Prediction of histopathologic grades of bladder cancer with radiomics based on MRI: comparison with traditional MRI

Abstract Purpose To compare Magnetic resonance imaging (MRI) radiomics signatures and traditional MRI model for the preoperative prediction of bladder cancer (BCa) grade. Methods This retrospective study included 255 consecutive patients with pathologically confirmed 113 low-grade and 142 high-grade BCa who underwent preoperative MRI, including T2-weighted imaging (T2WI) and apparent diffusion coefficient (ADC). The traditional MRI nomogram model was developed using univariate and multivariate logistic regression by the mean apparent diffusion coefficient (mADC), vesical imaging reporting and data system (VI-RADS) scoring, tumor size and number of tumors. Volumes of interest were manually drawn on T2WI and ADC maps by two radiologists. Using ANOVA, correlation and LASSO methods to select features. Then, a logistic regression (LR) classifier was used to develop the radiomics signatures in the training set and assessed in the validation set. Receiver operating characteristic (ROC) analysis was used to compare the diagnostic abilities of the radiomics and traditional MRI models by the DeLong test. Finally, decision curve analysis (DCA) was performed by estimating the clinical usefulness of the two models in both the training and validation sets. Results The areas under the ROC curves (AUCs) of the traditional MRI model were 0.841 in the training cohort and 0.806 in the validation cohort. The AUCs of the three groups of radiomics model [ADC, T2WI, bi-parametric-MRI(bp-MRI, ADC and T2WI)]-based logistic regression analysis algorithms were 0.888, 0.875 and 0.899 in the training cohort and 0.863, 0.805 and 0.867 in the validation cohort, respectively. The combined radiomics model achieved higher AUCs than the traditional MRI model and was compared using the DeLong test (P = 0.026 and 0.023 in the training and validation cohorts, respectively). DCA indicated that the radiomics model had higher net benefits than the traditional MRI model. Conclusions The MRI radiomics model can be helpful for preoperatively predicting low-grade or high-grade BCa and outperformed the traditional MRI model.