Background and Objectives: The Vesical Imaging–Reporting and Data System (VI-RADS) represents a standardized approach for interpreting multiparametric magnetic resonance imaging (mp-MRI) in bladder cancer (BC) evaluation. This systematic review aimed to assess the VI-RADS’ diagnostic performance and interobserver agreement in distinguishing muscle-invasive from non-muscle-invasive BC, a crucial differentiation for treatment planning. Materials and Methods: A systematic literature search was conducted through PubMed, Google Scholar, and Web of Science, over an initial five-year time span, from VI-RADS’ inception (May 2018) to November 2023. Studies reporting VI-RADS’ diagnostic performance with histopathological confirmation and interobserver agreement data were included. The diagnostic accuracy was assessed using sensitivity and specificity, while interobserver agreement was evaluated using Cohen’s κ coefficient. Results: Nine studies comprising 1249 participants met the inclusion criteria. Using a VI-RADS score cutoff of ≥3, the pooled sensitivity and specificity for detecting muscle invasion were 88.2% and 80.6%, respectively. Interobserver agreement showed excellent consistency with a mean κ value of 0.82. Individual study sensitivities ranged from 74.1% to 94.6%, while specificities varied from 43.9% to 96.5%. Conclusions: VI-RADS demonstrates high diagnostic accuracy and excellent interobserver agreement in BC staging, supporting its role as a reliable non-invasive diagnostic tool. However, it should be used as a complementary tool to, not a replacement for, histopathological confirmation. Moreover, the variability in specificity suggests the need for standardized training and interpretation protocols. Clinical correlation and adequate reader experience are essential for optimal implementation. Future integration with pathological data may further enhance its predictive value.

Background/Objectives: ISUP grade group discordance between prostate biopsy and radical prostatectomy (RP) impacts treatment decisions in over a third (~25–40%) of prostate cancer (PCa) patients. We aimed to identify ISUP grade migration predictors and assess the impact of preoperative imaging (MRI) in a contemporary Romanian PCa cohort. Methods: We retrospectively analyzed 142 PCa patients undergoing RP following biopsy between January 2021 and December 2024 at Pius Brinzeu County Hospital, Timișoara: 90 without and 52 with preoperative MRI. Clinical parameters, MRI findings (PI-RADS), and biopsy characteristics were evaluated. Machine learning models (gradient boosting, random forest) were developed with SHAP analysis for interpretability. Results: Grade migration occurred in 69/142 patients (48.6%): upstaging in 55 (38.7%) and downstaging in 14 (9.9%). In the non-MRI cohort, 37/90 (41.1%) were upstaged and 9/90 (10.0%) were downstaged, versus 18/52 (34.6%) upstaged and 5/52 (9.6%) downstaged in the MRI cohort. The MRI group showed a 6.5% absolute reduction in upstaging (34.6% vs. 41.1%), a promising non-significant trend (p = 0.469) that requires further investigation. Grade 1 patients showed the highest upstaging (69.4%), while Grades 3–4 showed the highest downstaging (11/43, 25.6%). PI-RADS 4 lesions had the highest upstaging (43.5%). PSA density > 0.20 ng/mL² emerged as the strongest predictor. Gradient boosting achieved superior performance (AUC = 0.812) versus logistic regression (AUC = 0.721), representing a 13% improvement in discrimination. SHAP analysis revealed PSA density as the most influential (importance: 0.287). Grade migration associated with adverse pathology: extracapsular extension (52.7% vs. 28.7%, p = 0.008) and positive margins (38.2% vs. 21.8%, p = 0.045). Conclusions: ISUP grade migration affects 48.6% of Romanian patients, with 38.7% upstaged and 9.9% downstaged. The 69.4% upstaging in Grade 1 patients emphasizes the need for enhanced risk stratification tools, while 10% downstaging suggests potential overtreatment. Machine learning with SHAP analysis provides superior predictive performance (13% AUC improvement) while offering clinically interpretable risk assessments. PSA density dominates risk assessment, while PI-RADS 4 lesions warrant closer scrutiny than previously recognized.