Predicting EGFR mutation subtypes in lung adenocarcinoma using 18F-FDG PET/CT radiomic features

Abstract

Background: Identification of epidermal growth factor receptor (EGFR) mutation types is crucial before tyrosine kinase inhibitors (TKIs) treatment. Radiomics is a new strategy to noninvasively predict the genetic status of cancer. In this study, we aimed to develop a predictive model based on 18 F-fluorodeoxyglucose positron emission tomography-computed tomography ( 18 F-FDG PET/CT) radiomic features to identify the specific EGFR mutation subtypes.Methods: We retrospectively studied 18 F-FDG PET/CT images of 148 patients with isolated lung lesions, which were scanned in two hospitals with different CT scan setting (slice thickness: 3 and 5 mm, respectively). The tumor regions were manually segmented on PET/CT images, and 1,570 radiomic features (1,470 from CT and 100 from PET) were extracted from the tumor regions. Seven hundred and ninety-four radiomic features insensitive to different CT settings were first selected using the Mann white U test, and collinear features were further removed from them by recursively calculating the variation inflation factor.Then, multiple supervised machine learning models were applied to identify prognostic radiomic features through: (I) a multi-variate random forest to select features of high importance in discriminating different EGFR mutation status; (II) a logistic regression model to select features of the highest predictive value of the EGFR subtypes. The EGFR mutation predicting model was constructed from prognostic radiomic features using the popular Xgboost machine-learning algorithm and validated using 3-fold cross-validation. The performance of predicting model was analyzed using the receiver operating characteristic curve (ROC) and measured with the area under the curve (AUC).Results: Two sets of prognostic radiomic features were found for specific EGFR mutation subtypes: 5 radiomic features for EGFR exon 19 deletions, and 5 radiomic features for EGFR exon 21 L858R missense.The corresponding radiomic predictors achieved the prediction accuracies of 0.77 and 0.92 in terms of AUC, respectively. Combing these two predictors, the overall model for predicting EGFR mutation positivity was also constructed, and the AUC was 0.87. Conclusions:In our study, we established predictive models based on radiomic analysis of 18F-FDG PET/ CT images. And it achieved a satisfying prediction power in the identification of EGFR mutation status as well as the certain EGFR mutation subtypes in lung cancer. 550 Liu et al. PET/CT radiomics predict EFGR mutation subtypes

A Predictive Model of EGFR Mutation Status in Patients with Lung Adenocarcinoma Based on PET/CT Metabolic Indexes and Clinicopathological Variables

“…The statistical analysis of the ROC curve showed that a maximum tumour diameter of 35 mm was the cutoff point, and tumours with smaller diameters (≤35 mm) had a higher EGFR mutation rate than those with larger tumours, which is consistent with previous ndings [25]. The results of this study suggest that patients with stage IV disease according to the TNM staging guidelines have a higher mutation rate, which is inconsistent with previous research [26], but the number of cases was small, and there may have been selection bias. Finally, univariate analysis showed that the EGFR mutation rate in non-smokers was higher than that in smokers which is consistent with another study [27,28].…”

Structural and functional radiomics for lung cancer

“…In a study with 248 lung cancer patients without treatment, researchers found that their model for prediction of EGFR mutations could reach an AUC of 0.87 when combined clinical and radiomic signature [105]. Similar performance has also been reported in another retrospective study [106]. In addition, for patients with EGFR mutation, a deep radiomic score was a non-invasive tool to identify NSCLC patients susceptible to tyrosine kinase or immune checkpoint inhibitors [107].…”

Performance of 18F-FDG PET/CT Radiomics for Predicting EGFR Mutation Status in Patients With Non-Small Cell Lung Cancer

“…Only GLCM_DV from PET images, which measures the heterogeneity of different intensity-level matrix, showed significant but unsatisfactory predictive performance in our study (AUC=0.661). Liu Q, et al recent study ( 35 ) established a predictive model for EGFR mutation subtypes using machine learning algorithm, which seemed to have better classification performance (AUC=0.77 and 0.92 for respectively predicting exons 19 del and 21 L858R mutations) than ours. However, the number of exons 19 del and 21 L858R mutations was small in Liu Q’s study (only 44 and 31 cases respectively), especially when divided as the train and test cohorts, so the generalization ability of the predictive model was not clear.…”