文献速递胸部DRCT

基于深度学习的自动检测算法减少胸片漏诊肺癌

Deep Learning-based Automatic Detection Algorithm for Reducing Overlooked Lung Cancers on Chest Radiographs.
PubMed 文献 · Radiology · 2020-07-21

本研究回顾性纳入117例既往胸片可见肺癌的患者和234例胸片正常对照,9名观察者分别在有、无深度学习自动检测算法(DLAD)辅助下阅片。使用DLAD后观察者平均AUC从0.67升至0.76(P < .001),对漏诊肺癌的平均敏感度从40%升至53%(P < .001),推荐行胸部CT的比例在病例组从47%升至62%(P < .001),而健康对照组CT推荐率无显著差异(10% vs 8%,P = .13)。

要点

  • DLAD辅助使观察者检出漏诊肺癌的平均敏感度从40%(42/105)升至53%(56/105)。
  • DLAD辅助使观察者平均AUC从0.67(95%CI 0.62, 0.72)升至0.76(95%CI 0.71, 0.81)。
  • 病例组胸部CT推荐率从47%(49/105)升至62%(66/105),对照组无显著差异(10% vs 8%,P = .13)。

核心结论

  • 使用基于深度学习的自动检测算法可能帮助观察者减少胸片上漏诊的肺癌,且不引起随访胸部CT检查数量的成比例增加。

研究设计与样本

  • 回顾性研究,2010年1月至2014年12月间诊断肺癌的患者中纳入117例(中位年龄69岁,IQR 64-74岁,57名女性)既往胸片可见肺癌者。
  • 健康对照组为随机选取的234例胸片正常患者(中位年龄58岁,IQR 48-68岁,123名女性)。
  • 9名观察者分别在有、无DLAD辅助下审阅每张胸片,判断潜在肺癌并决定是否推荐胸部CT随访。
  • 采用替代自由响应受试者工作特征曲线下面积(AUC)、敏感度和胸部CT推荐率比较观察者表现。

诊断标准与关键数值

  • 117例患者中105例的肺癌在原始胸片上被漏诊。
  • 所有观察者平均AUC从无DLAD时的0.67(95%CI 0.62, 0.72)显著升至有DLAD时的0.76(95%CI 0.71, 0.81)(P < .001)。
  • 有DLAD时观察者检出更多漏诊肺癌,平均敏感度53%(56/105) vs 无DLAD时40%(42/105)(P < .001)。
  • 有DLAD时推荐胸部CT的患者更多:62%(66/105) vs 无DLAD时47%(49/105)(P < .001)。
  • 健康对照组胸部CT推荐率无差异:无DLAD时10%(23/234) vs 有DLAD时8%(20/234)(P = .13)。

临床应用与阅片要点

  • 原文未据此给出推荐。

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 It is uncertain whether a deep learning-based automatic detection algorithm (DLAD) for identifying malignant nodules on chest radiographs will help diagnose lung cancers. Purpose To evaluate the efficacy of using a DLAD in observer performance for the detection of lung cancers on chest radiographs. Materials and Methods Among patients diagnosed with lung cancers between January 2010 and December 2014, 117 patients (median age, 69 years; interquartile range [IQR], 64-74 years; 57 women) were retrospectively identified in whom lung cancers were visible on previous chest radiographs. For the healthy control group, 234 patients (median age, 58 years; IQR, 48-68 years; 123 women) with normal chest radiographs were randomly selected. Nine observers reviewed each chest radiograph, with and without a DLAD. They detected potential lung cancers and determined whether they would recommend chest CT for follow-up. Observer performance was compared with use of the area under the alternative free-response receiver operating characteristic curve (AUC), sensitivity, and rates of chest CT recommendation. Results In total, 105 of the 117 patients had lung cancers that were overlooked on their original radiographs. The average AUC for all observers significantly rose from 0.67 (95% confidence interval [CI]: 0.62, 0.72) without a DLAD to 0.76 (95% CI: 0.71, 0.81) with a DLAD (P < .001). With a DLAD, observers detected more overlooked lung cancers (average sensitivity, 53% [56 of 105 patients] with a DLAD vs 40% [42 of 105 patients] without a DLAD) (P < .001) and recommended chest CT for more patients (62% [66 of 105 patients] with a DLAD vs 47% [49 of 105 patients] without a DLAD) (P < .001). In the healthy control group, no difference existed in the rate of chest CT recommendation (10% [23 of 234 patients] without a DLAD and 8% [20 of 234 patients] with a DLAD) (P = .13). Conclusion Using a deep learning-based automatic detection algorithm may help observers reduce the number of overlooked lung cancers on chest radiographs, without a proportional increase in the number of follow-up chest CT examinations. © RSNA, 2020 Online supplemental material is available for this article.

来源:Radiology,查看原文。版权归原作者所有。

引用

  1. Jang S, Song H, Shin YJ, et al. Deep Learning-based Automatic Detection Algorithm for Reducing Overlooked Lung Cancers on Chest Radiographs. Radiology. 2020. PMID: 32692300. doi:10.1148/radiol.2020200165

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。