Background: Radiomics is the computation of quantitative image features extracted from medical imaging modalities to help clinical decision support systems, which could ultimately meliorate personalized management based on individual characteristics.
Objective: This study aimed to create a predictive model of response to peptide receptor radionuclide therapy (PRRT) using radiomics computed tomography (CT) images to decrease the dose for patients if they are not a candidate for treatment.
Material and Methods: In the current retrospective study, 34 patients with neuroendocrine tumors whose disease is clinically confirmed participated. Effective factors in the treatment were selected by eXtreme gradient boosting (XGBoost) and minimum redundancy maximum relevance (mRMR). Classifications of decision trees (DT), random forest (RF), and K-nearest neighbors (KNN) with selected quantitative and clinical features were used for modeling. A confusion matrix was used to evaluate the performance of the model.
Results: Out of 866 quantitative and clinical features, nine features with the XGBoost method and ten features with the mRMR pattern were selected that had the most relevance in predicting response to treatment. Selected features of the XGBoost method in integration with the RF classifier provided the highest accuracy (accuracy: 89%), and features selected by the mRMR method in combination with the RF classifier showed satisfactory performance (accuracy: 74%).
Conclusion: This exploratory analysis shows that radiomic features with high accuracy can effectively predict response to personalize treatment.