Hand-Crafted Quantitative Radiomic Analysis of Computed Tomography Scans Using Machine and Deep Learning Techniques Accurately Predicts Histological Subtypes of Non-Small Cell Lung Cancer

Abstract Background Non-small cell lung cancer (NSCLC) histological subtypes impact treatment decisions. While pre-surgical histopathological examination is ideal, it’s not always possible. CT radiomic analysis shows promise to predict NSCLC histological subtypes. Objective To use CT scan radiomic analysis from NSCLC-Radiomics data to predict NSCLC histological subtypes using machine learning and deep learning models. Methods 422 CT scans from The Cancer Imaging Archive (TCIA) were analyzed. Primary neoplasms were segmented by expert radiologists. Using PyRadiomics, 2446 radiomic features were extracted; post-selection, 179 features remained. Machine learning models like logistic regression, SVM, random forest, XGBoost, LightGBM, and CatBoost were employed, alongside a deep neural network (DNN) model. Results Random forest demonstrated the highest accuracy at 78% (95% CI: 70%-84%) and AUC-ROC at 94% (95% CI: 90%-96%). LightGBM, XGBoost, and CatBoost had AUC-ROC values of 95%, 93%, and 93% respectively. The DNN’s AUC was 94.4% (95% CI: 94.1% to 94.6%). Logistic regression had the least efficacy. For histological subtype prediction, random forest, boosting models, and DNN were superior. Conclusions Quantitative radiomic analysis with machine learning can accurately determine NSCLC histological subtypes. Random forest, ensemble models, and DNNs show significant promise for pre-operative NSCLC classification, which can streamline therapy decisions.