17 390], P = .85) and PPV (0.9% [53 of 6233] vs 0.7% [56 of 7835], P = .42) remained unaffected. Conclusion An externally validated deep learning model showed the added value to the 2021 U.S. Preventive Services Task Force recommendations for low-dose CT lung cancer screening in reducing the number of screening candidates while maintaining the inclusion rate and positive predictive value for incident lung cancer. © RSNA, 2022 Online supplemental material is available for this article.
引用
- Lee, Lee, Lu, et al. Deep Learning to Optimize Candidate Selection for Lung Cancer CT Screening: Advancing the 2021 USPSTF Recommendations. Radiology. 2022. PMID: 35699582. doi:10.1148/radiol.212877
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。