Delta影像组学联合临床特征评估EGFR-TKI治疗肺腺癌的疗效  

Delta-radiomics combined with clinical features for predicting the therapeutic effect of EGFR-TKI forlung adenocarcinoma

作　　者：王慧慧 魏正琦 潘犇 杨鑫淼 梁长华[1] WANG Hui-hui;WEI Zheng-qi;PAN Ben(The First Affiliated Hospital of Xinxiang Medical University,Henan 453100,China)

机构地区：[1]新乡医学院第一附属医院放射科,河南新乡453100

出　　处：《放射学实践》2025年第4期464-469,共6页Radiologic Practice

基　　金：河南省慢病防治与智慧健康管理重点实验室2024年度开放课题(ZYYC2024MB)。

摘　　要：目的:探讨Delta影像组学联合临床特征对肺腺癌患者经表皮生长因子受体酪氨酸激酶抑制剂(EGFR-TKI)治疗后疗效的预测价值。方法:回顾性将2020年1月-2023年6月在本院经病理证实为肺腺癌并经过EGFR-TKI药物治疗的141例患者纳入本研究,并按照8∶2的比例分为训练集和测试集。搜集每例患者的人口统计学资料、肿瘤位置、肿瘤最大直径、分期和EGFR突变方式等11项临床资料。从治疗前及治疗6~12周后的动脉期CT图像中提取肺部病灶的影像组学特征,通过计算特征的净变化获得Delta影像组学特征。采用logistic回归方法建立Delta影像组学模型、治疗前影像组学模型及临床-组学联合模型,采用受试者工作特征(ROC)曲线下面积(AUC)、校准曲线和决策曲线分析(DCA)评估各模型对EGFR-TKI疗效的预测效能。结果:多因素逻辑回归分析显示11项临床资料中仅EGFR突变方式是评估EGFR-TKI治疗效果的独立预测因素。具有15个Delta影像组学特征的组学模型具有良好的预测效能,在训练集和测试集中的AUC分别为0.843和0.823,结合临床资料构建的联合模型显示出更好的预测效能,在训练集和测试集中的AUC分别为0.838和0.864,且具有较好的校准能力。DCA显示,联合模型的净获益在阈值为0.38~0.80时优于治疗前影像组学模型。结论:Delta影像组学联合临床特征有助于评估肺腺癌对EGFR-TKI的治疗效果,并有助于制定后续的治疗策略。Objective:The aim of this study was to evaluate the predictive value of Delta radiomics combined with clinical features in predicting the efficacy of epidermal growth factor receptor-tyrosine kinase inhibitor(EGFR-TKI)in lung adenocarcinoma treatment.Methods:Retrospectively enrolled 141 patients with pathologically confirmed lung adenocarcinoma and treated with EGFR-TKI drugs in our hospital from January 2020 to June 2023 were included in this study.All patients were randomly divided into training and testing cohorts at a ratio of 8∶2.The clinical data of 11 index such as demographic information,tumor location,maximum tumor diameter,stage,and EGFR mutation status were collected for each patient.Radiomics features of lung lesions were extracted from enhanced CT images before and after 6~12 weeks therapy using EGFR-TKI.Delta radiomics features were obtained by calculating the net changes of features,and defined as the relative net change of radiomics features between pre-treatment and the first following.The logistic regression method was used to establish the delta-radiomics model,pre-treatment radiomics model and radiomics-clinical combined model.The diagnostic performance of each model for EGFR-TKI efficacy was evaluated by receiver operating characteristic curve,area under the curve,calibration curve and decision curve analysis(DCA).Results:A total of 11 clinical data were collected,multivariate logistic regression analysis showed that only EGFR mutation mode was an independent predictor.The model with fifteen Delta radiomics features achieved the good discrimination capability with AUC of 0.843 in the training cohort and 0.823 in the test cohort.The clinical-radiomics combined model showed better predictive perfor-mance,with AUC of 0.838 in the training cohort and 0.864 in the test cohort,and good calibration performance was obtained.The DCA showed that the net benefit of the combined model was greater than that of the radiomics models at the threshold of 0.38~0.80.Conclusion:Delta radiomic combined with cli

关 键 词：肺肿瘤 腺癌 影像组学 表皮生长因子受体酪氨酸激酶抑制剂 体层摄影术 X线计算机 疗效评估 

分 类 号：R814.42[医药卫生—影像医学与核医学] R734.2[医药卫生—放射医学]