INTRODUCTION:Peyronie's disease causes penile curvature and painful erections, potentially impairing quality of life; surgical grafts are employed to correct curvature and restore penetrative sexual function. OBJECTIVES:This study aimed to summarize the evidence on perioperative and functional outcomes of surgical grafting procedures for Peyronie's disease. METHODS:A systematic review was conducted following the PRISMA guidelines. Databases including PubMed, EMBASE, Scopus, Google Scholar, and the Cochrane Library were searched up to April 1, 2023. Eligible studies included retrospective or prospective reports on patients aged 18 years or older treated with various graft materials, including vein, dermal, buccal mucosa, small intestinal submucosa, human cadaveric, and bovine pericardium. Quality was assessed using the JBI Critical Appraisal Checklist. Due to data heterogeneity and a lack of comparative studies, no quantitative synthesis was performed. The systematic review was registered on PROSPERO-CRD42024508997. The review focused on perioperative outcomes, erectile function changes, and complication rates associated with different graft materials. RESULTS:Out of 521 articles identified from 1933 to 2023, 71 studies involving 2692 patients met the inclusion criteria. Six studies were prospective, and the remainder were retrospective. Quality assessment revealed a high or severely high risk of bias across all included studies. Erectile function worsened in 0%-70% of patients, with complication rates ranging from 0% to 50%. No comparative studies among graft types were identified. CONCLUSION:Various graft materials offer reliable perioperative and functional outcomes for Peyronie's disease; however, further comparative studies are essential.

Xpert Bladder Cancer (BC) is an mRNA-based urine assay for diagnosis and surveillance of urothelial carcinoma. Although previous meta-analyses have examined Xpert, none has evaluated its accuracy in both BC detection and non-muscle-invasive bladder cancer (NMIBC) surveillance, while also exploring its potential role in guiding repeat transurethral resection (re-TURBT) and in the diagnostic evaluation of upper tract urothelial carcinoma (UTUC). We systematically assessed the diagnostic accuracy of Xpert in all these clinical settings, integrating grade-specific analysis and formal evidence-certainty assessment. PubMed/MEDLINE, Embase, Scopus, Web of Science, and the Cochrane Library were searched to January 2026 (PROSPERO: CRD420251184275). Sensitivity and specificity were pooled using bivariate random-effects models; PPV and NPV using univariate models. Grade-specific sensitivity was pooled across 13 studies with tumour-grade-stratified data. Evidence certainty was assessed using GRADE-DTA. Publication bias was evaluated with Deeks' funnel plots. Twenty-six studies (8613 patients) were included. For Detection (k = 8, where k denotes the number of cohorts pooled), pooled sensitivity was 0.83 (95% CI 0.73-0.90) and specificity 0.77 (0.65-0.86); NPV was 0.96. For Monitor (k = 15), sensitivity was 0.71 (0.63-0.77) and specificity 0.78 (0.70-0.85); NPV was 0.91. Grade-specific pooling showed high-grade (HG) sensitivity of 0.89 (0.83-0.93) in Detection and 0.80 (0.71-0.87) in Monitor, versus 0.60 for low-grade (LG) in both settings; heterogeneity was not statistically significant for HG estimates. Re-TURBT (k = 2) and UTUC (k = 2) were exploratory, with encouraging NPV but limited by sparse events. Evidence certainty was low for sensitivity/NPV and very low for specificity/PPV. No publication bias was detected. Xpert demonstrates high sensitivity and NPV, particularly for HG disease, supporting its role as an adjunctive rule-out tool. Grade-adapted interpretation is warranted. Prospective validation with standardised grade-specific reporting is needed.

OBJECTIVES:To systematically identify, appraise and synthesise artificial intelligence (AI) and machine-learning (ML) models that predict treatment response and clinical outcomes after intravesical bacillus Calmette-Guérin (BCG) in non-muscle-invasive bladder cancer (NMIBC), a setting in which current risk calculators underperform, and identifying non-responders has become urgent as alternatives to BCG enter practice. METHODS:PubMed, EMBASE and Web of Science were searched through April 2026 following the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) 2020 guidelines (International Prospective Register of Systematic Reviews [PROSPERO] number CRD420261376808). Studies developing or validating AI/ML models for BCG-associated outcomes with a quantitative performance metric were included. Risk of bias was assessed with the Prediction model Risk Of Bias ASsessment Tool (PROBAST). Evidence was synthesised along a clinically oriented framework: AI as a perceptual tool (extracting signal from histology or imaging) or integrative tool (re-weighting clinicopathological, molecular, or urinary variables). RESULTS:A total of 15 studies (>24 900 patients) were included: seven perceptual, eight integrative. By input data, six used digital pathology, two radiomics, two genomics/transcriptomics, four clinicopathological markers, and one urinary biomarkers. The digital-pathology Computational Histology Artificial Intelligence (CHAI) platform, validated across 12 international centres, stratified high-grade recurrence (hazard ratio [HR] 2.08), progression (HR 3.87) and BCG-unresponsive disease (HR 2.31), and was the only model providing a first signal of predictive value, demonstrating a significant BCG vs gemcitabine/docetaxel interaction (P = 0.029). Integrative models PROGRxN-BCa (concordance index [C-index] 0.79) and DeepSurv (C-index 0.881) outperformed standard calculators but with modest gains (ΔC-index 0.05-0.10). Only 40% of studies performed external validation, none prospectively; five were at high risk of bias. CONCLUSION:Perceptual AI, particularly digital pathology, has the highest external validation and provides the only biomarker with a first signal of predictive value for BCG vs alternatives, increasingly relevant in the context of the global BCG shortage. Integrative models such as PROGRxN-BCa and DeepSurv outperform standard calculators with incremental gains and are freely accessible. Prospective validation, systematic calibration reporting and treatment-by-biomarker interaction analyses, ideally embedded in trials such as the BRIDGE trial (ClinicalTrials.gov identifier: NCT05538663), remain priorities before clinical adoption.

BACKGROUND AND OBJECTIVE:This is the first prospective study analyzing the predictive value of preoperative Node-Reporting And Data System (RADS) determination at imaging for pelvic lymph node (PLN) involvement in cases of prostate cancer (PCa) considered for radical prostatectomy (RP) with extended pelvic lymph node dissection (ePLND). Node-RADS was compared with the validated predictive nomograms Briganti 2012, Gandaglia 2017, and Briganti 2019, and with prostate-specific membrane antigen - positron emission tomography/computed tomography (PSMA-PET/CT) total body scan. METHODS:A total of 267 patients with a histological diagnosis of PCa undergoing RP with an ePLND were prospectively examined. Overall, n = 104 patients underwent PSMA-PET/CT. Node-RADS determination of PLNs was centrally performed using preoperative magnetic resonance imaging and compared with the validated nomograms and PSMA-PET/CT. Correspondence in terms of positivity and localization with final pathology was analyzed. RESULTS:Node-RADS exceeded PSMA-PET/CT in overall accuracy (area under the curve [AUC] 0.637 vs 0.526), whereas the Briganti 2019 nomogram achieved the highest AUC (0.711). Combining Node-RADS and Briganti 2019 improved performance further (AUC 0.719). Node-RADS showed high specificity (0.993) and positive predictive value (0.506), useful to confirm nodal involvement, whereas Briganti 2019 demonstrated high sensitivity (0.952) and excellent NPV (0.960), useful to exclude nodal disease. PET/CT exhibited limited sensitivity and anatomical correspondence. At multivariate analysis, a high Node-RADS score (4-5) and pathological tumor (pT) stage (pT3) were the only variables associated with a higher risk of positive PLNs involvement at final pathology (adjusted odds ratio [aOR]: 12.60, 95% confidence interval [CI] 2.99-52.96, p < 0.001 for Node-RADS 4-5 and aOR 16.98, 95% CI 4.29-67.17, p < 0.001 for pT3b). CONCLUSIONS:Node-RADS, especially when combined with the Briganti 2019 nomogram, showed promising performance as a structured radiologic tool for preoperative nodal staging in this selected ePLND-eligible cohort.

This prospective imaging trial was designed to compare [68Ga]PSMA-11 PET/CT with multiparametric MRI (mpMRI) in parallel in men with suspicion of prostate cancer (PCa) after at least one previous negative biopsy (ClinicalTrials.gov: NCT05297162; GR-2018-12366240). Between April 2022 and June 2025, we enrolled 130 patients who met the inclusion criteria and completed protocol investigations. Target lesions were defined based on PI-RADS v2.1 for mpMRI and PRIMARY Score, SUVmax and SUVratio for [68Ga]PSMA-11 PET/CT. Findings were statistically correlated with pathology results. Subsequently, we developed a nomogram to predict clinically significant PCa (csPCa), defined as International Society of Urological Pathology [ISUP] grade ≥ 2, using Boruta’s algorithm for variable selection. Median age in our cohort was 65.5 years (range, 50.5–82.2) and median PSA 9.7 ng/ml (range, 4–35). According to pathology, 20 patients (15.4

High-Intensity Focused Ultrasound (HIFU) is an emerging focal therapy for localized prostate cancer, offering an alternative to radical prostatectomy and radiotherapy while balancing oncological control and functional preservation. However, early treatment failure remains a critical challenge, and tools to support early risk stratification are lacking. We developed a two-stage model integrating immediate post-ablation ultrasound with routinely available clinical variables to predict early recurrence (≤ 12 months) after HIFU. Seventy-two patients treated with HIFU were analyzed. In Stage 1, a deep-learning model (DenseNet121) analyzed immediate post-ablation ultrasound images to generate a patient-level probability of treatment failure. In Stage 2, this image-derived probability was combined with routinely available clinical variables (age, PSA density, ISUP grade, percentage of positive biopsy cores, and treated volume) in a Support Vector Machine (SVM) to predict early treatment failure. Model performance was evaluated using cross-validation. The integrated model achieved the highest predictive accuracy, with an area under the receiver-operating characteristic curve of 0.79, compared with 0.75 for the model based on clinical variables alone and 0.65 for the model based on imaging alone. Clinical variables accounted for most of the predictive signal, with the ultrasound-derived probability providing a modest but consistent additional value, particularly in larger treated volumes (≥ 5.7 cc). This two-stage framework combining deep learning and clinical variables improves prediction of early treatment failure after HIFU, supporting point-of-care risk stratification and individualized follow-up.

OBJECTIVES:To develop an international consensus on technical principles, training requirements, patient selection, and procedural best practices for retroperitoneal single-port (SP) robotic urological surgery through a structured Delphi methodology. METHODS:A five-step modified Delphi process was conducted in accordance with ACcurate COnsensus Reporting Document (ACCORD) guidelines. A total of 32 statements were formulated by a steering committee of expert robotic surgeons and distributed to an international panel of 16 urologists from five countries. Consensus was defined as ≥70% agreement with <15% disagreement using a 9-point Likert scale. Statements without consensus after the first round were discussed, revised, and re-voted during an in-person meeting (Naples, Italy, July 2025). Internal reliability was evaluated with Cronbach's α, and inter-rater concordance with Kendall's W. RESULTS:A total of 14 experts participated in Round I and 12 in Round II. Consensus was achieved for 22 of 32 statements (69%), primarily addressing general principles, surgeon training, patient selection, access techniques, and perioperative management. Agreement was highest for the need for structured and proctored training (92.9%), suitability of low-complexity renal tumours as index cases (78.6%), and feasibility of the lower anterior access to enhance recovery (84%). No consensus was reached on absolute contraindications, specimen extraction protocols, or standardised criteria for platform selection in obese patients. Reliability of expert ratings was excellent across rounds (Cronbach's α = 0.98 and 0.92). CONCLUSIONS:This Delphi study provides the first international consensus defining principles and technical considerations for retroperitoneal SP robotic surgery. These consensus recommendations represent a key step toward standardisation and safer clinical adoption of SP retroperitoneal surgery, while highlighting areas needing further evidence.

Background and Objective: Transurethral resection of bladder tumor (TURBT) is the standard for non-muscle-invasive bladder cancer (NMIBC), yet recurrence rates remain high. This study evaluates the safety, tolerability, and efficacy of neoadjuvant intravesical mitomycin C (neoMMC) before TURBT in reducing recurrence and improving surgical outcomes. Methods: This randomized phase III trial enrolled patients with primary or recurrent NMIBC. Participants were randomized 1:1 to a neoadjuvant group receiving two instillations of MMC (day -14 and -7) before TURBT, or a control group undergoing standard TURBT without neoadjuvant treatment. The primary endpoint was 12-month recurrence-free survival (RFS). Secondary endpoints included surgical quality (complete resection, cauterization only, absence of residual tumor) and safety. Exploratory endpoints included histopathologic response and time to recurrence. Key Findings and Limitations: Among 95 patients (48 neoMMC, 47 controls), baseline characteristics were balanced. After a median follow-up of 19.4 months, recurrences occurred in 9 StA and 4 NeoA patients, with one progression to MIBC in the NeoA arm. RFS did not differ significantly between groups at 12 or 18 months. Neoadjuvant MMC was well tolerated, with only grade 1-2 AEs. Exploratory microbiota analyses suggested that neoadjuvant MMC modulated urinary microbial diversity and was associated with a microbiota profile more similar to that observed in non-recurrent patients. Limitations include single-center design and relatively short follow-up. Conclusions and Clinical Implications: Neoadjuvant intravesical MMC before TURBT was feasible and well tolerated in patients with NMIBC, with no unexpected safety signals. In this prematurely terminated and underpowered trial, no significant improvement in RFS was observed. Larger adequately powered studies are needed to clarify the oncologic efficacy of this approach.

Abstract Objective The aim of this paper is to evaluate fellowship outcomes 10 years after implementation of the European Association of Urology Robotic Section (ERUS) structured curriculum for robot‐assisted radical prostatectomy (RARP), with a focus on completion rates and reasons for non‐completion. Subjects and methods Data were obtained from institutional records and a trainee survey. The primary outcome was fellowship completion (i.e., Certificate of Excellence achievement). Secondary outcomes included reasons for non‐completion and satisfaction. Completion rates were analysed annually, with trends assessed using the Cochran–Armitage test and log‐linear regression for the Estimated Annual Percentage Change (EAPC). Comparisons before and after introduction of a procedural diary (2023) and between pandemic and non‐pandemic years used Fisher's Exact Test. Results Among 126 fellows, a total of 42 (33%) completed the fellowship by achieving the Certificate of Excellence. The trainee survey achieved a response rate of 77%, supporting the representativeness of the collected data. The main barriers to fellowship completion included limited console access (49%), insufficient programme duration (20%), logistical difficulties (20%) and COVID‐19‐related disruptions (11%). Despite these limitations, overall satisfaction with the fellowship was high (83%), with particularly strong approval of the ORSI hands‐on training week (100%). Completion rates demonstrated a progressive increase over time, rising from 20% in 2018 to 52% in 2023. The Cochran–Armitage test confirmed a statistically significant upward trend in completion rates over the study period ( p < 0.001), while log‐linear regression analysis showed a numerical but non‐significant EAPC of 13% (95% CI –0.6 to 28.6). Although 2023 represented the highest observed completion rate, this peak was not significantly different from previous years (OR 2.63, 95% CI 0.91–7.63). Conclusions The RARP ERUS Fellowship remains a benchmark in robotic training, but unsatisfactory completion rates highlight the need for improvement. Recent reforms, including the procedural diary, show promise and warrant expansion.

BACKGROUND/OBJECTIVE:High-frequency micro-ultrasound (micro-US) offers real-time, high-resolution imaging for prostate cancer. Although artificial intelligence (AI) has shown potential in enhancing micro-US interpretation, a comprehensive review of this emerging field is currently missing. This review synthesizes current evidence on AI applied to ExactVu 29 MHz micro-US for prostate cancer. METHODS:PubMed/MEDLINE, Embase, Scopus, Web of Science and the Cochrane Library were searched up to December 2025. Studies were included if they applied machine learning or deep learning directly to 29 MHz micro-US data and reported quantitative performance metrics. RESULTS:Ten studies met the inclusion criteria: six on prostate cancer detection, three on prostate segmentation and one on micro-US-histopathology registration. Detection models ranged from classical quantitative ultrasound machine learning to deep architectures using self-supervision, transformers, multiple-instance learning, ensemble calibration and 3D segmentation-based pipelines. Among core-level models for clinically significant cancer, area under the receiver operating characteristic curve (AUROC) values clustered around 0.76-0.81; one lesion-level framework reported an AUROC of 0.92, though at a non-comparable analytical unit. Segmentation studies achieved accurate prostate delineation (Dice similarity coefficient ≈ 0.94), and a single study demonstrated high-precision 3D registration to whole-mount histopathology (Dice similarity coefficient 0.97 and landmark error < 3 mm). All studies evaluated AI on previously acquired data, without real-time clinical implementation. CONCLUSIONS:AI for micro-US shows promising and reproducible early results across detection, segmentation and registration, but evidence is still limited. In view of the potential of AI to optimize micro-US utilization and its related advantages, additional efforts are warranted to achieve clinical adoption.