Contribution of lesion shape features to the VI-RADS for predicting muscle invasion in bladder tumors

Abstract

Objective: Muscle invasion in bladder cancer is a crucial factor influencing treatment decisions and prognosis. We hypothesize that the integration of tumor shape characteristics with the VI-RADS scoring system improves the predictive accuracy for assessing muscle invasion in bladder cancer. Methods: This prospective observational study included patients scheduled for transurethral resection of bladder tumor (TURBT) and/or cystectomy due to suspected bladder cancer between March 2022 and November 2024. All patients underwent multiparametric bladder MRI following the VI-RADS protocol. Tumor segmentation was performed using 3D Slicer to assess shape features, including sphericity, surface area, surface-volume ratio, elongation, and flatness. Mann-Whitney U tests were conducted to evaluate the association between shape features and muscle invasion, while ROC (Receiver Operating Characteristic) analysis determined threshold values. Results: The study included 119 patients (98 males, 21 females; mean age 66.9 +/- 9.9 years, range 33-89). Using VI-RADS >= 3 as the threshold, sensitivity was 100 %, with a specificity of 65.91 %. For VI-RADS >= 4, sensitivity was 80.65 %, and specificity was 95.45 %. A significant relation was found between tumor sphericity and muscle invasion. For VI-RADS >= 3B, sensitivity was 100 %, and specificity was 66.67 %. Conclusion: The VI-RADS algorithm demonstrated high predictive accuracy for muscle invasion, particularly for tumors scored VI-RADS >= 4. Additionally, while a relation was identified between tumor sphericity and muscle invasion, its incorporation into the VI-RADS scoring system did not enhance the overall predictive performance of the algorithm.