文献速递胸部CT

基于部分实性肺结节胸部CT影像组学特征诊断浸润性肺腺癌:一项多中心研究

Diagnosis of Invasive Lung Adenocarcinoma Based on Chest CT Radiomic Features of Part-Solid Pulmonary Nodules: A Multicenter Study.
PubMed 文献 · Radiology · 2020-08-25

这项回顾性多中心研究纳入291例患者共297个部分实性肺结节,从整体肿瘤体积、实性成分、磨玻璃成分及结节周围区域提取影像组学特征构建随机森林模型。基于磨玻璃和实性成分特征的影像组学模型在测试集上诊断浸润性肺腺癌的AUC为0.98,显著高于Brock模型、临床-语义模型、体积模型和整体肿瘤体积影像组学模型,准确度为93%。

要点

  • 部分实性结节中分别提取磨玻璃和实性成分的影像组学特征,诊断浸润性肺腺癌的AUC达0.98。
  • 该模型诊断效能显著优于Brock模型(AUC 0.83)、临床-语义模型(AUC 0.90)、体积模型(AUC 0.87)和整体肿瘤体积影像组学模型(AUC 0.88)。
  • 加入结节周围区域特征并未进一步提升模型效能(integrated discrimination improvement -0.02,P = .56)。

核心结论

  • 将部分实性肺结节的磨玻璃和实性CT影像组学特征分开提取,有助于诊断肺腺癌的浸润性,预测效能优于Brock、临床-语义、体积及整体肿瘤体积影像组学模型。

研究设计与样本

  • 回顾性多中心研究(ClinicalTrials.gov注册号NCT03872362),纳入2013年1月至2017年10月291例患者(中位年龄60岁,四分位距55-65岁,191例女性)的297个部分实性肺腺癌结节。
  • 数据分为训练集229个结节和测试集68个结节,从整体肿瘤体积、实性、磨玻璃及结节周围区域提取影像组学特征。
  • 采用随机森林模型分别基于临床-语义特征、体积特征和影像组学特征训练,Brock模型通过在线结节计算器计算。
  • 模型效能采用受试者工作特征曲线下面积(AUC)、准确度和校准度等指标评价,并采用integrated discrimination improvement评估加入结节周围特征后的效能变化。

诊断标准与关键数值

  • 基于磨玻璃和实性特征的影像组学模型在测试集上的AUC为0.98(95%CI:0.96,1.00),显著高于Brock模型(AUC 0.83,95%CI:0.72,0.94;P = .007)。
  • 该模型AUC显著高于临床-语义模型(AUC 0.90,95%CI:0.83,0.98;P = .03)、体积GTV模型(AUC 0.87,95%CI:0.78,0.96;P = .008)和影像组学GTV模型(AUC 0.88,95%CI:0.80,0.96;P = .01)。
  • 该模型准确度最高,为93%(95%CI:84%,98%)。
  • 该模型与加入结节周围特征的模型均显示良好的校准度,但加入结节周围特征未改善效能(integrated discrimination improvement -0.02;P = .56)。

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 Solid components of part-solid nodules (PSNs) at CT are reflective of invasive adenocarcinoma, but studies describing radiomic features of PSNs and the perinodular region are lacking. Purpose To develop and to validate radiomic signatures diagnosing invasive lung adenocarcinoma in PSNs compared with the Brock, clinical-semantic features, and volumetric models. Materials and Methods This retrospective multicenter study (https://ClinicalTrials.gov, NCT03872362) included 291 patients (median age, 60 years; interquartile range, 55-65 years; 191 women) from January 2013 to October 2017 with 297 PSN lung adenocarcinomas split into training (n = 229) and test (n = 68) data sets. Radiomic features were extracted from the different regions (gross tumor volume [GTV], solid, ground-glass, and perinodular). Random-forest models were trained using clinical-semantic, volumetric, and radiomic features, and an online nodule calculator was used to compute the Brock model. Performances of models were evaluated using standard metrics such as area under the curve (AUC), accuracy, and calibration. The integrated discrimination improvement was applied to assess model performance changes after the addition of perinodular features. Results The radiomics model based on ground-glass and solid features yielded an AUC of 0.98 (95% confidence interval [CI]: 0.96, 1.00) on the test data set, which was significantly higher than the Brock (AUC, 0.83 [95% CI: 0.72, 0.94]; P = .007), clinical-semantic (AUC, 0.90 [95% CI: 0.83, 0.98]; P = .03), volumetric GTV (AUC, 0.87 [95% CI: 0.78, 0.96]; P = .008), and radiomics GTV (AUC, 0.88 [95% CI: 0.80, 0.96]; P = .01) models. It also achieved the best accuracy (93% [95% CI: 84%, 98%]). Both this model and the model with added perinodular features showed good calibration, whereas adding perinodular features did not improve the performance (integrated discrimination improvement, -0.02; P = .56). Conclusion Separating ground-glass and solid CT radiomic features of part-solid nodules was useful in diagnosing the invasiveness of lung adenocarcinoma, yielding a better predictive performance than the Brock, clinical-semantic, volumetric, and radiomics gross tumor volume models. Online supplemental material is available for this article. See also the editorial by Nishino in this issue. Published under a CC BY 4.0 license.

来源:Radiology,查看原文。版权归原作者所有。

引用

  1. Wu G, Woodruff HC, Shen J, et al. Diagnosis of Invasive Lung Adenocarcinoma Based on Chest CT Radiomic Features of Part-Solid Pulmonary Nodules: A Multicenter Study. Radiology. 2020. PMID: 32840472. doi:10.1148/radiol.2020192431

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。