论文部分内容阅读
目的:探究n 18F-脱氧葡萄糖(FDG)PET/CT影像组学特征预测肺腺癌患者程序性细胞死亡蛋白配体1(PD-L1)表达水平的临床应用价值。n 方法:回顾性纳入2017年1月至2019年1月间北京大学肿瘤医院核医学科101例病理确诊且治疗前行n 18F-FDG PET/CT检查的肺腺癌患者(男43例、女58例，中位年龄60岁)。免疫组织化学检测PD-L1表达阳性44例，阴性57例；分为训练组(71例)和验证组(30例)。分别提取患者临床病理资料、PET/CT影像组学特征、PET传统代谢参数、CT征象，将其纳入模型，使用过滤法和嵌入法进行特征选择。基于logistic回归、随机森林、XGBoost与轻量梯度提升机(LightGBM)，分别进行训练并评估预测效果，优化得出预测PD-L1水平的最佳模型参数及相应受试者工作特征曲线下面积(AUC)。n 结果:对于PD-L1表达，各模型均有一定的预测效果，以LightGBM模型最优，其对阳性和阴性的预测精确率分别为0.85和0.76。将临床资料+CT信息纳入LightGBM，精确率、召回率、F1指数在阳性组和阴性组中分别为0.71、0.67、0.69和0.69、0.73、0.72，准确性为0.70，AUC为0.79；相应地，临床资料+PET预测模型的精确率、召回率、F1指数在阳性组和阴性组中分别为0.79、0.73、0.76和0.75、0.80、0.77，准确性为0.77，AUC为0.80；临床资料+CT+PET预测模型的精确率、召回率、F1指数在阳性组和阴性组中分别为0.85、0.73、0.79和0.76、0.87、0.81，准确性为0.80，AUC为0.83。从最佳预测模型(临床资料+CT+PET)中筛选出的重要特征包括最大标准摄取值(SUVn max)、标准摄取峰值(SUVn peak)、CT特征_二维最大径、PET特征_形状伸长、PET特征_灰度共生矩阵相关等。n 结论:联合临床资料、PET/CT影像组学特征、传统代谢参数可以有效预测PD-L1表达水平，辅助临床筛选免疫治疗获益人群。“,”Objective:To explore the predictive value of n 18F-fluorodeoxyglucose (FDG) PET/CT radiomics for the programmed death ligand-1 (PD-L1) expression level in lung adenocarcinoma patients.n Methods:A total of 101 patients (43 males, 58 females; median age 60 years) with histologically confirmed lung adenocarcinoma who received pre-treatment n 18F-FDG PET/CT from January 2017 to January 2019 in Peking University Cancer Hospital were included retrospectively. There were 44 patients with positive PD-L1 by immunohistochemical assays, and 57 with PD-L1 negative. Patients were assigned to a training set (n n=71) and a validation set (n n=30). Clinical data, PET/CT radiomics parameters, conventional metabolic parameters, and observed CT characteristics of these patients were included in the models. The filter method and embedded method were used in feature selection. Models based on logistic regression, random forest, XGBoost and Light Gradient Boosting Machine (LightGBM) were trained and evaluated, and the optimal parameters to predict the PD-L1 expression as well as the area under curve (AUC) were attained.n Results:All models had predictive ability in the prediction of PD-L1 expression, while LightGBM was more powerful than the others, with the precision for positive and negative predictions of 0.85 and 0.76, respectively. Incorporating clinical data and data derived from thin-section CT images (clinical data+ CT) into the LightGBM, the precision, recall and F1-score for positive and negative patients were 0.71, 0.67, 0.69 and 0.69, 0.73, 0.72, respectively, with the accuracy of 0.70 and the AUC of 0.79. As for clinical data+ PET, the precision, recall and F1-score for positive and negative patients were 0.79, 0.73, 0.76 and 0.75, 0.80, 0.77, respectively, with the accuracy of 0.77 and the AUC of 0.80. As for clinical data+ CT+ PET, the precision, recall and F1-score for positive and negative patients were 0.85, 0.73, 0.79 and 0.76, 0.87, 0.81, respectively, with the accuracy of 0.80 and the AUC of 0.83. Features with significant importance in the model (clinical data+ CT+ PET) were as follows: maximum standardized uptake value (SUVn max), peak of standardized uptake value (SUVn peak), CT_shape_Maximum2DDiameterSlice, PET_shape_Elongation, PET_gray level co-occurrence matrix (GLCM)_Correlation, etc.n Conclusions:Incorporating clinical data, PET/CT radiomics features and conventional metabolic parameters, the PD-L1 expression can be effectively predicted, which help to assist the selection of patients who may benefit from the immunotherapy.