文献速递胸部CT

基于CT影像组学的孤立性肺结节特征分类预测效能

Prediction efficacy of feature classification of solitary pulmonary nodules based on CT radiomics.
PubMed 文献 · Eur J Radiol · 2021-03-18

该研究纳入189例病理确诊的肺结节患者,构建三个CT影像组学模型分别用于良性/恶性、恶性非浸润/浸润、以及良性/恶性非浸润/浸润的三分类,测试组AUC分别为0.85、0.89和0.84,表明影像组学特征模型能较好反映不同病理分类结节的差异并辅助分类。

要点

  • CT影像组学模型可用于肺结节良性、恶性非浸润、浸润的逐层分类。
  • 模型2区分恶性非浸润与浸润的AUC最高(0.89)。
  • 三分类模型3的AUC为0.84,敏感度71.34%、特异度85.05%。

核心结论

  • 基于CT图像的影像组学特征模型能较好反映良性结节、恶性非浸润结节和浸润结节之间的差异,并辅助其分类。

研究设计与样本

  • 回顾性研究纳入2017年7月至2019年8月病理确诊的189例肺结节患者,包括良性71例、恶性非浸润51例、浸润67例。
  • 基于CT影像勾画感兴趣区提取高通量特征,采用智能方法筛选特征和分类器,分别建立三个影像组学模型。
  • 模型1分类良性与恶性(含恶性非浸润和浸润),模型2分类恶性非浸润与浸润,模型3分类良性、恶性非浸润和浸润。
  • 以ROC曲线及曲线下面积(AUC)评价模型预测效能,并计算敏感度、特异度、准确率、阳性预测值和阴性预测值。

诊断标准与关键数值

  • 模型1、2、3分别筛选出20、2、20个影像组学特征。
  • 测试组中模型1的AUC为0.85,敏感度79.66%,特异度70.42%,准确率84.59%,阳性预测值81.74%,阴性预测值67.57%。
  • 测试组中模型2的AUC为0.89,敏感度88.06%,特异度74.51%,准确率82.2%,阳性预测值81.94%,阴性预测值82.61%。
  • 测试组中模型3的AUC为0.84,敏感度71.34%,特异度85.05%,准确率70.37%,阳性预测值83.2%,阴性预测值76.3%。

临床应用与阅片要点

  • 日常阅片可参考影像组学模型对肺结节进行良性、恶性非浸润、浸润的逐层分类辅助判断。
  • 模型2对区分恶性非浸润与浸润结节具有较高AUC(0.89),可作为浸润性评估的参考。
  • 模型3三分类特异度较高(85.05%),但敏感度相对较低(71.34%),需结合形态学特征综合判断。

局限性

  • 原文未明确报告研究局限性;本研究为单中心回顾性设计,样本量有限(189例),外部泛化能力需进一步验证。

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 investigate the relationship between CT radiomic features, pathological classification of pulmonary nodules, and evaluate the prediction effect of different stratified progressive radiomic models on the pathological classification of pulmonary nodules.

METHODS: Altogether, 189 patients pathologically confirmed with pulmonary nodules from July 2017 to August 2019 who had complete data were enrolled, including 71 patients with benign nodules, 51 with malignant non-invasive nodules, and 67 with invasive nodules. Three CT radiomic models were established respectively. Model 1 classified benign and malignant nodules (including malignant non-invasive and invasive nodules). Model 2 classified malignant non-invasive and invasive nodules. Model 3 classified benign, malignant non-invasive, and invasive nodules. High-throughput feature collection was carried out for all delineated regions of interest (ROIs), and the best models were established by screening features and classifiers using intelligent methods. ROC curves and areas under the curve (AUCs) were used to evaluate the prediction efficacy of the models by calculating the sensitivity, specificity, accuracies, positive predictive values, and negative predictive values.

RESULTS: Through Models 1, 2, and 3, we screened out 20, 2, and 20 radiomic features, respectively, and plotted the ROC curves. In the test group, the AUC values were 0.85, 0.89, and 0.84, respectively; the sensitivity, specificity, accuracy, positive predictive value, and negative predictive value were 79.66 %, 70.42 %, 84.59 %, and 81.74 % and 67.57% for Model 1, 88.06 %, 74.51 %, 82.2 %, 81.94 %, and 82.61 % for Model 2, and 71.34 %, 85.05 %, 70.37 %, 83.2 %, and 76.3 % for Model 3.

CONCLUSION: The radiomic feature models based on CT images could well reflect the differences between benign nodules, malignant non-invasive nodules, and invasive nodules, and assist in their classification.

来源:Eur J Radiol,查看原文。版权归原作者所有。

引用

  1. Xu QQ, Shan WL, Zhu Y, et al. Prediction efficacy of feature classification of solitary pulmonary nodules based on CT radiomics. Eur J Radiol. 2021. PMID: 33867180. doi:10.1016/j.ejrad.2021.109667

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。