CT纹理特征在埃克替尼治疗肺腺癌疗效预测中的应用价值探讨  

Application Value of CT Texture Features in Predicting Therapeutic Effect of Icotinib on Lung Adenocarcinoma

作　　者：郑婵 虞希祥 ZHENG Chan;YU Xixiang(Department of Radiology,the Third Afiliated Hospital of Wenzhou Medical University,Wenzhou 325200,Zhejiang,China;Department of Intervention,Wenzhou Third Clinical College,Wenzhou Medical University,Wenzhou 325000,Zhejiang,China)

机构地区：[1]温州医科大学附属第三医院放射影像科,浙江温州325200 [2]温州医科大学温州市第三临床学院介入科,浙江温州325000

出　　处：《中国药物滥用防治杂志》2022年第12期1789-1792,共4页Chinese Journal of Drug Abuse Prevention and Treatment

基　　金：浙江省瑞安市科技计划项目(编号:MS2020003)。

摘　　要：目的:探讨CT纹理特征在埃克替尼治疗肺腺癌疗效预测中的应用价值。方法:回顾性分析2019年1月—2022年1月温州医科大学附属第三医院收治的肺腺癌患者92例,根据实体肿瘤疗效标准(RECIST)将经埃克替尼治疗后患者分为有效组与无效组。对所有患者于治疗前、埃克替尼治疗3个月后行CT检查,通过单因素方差分析筛选治疗前后的CT纹理参数,采用受试者工作特征(ROC)曲线分析CT纹理特征在埃克替尼治疗肺腺癌疗效的预测效能,并比较有效组与无效组之间的CT纹理特征参数。结果:92例患者中,47例患者经埃克替尼治疗后归为有效组,45例为无效组。治疗后熵、偏度低于治疗前,逆差距与角二阶矩高于治疗前(P<0.05);ROC曲线分析显示,联合预测的AUC及敏感度均高于单项CT纹理特征参数(P<0.05)。两组治疗后熵、逆差距及偏度低于治疗前,角二阶矩高于治疗前(P<0.05),而有效组逆差距低于无效组(P<0.05)。结论:CT纹理特征在埃克替尼治疗肺腺癌疗效预测中具有较高的临床应用价值,建议临床予以重点关注。Objective: To investigate the application value of CT texture features in predicting the therapeutic effect of icotinib on lung adenocarcinoma. Methods: A total of 92 patients with lung adenocarcinoma admitted to the Third Affiliated Hospital of Wenzhou Medical University from January 2019 to January 2022 were retrospectively analyzed. According to the Response Evaluation Criteria In Solid Tumors(RECIST), the patients were divided into an effective group and an ineffective group. All patients underwent CT examination before treatment and after 3 months of icotinib treatment. CT texture parameters were screened by one-way analysis of variance before and after treatment, and the receiver operating characteristic(ROC) curve was used to analyze the predictive performance of CT texture features for the therapeutic effect of icotinib on lung adenocarcinoma. The CT texture parameters were compared between the effective group and the ineffective group.Results: Among the 92 patients, 47 patients were classified as effective group after icotinib treatment, and 45 patients were ineffective group. After treatment, entropy and skewness were lower than those before treatment, while inverse difference and angular second moment were higher than those before treatment(P<0.05). ROC curve analysis showed that AUC and sensitivity of combined prediction were higher than those of single CT texture feature parameters(P<0.05). After treatment,the entropy, reverse difference and skewness of the two groups were lower than those before treatment, and the angular second moment was higher than that before treatment(P<0.05), while the reverse difference of the effective group was lower than that of the ineffective group(P<0.05). Conclusion: CT texture features have high clinical application value in predicting the efficacy of icotinib in the treatment of lung adenocarcinoma, and it is recommended that clinical attention should be paid.

关 键 词：纹理特征 埃克替尼 肺腺癌 疗效预测 

分 类 号：R730.44[医药卫生—肿瘤] R734.2[医药卫生—临床医学]