Introduction: Future evolutions of artificial intelligence (AI) will support autonomous surgery, conducted without the need for human decision making and implementation, but we have not yet achieved this level of technology. Presently, the predominant applications of AI in urological surgery are achieved using the tool of computer vision. This review aims to summarise potential intra-operative AI tools for urologists. Method: A systematic search was conducted through Scopus, PubMed, Embase, and Medline by two independent reviewers, with a third to resolve any conflicts. As a rule, only original articles describing the use or potential use of artificial intelligence intra-operatively in urologic surgery were included. A total of 60 articles were reviewed. Key content and findings: There is significant research investigating the ability to diagnose bladder tumours using AI assistance at the time of cystoscopy, with studies showing the ability to also grade tumour based on appearance and differentiate between carcinoma in situ and indeterminate lesions. With the aid of AI, kidney stones can accurately be identified and diagnosed morphologically intra-operatively. Various studies show the ability to overlay 2D and 3D anatomical models on a surgeon’s screen, as well as correctly identify important anatomical landmarks and surgical instruments, with AI support. All types of intra-operative data can be analysed with AI to assess surgeon performance, predict post-operative outcomes such as continence post prostatectomy, and recognise complications such as bleeding and ischemia. Conclusions: AI holds great potential for urologists during surgery to improve safety, diagnostic accuracy, identification of anatomical structures and surgical instruments, assessment of the surgeon for self-evaluation, and prediction of post-operative outcomes. Before the use of AI as an aid during surgery becomes standard practice, more prospective studies are needed to evaluate its real-world application, feasibility, and costs.

Objectives: Cx bladder monitor (CxM) is a urine test with a proven high sensitivity and negative predictive value in bladder cancer surveillance. The aim of this retrospective study was to report on the outcomes of our newly implemented bladder cancer surveillance program for patients eligible for yearly cystoscopy, as per the European Association of Urology (EAU) guidelines. In this program, eligible patients alternate between yearly surveillance cystoscopy and CxM, instead of the standard yearly surveillance cystoscopy. Outcomes measures were overall results of CxM and subsequent treatment patterns of patients, impact on waiting lists, cost comparison and patient satisfaction.Patients and Methods: In 2022, 109 eligible and consenting patients were identified, with 98 commencing on the new surveillance program, starting with CxM instead of cystoscopy. A negative CxM, would result in a planned flexible cystoscopy in 12 months. If a patient had a positive CxM, they proceeded to undergo a cystoscopy, and if required, imaging.Results: Of the 98 that underwent testing, 90 had a negative CxM test and 8 patients had a positive CxM test. Three of these eight were true positive (PPV 0.375). Seventy negative CxM patients had no recurrence at the time of the next cystoscopy/imaging. Of the remaining 20 negative CxM patients, 11 were found to have a recurrence at subsequent cystoscopy/imaging and 9 did not proceed with further surveillance for various reasons. All of the tumour recurrences diagnosed after a negative CxM were non‐invasive, thus there was no progression to muscle‐invasive disease. All suitable patients consented to continuing with the CxM protocol. The hospital surveillance cystoscopy waitlist was reduced by approximately 59% and CxM was approximately $850 AUD cheaper than a cystoscopy.Conclusion: CxM can be safely used in an alternating schedule with Flexible Cystoscopy for patients on annual bladder cancer surveillance.

Despite the advent of transperineal (TP) biopsy and reduced risk of infective complications, transrectal ultrasound-guided (TRUS) prostate biopsy is still widely performed worldwide. The accepted prophylactic antibiotic is usually a single agent oral fluoroquinolone; however, this approach is beset by growing antibiotic resistance. The aim of this study was to assess whether the addition of intravenous gentamicin (2 mg/kg or at least 160 mg), immediately prior to biopsy, in conjunction with routine ciprofloxacin prophylaxis, reduced infection and sepsis rates post TRUS biopsy. Six hundred fifty-eight patients underwent TRUS biopsy at our center from 2017 to 2022, of whom 648 had data sufficient for analysis. We performed a retrospective analysis focusing on patient demographics (age, BMI, diabetes status), biopsy parameters, and outcomes of sepsis and urinary tract infection . Patients were recorded as developing sepsis if they required hospital admission for intravenous antibiotics. Fisher's exact test was employed for categorical variables, while the Student's t test was utilized for continuous variables for statistical significance. The rate of sepsis was 3.9% in the ciprofloxacin-only group, versus 0% in the ciprofloxacin plus gentamicin group (P value = 0.03). Overall aggregated post-TRUS infection rates was also 0% in the ciprofloxacin plus gentamicin group (P value = 0.005). We found no associated between infection and secondary risk factors. The administration of 2 mg/kg intravenous gentamicin with oral ciprofloxacin prophylaxis reduces infection and sepsis rates post TRUS biopsy.

Introduction: PI-RADS 3 lesions represent a diagnostic grey zone on multiparametric MRI, with clinically significant prostate cancer (csPCa) detected in only 10–30%. Their equivocal nature leads to both unnecessary biopsies and missed cancers. Artificial intelligence (AI) has emerged as a potential tool to provide objective, reproducible risk prediction. This review summarises current evidence on AI for risk stratification in patients with indeterminate mpMRI findings, including clarification of key multicentre initiatives such as the PI-CAI (Prostate Imaging–Artificial Intelligence) study—a global benchmarking effort comparing AI systems against expert radiologists. Methods: A narrative review of PubMed and Embase (search updated to August 2025) was conducted using terms including “PI-RADS 3”, “radiomics”, “machine learning”, “deep learning”, and “artificial intelligence.” Eligible studies included those evaluating AI-based prediction of csPCa in PI-RADS 3 lesions using biopsy or long-term follow-up as reference standards. Both single-centre and multicentre studies were included, with emphasis on externally validated models. Results: Radiomics studies demonstrate that handcrafted features extracted from T2-weighted and diffusion-weighted imaging can distinguish benign tissue from csPCa, particularly in the transition zone, with area-under-the-ROC curves typically 0.75–0.82. Deep learning approaches—including convolutional neural networks and large-scale representation-learning frameworks—achieve higher performance and can reduce benign biopsy rates by 30–40%. Models that integrate imaging-based AI with clinical predictors such as PSA density further improve discrimination. The PI-CAI study, the largest international benchmark to date (>10,000 MRI exams), shows that state-of-the-art AI systems can match or exceed expert radiologists for csPCa detection across diverse scanners, centres, and populations, though prospective validation remains limited. Conclusions: AI shows strong potential to refine management of PI-RADS 3 lesions by reducing unnecessary biopsies, improving csPCa detection, and mitigating inter-reader variability. Translation into routine practice will require prospective multicentre validation, harmonised imaging protocols, and integration of AI outputs into clinical workflows with clear thresholds, decision support, and safety-net recommendations.

Background/Objectives: Limited data exist on the outcomes of men with bladder stones undergoing cystolitholapaxy alone versus cystolitholapaxy with concurrent transurethral resection of the prostate (TURP). Additionally, factors associated with the need for subsequent TURP in these patients are not well defined. This study aimed to compare the clinical outcomes in men undergoing cystolitholapaxy alone with those undergoing concurrent cystolitholapaxy with TURP, and determine what factors were associated with the need for subsequent TURP. Methods: A retrospective review was conducted of men undergoing cystolitholapaxy at a single Australian hospital between 2014 and 2021. Patients were grouped into cystolitholapaxy alone (Group A) and cystolitholapaxy with concurrent TURP (Group B). Clinical outcomes compared included rates of acute urinary retention (AUR), urinary tract infection (UTI), and subsequent TURP. Prostate volume (PV), stone size, and the presence of intravesical prostatic protrusion (IPP) were evaluated as potential predictors of subsequent TURP in Group A. Results: Fifty men were included in the final analysis, with a median follow-up of 50 months (interquartile range [IQR] 24–81). Baseline characteristics did not differ significantly between groups. There was no statistically significant difference in the rates of AUR (11% vs. 13%) or UTI (22% vs. 30%) between Group A and Group B, respectively. However, 41% of Group A underwent subsequent TURP, compared to 9% in Group B (p = 0.0112). Within Group A, those requiring subsequent TURP had a significantly greater PV (65 vs. 34 cc, p = 0.0059), larger stone size (3.5 vs. 2.0 cm, p = 0.0175), and a higher prevalence of IPP (82% vs. 6%, p < 0.001). Conclusions: Cystolitholapaxy alone is a viable initial treatment for bladder stones, with comparable clinical outcomes to concurrent TURP. PV, stone size, and IPP may help identify patients likely to require future TURP, enabling more tailored treatment and potential reduction in TURP-related morbidity.