Search

The effect of radical cystectomy (RC) on cancer-specific mortality (CSM) is unclear in non-metastatic sarcomatoid bladder cancer (SBC) patients. We aimed to test the benefit of RC in SBC, and to perform a direct comparison vs urothelial bladder cancer (UCB).Within the Surveillance, Epidemiology, and End Results database (SEER 2001-2018) all non-metastatic SBC and UBC patients were identified. Endpoint of interest was CSM. Propensity score matching (PSM), cumulative incidence plots, competing risks regression (CRR) analyses, three-months landmark analyses, and sensitivity analyses were performed. All results were stratified according to organ-confined (OC: TOf 554 SBC patients, 49 vs 51% harbored OC vs NOC stages. Of 47,741 UBC patients, 62 vs 38% harbored OC vs NOC stages. RC rates were 33 vs 67% in OC vs NOC-SBC patients, and 40 vs 60% in OC vs NOC-UBC patients. After 1:1 PSM, comparison between RC vs no-RC was performed in OC-SBC (67 patients per group), OC-UBC (7611 patients per group), NOC-SBC (63 patients per group), and NOC-UBC patients (4644 patients per group). CRR hazard ratios associated with RC vs no-RC were 0.37 (p 0.001) in OC-SBC vs 0.45 (p 0.001) in OC-UBC, and 0.56 (p = 0.01) in NOC-SBC vs 0.68 (p 0.001) in NOC-UBC. These results were replicated in sensitivity and landmark analyses.The protective effect of RC vs no-RC is stronger in SBC than UBC patients, regardless of OC vs NOC stages.

Although multiparametric magnetic resonance imaging (MRI) has high sensitivity, its lower specificity leads to a high prevalence of false-positive lesions requiring biopsy.To develop and externally validate a scoring system for MRI-detected Prostate Imaging Reporting and Data System (PIRADS)/Likert ≥3 lesions containing clinically significant prostate cancer (csPCa).The multicentre Rapid Access to Prostate Imaging and Diagnosis (RAPID) pathway included 1189 patients referred to urology due to elevated age-specific prostate-specific antigen (PSA) and/or abnormal digital rectal examination (DRE); April 27, 2017 to October 25, 2019.Visual-registration or image-fusion targeted and systematic transperineal biopsies for an MRI score of ≥4 or 3 + PSA density ≥0.12 ng/ml/ml.Fourteen variables were used in multivariable logistic regression for Gleason ≥3 + 4 (primary) and Gleason ≥4 + 3, and PROMIS definition 1 (any ≥4 + 3 or ≥6 mm any grade; secondary). Nomograms were created and a decision curve analysis (DCA) was performed. Models with varying complexity were externally validated in 2374 patients from six international cohorts.The five-item Imperial RAPID risk score used age, PSA density, prior negative biopsy, prostate volume, and highest MRI score (corrected c-index for Gleason ≥3 + 4 of 0.82 and 0.80-0.86 externally). Incorporating family history, DRE, and Black ethnicity within the eight-item Imperial RAPID risk score provided similar outcomes. The DCA showed similar superiority of all models, with net benefit differences increasing in higher threshold probabilities. At 20%, 30%, and 40% of predicted Gleason ≥3 + 4 prostate cancer, the RAPID risk score was able to reduce, respectively, 11%, 21%, and 31% of biopsies against 1.8%, 6.2%, and 14% of missed csPCa (or 9.6%, 17%, and 26% of foregone biopsies, respectively).The Imperial RAPID risk score provides a standardised tool for the prediction of csPCa in patients with an MRI-detected PIRADS/Likert ≥3 lesion and can support the decision for prostate biopsy.In this multinational study, we developed a scoring system incorporating clinical and magnetic resonance imaging characteristics to predict which patients have prostate cancer requiring treatment and which patients can safely forego an invasive prostate biopsy. This model was validated in several other countries.

Combination systemic therapies have become the standard for metastatic hormone-sensitive prostate cancer (mHSPC). However, the effect of age on oncologic outcomes remains unknown. Our aim was to perform a systematic review, meta-analysis, and network meta-analysis (NMA) on the effect of chronological age on overall survival (OS) in patients treated with combination therapies for mHSPC.We searched the PubMedWe included nine RCTs with a total of 9183 patients. Younger and older men constituted 51% and 49% of included patients, respectively. Docetaxel plus ADT significantly improved OS among both older (HR 0.79, 95% CI 0.63-0.99, p = 0.04) and younger patients (HR 0.79, 95% CI 0.69-0.90, p 0.001) with no differences according to age. ARSI plus ADT improved OS in older (HR 0.72, 95% CI 0.64-0.80, p 0.001) and younger (HR 0.58, 95% CI 0.51-0.66, p 0.001) patients; younger patients did benefit more (p = 0.02). On NMA treatment ranking, triplet therapy showed the highest probability of OS benefit irrespective of age group; in older patients, the benefit of triplet therapy compared to doublet was less expressed.Patients with mHSPC benefit from combination systemic therapies irrespective of age; the effect is, however, more evident in younger patients. Chronological age alone seems not to be a selection criteria for the administration of combination systemic therapies.

Purpose: The PURE-01 study (NCT02736266) pioneered the neoadjuvant immune-checkpoint inhibitor (ICI) therapy before radical cystectomy (RC) in patients with muscle-invasive urothelial bladder carcinoma (MIBC). We herein present the survival outcomes after a median follow-up of three years. Patients and Methods: The intention-to-treat (ITT) population included 155 patients. Event-free survival (EFS) was defined as the time from pembrolizumab initiation until radiographic disease progression precluding RC, initiation of neoadjuvant chemotherapy, recurrence after RC, or death. Further outcomes were recurrence-free survival (RFS) post-RC and overall survival (OS). Multivariable Cox regression analyses for EFS were performed. Kaplan–Meier analyses compared EFS outcomes according with baseline programmed cell-death-ligand-1 (PD-L1) combined positive score (CPS) and according to the molecular subtypes. Results: After a median (interquartile range, IQR) follow-up of 39 (30–47) months, 36-month EFS and OS were 74.4% [95% confidence interval (CI), 67.8–81.7] and 83.8% (95% CI, 77.8–90.2) in the ITT population, respectively. Overall, 143 (92.3%) patients underwent RC. Within the cohort of patients who did not receive additional chemotherapy (N = 125), 36-month RFS was 96.3% (95% CI, 91.6–100) for patients achieving a ypT0N0, 96.1% (95% CI, 89–100) for ypT1/a/isN0, 74.9% (95% CI, 60.2–93) for ypT2–4N0, and 58.3% (95% CI, 36.2–94.1) for ypTanyN1–3 response. EFS was significantly stratified among PD-L1 tertiles (lower tertile: 59.7% vs. medium tertile: 76.7% vs. higher tertile: 89.8%, P = 0.0013). The claudin-low and basal/squamous subtypes displayed the lowest rates of events. Conclusions: At a median follow-up of three years, PURE-01 results further confirm the sustained efficacy of neoadjuvant pembrolizumab before RC. PD-L1 expression was the strongest predictor of sustained response post-RC.

The appropriate surveillance protocol after radical nephroureterectomy (RNU) for upper tract urothelial carcinoma (UTUC) is still poorly addressed.To evaluate the appropriate intensity and duration of oncologic surveillance following RNU, according to a prior history of bladder cancer (BCa).We identified 1378 high-risk UTUC patients, according to the European Association of Urology (EAU) guidelines, from a prospectively maintained database involving eight European referral centers. Surveillance protocol was based on cystoscopies and cross-sectional imaging, as per the EAU guidelines.First, we evaluated the noncumulative risk of bladder and other-site recurrences (including distant metastasis and locoregional relapse) against the follow-up time points, as suggested by the current EAU guidelines. Second, in an effort to identify the time points when the risk of other-cause mortality (OCM) exceeded that of recurrence and follow-up might be discontinued, we relied on adjusted Weibull regression.The median follow-up was 4 yr. A total of 427 and 951 patients with and without a prior BCa history, respectively, were considered. At 5-yr, the time point after which cystoscopies should be performed semiannually, the bladder recurrence risk was 10%; at 4 yr, the bladder recurrence risk was 13%. At 2 yr, the time point after which imaging should be obtained semiannually, the nonbladder recurrence risk was 42% in case of nonprior BCa and 47% in case of prior BCa; at 4 yr, the nonbladder recurrence risk was 23%. Among patients without a prior BCa history, individuals younger than 60 yr should continue both cystoscopies and imaging beyond 10 yr from RNU, 70-79-yr-old patients should continue only imaging beyond 10 yr, while patients older than 80 yr might discontinue oncologic surveillance because of an increased risk of OCM. Limitations include the fact that patients were treated and surveilled over a relatively long period of time.We suggest intensifying the frequency of imaging to semiannual till the 4th year after RNU, the time point after which the risk of recurrence was almost halved. Cystoscopies could be obtained annually from the 4th year given a similar risk of recurrence at 4 and 5 yr after RNU. Oncologic surveillance could be discontinued in some cases in the absence of a prior BCa history.In this study, we propose a revision of the current guidelines regarding surveillance protocols following radical nephroureterectomy. We also evaluated whether oncologic surveillance for high-risk upper tract urothelial carcinoma could be discontinued and, if so, in what circumstances.

The numbers needed to image to identify pelvic lymph node and/or distant metastases in newly diagnosed prostate cancer (PCa) patients according to risk level are unknown.Relying on Surveillance, Epidemiology, and End Results (2010-2016), we tabulated rates and proportions of patients with (a) lymph node or (b) distant metastases according to National Comprehensive Cancer Network (NCCN) risk level and calculated the number needed to image (NNI) for both endpoints. Multivariable logistic regression analyses were performed.Of 145,939 newly diagnosed PCa patients assessable for analyses of pelvic lymph node metastases (cN1), 4559 (3.1%) harbored cN1 stage: 13 (0.02%), 18 (0.08%), 63 (0.3%), 512 (2.8%), and 3954 (14.9%) in low, intermediate favorable, intermediate unfavorable, high, and very high-risk levels. These resulted in NNI of 4619, 1182, 319, 35, and 7, respectively. Of 181,109 newly diagnosed PCa patients assessable for analyses of distant metastases (M1Our observations perfectly validated the NCCN recommendations for imaging in newly diagnosed high and very high-risk PCa patients. However, in unfavorable intermediate-risk PCa patients, in whom bone and soft tissue imaging is recommended, the NNI might be somewhat elevated to support routine imaging in clinical practice.

Novel immune checkpoint inhibitors hold promise for non-muscle-invasive bladder cancer. Cooperation between urologists and other multidisciplinary bladder cancer specialists can surmount the challenges involved in using these agents in bladder-sparing approaches. This strategy could deliver a new era of comprehensive evaluation and multimodal treatment for this patient population.

Multiparametric MRI (mpMRI) has demonstrated high diagnostic accuracy for clinically significant PCa (csPCa). However, the accuracy of this test in men that received a previous prostatic surgery is still controversial. We aimed at assessing the effect of previous prostatic surgery on the detection of csPCa in a tertiary referral center.We relied on a cohort of 311 men with a positive mpMRI (prostate imaging - reporting and data system [PI-RADS] ≥ 3) who underwent a targeted (TBx) plus concomitant systematic random biopsy (SBx) at a single tertiary referral center between 2017 and 2020. The study outcome was to compare the detection of csPCa (Gleason score ≥ 3 + 4) between the two groups (no previous prostate surgery [Group 1] vs. previous prostate surgery [Group 2]). Multivariable logistic regression analysis (MVA) was used to assess the relationship between previous prostate surgery and the detection of csPCa at TBx, after taking into account potential clinical confounders.Overall, 24 (8%) patients received a previous prostate surgery before undergoing mpMRI. Median prostate-specific antigen density was 0.15 versus 0.08 ng/ml/cc, in Group 1 versus 2, respectively. The most frequent finding at mpMRI was in Group 1 versus 2, PI-RADS 4 (55%) versus PI-RADS 3 and 4 (42% each). The majority of patients were biopsy naïve in both Groups 1 (66%) and 2 (71%). The overall detection of csPCa in Group 1 versus 2 was 83% versus 75%, respectively. Differently, the detection of csPCa at TBx in Groups 1 versus 2 was 76% versus 71%, respectively. At MVA, previous prostate surgery (odds ratio: 0.65; p = 0.02) was significantly associated with lower csPCa detection at TBx, after accounting for potential confounders.The presence of previous prostate surgery significantly decreases the accuracy of mpMRI in detecting csPCa. These results should be taken into account when assessing patients with a history of prostatic surgery and a suspicious lesion at mpMRI, to better select those who might avoid an unnecessary biopsy.

To determine whether use of neoadjuvant chemotherapy (NAC) is associated with a higher risk of post-operative complications following radical cystectomy (RC) for bladder cancer (BCa).We retrospectively reviewed records of patients undergoing RC for non-metastatic urothelial BCa at 13 tertiary care centres from 2007-2019. Patients who received NAC ('NAC + RC' group) were compared with those who underwent upfront RC ('RC alone' group) for intra-operative variables, incidence of post-operative complications as per the Clavien-Dindo classification (CDC) and rates of re-admission and re-intervention. Multivariable logistic regression analysis was performed to determine predictors of CDC overall and CDC major (grade III-V) complications. We also analysed the trend of NAC utilization over the study period.Of the 3113 patients included, 968 (31.1%) received NAC while the remaining 2145 (68.9%) underwent upfront RC for BCa. There was no significant difference between the NAC + RC and RC alone groups with regards to 30-day CDC overall (53.2% vs 54.6%, p = 0.4) and CDC major (15.5% vs 16.5%, p = 0.6) complications. The two groups were comparable for the rate of surgical re-intervention (14.6% in each group) and re-hospitalization (19.6% in NAC + RC vs 17.9% in RC alone, p = 0.2%) at 90 days. On multivariable regression analysis, NAC use was not found to be a significant predictor of 90-day CDC overall (OR 1.02, CI 0.87-1.19, p = 0.7) and CDC major (OR 1.05, CI 0.87-1.26, p = 0.6) complications. We also observed that the rate of NAC utilization increased significantly (p 0.001) from 11.1% in 2007 to 41.2% in 2019, reaching a maximum of 48.3% in 2018.This large multicentre analysis with a substantial rate of NAC utilization showed that NAC use does not lead to an increased risk of post-operative complications following RC for BCa. This calls for increasing NAC use to allow patients to avail of its proven oncologic benefit.

Contemporary seminal vesicle invasion (SVI) rates in National Cancer Comprehensive Network (NCCN) high-risk prostate cancer (PCa) patients are not well known but essential for treatment planning. We examined SVI rates according to individual patient characteristics for purpose of treatment planning.Within Surveillance, Epidemiology, and End Results (SEER) database (2010-2015), 4975 NCCN high-risk patients were identified. In the development cohort (SEER geographic region of residence: South, North-East, Mid-West, n = 2456), we fitted a multivariable logistic regression model predicting SVI. Its accuracy, calibration, and decision curve analyses (DCAs) were then tested versus previous models within the external validation cohort (SEER geographic region of residence: West, n = 2519).Out of 4975 patients, 28% had SVI. SVI rate ranged from 8% to 89% according to clinical T stage, prostate-specific antigen (PSA), biopsy Gleason Grade Group and percentage of positive biopsy cores. In the development cohort, these variables were independent predictors of SVI. In the external validation cohort, the current model achieved 77.6% accuracy vs 73.7% for Memorial Sloan Kettering Cancer Centre (MSKCC) vs 68.6% for Gallina et al. Calibration was better than for the two alternatives: departures from ideal predictions were 6.0% for the current model vs 9.8% for MSKCC vs 38.5% for Gallina et al. In DCAs, the current model outperformed both alternatives. Finally, different nomogram cutoffs allowed to discriminate between low versus high SVI risk patients.More than a quarter of NCCN high-risk PCa patients harbored SVI. Since SVI positivity rate varies from 8% to 89%, the currently developed model offers a valuable approach to distinguish between low and high SVI risk patients.

Background: Pathological stage and grade of renal pelvis urothelial carcinoma (RPUC) are difficult to estimate before radical nephroureterectomy (RNU). Objective: To examine tumor size as an independent predictor of muscle-invasive and/or non–organ-confined rates of RPUC at RNU. Design, setting, and participants: Within the Surveillance, Epidemiology and End Results (SEER) database (2004–2016), we identified nonmetastatic RPUC at RNU. Outcome measurements and statistical analysis: First, we examined stage and grade distributions. Second, two separate univariable and subsequent multivariable logistic regression models (LRMs) were fitted to test the association between tumor size and the rate of (1) muscle-invasive or higher (pT2–4N0–2) and (2) non–organ-confined (pT3–4N0–2) RPUC at RNU. Results and limitations: Of 4657 patients, 3052 (65.5%) had pT2–4N0–2 and 2382 (51.2%) pT3–4N0–2 RPUC at RNU. The median tumor size was 3.7 cm (interquartile range 2.5–5.0). The high-grade RPUC rate ranged from 71.1% to 87.2% (p < 0.001) among SEER registries. Conversely, no differences were recorded for stage (p > 0.05) or tumor size (p = 0.1) across all registries. Rates of pT2–4N0–2 and pT3–4N0–2 RPUC increased with tumor size. Specifically, for tumor size intervals from 0.1–1.0 cm to 9.1–10.0 cm, the pT2–4N0–2 rate ranged from 45% to 83% and the pT3–4N0–2 rate ranged from 23% to 75%, respectively (both p < 0.001). In multivariable LRMs, tumor size (in 1-cm units) was an independent predictor of pT2–4N0–2 (odds ratio [OR] 1.25; p < 0.001) and pT3–4N0–2 (OR 1.30; p < 0.001) disease at RNU. Conclusions: Tumor size is a key predictor of muscle-invasive or non–organ-confined RPUC. Greater tumor size directly and virtually linearly predicts a higher rate of invasive or non–organ-confined RPUC at RNU. Patient summary: For patients with cancer in urinary tract cells lining the kidney, larger tumor size predicts worse stage of the disease at surgery.

Background: Prospective data collection for perioperative outcomes might increase awareness of surgical results obtained for patients with prostate cancer (PCa) undergoing robot-assisted radical prostatectomy (RARP). This would prompt the implementation of measures aimed at reducing the risk of adverse outcomes. Objective: To assess the efficacy of an audit and feedback process aimed at identifying the most common complications after RARP and at implementing measures to improve outcomes. Design, setting, and participants: Overall, 415 patients treated with RARP by a high-volume surgeon were included. Perioperative outcomes for 187 patients treated between September 2016 and December 2017 were prospectively collected at 30 d according to the European Association of Urology guideline recommendations (group 1). An audit and feedback process was implemented in January 2018 whereby the most common complication (anastomotic leak) was identified and measures aimed at improving outcomes (changes in the anastomotic technique) were implemented. The outcomes for group 1 were then compared to 228 patients treated after implementation of the modified surgical technique (group 2). Surgical procedure: A novel technique for posterior reconstruction and urethrovesical anastomosis was introduced. Measurements: Perioperative outcomes included blood loss, operative time, length of stay, and 30-d postoperative complications. Logistic regression models tested the effect of the novel surgical technique on anastomotic leaks. Results and limitations: Overall, 97 patients (23%) experienced postoperative complications at 30 d. The rate of anastomotic leaks was significantly lower in group 2 compared to group 1 (3.1% vs 9.6%; p < 0.01). Similarly, overall and Clavien-Dindo grade ≥2 complication rates were lower in group 2 versus group 1 (17% vs 31%, and 6% vs 20%; both p ≤ 0.001). In multivariable analyses, treatment after implementation of changes in the anastomotic technique independently predicted a lower risk of complications (odds ratio [OR] 0.58, 95% confidence interval [CI] 0.38–0.89) and of anastomotic leaks (OR 0.43, 95% CI 0.17–0.97). The lack of randomization represents the main limitation. Conclusions: Implementation of changes in the urethrovesical anastomosis technique arising from increased awareness of surgical outcomes reduced the risk of anastomotic leaks. These findings highlight the importance of audit and feedback processes using a standardized method for reporting surgical morbidity. Patient summary: Increased awareness of surgical outcomes prompted us to change our technique for connecting the bladder to the urethra during robot-assisted surgery to remove the prostate in patients with prostate cancer. These changes resulted in significant improvements in surgical outcomes.

Background: Evidence-practice gaps exist in urology. We previously surveyed European Association of Urology (EAU) guidelines for strong recommendations underpinned by high-certainty evidence that impact patient experience for which practice variations were suspected. The recommendation “Do not offer neoadjuvant androgen deprivation therapy (ADT) before surgery for patients with prostate cancer” was prioritised for further investigation. ADT before surgery is neither clinically effective nor cost effective and has serious side effects. The first step in improving implementation problems is to understand their extent. A clear picture of practice regarding ADT before surgery across Europe is not available. Objective: To assess current ADT use before prostate cancer surgery in Europe. Design, setting, and participants: This was an observational cross-sectional study. We retrospectively audited recent ADT practices in a multicentre international setting. We used nonprobability purposive sampling, aiming for breadth in terms of low- versus high-volume, academic, versus community and public versus private centres. Outcome measurements and statistical analysis: Our primary outcome was adherence to the ADT recommendation. Descriptive statistics and a multilevel model were used to investigate differences between countries across different factors (volume, centre type, and funding type). Subgroup analyses were performed for patients with low, intermediate, and high risk, and for those with locally advanced prostate cancer. We also collected reasons for nonadherence. Results and limitations: We included 6598 patients with prostate cancer from 187 hospitals in 31 countries from January 1, 2017 to May 1, 2020. Overall, nonadherence was 2%, (range 0–32%). Most of the variability was found in the high-risk subgroup, for which nonadherence was 4% (range 0–43%). Reasons for nonadherence included attempts to improve oncological outcomes or preoperative tumour parameters; attempts to control the cancer because of long waiting lists; and patient preference (changing one's mind from radiotherapy to surgery after neoadjuvant ADT had commenced or feeling that the side effects were intolerable). Although we purposively sampled for variety within countries (public/private, academic/community, high/low-volume), a selection bias toward centres with awareness of guidelines is possible, so adherence rates may be overestimated. Conclusions: EAU guidelines recommend against ADT use before prostate cancer surgery, yet some guideline-discordant ADT use remains at the cost of patient experience and an additional payer and provider burden. Strategies towards discontinuation of inappropriate preoperative ADT use should be pursued. Patient summary: Androgen deprivation therapy (ADT) is sometimes used in men with prostate cancer who will not benefit from it. ADT causes side effects such as weight gain and emotional changes and increases the risk of cardiovascular disease, diabetes, and osteoporosis. Guidelines strongly recommend that men opting for surgery should not receive ADT, but it is unclear how well the guidance is followed. We asked urologists across Europe how patients in their institutions were treated over the past few years. Most do not use ADT before surgery, but this still happens in some places. More research is needed to help doctors to stop using ADT in patients who will not benefit from it.

Localized prostate cancer is composed of multiple spatially distinct tumors with significant inter- and intra-tumoral molecular heterogeneity. This genomic diversity gives rise to many competing subclones that may drive the biological trajectory of the disease. Previous large scale sequencing efforts have focused on the evolutionary process of metastatic prostate cancer, revealing a potential clonal progression to castration resistance. However, the clonal origin of synchronous lymph node (LN) metastases in primary disease is still unknown. Here, we performed multi-region, targeted DNA/RNA next generation sequencing (NGS) and constructed phylogenetic trees from 14 patients with LN metastasis (88 primary prostate cancer foci with 23 synchronous LN metastases) to better define the molecular features of primary disease most likely to spread to the LNs. Of eight primary prostate cancer cases with evidence of extra-prostatic extension (EPE), phylogenetic analysis supported this region as the likely source of LN metastasis in four cases. In two patients with organ-confined disease and LN metastasis, sub-clonal seeding and clonal evolution was observed, with LN metastasis likely arising from a Gleason Grade Group 5 focus. Cribriform pattern was observed in seven patients in both LNs and the primary tumor foci most clonally related. Driver alterations, either oncogenic gene fusions or somatic mutations (e.g., CDK12, FOXA1), were shared among primary tumor and LN metastatic foci. Collectively, we found that a combination of histopathologic and molecular factors, including tumor grade, EPE, cellular morphology (e.g., cribriform pattern), and oncogenic genomic alterations were associated with synchronous LN metastasis. More work is needed to better define the molecular features of primary prostate cancer foci most likely to give rise to metastasis to improve risk stratification, guide treatment allocation, and inform novel therapeutic strategies.

INTRODUCTION Radiomics has been proven effective for the characterisation of primary prostate cancer (PCa).1,2 However, the limited interpretability of the proposed models represents one of the major limitations in this field.3,4 This study investigated 68Ga-prostate-specific membrane antigen (PSMA) PET radiomics for the prediction of post-surgical International Society of Urological Pathology (ISUP) grade in patients with primary PCa, ensuring model interpretability. MATERIALS AND METHODS Forty-seven patients with PCa were examined with 68Ga-PSMA PET at the authors’ institution. Those patients were enrolled in this study prior to radical prostatectomy. Images were acquired using either PET/MRI or PET/CT. ISUP grade was available at both biopsy and radical prostatectomy for all patients. A radiologist manually segmented the whole prostate on PET images using the co-registered CT or MRI for anatomical localisation on 3D Slicer software (Brigham and Women’s Hospital, Boston, Massachusetts, USA).5 The whole prostate was used as volume of interest (VOI) to avoid the limitations of radiomics for small volumes.6 VOIs were normalised, resampled, and discretised. A total of 103 image biomarker standardisation initiative-compliant, radiomic features (RF) were extracted using PyRadiomics (Python Software Foundation, Beaverton, Oregon, USA).7 RFs were harmonised with the ComBat method8 to control for the scanner effect, and selected using the minimum redundancy maximum relevance algorithm. Combinations of the four most relevant RFs were used to train 12 radiomics machine learning models for the prediction of post-surgical ISUP ≥4 versus ISUP 0.05). See Table 1 for a detailed report of all the generated models’ performance. CONCLUSION These findings support the role of 68Ga-PSMA PET radiomics for the accurate and non-invasive prediction of post-surgical ISUP grade. Future multicentre studies will be needed to establish with certainty the accuracy and reproducibility of the radiomic signature proposed here.