文献速递胸部CTMR

慢性阻塞性肺疾病:胸部CT纹理分析与机器学习预测肺通气

Chronic Obstructive Pulmonary Disease: Thoracic CT Texture Analysis and Machine Learning to Predict Pulmonary Ventilation.
PubMed 文献 · Radiology · 2019-10-22

这项前瞻性研究将超极化氦3 MRI通气图与胸部CT共配准作为参考标准,提取CT纹理特征并用机器学习建模预测COPD患者的通气异质性。二次支持向量机模型预测的通气图准确率88%(95%CI:88%,88%),AUC 0.82(95%CI:0.82,0.83),模型预测的通气缺陷百分比与MRI通气缺陷百分比相关(r=0.90,P<.001)。

要点

  • CT纹理+机器学习生成的通气图与超极化氦3 MRI通气图相关(r=0.90,P<.001)。
  • 模型预测通气图的准确率88%(95%CI:88%,88%),AUC 0.82(95%CI:0.82,0.83)。
  • 模型预测与MRI的通气缺陷百分比均与FEV1、FEV1/FVC、弥散功能及生活质量评分相关。

核心结论

  • 利用CT纹理和机器学习生成的模型预测通气图与MRI通气图相关(r=0.90,P<.001)。

研究设计与样本

  • 前瞻性研究(ClinicalTrials.gov:NCT02723474;2010年1月至2017年2月开展),参与者随机分为优化集(n=1)、训练集(n=67)和测试集(n=27)。
  • 以超极化氦3 MRI通气图为参考标准,与胸部CT共配准提供真实标签。
  • 提取87个定量影像特征并归一化至全肺平均值,生成174个特征。

关键影像表现/征象

  • 模型预测通气图以超极化氦3 MRI通气图为参考标准时,准确率88%(95%CI:88%,88%),AUC 0.82(95%CI:0.82,0.83)。
  • 模型预测的通气缺陷百分比与超极化氦3 MRI的通气缺陷百分比相关(r=0.90,P<.001)。

诊断标准与关键数值

  • 优化感兴趣区维度和训练数据采样方法以最大化受试者工作特征曲线下面积(AUC)。
  • 采用前向特征选择减少特征数量;逻辑回归、线性支持向量机和二次支持向量机分类器通过五折交叉验证训练。
  • 二次支持向量机在训练中表现最佳,并应用于测试数据集。

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 Fixed airflow limitation and ventilation heterogeneity are common in chronic obstructive pulmonary disease (COPD). Conventional noncontrast CT provides airway and parenchymal measurements but cannot be used to directly determine lung function. Purpose To develop, train, and test a CT texture analysis and machine-learning algorithm to predict lung ventilation heterogeneity in participants with COPD. Materials and Methods In this prospective study (ClinicalTrials.gov: NCT02723474; conducted from January 2010 to February 2017), participants were randomized to optimization (n = 1), training (n = 67), and testing (n = 27) data sets. Hyperpolarized (HP) helium 3 (3He) MRI ventilation maps were co-registered with thoracic CT to provide ground truth labels, and 87 quantitative imaging features were extracted and normalized to lung averages to generate 174 features. The volume-of-interest dimension and the training data sampling method were optimized to maximize the area under the receiver operating characteristic curve (AUC). Forward feature selection was performed to reduce the number of features; logistic regression, linear support vector machine, and quadratic support vector machine classifiers were trained through fivefold cross validation. The highest-performing classification model was applied to the test data set. Pearson coefficients were used to determine the relationships between the model, MRI, and pulmonary function measurements. Results The quadratic support vector machine performed best in training and was applied to the test data set. Model-predicted ventilation maps had an accuracy of 88% (95% confidence interval [CI]: 88%, 88%) and an AUC of 0.82 (95% CI: 0.82, 0.83) when the HP 3He MRI ventilation maps were used as the reference standard. Model-predicted ventilation defect percentage (VDP) was correlated with VDP at HP 3He MRI (r = 0.90, P < .001). Both model-predicted and HP 3He MRI VDP were correlated with forced expiratory volume in 1 second (FEV1) (model: r = -0.65, P < .001; MRI: r = -0.70, P < .001), ratio of FEV1 to forced vital capacity (model: r = -0.73, P < .001; MRI: r = -0.75, P < .001), diffusing capacity (model: r = -0.69, P < .001; MRI: r = -0.65, P < .001), and quality-of-life score (model: r = 0.59, P = .001; MRI: r = 0.65, P < .001). Conclusion Model-predicted ventilation maps generated by using CT textures and machine learning were correlated with MRI ventilation maps (r = 0.90, P < .001). © RSNA, 2019 Online supplemental material is available for this article. See also the editorial by Fain in this issue.

来源:Radiology,查看原文。版权归原作者所有。

引用

  1. Westcott A, Capaldi DPI, McCormack DG, et al. Chronic Obstructive Pulmonary Disease: Thoracic CT Texture Analysis and Machine Learning to Predict Pulmonary Ventilation. Radiology. 2019. PMID: 31638491. doi:10.1148/radiol.2019190450

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。