Prediction of radiation pneumonitis after definitive radiotherapy for locally advanced non-small cell lung cancer using multi-region radiomics analysis

Abstract To predict grade ≥ 2 radiation pneumonitis (RP) in patients with locally advanced non-small cell lung cancer (NSCLC) using multi-region radiomics analysis. Data from 77 NSCLC who underwent definitive radiotherapy between 2008 and 2018 were analyzed. Radiomic feature extraction the whole (whole-lung analysis) imaging- dosimetric-based segmentation (multi-region performed. Patients RP or < classified. Predictors selected least absolute shrinkage selection operator logistic regression model was built neural network classifiers. A total of 49,383 features per patient image extracted planning computed tomography. We identified 4 13 whole-lung analysis for classification, respectively. The accuracy area under curve (AUC) without synthetic minority over-sampling technique (SMOTE) 60.8%, 0.62 80.1%, 0.84 These improved 1.7% 2.1% SMOTE. developed can help RP. median- high-dose regions, local intensity roughness variation important factors predicting