文献速递胸部技术与安全DRCT

基于深度学习算法在健康体检人群胸片上检出 Lung-RADS 4 类结节的价値:随机对照试验样本量估算

Value of a deep learning-based algorithm for detecting Lung-RADS category 4 nodules on chest radiographs in a health checkup population: estimation of the sample size for a randomized controlled trial.
PubMed 文献 · Eur Radiol · 2021-07-15

该研究基于年度回顾性队列,纳入 3073 名健康体检者中 118 例 CT 显示 Lung-RADS 4 类结节者及 51 名无结节者,由 4 名放射科医师在有/无深度学习算法辅助下独立判读胸片。算法辅助使汇总敏感度从 38.8% 升至 45.1%(p < .001),特异度无显著变化;但队列年检出率差异仅 0.24%,随机对照试验需每组 41,776 例、总样本超 80,000 例。

要点

  • 算法辅助使放射科医师检出 Lung-RADS 4 类结节的汇总敏感度从 38.8% 升至 45.1%(p < .001)。
  • 算法辅助未显著改变特异度(94.1% vs. 92.2%,p = .22),假阳性率保持 0.09 不变。
  • 健康体检人群 Lung-RADS 4 类结节患病率为 3.8%(118/3073),算法仅使年检出率提高 0.24%。

核心结论

  • 深度学习算法可实质性提高放射科医师在健康体检人群胸片上检出 Lung-RADS 4 类结节的敏感度,但队列年检出率差异仅 0.24%,随机对照试验需每组 41,776 例、总样本超 80,000 例方能证实。

研究设计与样本

  • 年度回顾性队列研究,从 3073 名健康体检者中选取 118 例 CT 显示 Lung-RADS 4 类结节者及随机选取的 51 名无结节者,由 4 名放射科医师在有/无算法辅助下独立判读胸片,比较敏感度与特异度,并估算随机对照试验所需样本量。

诊断标准与关键数值

  • 放射科医师无算法辅助时敏感度为 38.8%(183/472),有算法辅助时为 45.1%(213/472),p < .001。
  • 放射科医师无算法辅助时特异度为 94.1%(192/204),有算法辅助时为 92.2%(188/204),p = .22。
  • 汇总放射科医师无算法辅助时结节检出率为 32.0%(156/488),有算法辅助时为 38.9%(190/488),p < .001。
  • 有/无算法辅助时假阳性率均为 0.09(62/676)。
  • 队列年检出率无算法辅助时为 1.49%(183/12,292),有算法辅助时为 1.73%(213/12,292),差异 0.24%。

临床应用与阅片要点

  • 在健康体检人群胸片判读中,深度学习算法辅助可提高放射科医师对 Lung-RADS 4 类结节的检出敏感度,且不增加假阳性率。
  • 尽管敏感度提升,算法辅助带来的队列年检出率绝对差异仅 0.24%,提示对人群总体检出率的影响有限。
  • 原文估算随机对照试验需每组 41,776 例、总样本 84,000 例方能证实检出率差异有统计学意义。

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

OBJECTIVE: To explore the value of a deep learning-based algorithm in detecting Lung CT Screening Reporting and Data System category 4 nodules on chest radiographs from an asymptomatic health checkup population.

METHODS: Data from an annual retrospective cohort of individuals who underwent chest radiographs for health checkup purposes and chest CT scanning within 3 months were collected. Among 3073 individuals, 118 with category 4 nodules on CT were selected. A reader performance test was performed using those 118 radiographs and randomly selected 51 individuals without any nodules. Four radiologists independently evaluated the radiographs without and with the results of the algorithm; and sensitivities/specificities were compared. The sample size needed to confirm the difference in detection rates was calculated, i.e., the number of true-positive radiographs divided by the total number of radiographs.

RESULTS: The sensitivity of the radiologists substantially increased aided by the algorithm (38.8% [183/472] to 45.1% [213/472]; p < .001) without significant change in specificity (94.1% [192/204] vs. 92.2% [188/204]; p = .22). Pooled radiologists detected more nodules with the algorithm (32.0% [156/488] vs. 38.9% [190/488]; p < .001), without alteration of false-positive rates (0.09 [62/676], both). Pooled detection rates for the annual cohort were 1.49% (183/12,292) and 1.73% (213/12,292) without and with the algorithm, respectively. A sample size of 41,776 in each arm would be required to demonstrate significant detection rate difference with < 5% type I error and > 80% power.

CONCLUSION: Although readers substantially increased sensitivity in detecting nodules on chest radiographs from a health checkup population aided by the algorithm, detection rate difference was only 0.24%, requiring a sample size >80,000 for a randomized controlled trial.

KEY POINTS: • Aided by a deep learning algorithm, pooled radiologists improved their sensitivity in detecting Lung-RADS category 4 nodules on chest radiographs from a health checkup population (38.8% [183/472] to 45.1% [213/472]; p < .001), without increasing false-positive rate. • The prevalence of the Lung-RADS category 4 nodules was 3.8% (118/3073) on the population, resulting in only 0.24% increase of the detection rate for the radiologists with assistance of the algorithm. • To confirm the significant detection rate increase by a randomized controlled trial, a sample size of 84,000 would be required.

来源:Eur Radiol,查看原文。版权归原作者所有。

引用

  1. Nam JG, Kim HJ, Lee EH, et al. Value of a deep learning-based algorithm for detecting Lung-RADS category 4 nodules on chest radiographs in a health checkup population: estimation of the sample size for a randomized controlled trial. Eur Radiol. 2021. PMID: 34264351. doi:10.1007/s00330-021-08162-8

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。