AI is increasingly integrated within prostate cancer diagnosis pathway. To provide estimates of diagnostic accuracy of AI assistance for clinically significant prostate cancer (csPCa) via MRI. A systematic search of PubMed, Embase, Cochrane, Scopus and Web of Science from January 2017 to October 2024 was performed for studies on the diagnostic utility of AI for prostate MRI. Diagnostic performance metrics were synthesized through hierarchical summary receiver operating characteristic modeling with random-effects assumptions. Specially, to test inferiority and potential superiority of AI, sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), cancer detection rate (CDR), and accuracy was pairwisely compared between AI and radiologists in study level using odds ratios (ORs) with Z-statistics. 7398 patients from 29 studies with AI-vs-human pairwise comparison were included. When acting as an assistant to human readers, AI demonstrated superior performance compared to stand-alone human readers in diagnosing csPCa via MRI, specifically with higher sensitivity (86.5% vs 82.6%, P = 0.001), specificity (57.8% vs 50.0%, P = 0.028), PPV (64.3% vs 58.9%, P = 0.001), and NPV (82.9% vs 76.5%, P = 0.001) while maintaining comparable CDR (40.5% vs 38.6%, P = 0.093). When used as standalone readers, AI exhibited higher specificity (58.7% vs 48.7%, P = 0.026) but at the cost of reduced sensitivity (87.2% vs 90.1%, P = 0.017). Subgroup analysis indicated that readers of varying experience levels could all improve their diagnostic performance with AI assistance. Integrating AI as an assistant in csPCa diagnostic workflows could enhance accuracy, particularly for less experienced readers. Trial Name: The efficiency comparison of radiologists with or without assistance of artificial intelligence in prostate cancer diagnosis: a meta-analysis. Registration date: April 17, 2024. CRD42024533016. Registration information available at: https://www.crd.york.ac.uk/PROSPERO/ .

Black individuals in the U.S. experience significantly higher prostate cancer mortality and are more likely to be diagnosed at younger ages with aggressive disease. This disparity may be influenced by negative healthcare perceptions and racial discordance between patients and providers, impacting lower rates of prostate-specific antigen (PSA) screening. We hypothesized that these factors would be associated with reduced PSA screening uptake, particularly among Black men. This study aimed to examine the association between negative healthcare perceptions and PSA screening, assess whether this relationship differs by race, and evaluate the role of racial discordance in influencing screening behavior. We analyzed data from the 2018-2022 Medical Expenditure Panel Survey. The sample included 2373 men aged 45-70 who self-identified as non-Hispanic White or Black and had complete data on PSA screening, healthcare perceptions, and demographics. Negative healthcare perceptions were measured using a Health Perceptions Index (HePI), constructed from MEPS items (higher scores reflect more negative perceptions). Higher HePI scores were significantly associated with lower PSA screening rates (p < 0.01). Interaction models indicated that Black men with higher HePI scores were disproportionately less likely to undergo screening. Racial discordance with providers was independently associated with reduced screening likelihood (~10.2 percentage points; p < 0.01). Models including interaction terms (age, race, and discordance) showed that older Black men with high HePI scores and discordant providers were least likely to be screened. PSA screening disparities are shaped by negative healthcare perceptions and racial discordance, particularly among older Black men. Addressing these barriers through culturally tailored education, improved workforce diversity, and strengthened provider-patient relationships may help close screening gaps. These findings highlight the relevance of healthcare system perceptions in understanding screening disparities and may inform future strategies to identify at-risk individuals.

Oligometastatic hormone-sensitive prostate cancer (omHSPC) represents a favorable and potentially curable disease state in which metastasis-directed therapy (MDT) improves outcomes. The combination of MDT and systemic treatment is the next frontier of omHSPC. To review and synthesize current evidence from prospective trials evaluating MDT alone or combined with systemic therapy in synchronous and metachronous omHSPC, and to highlight the evolving role of advanced imaging, genomics, and ongoing efforts in refining treatment strategies. This review synthesizes data from prospective trials, meta-analyses, and ongoing studies assessing MDT in omHSPC. Key trials include STOMP, ORIOLE, EXTEND, RADIOSA, and the X-MET meta-analysis, with emphasis on clinical outcomes and biomarkers RESULTS: In metachronous omHSPC, STOMP and ORIOLE phase II trials demonstrated that MDT significantly improves progression-free survival (PFS) and delays androgen deprivation therapy (ADT) compared to observation. The EXTEND and RADIOSA trials suggest combining MDT with short-term ADT further improves outcomes. The X-MET meta-analysis confirmed benefits in PFS, radiographic PFS, and castration-resistance-free survival with MDT. No randomized trial has yet evaluated MDT with current standard of care ADT + androgen receptor pathway inhibitor (ARPI) therapy, though EXTEND did include a limited subset of patients receiving ARPI. Advanced imaging, especially PSMA-PET, is transforming MDT planning by enabling more accurate lesion detection than conventional imaging. In synchronous omHSPC, the role of MDT remains under investigation in ongoing trials such as TERPS, STAMPEDE2 and START-MET. MDT offers clinical benefit in metachronous omHSPC, particularly when combined with systemic therapy. Advanced imaging and genomic profiling are critical tools for refining patient selection. Most data stem from phase II studies without ADT + ARPI control groups; larger randomized trials are needed to definethe role of MDT in standard practice and optimize personalized care strategies.

The combination of multiparametric magnetic resonance imaging (MP-MRI) and ultrasound-guided fusion biopsy is increasingly recognized as a valuable tool for diagnosing prostate cancer. However, up to 80% of PI-RADS 3 lesions and 50% of PI-RADS 4 lesions are benign. This study evaluates whether lesion echogenicity observed during MRI-ultrasound fusion biopsy is associated with detecting clinically significant prostate cancer (csPCa). In this retrospective analysis (March 2017-February 2022), we reviewed patients who underwent both standard 12-core random biopsies and targeted MP-MRI/US fusion-guided biopsies at our institution. Lesions were categorized as strongly hypoechoic, weakly hypoechoic, or non-hypoechoic based on ultrasound echogenicity. CsPCa was defined as a Gleason score ≥7. Among 222 biopsy patients, 59.3% were diagnosed with PCa, and 68% had csPCa. Of 420 lesions, 19.1% were strongly hypoechoic (45% csPCa), 29.5% were weakly hypoechoic (25% csPCa), and 51.4% were non-hypoechoic (11.8% csPCa) (p < 0.001). Echogenicity improved csPCa detection for PI-RADS ≤ 3 lesions from 7.5% (non-hypoechoic) to 27.5% (strongly hypoechoic), for PI-RADS 4 from 13.1% to 35.1%, and for PI-RADS 5 from 42% to 63.5%. The ROC analysis demonstrated AUCs of 0.6958 for PI-RADS, 0.6929 for echogenicity, and 0.7434 for their combination (all p < 0.001). Lesion echogenicity observed during MRI-ultrasound fusion biopsy enhances csPCa detection and complements PI-RADS scoring. Incorporating echogenicity into risk assessment may improve biopsy decision-making and diagnostic accuracy.

AUA guidelines for shared decision making (SDM) in prostate cancer recommend discussion of five content areas in consultations: (1) cancer severity (tumor risk (TR), pathology results (PR)); (2) life expectancy (LE); (3) cancer prognosis (CP); (4) baseline urinary and erectile function (UF and EF); and (5) treatment side effects (erectile dysfunction (ED), urinary incontinence (UI), and irritative urinary symptoms (LUTS)). However, patient retention of information after the visit and inconsistent risk communication by physicians are barriers to informed SDM. We sought to develop natural language processing (NLP) models based on recorded consultations to provide key information to patients and audit quality of physician communication. We used 50 consultation transcripts to train and validate NLP models to identify sentences related to key concepts. We then tested whether communication quality across entire consultations could be determined by sentences with the highest model-predicted topic concordance in 20 separate consultation transcripts. Our development dataset included 28,927 total sentences, with 75% reserved for training and 25% for internal validation. The Random Forest model had the highest accuracy for identifying topic-concordant sentences, with area under the curve 0.98, 0.94, 0.89, 0.92, 0.84, 0.96, 0.98, 0.97, and 0.99 for TR, PR, LE, CP, UF, EF, ED, UI, and LUTS compared with manual coding across all concepts in the internal validation dataset. In 20 separate consultations, the top 10 model-identified sentences correctly graded communication quality across entire consultations with accuracies of 100%, 90%, 95%, 95%, 80%, 95%, 85%, 100%, and 95% for TR, PR, LE, CP, UF, EF, ED, UI, and LUTS compared with manual coding, respectively. NLP models accurately capture key information and grade quality of physician communication in prostate cancer consultations, providing the foundation for scalable quality assessment of risk communication.

This study aims to evaluate the diagnostic value of machine learning-based MRI imaging in differentiating benign and malignant prostate cancer and detecting clinically significant prostate cancer (csPCa, defined as Gleason score ≥7) using systematic review and meta-analysis methods. Electronic databases (PubMed, Web of Science, Cochrane Library, and Embase) were systematically searched for predictive studies using machine learning-based MRI imaging for prostate cancer diagnosis. Sensitivity, specificity, and area under the curve (AUC) were used to assess the diagnostic accuracy of machine learning-based MRI imaging for both benign/malignant prostate cancer and csPCa. A total of 12 studies met the inclusion criteria, with 3474 patients included in the meta-analysis. Machine learning-based MRI imaging demonstrated good diagnostic value for both benign/malignant prostate cancer and csPCa. The pooled sensitivity and specificity for diagnosing benign/malignant prostate cancer were 0.92 (95% CI: 0.83-0.97) and 0.90 (95% CI: 0.68-0.97), respectively, with a combined AUC of 0.96 (95% CI: 0.94-0.98). For csPCa diagnosis, the pooled sensitivity and specificity were 0.83 (95% CI: 0.77-0.87) and 0.73 (95% CI: 0.65-0.81), respectively, with a combined AUC of 0.86 (95% CI: 0.83-0.89). Machine learning-based MRI imaging shows good diagnostic accuracy for both benign/malignant prostate cancer and csPCa. Further in-depth studies are needed to validate these findings.

Extraprostatic extension (EPE) in prostate cancer (PCa) has implications for nerve-sparing approaches. mpMRI-based nomograms show modest accuracy, highlighting the need for improved predictive models. This study evaluates 18F-DCFPyL prostate-specific membrane antigen (PSMA) positron emission tomography/ computed tomography (PET/CT) for predicting side-specific EPE using maximum standardized uptake value (SUVmax). This single-center cohort study included patients undergoing RALP by a single surgeon (AKT) from January 2022 to September 2024. Baseline variables included demographics, PSA, biopsy, MRI, and PSMA parameters (SUVmax, EPE, SVI). The primary endpoint was side-specific EPE on final pathology. Univariable and multivariable logistic regression identified significant predictors. A nomogram was built based on this. To evaluate model performance, a 1000-iteration bootstrap approach was used to compare (1) the institutional MRI-only 2018 model, (2) an MRI + PSMA Fixed Model, and (3) a retrained MRI + PSMA Model built on each bootstrap sample. Three hundred fifty-five patients were analyzed. EPE was detected in 18.9% by MRI and 5.4% by PSMA PET. Median intraprostatic SUVmax was 11.30. EPE-positive sides were more likely to have MRI/PSMA-detected EPE (p < 0.001), PIRADS 5 lesions (p < 0.001), aggressive biopsy GGG (p < 0.001), higher positive cores (p < 0.001), and greater percent tumor involvement (p < 0.001). Median SUVmax was significantly higher in the EPE group (9.1 vs. 5.4; p < 0.001). Multivariable analysis identified PSA, MRI-detected EPE, GGG, tumor involvement percentage, and SUVmax ≥13 as significant predictors. The PSMA + MRI Fixed Model outperformed the MRI-only model (median AUC: 0.7542 vs. 0.7350) with p < 0.001. Calibration plots showed strong agreement between predicted and observed probabilities, and decision curve analysis demonstrated greater net clinical benefit across relevant thresholds. We developed a nomogram integrating PSMA PET with MRI and clinicopathological variables, outperforming our institutional model. PSMA uptake strongly predicts side-specific EPE, which can enhance preoperative assessment and improve postoperative functional outcomes.

To report active surveillance (AS) outcomes in patients with Grade Group (GG) 2 prostate cancer (PCa) according to the baseline amount of pattern 4 on image-guided biopsy. Our database includes GG2 PCa patients managed with AS in ten European centers. In total, 104 patients were included (median pattern 4: 10%, ranges 5-40). The percentage of pattern 4 was not statistically correlated with upgrading (Spearman, r = 0.073, p = 0.5) or downgrading on confirmatory biopsy (r = -0.049, p = 0.6). The median follow-up was 33 months. In multivariable Cox regression analysis, percentage of pattern 4 was not associated with GG3 upgrading (p = 0.6) or definitive treatment (p = 0.4). Patients with GG2 PCa should not be excluded from AS solely because of grade 4 > 10% when other parameters are otherwise favorable.

Standard surgical options for Benign Prostatic Hyperplasia [BPH], despite their excellent functional outcomes, are associated with multiple side effects and require general/spinal anesthesia and hospitalization. In this scenario, Transperineal Laser Ablation of the Prostate [TPLA] emerged as an ultra-minimally invasive ejaculation-sparing procedure, showing promising functional results, with a good safety profile. This systematic review aimed to provide an overview of the current role of TPLA in clinical practice, focusing on operative setting, safety, and efficacy. Literature search was performed on June 12th, 2024 using PubMed, Embase, and Cochrane Central databases, following the EAU Guidelines Office and the PRISMA statement recommendations. All studies reporting outcomes after TPLA procedures were included. Seventeen studies were included in this systematic review, of which 2 RCTs compared TPLA with TURP, 12 prospective and 3 retrospective non-randomized studies (of which 1 comparing TPLA and Prostatic Artery Embolization [PAE]). All procedures were performed using the same EchoLaserTM system (SoracteLiteTM) (Elesta s.r.l., Calenzano (FI), Italy), however great heterogeneity exists considering inclusion criteria, peri- and post-operative management. Mainly low-grade complications (Clavien-Dindo [CD] Grade ≤ II) were reported, while no major adverse events (CD grade > III) occurred. In all studies TPLA led to a great improvement in urinary function, up to 5 years after the procedure, while not significantly impacting erectile and ejaculatory functions. TPLA showed promising results both in the short- and mid-term, improving urinary function while preserving sexual function and keeping a good safety profile. Since the evidence available is still limited, larger prospective comparative studies are warranted to confirm the efficacy of TPLA and to adequately compare it to standard endoscopic techniques and other minimally invasive surgical treatments.