Shandong Key Laboratory of Medical Physics and Image Processing & Shandong Provincial Engineering and Technical Center of Light Manipulations, School of Physics and Electronics, Shandong Normal University, Jinan, 250358, China.
Department of Radiation Oncology, Shandong Cancer Hospital and Institute, Shandong First Medical University and Shandong Academy of Medical Sciences, No.440, Jiyan Road, Jinan, 250117, Shandong, China.
BMC Med Imaging. 2020 Feb 5;20(1):12. doi: 10.1186/s12880-020-0416-3.
We aimed to develop radiomic models based on different phases of computed tomography (CT) imaging and to investigate the efficacy of models for diagnosing mediastinal metastatic lymph nodes (LNs) in non-small cell lung cancer (NSCLC).
Eighty-six NSCLC patients were enrolled in this study, and we selected 231 mediastinal LNs confirmed by pathology results as the subjects which were divided into training (n = 163) and validation cohorts (n = 68). The regions of interest (ROIs) were delineated on CT scans in the plain phase, arterial phase and venous phase, respectively. Radiomic features were extracted from the CT images in each phase. A least absolute shrinkage and selection operator (LASSO) algorithm was used to select features, and multivariate logistic regression analysis was used to build models. We constructed six models (orders 1-6) based on the radiomic features of the single- and dual-phase CT images. The performance of the radiomic model was evaluated by the area under the receiver operating characteristic curve (AUC), sensitivity, specificity, accuracy, positive predictive value (PPV) and negative predictive value (NPV).
A total of 846 features were extracted from each ROI, and 10, 9, 5, 2, 2, and 9 features were chosen to develop models 1-6, respectively. All of the models showed excellent discrimination, with AUCs greater than 0.8. The plain CT radiomic model, model 1, yielded the highest AUC, specificity, accuracy and PPV, which were 0.926 and 0.925; 0.860 and 0.769; 0.871 and 0.882; and 0.906 and 0.870 in the training and validation sets, respectively. When the plain and venous phase CT radiomic features were combined with the arterial phase CT images, the sensitivity increased from 0.879 and 0.919 to 0.949 and 0979 and the NPV increased from 0.821 and 0.789 to 0.878 and 0.900 in the training group, respectively.
All of the CT radiomic models based on different phases all showed high accuracy and precision for the diagnosis of LN metastasis (LNM) in NSCLC patients. When combined with arterial phase CT, the sensitivity and NPV of the model was be further improved.
本研究旨在建立基于 CT 不同时相的影像组学模型，并探讨其对非小细胞肺癌（NSCLC）纵隔转移性淋巴结（LNs）的诊断效能。
本研究纳入 86 例 NSCLC 患者，共 231 枚经病理证实的纵隔淋巴结作为研究对象，将其分为训练集（n=163）和验证集（n=68）。分别在 CT 平扫、动脉期和静脉期勾画感兴趣区（ROI），提取各时相 CT 图像的影像组学特征。采用最小绝对收缩和选择算子（LASSO）算法筛选特征，多因素 logistic 回归分析构建模型。基于单时相和双时相 CT 图像的影像组学特征，构建了 6 个模型（order1-6）。采用受试者工作特征曲线下面积（AUC）、敏感度、特异度、准确率、阳性预测值（PPV）和阴性预测值（NPV）评估模型效能。
每个 ROI 提取了 846 个特征，分别用于构建模型 1-6，共选择了 10、9、5、2、2 和 9 个特征。所有模型的 AUC 均大于 0.8，表现出良好的区分度。基于 CT 平扫的影像组学模型（model1）在训练集和验证集的 AUC、特异度、准确率和 PPV 分别为 0.926 和 0.925、0.860 和 0.769、0.871 和 0.882、0.906 和 0.870。当将 CT 平扫和静脉期的影像组学特征与动脉期 CT 图像相结合时，模型的敏感度从 0.879 和 0.919 提高到 0.949 和 0.979，NPV 从 0.821 和 0.789 提高到 0.878 和 0.900。
基于 CT 不同时相的影像组学模型均能准确、精确地诊断 NSCLC 患者的 LN 转移（LNM）。与动脉期 CT 相结合时，可进一步提高模型的敏感度和 NPV。
