Zha Xinyi, Liu Yuanqing, Ping Xiaoxia, Bao Jiayi, Wu Qian, Hu Su, Hu Chunhong
Department of Radiology, The First Affiliated Hospital of Soochow University, Suzhou, China.
Institute of Medical Imaging, Soochow University, Suzhou, China.
Front Oncol. 2022 May 25;12:876264. doi: 10.3389/fonc.2022.876264. eCollection 2022.
To develop and validate a nomogram model based on radiomics features for preoperative prediction of visceral pleural invasion (VPI) in patients with lung adenocarcinoma.
A total of 659 patients with surgically pathologically confirmed lung adenocarcinoma underwent CT examination. All cases were divided into a training cohort (n = 466) and a validation cohort (n = 193). CT features were analyzed by two chest radiologists. CT radiomics features were extracted from CT images. LASSO regression analysis was applied to determine the most useful radiomics features and construct radiomics score (radscore). A nomogram model was developed by combining the optimal clinical and CT features and the radscore. The model performance was evaluated using ROC analysis, calibration curve and decision curve analysis (DCA).
A total of 1316 radiomics features were extracted. A radiomics signature model with a selection of the six optimal features was developed to identify patients with or without VPI. There was a significant difference in the radscore between the two groups of patients. Five clinical features were retained and contributed as clinical feature models. The nomogram combining clinical features and radiomics features showed improved accuracy, specificity, positive predictive value, and AUC for predicting VPI, compared to the radiomics model alone (specificity: training cohort: 0.89, validation cohort: 0.88, accuracy: training cohort: 0.84, validation cohort: 0.83, AUC: training cohort: 0.89, validation cohort: 0.89). The calibration curve and decision curve analyses suggested that the nomogram with clinical features is beyond the traditional clinical and radiomics features.
A nomogram model combining radiomics and clinical features is effective in non-invasively prediction of VPI in patients with lung adenocarcinoma.
基于影像组学特征开发并验证一种列线图模型，用于术前预测肺腺癌患者的脏层胸膜侵犯（VPI）。
共有659例经手术病理确诊的肺腺癌患者接受了CT检查。所有病例分为训练队列（n = 466）和验证队列（n = 193）。由两名胸部放射科医生分析CT特征。从CT图像中提取CT影像组学特征。应用LASSO回归分析确定最有用的影像组学特征并构建影像组学评分（radscore）。通过结合最佳临床和CT特征以及radscore开发列线图模型。使用ROC分析、校准曲线和决策曲线分析（DCA）评估模型性能。
共提取了1316个影像组学特征。开发了一种选择六个最佳特征的影像组学特征模型，以识别有无VPI的患者。两组患者的radscore存在显著差异。保留了五个临床特征并作为临床特征模型。与单独的影像组学模型相比，结合临床特征和影像组学特征的列线图在预测VPI方面显示出更高的准确性、特异性、阳性预测值和AUC（特异性：训练队列：0.89，验证队列：0.88；准确性：训练队列：0.84，验证队列：0.83；AUC：训练队列：0.89，验证队列：0.89）。校准曲线和决策曲线分析表明，具有临床特征的列线图优于传统的临床和影像组学特征。
结合影像组学和临床特征的列线图模型可有效无创预测肺腺癌患者的VPI。
