文献速递胸部DR

深度学习算法在健康筛查人群中胸部X线片肺癌检测的性能与放射科医师解读的比较

Performance of a Deep Learning Algorithm Compared with Radiologic Interpretation for Lung Cancer Detection on Chest Radiographs in a Health Screening Population.
PubMed 文献 · Radiology · 2020-09-22

本研究回顾性验证商业化深度学习算法在健康筛查人群胸部X线片上的肺癌检测性能,并与放射科医师比较。验证集10 285张X线片(10例可见肺癌)中算法AUC为0.99,敏感度90%与医师60%无显著差异(P=.25),但假阳性率更高(3.1% vs 0.3%,P<.001)。筛查队列100 525张X线片(47例可见肺癌)中算法AUC为0.97,敏感度83%、假阳性率3%。结论认为算法检测性能与放射科医师相当,有助于低患病率健康人群的阅片。

要点

  • 健康筛查人群验证集中算法AUC 0.99,敏感度90%与医师60%无显著差异(P=.25)。
  • 算法假阳性率显著高于放射科医师(3.1% vs 0.3%,P<.001)。
  • 大型筛查队列中算法AUC 0.97,敏感度83%、假阳性率3%。

核心结论

  • 深度学习算法在胸部X线片上检测肺癌的性能与放射科医师相当,有助于低患病率健康人群的阅片。

研究设计与样本

  • 对商业化深度学习算法进行样本外测试,回顾性使用2008年7月至2008年12月接受综合医学检查者的胸部X线片作为验证测试。
  • 验证测试纳入10 202人的10 285张胸部X线片(平均年龄54岁±11,5857名男性),其中10张为可见肺癌。
  • 另将算法应用于2008年1月至2012年12月接受胸部X线摄影的筛查队列,共50 070人的100 525张胸部X线片(平均年龄53岁±11,28 090名男性),其中47张为可见肺癌。

诊断标准与关键数值

  • 验证测试中算法检测可见肺癌的AUC为0.99(95%CI:0.97,1),敏感度90%(9/10张),假阳性率3.1%(319/10 275张)。
  • 验证测试中放射科医师敏感度60%(6/10张),假阳性率0.3%(26/10 275张),算法敏感度与医师无显著差异(P=.25),假阳性率高于医师(P<.001)。
  • 筛查队列中算法检测可见肺癌的AUC为0.97(95%CI:0.95,0.99),敏感度83%(39/47张),假阳性率3%(2999/100 478张)。

临床应用与阅片要点

  • 原文结论认为该算法检测肺癌的性能与放射科医师相当,有助于放射科医师在低患病率健康人群中阅片。

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 The performance of a deep learning algorithm for lung cancer detection on chest radiographs in a health screening population is unknown. Purpose To validate a commercially available deep learning algorithm for lung cancer detection on chest radiographs in a health screening population. Materials and Methods Out-of-sample testing of a deep learning algorithm was retrospectively performed using chest radiographs from individuals undergoing a comprehensive medical check-up between July 2008 and December 2008 (validation test). To evaluate the algorithm performance for visible lung cancer detection, the area under the receiver operating characteristic curve (AUC) and diagnostic measures, including sensitivity and false-positive rate (FPR), were calculated. The algorithm performance was compared with that of radiologists using the McNemar test and the Moskowitz method. Additionally, the deep learning algorithm was applied to a screening cohort undergoing chest radiography between January 2008 and December 2012, and its performances were calculated. Results In a validation test comprising 10 285 radiographs from 10 202 individuals (mean age, 54 years ± 11 [standard deviation]; 5857 men) with 10 radiographs of visible lung cancers, the algorithm's AUC was 0.99 (95% confidence interval: 0.97, 1), and it showed comparable sensitivity (90% [nine of 10 radiographs]) to that of the radiologists (60% [six of 10 radiographs]; P = .25) with a higher FPR (3.1% [319 of 10 275 radiographs] vs 0.3% [26 of 10 275 radiographs]; P < .001). In the screening cohort of 100 525 chest radiographs from 50 070 individuals (mean age, 53 years ± 11; 28 090 men) with 47 radiographs of visible lung cancers, the algorithm's AUC was 0.97 (95% confidence interval: 0.95, 0.99), and its sensitivity and FPR were 83% (39 of 47 radiographs) and 3% (2999 of 100 478 radiographs), respectively. Conclusion A deep learning algorithm detected lung cancers on chest radiographs with a performance comparable to that of radiologists, which will be helpful for radiologists in healthy populations with a low prevalence of lung cancer. © RSNA, 2020 Online supplemental material is available for this article. See also the editorial by Armato in this issue.

来源:Radiology,查看原文。版权归原作者所有。

引用

  1. Lee JH, Sun HY, Park S, et al. Performance of a Deep Learning Algorithm Compared with Radiologic Interpretation for Lung Cancer Detection on Chest Radiographs in a Health Screening Population. Radiology. 2020. PMID: 32960729. doi:10.1148/radiol.2020201240

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。