Application of CT radiomics features to predict the EGFR mutation status and therapeutic sensitivity to TKIs of advanced lung adenocarcinoma

Abstract

Background: To explore the ability of computed tomography (CT) radiomics features to predict the epidermal growth factor receptor (EGFR) mutation status and the therapeutic response of advanced lung adenocarcinoma to treatment with EGFR tyrosine kinase inhibitors (TKIs). Methods: A retrospective analysis was performed on 253 patients with advanced lung adenocarcinoma who underwent EGFR mutation detection, and those with EGFR-sensitive mutations were treated with TKIs. Using the least absolute shrinkage and selection operator (LASSO) regression model and the 10-fold cross-validation method, the radiomics features that predicted EGFR mutation status and TKI sensitivity were obtained. Results: The area under the curve (AUC) values of the unenhanced, arterial and venous phases in the EGFR mutation status training group were 0.6713, 0.8194 and 0.8464, respectively. A total of 5, 18 and 23 radiomics features were extracted from the unenhanced, arterial and venous phases, respectively; these features could distinguish the EGFR mutation status. The AUC values of the unenhanced, arterial and venous phases in the EGFR-TKI-sensitive training group were 0.7268, 0.7793 and 0.9104, respectively. A total of 3, 7 and 22 radiomics features were extracted from the unenhanced, arterial and venous phases, respectively; these features could be used to identify the appropriate population for TKI treatment. Conclusions: Radiomics features extracted from CT scans can be used as biomarkers to predict the EGFR mutation status of lung adenocarcinoma and to further screen the dominant population for TKI therapy, providing a basis for accurate targeted therapy of tumors.