
Introduction Urinary stone composition analysis is essential for guiding treatment and preventive strategies, but conventional methods such as Fourier-transform infrared spectroscopy (FTIR) are costly and limited in availability. Artificial intelligence (AI), particularly convolutional neural networks (CNNs), offers potential as a non-invasive alternative using computed tomography (CT) imaging. The aim of the study is to evaluate the performance of a CNN model in predicting urinary stone composition from non-conMaterial and methods A retrospective analysis was conducted using an institutional database of patients with urinary stones surgically removed between 2020 and 2024. Stone composition was confirmed via FTIR. A total of 1,487 NCCT scan images were used for CNN development and internal validation, with 105 scan images reserved for external validation. Transfer learning with VGG16 architecture was applied, incorporating data augmentation and fine-tuning strategies. Performance metrics included accuracy, area under the ROC curve (AUC), and Cohen's kappa coefficient. Results The dataset comprised calcium oxalate monohydrate (74.9%), calcium oxalate dihydrate (17.6%), uric acid (2.7%), struvite (2.3%), and other compositions (2.5%). The CNN achieved an internal accuracy of 89.8% (AUC 0.92). In independent temporal validation the cohort accuracy was 85.4%, with an AUC of 0.81 and a Cohen's kappa of 0.864. Misclassifications occurred mainly between calcium oxalate subtypes due to overlapping radiological features. Conclusions CNN-based analysis of NCCT images provides accurate, non-invasive prediction of urinary stone composition, with performance comparable to conventional methods. This approach may improve preoperative planning and broaden diagnostic access, particularly in settings where FTIR is unavailable. Prospective multicenter studies are warranted to validate clinical implementation.
Introduction:Transurethral resection of the prostate (TURP) is widely recognized as the gold standard surgical treatment for benign prostatic enlargement (BPE). However, despite its effectiveness, TURP is associated with male sexual dysfunction, with up to 70% of patients developing retrograde ejaculation. Recent evidence suggests that preserving supramontanal tissue around the verumontanum may preserve sexual outcomes. This study aims to assess the efficacy of supramontanal-sparing TURP as an ejaculation sparing approach in sexually active males with BPE through a systematic review and meta-analysis. Material and methods:The present review was performed using a systematic search, registered in PROSPERO (CRD42024614954), and followed PRISMA guideline. Sexual function and voiding outcomes were measured, including symptom scores, maximum flow rate (Qmax), and post-void residual (PVR). The results were presented as risk ratios (RRs) and mean differences (MDs), with 95% confidence intervals (CIs). Results:Six studies involving 540 patients, supramontanal-sparing TURP was compared to conventional TURP. The supramontanal-sparing TURP significantly reduced retrograde ejaculation (RR = 0.26, 95% CI: 0.14-0.46, p <0.01) and preserved semen volume better (MD = 1.04 ml, 95% CI: 0.36-1.73, p <0.01). Both techniques showed comparable outcomes in voiding function, including postoperative maximum flow rate, IPSS scores, and post-void residual volume (p = 0.49, p = 0.97, and p = 0.82, respectively). Conclusions:The supramontanal-sparing TURP technique demonstrated lower rates of retrograde ejaculation, while achieving similar voiding outcomes compared to standard TURP. These findings highlight the potential for preserving antegrade ejaculation after TURP when using the supramontanal-sparing technique.