Radiomics-based computed tomography urography image analysis for prediction of HER2 status in bladder cancer

This study aimed to develop a computed tomography urography (CTU)-based radiomics model for preoperative prediction of human epidermal growth factor receptor 2 (HER2) status in bladder cancer (BCa). This single-center retrospective study enrolled 190 patients with pathologically confirmed BCa who underwent preoperative CTU between October 2019 and September 2024. The cohort was randomly divided into training ( n = 133) and test ( n = 57) cohorts. Radiomics models were developed using Least Absolute Shrinkage and Selection Operator (LASSO) regression combined with five machine learning methods: logistic regression (LR), support vector machine (SVM), k-nearest neighbors (KNN), extreme gradient boosting (XGBoost), and random forest (RF). A clinical-radiomics model was subsequently established by integrating radiomics features with clinical parameters. Model performance was assessed using the area under the curve (AUC), calibration curves and Decision curve analysis (DCA). Among 190 patients (HER2-positive: 62.1%, 118/190), overall age ranged 26–90 years; median (IQR) ages were 72.0 (17.0) and 68.0 (18.0) for the HER2-positive and HER2-negative groups, respectively. Comparative analysis of CTU phases revealed that the RF radiomics model based on corticomedullary-phase images demonstrated superior predictive accuracy for HER2 status, achieving AUCs of 0.798 (95% CI: 0.718–0.877) in the training set and 0.734 (95% CI: 0.601–0.866) in the test set. The clinical-radiomics model also exhibited strong performance, with AUCs of 0.876 (95% CI: 0.817–0.935) and 0.763 (95% CI: 0.634–0.892) for the training and test sets, respectively. CTU-based clinical-radiomics model may provide a novel non-invasive method to predict HER2 status in BCa with acceptable diagnostic performance.