The performance of pretreatment MR-based radiomics in Recombinant human endostatin plus concurrent chemoradiotherapy response prediction in nasopharyngeal carcinoma: A primary study

Abstract

Background: Antiangiogenic therapy may transiently “normalize” the tumor vasculature to increase the effect of chemoradiotherapy. The present study confirmed the combination of antiangiogenic therapy with chemoradiotherapy provides a promising strategy for the improvement of the prognosis of nasopharyngeal carcinoma(NPC) patients. Recombinant human endostatin (RHES) is a new type of antiangiogenic agent. Radiomics is a new method to study tumor heterogeneity, and it can evaluate tumor heterogeneity and biological characteristics by screening these features and constructing models. This study was aimed at investigating the capability of an MRI radiomics model based on pre-treatment texture features in predicting the efficacy of RHES + concurrent chemoradiotherapy (CCRT) for NPC.Methods:In total, we retrospectively enrolled 65 patients newly diagnosed as having NPC and treated with RHES + CCRT. 144 texture features were extracted from the MRI before RHES+CCRT treatment of all the NPC patients. The maximum relevance minimum redundancy (mRMR) method was used to remove redundant, irrelevant texture features, and calculate the Rad score of the primary tumor. Multivariable logistic regression was used to select the most predictive features subset, and prediction models were constructed, which included radiomics models, clinics models, and combined models. The performance of the three models in predicting the early response of RHES + CCRT for NPC was explored.Result:The diagnostic efficiency of combined model and radiomics model in distinguishing between the groups was found to be moderate. The area under the curve (AUC) of the combined model and radiomics model was 0.74 (95% CI: 0.62–0.86) and 0.71 (95% CI: 0.58–0.84), respectively, with both being higher than the AUC of the clinics model (0.63, 95% CI: 0.49–0.78). Compared with the pure radiomics model, the combined model showed marginally improved diagnostic performance in predicting RHES + CCRT treatment response. The accuracy of combined model and radiomics model for RHES + CCRT response assessment in NPC were higher than those of the clinics model (0.723, 0.723 vs. 0.677). Conclusion:The pretreatment MRI based radiomics can predict RHES + CCRT response in patients with NPC with a better accuracy than the clinics model.