文献速递胸部CT

人工智能辅助放射科医师在胸部CT上区分COVID-19与其他原因肺炎的表现

Artificial Intelligence Augmentation of Radiologist Performance in Distinguishing COVID-19 from Pneumonia of Other Origin at Chest CT.
PubMed 文献 · Radiology · 2020-04-27

研究回顾性纳入10家医院521例COVID-19患者和3家医院665例非COVID-19肺炎患者,建立EfficientNet B4深度学习系统区分两者。模型测试准确率96%、敏感度95%、特异度96%,独立测试准确率87%;6名放射科医师在AI辅助下平均准确率由85%升至90%、敏感度由79%升至88%、特异度由88%升至91%。

要点

  • AI模型区分COVID-19与非COVID-19肺炎的测试准确率96%、敏感度95%、特异度96%,AUC 0.95。
  • 独立外院测试中模型准确率87%、敏感度89%、特异度86%,AUC 0.90,性能有所下降。
  • 放射科医师在AI概率辅助下平均准确率由85%升至90%(Δ=5,P<.001),敏感度由79%升至88%(Δ=9,P<.001)。

核心结论

  • AI辅助提高了放射科医师在胸部CT上区分COVID-19肺炎与非COVID-19肺炎的表现。

研究设计与样本

  • 回顾性研究,COVID-19组521例来自10家医院(2020年1月至2020年4月),非COVID-19肺炎组665例来自3家医院(2017年至2019年),最终队列1186例、132 583层CT。
  • 异常CT层面经肺分割后输入EfficientNet B4深度神经网络,再经两层全连接神经网络汇总层面分类。
  • 队列按7:2:1比例分为训练集、验证集和测试集,并在独立医院进行独立测试;由6名放射科医师在无AI和有AI辅助下盲法阅片。

诊断标准与关键数值

  • 最终模型测试准确率96%(95%CI:90%,98%),敏感度95%(95%CI:83%,100%),特异度96%(95%CI:88%,99%),AUC 0.95,PR曲线下面积0.90。
  • 独立测试准确率87%(95%CI:82%,90%),敏感度89%(95%CI:81%,94%),特异度86%(95%CI:80%,90%),AUC 0.90,PR曲线下面积0.87。
  • 放射科医师无AI辅助平均测试准确率85%、敏感度79%、特异度88%;有AI辅助平均准确率90%(Δ=5,P<.001)、敏感度88%(Δ=9,P<.001)、特异度91%(Δ=3,P=.001)。

临床应用与阅片要点

  • 模型输出概率可作为辅助信息供放射科医师阅片时参考,以提高区分COVID-19与其他肺炎的准确率、敏感度和特异度。

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 Coronavirus disease 2019 (COVID-19) and pneumonia of other diseases share similar CT characteristics, which contributes to the challenges in differentiating them with high accuracy. Purpose To establish and evaluate an artificial intelligence (AI) system for differentiating COVID-19 and other pneumonia at chest CT and assessing radiologist performance without and with AI assistance. Materials and Methods A total of 521 patients with positive reverse transcription polymerase chain reaction results for COVID-19 and abnormal chest CT findings were retrospectively identified from 10 hospitals from January 2020 to April 2020. A total of 665 patients with non-COVID-19 pneumonia and definite evidence of pneumonia at chest CT were retrospectively selected from three hospitals between 2017 and 2019. To classify COVID-19 versus other pneumonia for each patient, abnormal CT slices were input into the EfficientNet B4 deep neural network architecture after lung segmentation, followed by a two-layer fully connected neural network to pool slices together. The final cohort of 1186 patients (132 583 CT slices) was divided into training, validation, and test sets in a 7:2:1 and equal ratio. Independent testing was performed by evaluating model performance in separate hospitals. Studies were blindly reviewed by six radiologists without and then with AI assistance. Results The final model achieved a test accuracy of 96% (95% confidence interval [CI]: 90%, 98%), a sensitivity of 95% (95% CI: 83%, 100%), and a specificity of 96% (95% CI: 88%, 99%) with area under the receiver operating characteristic curve of 0.95 and area under the precision-recall curve of 0.90. On independent testing, this model achieved an accuracy of 87% (95% CI: 82%, 90%), a sensitivity of 89% (95% CI: 81%, 94%), and a specificity of 86% (95% CI: 80%, 90%) with area under the receiver operating characteristic curve of 0.90 and area under the precision-recall curve of 0.87. Assisted by the probabilities of the model, the radiologists achieved a higher average test accuracy (90% vs 85%, Δ = 5, P < .001), sensitivity (88% vs 79%, Δ = 9, P < .001), and specificity (91% vs 88%, Δ = 3, P = .001). Conclusion Artificial intelligence assistance improved radiologists' performance in distinguishing coronavirus disease 2019 pneumonia from non-coronavirus disease 2019 pneumonia at chest CT. © 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. Bai HX, Wang R, Xiong Z, et al. Artificial Intelligence Augmentation of Radiologist Performance in Distinguishing COVID-19 from Pneumonia of Other Origin at Chest CT. Radiology. 2020. PMID: 32339081. doi:10.1148/radiol.2020201491

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。