In this work, several machine learning (ML) algorithms, both classical ML and modern deep learning, were investigated for their ability to improve the performance of a pipeline for the segmentation and classification of prostate lesions using MRI data. The algorithms were used to perform a binary classification of benign and malignant tissue visible in MRI sequences. The model choices include support vector machines (SVMs), random decision forests (RDFs), and multi-layer perceptrons (MLPs), along with radiomic features that are reduced by applying PCA or mRMR feature selection. Modern CNN-based architectures, such as ConvNeXt, ConvNet, and ResNet, were also evaluated in various setups, including transfer learning. To optimize the performance, different approaches were compared and applied to whole images, as well as gland, peripheral zone (PZ), and lesion segmentations. The contribution of this study is an investigation of several ML approaches regarding their performance in prostate cancer (PCa) diagnosis algorithms. This work delivers insights into the applicability of different approaches for this context based on an exhaustive examination. The outcome is a recommendation or preference for which machine learning model or family of models is best suited to optimize an existing pipeline when the model is applied as an upstream filter.

Robot-assisted radical cystectomy with intracorporeal urinary diversion (iRARC) is increasingly being performed instead of open surgery. A criticism of this technique is the long learning curve, but limited data are available on this topic. At our center, the transition from open radical cystectomy (ORC) to iRARC began in May 2017. A retrospective analysis was conducted on the initial 53 cases of robot-assisted cystectomy with intracorporeal urinary diversion via ileal conduit, which were performed by one single surgeon. The patients were divided into four consecutive groups according to the surgeon’s increasing experience, and perioperative parameters were analyzed as a surrogate for the learning curve. Over the course of the learning curve, a decline in median operation time from 415 to 361 min (p = 0.02), blood loss from 400 to 200 mL (p = 0.01), and minor complications from 71% to 15% (p = 0.02) was observed. No significant difference in overall and major complications, length of hospital stay, and total lymph node yield was shown. During the initial period of the learning curve, only the less complex cases were operated on using robotic surgery, while the more challenging ones were handled through open surgery. After experience with 28 cases, no more cystectomies were performed through open surgery. This led to an increase in operation time and length of hospital stay, as well as a higher incidence of both minor and overall complications among cases 28–40. After 40 cases, a significant decrease in these parameters was observed again. Our analysis demonstrated that operation time, blood loss, and minor complications decrease with increasing surgical experience in iRARC, while suggesting that technically challenging cases should be operated on after experience with 40 robotic cystectomies.

Purpose: To provide a detailed description of the Swiss Society of Urology prospective database of radical cystectomy (RC) due to bladder cancer (BC) about differences in operative outcomes between teaching and non-teaching RC. Methods: We collected the data of all RCs for BC from the register from March 2017 to March 2025, leading to 1587 cases. Afterwards, we decided about the extraction of 34 variables, e.g. operating approach and intraoperative complications. Furthermore, we determined that only complete data sets for our pre-defined variables will be included in the analysis, which led to 1304 RC cases. Results: Median patient age was 72.0 years (IQR 64.0–78.0). The majority of patients underwent open RC ( n = 838; 64.3%). More than one quarter ( n = 344; 26.4%) were teaching surgeries and there was no significant difference between both groups regarding demographic characteristics. There were no significant differences between teaching and non-teaching operative results in terms of surgical resection (R1 status; p = 0.295), duration of inpatient treatment ( p = 0.394), infection ( p = 0.023), wound healing disorders ( p = 0.484), duration of surgery ( p = 0.365), intraoperative bleeding ( p = 0.635) and intraoperative blood loss ( p = 0.074). However, in terms of the number of resected lymph nodes, blood transfusion rate, number of transfused packed red blood cells, intraoperative complications as well as the highest grade of complication during inpatient treatment teaching RC showed less favorable results, e.g. number of evaluated lymph nodes (teaching median 18.0 versus non-teaching median 20.0, p < 0.001). Conclusion: Teaching RC is safe, for a high complex procedure, according to our prospective pilot study.

Background: Preoperative side-specific identification of extracapsular extension (ECE) is important for selecting an appropriate nerve-sparing strategy at radical prostatectomy. Patients with multiparametric magnetic resonance imaging (mpMRI)-defined capsular contact represent a clinically challenging subgroup because contact raises concern for ECE but does not uniformly indicate extraprostatic disease. We aimed to develop a side-specific nomogram for individualized ECE prediction and perform preliminary internal validation in this selected population. Materials and Methods: We retrospectively analyzed 323 prostate lobes from 286 patients with biopsy-proven, non-metastatic prostate cancer and mpMRI-defined capsular contact who underwent robot-assisted radical prostatectomy between 2015 and 2021 at a single institution. The dataset was randomly split into training (70%) and testing (30%) cohorts. Three multivariable logistic-regression models were developed and compared. Discrimination was assessed using the area under the receiver operating characteristic curve (AUC-ROC), calibration by intercept and slope, and clinical utility by decision curve analysis. A nomogram was derived from the best-performing model in the internal split-sample comparison. Results: Side-specific ECE was present in 110/323 lobes (34.1%). Among the candidate models, the forward-selection model showed the most favorable apparent performance, with an AUC-ROC of 0.85 in training and 0.83 in testing, together with good test-set calibration (intercept 0.24; slope 0.97). The final model included a capsular contact length ≥10 mm, percentage tumor involvement in positive biopsy cores, number of positive biopsy cores, and index lesion size. At a 10% predicted risk threshold, 32% of lobes were classified as low risk, with an observed ECE rate of about 5%. Conclusions: We developed a side-specific nomogram tailored to patients with mpMRI-defined capsular contact and performed preliminary internal validation. The model may aid preoperative side-specific risk assessment relevant to nerve-sparing planning, but external validation and assessment of clinical impact are required before clinical adoption.