An interpretable deep learning model based on enhanced CT predicts the recurrence of non-muscle-invasive bladder cancer within 2 years

Abstract

Accurate risk stratification for non-muscle-invasive bladder cancer (NMIBC) recurrence is essential for personalized treatment. This study aimed to develop and validate a contrast-enhanced computed tomography (CT)-based model for predicting postoperative NMIBC recurrence within two years. We retrospectively enrolled 192 patients with NMIBC from three centers between June 2017 and May 2023. Center 1 formed the training set ( n = 139; 74 recurrence events), and Centers 2 and 3 formed the test set ( n = 53; 24 recurrence events). Super-resolution reconstruction based on a generative adversarial network (GAN) was used to enhance contrast-enhanced CT images, from which radiomics and deep-learning (DL) features were extracted. Clinical predictors were evaluated using univariable and multivariable logistic regression. Fusion Model C (FMC), integrating radiomics, DL, and clinical features, was developed exclusively in the training set and evaluated in the test set. Model interpretation used Shapley additive explanations (SHAP), and performance was assessed using the area under the receiver operating characteristic curve (AUC), calibration curves, Brier scores, and decision-curve analysis. FMC outperformed the radiomics model (test set AUC = 0.754), achieving AUCs of 0.917 (95% confidence interval [CI], 0.874–0.960) in the training set and 0.865 (95% CI, 0.756–0.974) in the test set. Tumor number, T stage, and one DL feature were the three highest-ranked predictors in the SHAP analysis, and decision-curve analysis suggested potential clinical utility. The CT-based FMC showed promising accuracy for predicting observed 24-month recurrence among selected patients with NMIBC undergoing preoperative contrast-enhanced CT. The model may provide complementary risk-stratification information for postoperative surveillance planning, while SHAP-based explanations may facilitate interpretation of individual predictions.