摘要
目的探讨影像组学特征在非小细胞肺癌EGFR基因突变中的预测价值。方法回顾性分析127例病理证实为非小细胞肺癌患者的PET/CT及临床实验室资料,对CT和PET图像上的肿瘤病灶进行手动分割并提取影像组学特征,以EGFR突变状态进行分组,采用t检验、Wilcoxon rank-sum检验及卡方分析分析组间影像组学特征及临床特征的差异。采用Logistic回归分析建模,比较影像组学模型、临床模型、联合模型对基因状态的预测价值。结果 EGFR突变与年龄、大小、最大标准摄取值(SUVmax)、癌胚抗原(CEA)无显著相关(P>0.05),与吸烟史、性别、糖类抗原125(CA125)显著相关(P<0.05)。CT影像组学模型可以区分EGFR状态[曲线下面积(AUC)=0.775],结合该模型与临床特征(AUC=0.786)可以提高预测的准确性(AUC=0.867),但不具有显著性(P>0.05)。PET影像组学模型可以很好区分EGFR状态(AUC=0.819),结合临床模型(AUC=0.786),显著地提高了性能(AUC=0.927)。结论基因突变可以驱动不同的影像学表现,基于影像组学特征和临床特征的高级生物标志物可能用于预测EGFR突变状态。
Objective This study investigated the association and predictive power of18 F-FDG PET-based radiomic features for EGFR mutations in non-small cell lung cancer(NSCLC) patients.Methods The PET/CT images and clinical data of 127 patients diagnosed with non-small cell lung cancer were retrospectively analyzed.The groups were matched by EGFR mutation status and we analyzed the differences in radiomics and clinical data.Results There was no significant difference between EGFR mutation and age,size,SUVmax,and carcinoembryonic antigen(CEA)(P>0.05),but there was correlation with smoking history,gender,and carbohydrate antigen(CA125)(P<0.05).The CT radiomic model successfully discriminated EGFR status(AUC=0.775).Combining this model with a clinical model(AUC=0.786) improved prediction accuracy(AUC=0.867),but there was no significance(P>0.05).The PET radiomic model successfully discriminated EGFR status(AUC=0.819).When combined with a clinical model(AUC=0.786),it substantially improved its performance(AUC=0.927).Conclusion Gene mutations can drive different tumor imaging phenotypes,and advanced biomarkers based on radiomics features and clinical features may be used to predict EGFR mutation status.
引文
1陈万青,孙可欣,郑荣寿,等.2014年中国分地区恶性肿瘤发病和死亡分析[J].中国肿瘤,2018,27:1-14.
2 Fitzmaurice C,Allen C,Barber RM,et al.Global,Regional,and National Cancer Incidence,Mortality,Years of Life Lost,Years Lived With Disability,and Disability-Adjusted Life-years for 32 Cancer Groups,1990 to 2015:A Systematic Analysis for the Global Burden of Disease Study[J].JAMA oncology,2017,3:524-548.
3 Valente IR,Cortez PC,Neto EC,et al.Automatic 3D pulmonary nodule detection in CT images:A survey[J].Computer methods and programs in biomedicine,2016,124:91-107.
4 Dearden S,Stevens J,Wu YL,et al.Mutation incidence and coincidence in non small-cell lung cancer:meta-analyses by ethnicity and histology(mutMap)[J].Annals of Oncology,2013,24:2371-2376.
5 Veldore VH,Patil S,Satheesh CT,et al.Genomic profiling in a homogeneous molecular subtype of non-small cell lung cancer:An effort to explore new drug targets[J].Indian journal of cancer,2015,52:243-248.
6 Bedard PL,Hansen AR,Ratain MJ,et al.Tumour heterogeneity in the clinic[J].Nature,2013,501:355-364.
7 Aerts HJ,Grossmann P,Tan Y,et al.Defining a Radiomic Response Phenotype:A Pilot Study using targeted therapy in NSCLC[J].Sci Rep,2016,6:33860-33866.
8 Liu Y,Kim J,Balagurunathan Y,et al.Radiomic features are associated with EGFR mutation status in lung adenocarcinomas[J].Clinical lung cancer,2016,17:441-448.
9 Rizzo S,Petrella F,Buscarino V,et al.CT Radiogenomic Characterization of EGFR,K-RAS,and ALK Mutations in Non-Small Cell Lung Cancer[J].European radiology,2016,26:32-42.
10 Hsu JS,Huang MS,Chen CY,et al.Correlation Between EGFR Mutation Status and Computed Tomography Features in Patients With Advanced Pulmonary Adenocarcinoma[J].Journal of thoracic imaging,2014,29:357-363.
11 Yip SS,Kim J,Coroller TP,et al.Associations Between Somatic Mutations and Metabolic Imaging Phenotypes in Non-Small Cell Lung Cancer[J].Journal of Nuclear Medicine,2017,58:569-576.
12 Lee Y,Lee HJ,Kim YT,et al.Imaging Characteristics of Stage INon-Small Cell Lung Cancer on CT and FDG-PET:Relationship with Epidermal Growth Factor Receptor Protein Expression Status and Survival[J].Korean Journal of Radiology,2013,14:375-383.
13 Liu A,Han A,Zhu H,et al.The role of metabolic tumor volume(MTV)measured by18F FDG PET/CT in predicting EGFR gene mutation status in non-small cell lung cancer[J].Oncotarget,2017,8:33736-33744.
14吕昌生,王金,徐智杰,等.肺腺癌EGFR突变状态与CT纹理灰度共生矩阵的相关性研究[J].中国临床医学影像杂志,2017,28:624-627.
15 Ozkan E,West A,Dedelow JA,et al.CT Gray-Level Texture Analysis as a Quantitative Imaging Biomarker of Epidermal Growth Factor Receptor Mutation Status in Adenocarcinoma of the Lung[J].AJR A-merican journal of roentgenology,2015,205:1016-1025.
16 Rios Velazquez E,Parmar C,Liu Y,et al.Somatic Mutations Drive Distinct Imaging Phenotypes in Lung Cancer[J].Cancer research,2017,77:3922-3930.