Dual-energy CT quantitative parameters combined with CT signs in predicting epidermal growth factor receptor gene mutation in advanced lung adenocarcinoma
YU Lei
CHEN Wang
SUN Qian
JIAO Zhiyun
Abstract：Objective To explore the correlation between the quantitative parameters of dual-energy CT combined with CT signs,clinical characteristics and epidermal growth factor receptor(EGFR)gene mutations in patients with advanced lung adenocarcinoma,and to predict the mutation in patients with advanced lung adenocarcinoma.Methods A retrospective collection was performed for 172 cases of advanced lung adenocarcinoma(clinical stage Ⅲ～Ⅳ)diagnosed by pathology(fiber bronchoscopy,lymph node,percutaneous lung puncture)biopsy in the First People's Hospital of Yancheng City from January 2022 to June 2023.The patient's general clinical features,CT signs,and dual-energy CT(DECT)parameters were collected.According to the results of EGFR gene testing,they were divided into positive group and negative group.The independent samples t-test or rank-sum test were used to analyze the differences between the groups,and a binary logistic regression model based on clinical characteristics,conventional CT signs,DECT quantitative parameters and combination was gradually established for statistically significant parameters,and the prediction performance of the combined model was evaluated.Results A total of 172 patients with lung adenocarcinoma during the study period were identified,including 80 positive for EGFR gene expression patients and 92 negative patients.There were significant differences in IC,NIC,slope K40-100kev in arterial phase and IC in venous phase between the two groups(P<0.001);There were significant differences in air bronchogram sign and pleural traction sign between the two EGFR groups(P<0.05);Univariate logistic regression analysis showed that arterial phase IC,NIC,slope K40-100 keV,venous phase IC,air bronchogram sign,and pleural traction sign were associated with EGFR gene mutations.The AUC for the DECT model,the DECT model combined with clinical characteristics,and the DECT model combined with clinical characteristics and CT signs were 0.746(sensitivity 63.75％,specificity 92.39％),0.787(sensitivity 65.00％,specificity 91.30％),and 0.819(sensitivity 77.50％,specificity 82.61％),respectively.According to the DeLong test,there was no significant difference in AUC among the three models(P>0.05).Conclusion The combined DECT model,incorporating clinical characteristics and CT signs,effectively predicts EGFR mutations and performs better than the single model in patients with advanced-stage lung adenocarcinoma.
Keywords：epidermal factor growth receptordual-energy CTadenocarcinoma of the lunggene mutationprediction model
Publication Date：2024-08-28
Online Publishing Date：2025-08-15(First online date of this platform, not the publication date of the document)
Pages：9( 811-819 )