Radiomics Based On Multi-parametric MRI For Preoperative Prediction Of Biological Behavior Of Sinonasal Tumors

Part Ⅰ Radiomics Based on Multi-Parametric MRI for Preoperative Differential Diagnosis of Malignant and Benign Sinonasal Tumors: A Two-Centre Study Objective:To investigate the efficacy of multi-parametric MRI-based radiomics nomograms for preoperative distinction between benign and malignant sinonasal tumors.Methods:Data of 244 patients with sinonasal tumor(training set,n=192;test set,n=52)who had undergone pre-contrast MRI,and 101 patients who underwent post-contrast MRI(training set,n=74;test set,n=27)were retrospectively analyzed.Independent predictors of malignancy were identified and their performance were evaluated.Seven radiomics signatures(RSs)using maximum relevance minimum redundancy(m RMR),and the least absolute shrinkage selection operator(LASSO)algorithm were established.The radiomics nomograms,comprising the clinical model and the RS algorithms were built: one based on pre-contrast MRI(RNWOC);the other based on pre-contrast and postcontrast MRI(RNWC).The performances of the models were evaluated with area under the curve(AUC),calibration,and decision curve analysis(DCA)respectively.Results:The efficacy of the clinical model(AUC=0.81)of RNWC was higher than that of the model(AUC=0.76)of RNWOC in the test set.There was no significant difference in the AUC of radiomic algorithms in the test set.The RS-T1T2(AUC=0.74)and RST1T2T1C(RSWC,AUC=0.81)achieved a good distinction efficacy in the test set.The RNWC and the RNWOC showed excellent distinction(AUC=0.89 and 0.82respectively)in the test set.The DCA of the nomograms showed better clinical usefulness than the clinical models and radiomics signatures.Conclusions:The radiomics nomograms combining the clinical model and RS can be accurately,safely,and efficiently used to distinguish between benign and malignant sinonasal tumors.Part Ⅱ Multi-parametric MRI-based Radiomics Signature forPreoperative Prediction of Ki-67 Proliferation Status in Sinonasal Malignancies: A Two-Centre Study Objective:To assess the predictive ability of a multi-parametric MRI-based radiomics signature(RS)for the preoperative evaluation of Ki-67 proliferation status in sinonasal malignancies.Methods:A total of 128 patients with sinonasal malignancies that underwent multiparametric MRIs at two medical centers are retrospectively analyzed.Data from one medical center(n = 77)are used to develop the predictive models,and data from the other medical center(n = 51)constitute the test dataset.Clinical data and conventional MRI findings are reviewed to identify significant predictors.Radiomic features are determined using the maximum relevance minimum redundancy and least absolute shrinkage and selection operator algorithms.Subsequently,RSs are established using a logistic regression(LR)algorithm.The predictive performance of the RSs is assessed using calibration,decision curve analysis(DCA),accuracy,and AUC.Results:No independent predictors of high Ki-67 proliferation are observed based on clinical data and conventional MRI findings.RS-T1,RS-T2,and RS-T1c(contrast enhancement T1WI)are established based on a single-parametric MRI.RS-Combined(combining T1 WI,FS-T2 WI,and T1 c features)is developed based on multi-parametric MRI and achieves an AUC and accuracy of 0.852(0.733–0.971)and 86.3%,respectively,on the test dataset.The calibration curve and DCA demonstrate an improved fitness and benefits in clinical practice.Conclusions:A multi-parametric MRI-based RS may be a non-invasive,dependable,and accurate tool to preoperatively evaluate tumors for overcoming the sampling bias concerning Ki-67 in sinonasal malignancies.