Novel Immune Checkpoint Inhibitor Targets in Advanced or Metastatic Renal Cell Carcinoma: State of the Art and Future Perspectives.

Immune checkpoint inhibitors (ICI) have become the cornerstone of treatment in renal cell carcinoma (RCC), for both metastatic disease and in an adjuvant setting. However, an adaptive resistance from cancer cells may arise during ICI treatment, therefore many studies are focusing on additional immune checkpoint inhibitor pathways. Promising targets of immunotherapeutic agents under investigation include T cell immunoglobulin and ITIM domain (TIGIT), immunoglobulin-like transcript 4 (ILT4), lymphocyte activation gene-3 (LAG-3), vaccines, T cell immunoglobulin and mucin domain-containing protein 3 (TIM-3), and chimeric antigen receptor (CAR) T cells. In this review of the literature, we recollect the current knowledge of the novel treatment strategies in the field of immunotherapy that are being investigated in RCC and analyze their mechanism of action, their activity and the clinical studies that are currently underway.

Metaverse in surgery - origins and future potential.

The metaverse refers to a collective virtual space that combines physical and digital realities to create immersive, interactive environments. This space is powered by technologies such as augmented reality (AR), virtual reality (VR), artificial intelligence (AI) and blockchain. In healthcare, the metaverse can offer many applications. Specifically in surgery, potential uses of the metaverse include the possibility of conducting immersive surgical training in a VR or AR setting, and enhancing surgical planning through the adoption of three-dimensional virtual models and simulated procedures. At the intraoperative level, AR-guided surgery can assist the surgeon in real time to increase surgical precision in tumour identification and selective management of vessels. In post-operative care, potential uses of the metaverse include recovery monitoring and patient education. In urology, AR and VR have been widely explored in the past decade, mainly for surgical navigation in prostate and kidney cancer surgery, whereas only anecdotal metaverse experiences have been reported to date, specifically in partial nephrectomy. In the future, further integration of AI will improve the metaverse experience, potentially increasing the possibility of carrying out surgical navigation, data collection and virtual trials within the metaverse. However, challenges concerning data security and regulatory compliance must be addressed before the metaverse can be used to improve patient care.

Machine Learning and External Validation of the IDENTIFY Risk Calculator for Patients with Haematuria Referred to Secondary Care for Suspected Urinary Tract Cancer.

BACKGROUND: The IDENTIFY study developed a model to predict urinary tract cancer using patient characteristics from a large multicentre, international cohort of patients referred with haematuria. In addition to calculating an individual's cancer risk, it proposes thresholds to stratify them into very-low-risk (<1%), low-risk (1-<5%), intermediate-risk (5-<20%), and high-risk (≥20%) groups. OBJECTIVE: To externally validate the IDENTIFY haematuria risk calculator and compare traditional regression with machine learning algorithms. DESIGN, SETTING, AND PARTICIPANTS: Prospective data were collected on patients referred to secondary care with new haematuria. Data were collected for patient variables included in the IDENTIFY risk calculator, cancer outcome, and TNM staging. Machine learning methods were used to evaluate whether better models than those developed with traditional regression methods existed. OUTCOME MEASUREMENTS AND STATISTICAL ANALYSIS: The area under the receiver operating characteristic curve (AUC) for the detection of urinary tract cancer, calibration coefficient, calibration in the large (CITL), and Brier score were determined. RESULTS AND LIMITATIONS: There were 3582 patients in the validation cohort. The development and validation cohorts were well matched. The AUC of the IDENTIFY risk calculator on the validation cohort was 0.78. This improved to 0.80 on a subanalysis of urothelial cancer prevalent countries alone, with a calibration slope of 1.04, CITL of 0.24, and Brier score of 0.14. The best machine learning model was Random Forest, which achieved an AUC of 0.76 on the validation cohort. There were no cancers stratified to the very-low-risk group in the validation cohort. Most cancers were stratified to the intermediate- and high-risk groups, with more aggressive cancers in higher-risk groups. CONCLUSIONS: The IDENTIFY risk calculator performed well at predicting cancer in patients referred with haematuria on external validation. This tool can be used by urologists to better counsel patients on their cancer risks, to prioritise diagnostic resources on appropriate patients, and to avoid unnecessary invasive procedures in those with a very low risk of cancer. PATIENT SUMMARY: We previously developed a calculator that predicts patients' risk of cancer when they have blood in their urine, based on their personal characteristics. We have validated this risk calculator, by testing it on a separate group of patients to ensure that it works as expected. Most patients found to have cancer tended to be in the higher-risk groups and had more aggressive types of cancer with a higher risk. This tool can be used by clinicians to fast-track high-risk patients based on the calculator and investigate them more thoroughly.

Immunohistochemistry analysis of PSMA expression at prostatic biopsy in high-risk prostate cancer: potential implications for PSMA-PET patient selection.

Introduction: Prostate-specific membrane antigen (PSMA) is a transmembrane protein expressed by normal prostatic tissue. Therefore, molecular imaging targeting PSMA (PSMA-PET) has gained particular interest and diffusion for PCa staging and restaging. Several factors may affect PSMA-PET results, and many tools have been proposed to improve patient selection. Furthermore, PSMA expression is not homogeneous among different tissues and within the prostate itself. The aims of this study were to evaluate immunohistochemistry (IHC) features of prostate biopsy samples and to assess their correlation with whole-mount specimens and PSMA-PET parameters. Methods: We included consecutive high-risk PCa patients who underwent PSMA-PET for staging proposal at our institution from January 2022 to December 2022. The PET parameters selected were SUVmax, total volume (TV), and total lesion activity (TL). Each patient underwent multiparametric MRI (mpMRI) and fusion-targeted prostate biopsy prior to surgery. IHC analyses were performed on the index lesion cores. IHC visual score (VS) (1, 2, 3) and visual pattern (VP) (membranous, cytoplasmic, and combined) and the percentage of PSMA-negative tumor areas (PSMA%neg) within biopsy cores were evaluated. Results: Forty-three patients who underwent robotic radical prostatectomy after PSMA-PET were available for analyses. Concordance between VS and VP at biopsy and final pathology showed a Cohen's kappa coefficient of 0.39 and 0.38, respectively. Patients with PSMA%neg <20% had a higher concordance in VS and VP (Cohen's kappa 0.49 and 0.4, respectively). No difference emerged in terms of median PSMA-TV (p = 0.3) and PSMA-TL (p = 0.9) according to VS at biopsy, while median SUVmax was higher in patients with VS 3 (p = 0.04). Higher SUVmax was associated with membranous and combined VP expression (p = 0.008). No difference emerged between patients with PSMA%neg <20% or PSMA%neg >20% on biopsy cores in terms of SUVmax, PSMA-TL, and PSMA-TV (p = 0.5, p = 0.5, and p = 0.9 respectively). Conclusions: We found a correlation between IHC VS and VP on targeted biopsy cores and SUVmax at PSMA-PET. However, the correlation between the IHC parameters of biopsy cores and final pathology was not as high as expected. Nevertheless, the presence of PSMA%neg <20% seems to have a better concordance in terms of visual score.

Location-Based Oncological Outcomes of Sentinel Node Dissection in Radical Prostatectomy.

PURPOSE: Our study aimed to assess the oncological outcomes of sentinel node dissection during radical prostatectomy according to nodal location in comparison to extended pelvic lymph node dissection. MATERIALS AND METHODS: Prospectively collected data of clinically node-negative patients who underwent prostatectomy and extended lymph node dissection with or without sentinel node from January 2013 to January 2023 were retrospectively analyzed. The primary end point was to assess oncological outcomes on the whole population. Kaplan-Meier curves were used to depict biochemical and clinical recurrence-free survival. Multivariable Cox regression models assessed the impact of nodal location on single-photon emission computed tomography on oncological outcomes. Adjustment for case mix included: pathological T stage, ISUP (International Society of Urological Pathology) grade group, initial PSA, nodal burden, age at surgery, and surgical margin status. Secondarily, a propensity score match was performed according to age at surgery, PSA, biopsy ISUP, clinical T stage, and Briganti risk of nodal invasion. Survival and regression analyses were also performed in the matched population. RESULTS: Of the patients, 55.8% had at least 1 sentinel node outside of lymph node dissection template at single-photon emission computed tomography/CT. Log-rank test showed comparable 36-month biochemical (P = .3) and clinical recurrence-free survival (P = .6) among patients with sentinel node inside template, outside template, or extended pelvic lymph node dissection alone. At Cox regression, sentinel node location outside template was associated with lower hazard of metastases (HR 0.62; P = .04) in the overall cohort, while in the matched cohort benefits were observed only for biochemical recurrence (HR 0.57; P = .001). CONCLUSIONS: Wider nodal resection boundaries outside the "classic" template, driven by sentinel node procedure, have a positive impact on oncological outcomes in selected patient.

Use of Soft Penile Prosthesis in Grafting Surgery for Peyronie's Disease and Mild Erectile Dysfunction: Still an Option?

BACKGROUND: Plaque incision and grafting (PEG) is a primary surgical therapy for severe penile curvature in Peyronie's disease (PD); However, it can increase the risk of erectile dysfunction (ED), particularly in patients with pre-operative mild ED. Soft penile prosthesis (SPP) implantation is a viable treatment option in such cases. This study aims to compare the outcomes of PEG-only approach to PEG plus SPP implantation. METHODS: Between 2010 and 2019, 32 patients with PD and mild ED (5-item version of the International Index of Erectile Function scores: 17-21) underwent PEG surgery. Two groups were defined based on the surgery type: PEG-only and PEG plus SPP. The long-term outcomes included correction of penile bending, erection quality, intercourse ability, penile length and sensitivity. The overall satisfaction and impact of surgery on sexual activity and quality of life were also assessed. RESULTS: Of the 32 patients, 13 (40.6%) underwent PEG-only surgery, whereas 19 (59.4%) underwent PEG plus SPP. No significant differences were noted between the groups regarding pre-operative characteristics (all p > 0.1) or intra- and post-operative complication rates (all p > 0.2). The median patch area was larger in the PEG-only group (28 cm2 vs. 16.2 cm2; p = 0.001), whereas patients in the PEG plus SPP group were more likely to receive a single patch implant (100% vs. 53.8%; p < 0.001). The penile length increased in 18 patients (61.6%), with significant differences between the two groups (30% vs. 81.2%; p = 0.03). Overall, 14 patients (53.8%) reported greater satisfaction with their sexual life post-operatively, with comparable rates between the groups (p = 0.2). No significant differences were found in the post-operative 5-item version of the International Index of Erectile Function scores or severe post-operative ED (all p > 0.5). CONCLUSIONS: SPP placement during corporoplasty in patients with mild ED is safe and feasible, and it may be a suitable option for patients uncertain about inflatable prosthesis placement. The use of SPP resulted in longer penile lengths and necessitated smaller grafts. However, further data are required to understand the long-term clinical implications of this approach.

Biophotonics-Intraoperative Guidance During Partial Nephrectomy: A Systematic Review and Meta-analysis.

CONTEXT: Partial nephrectomy (PN) with intraoperative guidance by biophotonics has the potential to improve surgical outcomes due to higher precision. However, its value remains unclear since high-level evidence is lacking. OBJECTIVE: To provide a comprehensive analysis of biophotonic techniques used for intraoperative real-time assistance during PN. EVIDENCE ACQUISITION: We performed a comprehensive database search based on the PICO criteria, including studies published before October 2022. Two independent reviewers screened the titles and abstracts followed by full-text screening of eligible studies. For a quantitative analysis, a meta-analysis was conducted. EVIDENCE SYNTHESIS: In total, 35 studies were identified for the qualitative analysis, including 27 studies on near-infrared fluorescence (NIRF) imaging using indocyanine green, four studies on hyperspectral imaging, two studies on folate-targeted molecular imaging, and one study each on optical coherence tomography and 5-aminolevulinic acid. The meta-analysis investigated seven studies on selective arterial clamping using NIRF. There was a significantly shorter warm ischemia time in the NIRF-PN group (mean difference [MD]: -2.9; 95% confidence interval [CI]: -5.6, -0.1; p = 0.04). No differences were noted regarding transfusions (odds ratio [OR]: 0.5; 95% CI: 0.2, 1.7; p = 0.27), positive surgical margins (OR: 0.7; 95% CI: 0.2, 2.0; p = 0.46), or major complications (OR: 0.4; 95% CI: 0.1, 1.2; p = 0.08). In the NIRF-PN group, functional results were favorable at short-term follow-up (MD of glomerular filtration rate decline: 7.6; 95% CI: 4.6, 10.5; p < 0.01), but leveled off at long-term follow-up (MD: 7.0; 95% CI: -2.8, 16.9; p = 0.16). Remarkably, these findings were not confirmed by the included randomized controlled trial. CONCLUSIONS: Biophotonics comprises a heterogeneous group of imaging modalities that serve intraoperative decision-making and guidance. Implementation into clinical practice and cost effectiveness are the limitations that should be addressed by future research. PATIENT SUMMARY: We reviewed the application of biophotonics during partial removal of the kidney in patients with kidney cancer. Our results suggest that these techniques support the surgeon in successfully performing the challenging steps of the procedure.

Awareness and Use of ChatGPT and Large Language Models: A Prospective Cross-sectional Global Survey in Urology.

BACKGROUND: Since its release in November 2022, ChatGPT has captivated society and shown potential for various aspects of health care. OBJECTIVE: To investigate potential use of ChatGPT, a large language model (LLM), in urology by gathering opinions from urologists worldwide. DESIGN, SETTING, AND PARTICIPANTS: An open web-based survey was distributed via social media and e-mail chains to urologists between April 20, 2023 and May 5, 2023. Participants were asked to answer questions related to their knowledge and experience with artificial intelligence, as well as their opinions of potential use of ChatGPT/LLMs in research and clinical practice. OUTCOME MEASUREMENTS AND STATISTICAL ANALYSIS: Data are reported as the mean and standard deviation for continuous variables, and the frequency and percentage for categorical variables. Charts and tables are used as appropriate, with descriptions of the chart types and the measures used. The data are reported in accordance with the Checklist for Reporting Results of Internet E-Surveys (CHERRIES). RESULTS AND LIMITATIONS: A total of 456 individuals completed the survey (64% completion rate). Nearly half (47.7%) reported that they use ChatGPT/LLMs in their academic practice, with fewer using the technology in clinical practice (19.8%). More than half (62.2%) believe there are potential ethical concerns when using ChatGPT for scientific or academic writing, and 53% reported that they have experienced limitations when using ChatGPT in academic practice. CONCLUSIONS: Urologists recognise the potential of ChatGPT/LLMs in research but have concerns regarding ethics and patient acceptance. There is a desire for regulations and guidelines to ensure appropriate use. In addition, measures should be taken to establish rules and guidelines to maximise safety and efficiency when using this novel technology. PATIENT SUMMARY: A survey asked 456 urologists from around the world about using an artificial intelligence tool called ChatGPT in their work. Almost half of them use ChatGPT for research, but not many use it for patients care. The resonders think ChatGPT could be helpful, but they worry about problems like ethics and want rules to make sure it's used safely.

Positive Surgical Margins After Anterior Robot-assisted Radical Prostatectomy: Assessing the Learning Curve in a Multi-institutional Collaboration.

BACKGROUND: The learning curve for robot-assisted radical prostatectomy (RARP) remains controversial, with prior studies showing that, in contrast with evidence on open and laparoscopic radical prostatectomy, biochemical recurrence rates of experienced versus inexperienced surgeons did not differ. OBJECTIVE: To characterize the learning curve for positive surgical margins (PSMs) after RARP. DESIGN, SETTING, AND PARTICIPANTS: We analyzed the data of 13 090 patients with prostate cancer undergoing RARP by one of 74 surgeons from ten institutions in Europe and North America between 2003 and 2022. OUTCOME MEASUREMENTS AND STATISTICAL ANALYSIS: Multivariable models were used to assess the association between surgeon experience at the time of each patient's operation and PSMs after surgery, with adjustment for preoperative prostate-specific antigen level, grade, stage, and year of surgery. Surgeon experience was coded as the number of robotic radical prostatectomies done by the surgeon before the index patient's operation. RESULTS AND LIMITATIONS: Overall, 2838 (22%) men had PSMs on final pathology. After adjusting for case mix, we found a significant, nonlinear association between surgical experience and probability of PSMs after surgery, with a lower risk of PSMs for greater surgeon experience (p < 0.0001). The probabilities of PSMs for a patient treated by a surgeon with ten, 250, 500, and 2000 prior robotic procedures were 26%, 21%, 18%, and 14%, respectively (absolute risk difference between ten and 2000 procedures: 11%; 95% confidence interval: 9%, 14%). Similar results were found after stratifying patients according to extracapsular extension at final pathology. Results were also unaltered after excluding surgeons who had moved between institutions. CONCLUSIONS: While we characterized the learning curve for PSMs after RARP, the relative contribution of surgical learning to the achievement of optimal outcomes remains controversial. Future investigations should focus on what experienced surgeons do to avoid positive margins and should explore the relationship between learning, margin rate, and biochemical recurrence. Understanding what margins affect recurrence and whether these margins are trainable or a result of other factors may shed light on where to focus future efforts in surgical education. PATIENT SUMMARY: In patients receiving robotic radical prostatectomy for prostate cancer, we characterized the learning curve for positive margins. The risk of surgical margins decreased progressively with increasing experience, and plateaued around the 500th procedure. Understanding what margins affect recurrence and whether these margins are trainable or a result of other factors has implications for surgeons and patients, and it may shed light on where to focus future efforts in surgical education.

Can the Abdominal Aortic Atherosclerotic Plaque Index Predict Functional Outcomes after Robot-Assisted Partial Nephrectomy?

This study aims to evaluate the abdominal aortic atherosclerotic plaque index (API)'s predictive role in patients with pre-operatively or post-operatively developed chronic kidney disease (CKD) treated with robot-assisted partial nephrectomy (RAPN) for renal cell carcinoma (RCC). One hundred and eighty-three patients (134 with no pre- and post-operative CKD (no CKD) and 49 with persistent or post-operative CKD development (post-op CKD)) who underwent RAPN between January 2019 and January 2022 were deemed eligible for the analysis. The API was calculated using dedicated software by assessing the ratio between the CT scan atherosclerotic plaque volume and the abdominal aortic volume. The ROC regression model demonstrated the influence of API on CKD development, with an increasing effect according to its value (coefficient 0.13; 95% CI 0.04-0.23; p = 0.006). The Model 1 multivariable analysis of the predictors of post-op CKD found that the following are independently associated with post-op CKD: Charlson Comorbidity Index (OR 1.31; p = 0.01), last follow-up (FU) Δ%eGFR (OR 0.95; p < 0.01), and API ≥ 10 (OR 25.4; p = 0.01). Model 2 showed API ≥ 10 as the only factor associated with CKD development (OR 25.2; p = 0.04). The median follow-up was 22 months. Our results demonstrate API to be a strong predictor of post-operative CKD, allowing the surgeon to tailor the best treatment for each patient, especially in those who might be at higher risk of CKD.

Artificial Intelligence in Surgical Training for Kidney Cancer: A Systematic Review of the Literature.

The prevalence of renal cell carcinoma (RCC) is increasing due to advanced imaging techniques. Surgical resection is the standard treatment, involving complex radical and partial nephrectomy procedures that demand extensive training and planning. Furthermore, artificial intelligence (AI) can potentially aid the training process in the field of kidney cancer. This review explores how artificial intelligence (AI) can create a framework for kidney cancer surgery to address training difficulties. Following PRISMA 2020 criteria, an exhaustive search of PubMed and SCOPUS databases was conducted without any filters or restrictions. Inclusion criteria encompassed original English articles focusing on AI's role in kidney cancer surgical training. On the other hand, all non-original articles and articles published in any language other than English were excluded. Two independent reviewers assessed the articles, with a third party settling any disagreement. Study specifics, AI tools, methodologies, endpoints, and outcomes were extracted by the same authors. The Oxford Center for Evidence-Based Medicine's evidence levels were employed to assess the studies. Out of 468 identified records, 14 eligible studies were selected. Potential AI applications in kidney cancer surgical training include analyzing surgical workflow, annotating instruments, identifying tissues, and 3D reconstruction. AI is capable of appraising surgical skills, including the identification of procedural steps and instrument tracking. While AI and augmented reality (AR) enhance training, challenges persist in real-time tracking and registration. The utilization of AI-driven 3D reconstruction proves beneficial for intraoperative guidance and preoperative preparation. Artificial intelligence (AI) shows potential for advancing surgical training by providing unbiased evaluations, personalized feedback, and enhanced learning processes. Yet challenges such as consistent metric measurement, ethical concerns, and data privacy must be addressed. The integration of AI into kidney cancer surgical training offers solutions to training difficulties and a boost to surgical education. However, to fully harness its potential, additional studies are imperative.

Digital Therapeutics in Urology: An Innovative Approach to Patient Care and Management.

Digital therapeutics (DTx) are a new class of intervention involving evidence-based software applications and have been used in neurology and psychiatry. To assess the potential of DTx in urology, we conducted a survey to assess the current prevalence of the digital infrastructure required for DTx, areas of support expected by patients, and requirements for uptake. Between November 2022 and January 2023, we conducted an anonymized survey at two German academic centers among patients with urologic conditions. We found that among patients aged <65 yr versus ≥65 yr, digital devices including smartphones (93.6% vs 77.3%; p < 0.001), computers (80.4% vs 70.1%; p < 0.001), tablets (51.7% vs 38.1%; p < 0.001), and smartwatches (24.7% vs 7.7%; p < 0.001) are already widely used, especially in the younger age group. Apps (95.6% vs 74.4%; p < 0.001) and health apps (57.6% vs 30.4%; p < 0.001) are already frequently used, but certified DTx apps are not (7.3% vs 5.4%; p = 0.25). Patients favor solutions that provide access to validated information (49.6%), give medical advice based on data or symptoms captured by the app (43.0%), or replace a physiotherapist (41.7%). Patients feel that optimization of therapy (78.4%), significant positive health outcomes (76.9%), and better patient autonomy (73.4%) are important requirements for DTx in urology. Regulatory and reimbursement changes mean that DTx might play an increasing role in urology. Patient summary: Patients can use digital therapeutics (DTx), which are mainly smartphone apps, to improve their health status or treat medical conditions. We assessed the current and future use of DTx in urology. Patients are already widely using smartphones and frequently use uncertified health apps, but do not use DTx. Patients would like to use DTx to optimize therapy that provides a significant health improvement.

A Systematic Review of New Imaging Technologies for Robotic Prostatectomy: From Molecular Imaging to Augmented Reality.

New imaging technologies play a pivotal role in the current management of patients with prostate cancer. Robotic assisted radical prostatectomy (RARP) is a standard of care for localized disease and through the already imaging-based console subject of research towards combinations of imaging technologies and RARP as well as their impact on surgical outcomes. Therefore, we aimed to provide a comprehensive analysis of the currently available literature for new imaging technologies for RARP. On 24 January 2023, we performed a systematic review of the current literature on Pubmed, Scopus and Web of Science according to the PRISMA guidelines and Oxford levels of evidence. A total of 46 studies were identified of which 19 studies focus on imaging of the primary tumor, 12 studies on the intraoperative tumor detection of lymph nodes and 15 studies on the training of surgeons. While the feasibility of combined approaches using new imaging technologies including MRI, PSMA-PET CT or intraoperatively applied radioactive and fluorescent dyes has been demonstrated, the prospective confirmation of improvements in surgical outcomes is currently ongoing.

The Impact on Urology Residents' Learning of Social Media and Web Technologies after the Pandemic: A Step Forward through the Sharing of Knowledge.

The COVID-19 pandemic has impacted urology residents and their training. However, several new technologies or knowledge platforms as social media (SoMe) and web-based learning solutions have filled this gap. Therefore, we aimed to analyze resident's learning curves of new learning modalities, identify the evidence that is provided in the literature, and evaluate the possible impact of such solutions in the future. We conducted a non-systematic literature search using Medline, PubMed, and Embase. In addition, online resources of national and international urology resident societies were queried. The identified paper described SoMe, webinars, podcasts, pre-recorded surgical videos, educational platforms, and mobile apps in the field of urology that are used to gain access to information, teach and provide feedback to residents, and were used under the conditions of the pandemic. The application of those technologies harbors the risk of mis- and disinformation, but have the potential to provide access to education and validated knowledge, training, and feedback and thereby might democratize training of residents in urology globally.

The Long but Necessary Journey Towards Optimization of the Cause-Effect Relationship Between Input and Output for Accountable Use of ChatGPT for Academic Purposes.

The use of appropriate inputs can significantly improve the outputs obtained from ChatGPT for academic research.

A systematic review and meta-analysis of artificial intelligence diagnostic accuracy in prostate cancer histology identification and grading.

BACKGROUND: Artificial intelligence (AI) is a promising tool in pathology, including cancer diagnosis, subtyping, grading, and prognostic prediction. METHODS: The aim of the study is to assess AI application in prostate cancer (PCa) histology. We carried out a systematic literature search in 3 databases. Primary outcome was AI accuracy in differentiating between PCa and benign hyperplasia. Secondary outcomes were AI accuracy in determining Gleason grade and agreement among AI and pathologists. RESULTS: Our final sample consists of 24 studies conducted from 2007 to 2021. They aggregate data from roughly 8000 cases of prostate biopsy and 458 cases of radical prostatectomy (RP). Sensitivity for PCa diagnostic exceeded 90% and ranged from 87% to 100%, and specificity varied from 68% to 99%. Overall accuracy ranged from 83.7% to 98.3% with AUC reaching 0.99. The meta-analysis using the Mantel-Haenszel method showed pooled sensitivity of 0.96 with I2 = 80.7% and pooled specificity of 0.95 with I2 = 86.1%. Pooled positive likehood ratio was 15.3 with I2 = 87.3% and negative - was 0.04 with I2 = 78.6%. SROC (symmetric receiver operating characteristics) curve represents AUC = 0.99. For grading the accuracy of AI was lower: sensitivity for Gleason grading ranged from 77% to 87%, and specificity from 82% to 90%. CONCLUSIONS: The accuracy of AI for PCa identification and grading is comparable to expert pathologists. This is a promising approach which has several possible clinical applications resulting in expedite and optimize pathology reports. AI introduction into common practice may be limited by difficult and time-consuming convolutional neural network training and tuning.

PSMA-PET Guided Treatment in Prostate Cancer Patients with Oligorecurrent Progression after Previous Salvage Treatment.

BACKGROUND: Prostate Specific Membrane Antigen-Positron Emission Tomography (PSMA-PET) is used to select recurrent prostate cancer (PCa) patients for metastases-directed therapy (MDT). We aimed to evaluate the oncologic outcomes of second-line PSMA-guided MDT in oligo-recurrent PCa patients. METHODS: we performed a retrospective analysis of 113 recurrent PCa after previous radical prostatectomy and salvage therapies with oligorecurrent disease at PSMA-PET (≤3 lesions in N1/M1a-b) in three high-volume European centres. Patients underwent second-line salvage treatments: MDT targeted to PSMA (including surgery and/or radiotherapy), and the conventional approach (observation or Androgen Deprivation Therapy [ADT]). Patients were stratified according to treatments (MDT vs. conventional approach). Patients who underwent MDT were stratified according to stage in PSMA-PET (N1 vs. M1a-b). The primary outcome of the study was Progression-free survival (PFS). Secondary outcomes were Metastases-free survival (MFS) and Castration Resistant PCa free survival (CRPC-FS). Kaplan-Meier analyses assessed PFS, MFS and CRPC-FS. Multivariable Cox regression models identified predictors of progression and metastatic disease. RESULTS: Overall, 91 (80%) and 22 (20%) patients were treated with MDT and the conventional approach, respectively. The median follow-up after PSMA-PET was 31 months. Patients who underwent MDT had a similar PFS compared to the conventional approach (p = 0.3). Individuals referred to MDT had significantly higher MFS and CRPC-FS compared to those who were treated with the conventional approach (73.5% and 94.7% vs. 30.5% and 79.5%; all p ≤ 0.001). In patients undergoing MDT, no significant differences were found for PFS and MFS according to N1 vs. M1a-b disease, while CRPC-FS estimates were significantly higher in patients with N1 vs. M1a-b (100% vs. 86.1%; p = 0.02). At multivariable analyses, age (HR = 0.96) and ADT during second line salvage treatment (HR = 0.5) were independent predictors of PFS; MDT (HR 0.27) was the only independent predictor of MFS (all p ≤ 0.04) Conclusion: Patients who underwent second-line PSMA-guided MDT experienced higher MFS and CRPC-FS compared to men who received conventional management.