Department of Medical Imaging, Shanghai Electric Power Hospital, Changning District, No. 937 Yan'an West Road, Shanghai, 20050, China.
J Digit Imaging. 2023 Jun;36(3):1029-1037. doi: 10.1007/s10278-023-00792-2. Epub 2023 Feb 24.
Non-invasive diagnostic method based on radiomic features in patients with non-small cell lung cancer (NSCLC) has attracted attention. This study aimed to develop a CT image-based model for both histological typing and clinical staging of patients with NSCLC. A total of 309 NSCLC patients with 537 CT series from The Cancer Imaging Archive (TCIA) database were included in this study. All patients were randomly divided into the training set (247 patients, 425 CT series) and testing set (62 patients, 112 CT series). A total of 107 radiomic features were extracted. Four classifiers including random forest, XGBoost, support vector machine, and logistic regression were used to construct the classification model. The classification model had two output layers: histological type (adenocarcinoma, squamous cell carcinoma, and large cell) and clinical stage (I, II, and III) of NSCLC patients. The area under the receiver operating characteristic curve (AUC), accuracy, sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV) with 95% confidence interval (CI) were utilized to evaluate the performance of the model. Seven features were selected for inclusion in the classification model. The random forest model had the best classification ability compared with other classifiers. The AUC of the RF model for histological typing and clinical staging of NSCLC patients in the testing set was 0.700 (95% CI, 0.641-0.759) and 0.881 (95% CI, 0.842-0.920), respectively. The CT image-based radiomic feature model had good classification ability for both histological typing and clinical staging of patients with NSCLC.
基于放射组学特征的非侵入性诊断方法在非小细胞肺癌（NSCLC）患者中受到关注。本研究旨在为 NSCLC 患者建立一种基于 CT 图像的组织学分型和临床分期模型。共纳入来自癌症成像档案（TCIA）数据库的 309 例 NSCLC 患者的 537 个 CT 系列。所有患者被随机分为训练集（247 例患者，425 个 CT 系列）和测试集（62 例患者，112 个 CT 系列）。共提取了 107 个放射组学特征。使用随机森林、XGBoost、支持向量机和逻辑回归四种分类器构建分类模型。分类模型有两个输出层：NSCLC 患者的组织学类型（腺癌、鳞状细胞癌和大细胞癌）和临床分期（I、II 和 III）。使用受试者工作特征曲线下面积（AUC）、准确率、敏感度、特异度、阳性预测值（PPV）和阴性预测值（NPV）及其 95%置信区间（CI）来评估模型的性能。选择了 7 个特征纳入分类模型。随机森林模型与其他分类器相比具有最佳的分类能力。在测试集中，RF 模型对 NSCLC 患者组织学分型和临床分期的 AUC 分别为 0.700（95%CI，0.641-0.759）和 0.881（95%CI，0.842-0.920）。基于 CT 图像的放射组学特征模型对 NSCLC 患者的组织学分型和临床分期具有良好的分类能力。
