Preoperative contrast-enhanced CT-based radiomics nomogram for differentiating benign and malignant primary retroperitoneal tumors

ObjectivesThis study evaluated the ability of a preoperative contrast-enhanced CT (CECT)-based radiomics nomogram to differentiate benign and malignant primary retroperitoneal tumors (PRT).MethodsImages and data from 340 patients with pathologically confirmed PRT were randomly placed into training (n = 239) and validation sets (n = 101). Two radiologists independently analyzed all CT images and made measurements. Key characteristics were identified through least absolute shrinkage selection combined with four machine-learning classifiers (support vector machine, generalized linear model, random forest, and artificial neural network back propagation) to create a radiomics signature. Demographic data and CECT characteristics were analyzed to formulate a clinico-radiological model. Independent clinical variables were merged with the best-performing radiomics signature to develop a radiomics nomogram. The discrimination capacity and clinical value of three models were quantified by the area under the receiver operating characteristics (AUC), accuracy, and decision curve analysis.ResultsThe radiomics nomogram was able to consistently differentiate between benign and malignant PRT in the training and validation datasets, with AUCs of 0.923 and 0.907, respectively. Decision curve analysis manifested that the nomogram achieved higher clinical net benefits than did separate use of the radiomics signature and clinico-radiological model.ConclusionsThe preoperative nomogram is valuable for differentiating between benign and malignant PRT; it can also aid in treatment planning.