文献速递胸部CT

基于胸部CT肺实质与支气管壁深度学习的COPD识别与分级

COPD identification and grading based on deep learning of lung parenchyma and bronchial wall in chest CT images.
PubMed 文献 · Br J Radiol · 2022-02-16

回顾性纳入一家医院373例、另一家医院226例外部队列,用肺实质和支气管壁CT图像训练两个DenseNet-201卷积神经网络并经逻辑回归组合,以肺功能检查为参考标准诊断和分级COPD。外部队列中CNN判断COPD存在的AUC为0.899(95%CI 0.853-0.935),准确率81.7%(76.2-86.7%),显著高于定量CT的68.1%(61.6%-74.2%)(p<0.05);三分类和五分类准确率分别为77.4%和67.9%。

要点

  • 外部队列CNN判断COPD存在的AUC为0.899(95%CI 0.853-0.935),准确率81.7%。
  • CNN准确率81.7%显著高于定量CT的68.1%(p<0.05)。
  • 三分类(正常、GOLD 1-2、GOLD 3-4)和五分类准确率分别为77.4%和67.9%。

核心结论

  • CNN可识别CT图像上的肺气肿和气道壁重塑,推断肺功能并判断COPD的存在与严重程度,为利用广泛可及的胸部CT检测COPD提供替代途径。

研究设计与样本

  • 回顾性研究,训练队列为一家医院373例,外部队列为另一家医院226例,均接受胸部CT和肺功能检查。

关键影像表现/征象

  • 以肺实质和支气管壁CT图像分别训练两个DenseNet-201卷积神经网络,输出两个置信度并经逻辑回归组合。
  • 以肺功能检查结果将受试者标记为GOLD 1、2、3、4级或正常。
  • 定量CT作为对照方法进行比较。

诊断标准与关键数值

  • 外部队列CNN判断COPD存在的AUC为0.899(95%CI 0.853-0.935),准确率81.7%(76.2-86.7%)。
  • 外部队列定量CT准确率68.1%(61.6%-74.2%),CNN显著高于定量CT(p<0.05)。
  • 三分类(正常、GOLD 1-2、GOLD 3-4)准确率77.4%,五分类(正常、GOLD 1、2、3、4)准确率67.9%。
  • 进展部分报告CNN在外部队列判断COPD存在的AUC为0.853。

临床应用与阅片要点

  • CNN可基于常规胸部CT识别肺气肿和气道壁重塑,推断肺功能并判断COPD存在与严重程度。
  • CNN为利用广泛使用的胸部CT检测COPD提供替代且有效的方法,可作为肺功能检查的重要替代手段。

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: Chest CT can display the main pathogenic factors of chronic obstructive pulmonary disease (COPD), emphysema and airway wall remodeling. This study aims to establish deep convolutional neural network (CNN) models using these two imaging markers to diagnose and grade COPD.

METHODS: Subjects who underwent chest CT and pulmonary function test (PFT) from one hospital (n = 373) were retrospectively included as the training cohort, and subjects from another hospital (n = 226) were used as the external test cohort. According to the PFT results, all subjects were labeled as Global Initiative for Chronic Obstructive Lung Disease (GOLD) Grade 1, 2, 3, 4 or normal. Two DenseNet-201 CNNs were trained using CT images of lung parenchyma and bronchial wall to generate two corresponding confidence levels to indicate the possibility of COPD, then combined with logistic regression analysis. Quantitative CT was used for comparison.

RESULTS: In the test cohort, CNN achieved an area under the curve of 0.899 (95%CI: 0.853-0.935) to determine the existence of COPD, and an accuracy of 81.7% (76.2-86.7%), which was significantly higher than the accuracy 68.1% (61.6%-74.2%) using quantitative CT method (p < 0.05). For three-way (normal, GOLD 1-2, and GOLD 3-4) and five-way (normal, GOLD 1, 2, 3, and 4) classifications, CNN reached accuracies of 77.4 and 67.9%, respectively.

CONCLUSION: CNN can identify emphysema and airway wall remodeling on CT images to infer lung function and determine the existence and severity of COPD. It provides an alternative way to detect COPD using the extensively available chest CT.

ADVANCES IN KNOWLEDGE: CNN can identify the main pathological changes of COPD (emphysema and airway wall remodeling) based on CT images, to infer lung function and determine the existence and severity of COPD. CNN reached an area under the curve of 0.853 to determine the existence of COPD in the external test cohort. The CNN approach provides an alternative and effective way for early detection of COPD using extensively used chest CT, as an important alternative to pulmonary function test.

来源:Br J Radiol,查看原文。版权归原作者所有。

引用

  1. Zhang, Jiang, Wisselink, et al. COPD identification and grading based on deep learning of lung parenchyma and bronchial wall in chest CT images. Br J Radiol. 2022. PMID: 35143286. doi:10.1259/bjr.20210637

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。