CT Radiomics in Predicting EGFR Mutation in Non-small Cell Lung Cancer: A Single Institutional Study

Abstract

Objective: To evaluate the value of CT radiomics in predicting the epidermal growth factor receptor (EGFR) mutation of patients with non-small cell lung cancer (NSCLC), and combing with the clinical characteristic to construct the prediction model. Methods: Sixty-seven cases of NSCLC confirmed by pathology were enrolled. The pre-treatment chest CT enhanced images were used in Radiomics analysis. Two experienced radiologists delineated the region of interest (ROI) on open source software 3D-Slicer. The feature of ROI was extracted by Pyradiomics software package and a total of 849 features were extracted. By calculating Pearson correlation coefficient between pair-wise features and LASSO method for feature screening. The prediction model was constructed by logical regression, diagnostic efficacy of the model by the area under the receiver operating characteristic (ROC) curve was calculated. Results: Based on clinical model and the radiomics model, the AUC under the ROC was 0.8387 and 0.8815, respectively. The model combining clinical and radiomics features perfect best, the AUC under the ROC was 0.9724, the sensitivity and specificity were 85.3 and 90.9%, respectively. Conclusions: Compared with clinical features or radiomics features alone, the model constructed by combining clinical and pre-treatment chest enhanced CT features may show more utility for improved patient stratification in EGFR mutation and EGFR wild.

MRI‐based radiomics analysis for predicting the EGFR mutation based on thoracic spinal metastases in lung adenocarcinoma patients

“…The s-CEA was suggested as a predictor to the EGFR mutation, 41,42 but pointed to have no predictive value in a recent work. 43 The age has been demonstrated to be predictive, 44 but also found to be ineffective for predicting the EGFR mutation. 43 To explore the potential clinical utility, an easy-to-use nomogram integrating the Combined Rad score and smoking was constructed and achieved the best prediction performance.…”

Magnetic Resonance Imaging Radiomics‐Based Nomogram From Primary Tumor for Pretreatment Prediction of Peripancreatic Lymph Node Metastasis in Pancreatic Ductal Adenocarcinoma: A Multicenter Study

“…Before the process of feature selection, normalization of the extracted radiomics features to the range (0-1) was first performed. The Pearson's correction coefficient (PCC) analysis for reference to the previous studies, [24][25][26] and an optimal PCC value of 0.86 was applied to reduce the redundancy and maintain independent between the image features. The least absolute shrinkage and selection operator logistic regression (LASSO-LR) 27 algorithm was applied for further feature selection and construction of the MRIbased radiomics signature for pretreatment prediction of peripancreatic LN metastasis.…”

Clinicopathologic Features and Molecular Biomarkers as Predictors of Epidermal Growth Factor Receptor Gene Mutation in Non-Small Cell Lung Cancer Patients

“…At present, a number of studies have established a combined detection factor model to indicate EGFR gene mutation status for NSCLC patients by combining multiple predictors [ 99 ]. Wu et al [ 100 ] reported a study involving 67 NSCLC patients who were examined by enhanced chest CT before treatment and built the prediction models using clinical features and radiomics features. The AUC under the ROC of clinical characteristics and radionics characteristics was 0.8387 and 0.8815, respectively.…”