文献速递胸部CT

深度学习在胸部CT图像中表征2019冠状病毒病(COVID-19)肺炎的方法研究

A deep learning approach to characterize 2019 coronavirus disease (COVID-19) pneumonia in chest CT images.
PubMed 文献 · Eur Radiol · 2020-07-02

研究训练并验证了一个包含病灶检测、分割和定位的深度学习算法,用于自动检测COVID-19患者胸部CT异常,并在中国3家医院96例确诊病例中测试,与3名放射科住院医师比较定量检测性能,以2名高年资放射科医师的读片报告为参考标准。算法在患者层面敏感度为1.00(95%CI 0.95,1.00)、F1评分0.97,在肺叶层面敏感度0.96(95%CI 0.94,0.98)、F1评分0.86。算法平均运行速度20.3 s±5.8/例,快于住院医师(均p<0.017),并可辅助放射科医师更快诊断(均p<0.0001)且诊断性能更优。

要点

  • 患者层面算法检测COVID-19肺炎病灶敏感度1.00(95%CI 0.95,1.00),F1评分0.97。
  • 肺叶层面算法敏感度0.96(95%CI 0.94,0.98),F1评分0.86。
  • 算法自动计算病灶中位体积为40.10 cm³,可自动计算病灶和全肺体积。

关键影像表现/征象

  • 96例患者中88例CT图像上有肺炎病灶,8例CT图像上无异常。

诊断标准与关键数值

  • 患者层面:算法检测病灶敏感度1.00(95%CI 0.95,1.00),F1评分0.97。
  • 肺叶层面:算法敏感度0.96(95%CI 0.94,0.98),F1评分0.86。
  • 评估指标包括准确率、敏感度、特异度和F1评分,以2名有经验放射科医师的读片报告为参考标准。
  • 算法计算病灶中位体积为40.10 cm³。

临床应用与阅片要点

  • 算法平均运行速度20.3 s±5.8/例,评估CT图像快于住院医师(均p<0.017)。
  • 算法可辅助放射科医师更快诊断(均p<0.0001)且诊断性能更优。
  • 算法可自动计算病灶体积和全肺体积。

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

OBJECTIVES: To utilize a deep learning model for automatic detection of abnormalities in chest CT images from COVID-19 patients and compare its quantitative determination performance with radiological residents.

METHODS: A deep learning algorithm consisted of lesion detection, segmentation, and location was trained and validated in 14,435 participants with chest CT images and definite pathogen diagnosis. The algorithm was tested in a non-overlapping dataset of 96 confirmed COVID-19 patients in three hospitals across China during the outbreak. Quantitative detection performance of the model was compared with three radiological residents with two experienced radiologists' reading reports as reference standard by assessing the accuracy, sensitivity, specificity, and F1 score.

RESULTS: Of 96 patients, 88 had pneumonia lesions on CT images and 8 had no abnormities on CT images. For per-patient basis, the algorithm showed superior sensitivity of 1.00 (95% confidence interval (CI) 0.95, 1.00) and F1 score of 0.97 in detecting lesions from CT images of COVID-19 pneumonia patients. While for per-lung lobe basis, the algorithm achieved a sensitivity of 0.96 (95% CI 0.94, 0.98) and a slightly inferior F1 score of 0.86. The median volume of lesions calculated by algorithm was 40.10 cm3. An average running speed of 20.3 s ± 5.8 per case demonstrated the algorithm was much faster than the residents in assessing CT images (all p < 0.017). The deep learning algorithm can also assist radiologists make quicker diagnosis (all p < 0.0001) with superior diagnostic performance.

CONCLUSIONS: The algorithm showed excellent performance in detecting COVID-19 pneumonia on chest CT images compared with resident radiologists.

KEY POINTS: • The higher sensitivity of deep learning model in detecting COVID-19 pneumonia were found compared with radiological residents on a per-lobe and per-patient basis. • The deep learning model improves diagnosis efficiency by shortening processing time. • The deep learning model can automatically calculate the volume of the lesions and whole lung.

来源:Eur Radiol,查看原文。版权归原作者所有。

引用

  1. Ni Q, Sun ZY, Qi L, et al. A deep learning approach to characterize 2019 coronavirus disease (COVID-19) pneumonia in chest CT images. Eur Radiol. 2020. PMID: 32617690. doi:10.1007/s00330-020-07044-9

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。