PDF(Pubmed)
Abstract：
OBJECTIVE: Stereotactic body radiotherapy (SBRT) is an important treatment modality for lung cancer patients, however, tumor local recurrence rate remains some challenge and there is no reliable prediction tool. This study aims to develop a prediction model of local control for lung cancer patients undergoing SBRT based on radiomics signature combining with clinical and dosimetric parameters.
METHODS: The radiomics model, clinical model and combined model were developed by radiomics features, incorporating clinical and dosimetric parameters and radiomics signatures plus clinical and dosimetric parameters, respectively. Three models were established by logistic regression (LR), decision tree (DT) or support vector machine (SVM). The performance of models was assessed by receiver operating characteristic curve (ROC) and DeLong test. Furthermore, a nomogram was built and was assessed by calibration curve, Hosmer-Lemeshow and decision curve.
RESULTS: The LR method was selected for model establishment. The radiomics model, clinical model and combined model showed favorite performance and calibration (Area under the ROC curve (AUC) 0.811, 0.845 and 0.911 in the training group, 0.702, 0.786 and 0.818 in the validation group, respectively). The performance of combined model was significantly superior than the other two models. In addition, Calibration curve and Hosmer-Lemeshow (training group: P = 0.898, validation group: P = 0.891) showed good calibration of combined nomogram and decision curve proved its clinical utility.
CONCLUSIONS: The combined model based on radiomics features plus clinical and dosimetric parameters can improve the prediction of 1-year local control for lung cancer patients undergoing SBRT.
METHODS: The radiomics model, clinical model and combined model were developed by radiomics features, incorporating clinical and dosimetric parameters and radiomics signatures plus clinical and dosimetric parameters, respectively. Three models were established by logistic regression (LR), decision tree (DT) or support vector machine (SVM). The performance of models was assessed by receiver operating characteristic curve (ROC) and DeLong test. Furthermore, a nomogram was built and was assessed by calibration curve, Hosmer-Lemeshow and decision curve.
RESULTS: The LR method was selected for model establishment. The radiomics model, clinical model and combined model showed favorite performance and calibration (Area under the ROC curve (AUC) 0.811, 0.845 and 0.911 in the training group, 0.702, 0.786 and 0.818 in the validation group, respectively). The performance of combined model was significantly superior than the other two models. In addition, Calibration curve and Hosmer-Lemeshow (training group: P = 0.898, validation group: P = 0.891) showed good calibration of combined nomogram and decision curve proved its clinical utility.
CONCLUSIONS: The combined model based on radiomics features plus clinical and dosimetric parameters can improve the prediction of 1-year local control for lung cancer patients undergoing SBRT.
摘要：
目的:立体定向放射治疗(SBRT)是肺癌患者的重要治疗方式,然而,肿瘤局部复发率仍然存在一定的挑战，没有可靠的预测工具。本研究旨在基于影像组学特征结合临床和剂量学参数，建立接受SBRT的肺癌患者局部控制预测模型。
方法：影像组学模型，临床模型和组合模型由影像组学特征开发，结合临床和剂量学参数和影像组学特征以及临床和剂量学参数，分别。通过逻辑回归(LR)建立了三个模型，决策树(DT)或支持向量机(SVM)。通过受试者工作特征曲线（ROC）和DeLong检验评估模型的性能。此外，建立了列线图，并通过校准曲线进行了评估，Hosmer-Lemeshow和决策曲线。
结果：选择LR方法进行模型建立。影像组学模型，临床模型和联合模型在训练组中表现出喜欢的表现和校准(ROC曲线下面积(AUC)0.811、0.845和0.911,验证组中的0.702、0.786和0.818，分别)。组合模型的性能明显优于其他两种模型。此外,校准曲线和Hosmer-Lemeshow（训练组：P=0.898，验证组：P=0.891）显示了组合列线图的良好校准，决策曲线证明了其临床实用性。
结论：基于影像组学特征加上临床和剂量学参数的组合模型可以改善接受SBRT的肺癌患者1年局部控制的预测。
方法：影像组学模型，临床模型和组合模型由影像组学特征开发，结合临床和剂量学参数和影像组学特征以及临床和剂量学参数，分别。通过逻辑回归(LR)建立了三个模型，决策树(DT)或支持向量机(SVM)。通过受试者工作特征曲线（ROC）和DeLong检验评估模型的性能。此外，建立了列线图，并通过校准曲线进行了评估，Hosmer-Lemeshow和决策曲线。
结果：选择LR方法进行模型建立。影像组学模型，临床模型和联合模型在训练组中表现出喜欢的表现和校准(ROC曲线下面积(AUC)0.811、0.845和0.911,验证组中的0.702、0.786和0.818，分别)。组合模型的性能明显优于其他两种模型。此外,校准曲线和Hosmer-Lemeshow（训练组：P=0.898，验证组：P=0.891）显示了组合列线图的良好校准，决策曲线证明了其临床实用性。
结论：基于影像组学特征加上临床和剂量学参数的组合模型可以改善接受SBRT的肺癌患者1年局部控制的预测。
