Predictive Value of 18F-FDG PET/CT Imaging for KRAS Mutation in Lung Adenocarcinoma
Objective To investigate the predictive value of 18F-deoxyglucose(FDG)PET/CT imaging for murine sarcoma virus oncogene(KRAS)mutation in lung adenocarcinoma.Methods The imaging and pathological data of 120 patients with lung adenocarcinoma who received 18F-FDG PET/CT examination in our hospital from January 2019 to May 2022 were retrospectively collected,The patients were divided into a modeling group(80 cases)and a verification group(40 cases)by cross-sectional stratification,and the patients in the modeling group were divided into a mutant group(22 cases)and a wild group(58 cases)according to whether the KRAS gene was mutated.The clinical data and imaging characteristics of the two groups were compared.The clinics model,Rad model and Combine model were established according to clinical data and imaging characteristics to predict the mutation of KRAS gene in lung adenocarcinoma patients.Receiver operating characteristic(ROC)curve,calibration curve and clinical decision curve were used to evaluate the predictive value of the three models.Results Clinic model of patients in modeling group=1.168+0.976× gender+0.041× age+1.298× smoking history,Rad model=1.451+1.412×orig_shape_MAL+1.274× wave_LHH_GLSZM_GLNU+0.925× wave_HHH_GLDM_DE+0.753× wave_HLL_FO_Minimum+1.168×wave_HHH_FO_TE,Combine model=0.943+0.305× gender+0.351× age+0.941× smoking history+0.795× Rad-score.ROC curves of modeling group and validation group showed that the three models had good predictive efficiency.Delong test found that the area under ROC curve of the combine model in the modeling group and the verification group was significantly higher than that in the Rad and Clinical models(all P＜0.05).Calibration curves show that all models have good fitting effect in modeling group and verification group.The clinical decision curve showed that the combine model had higher clinical practical value in the modeling group and the validation group than the other two models.Conclusion The combination of 18F-FDG PET/CT imaging and clinical features has a good predictive value for KRAS mutation in lung adenocarcinoma patients.
Kirsten Rat Sarcoma Viral OncogeneRadiomicsLung AdenocarcinomaPET/CT
NETL
NSTL
万方数据
维普
