Supervised machine learning enables non-invasive lesion characterization in primary prostate cancer with [68Ga]Ga-PSMA-11 PET/MRI.

PURPOSE: Risk classification of primary prostate cancer in clinical routine is mainly based on prostate-specific antigen (PSA) levels, Gleason scores from biopsy samples, and tumor-nodes-metastasis (TNM) staging. This study aimed to investigate the diagnostic performance of positron emission tomography/magnetic resonance imaging (PET/MRI) in vivo models for predicting low-vs-high lesion risk (LH) as well as biochemical recurrence (BCR) and overall patient risk (OPR) with machine learning. METHODS: Fifty-two patients who underwent multi-parametric dual-tracer [18F]FMC and [68Ga]Ga-PSMA-11 PET/MRI as well as radical prostatectomy between 2014 and 2015 were included as part of a single-center pilot to a randomized prospective trial (NCT02659527). Radiomics in combination with ensemble machine learning was applied including the [68Ga]Ga-PSMA-11 PET, the apparent diffusion coefficient, and the transverse relaxation time-weighted MRI scans of each patient to establish a low-vs-high risk lesion prediction model (MLH). Furthermore, MBCR and MOPR predictive model schemes were built by combining MLH, PSA, and clinical stage values of patients. Performance evaluation of the established models was performed with 1000-fold Monte Carlo (MC) cross-validation. Results were additionally compared to conventional [68Ga]Ga-PSMA-11 standardized uptake value (SUV) analyses. RESULTS: The area under the receiver operator characteristic curve (AUC) of the MLH model (0.86) was higher than the AUC of the [68Ga]Ga-PSMA-11 SUVmax analysis (0.80). MC cross-validation revealed 89% and 91% accuracies with 0.90 and 0.94 AUCs for the MBCR and MOPR models respectively, while standard routine analysis based on PSA, biopsy Gleason score, and TNM staging resulted in 69% and 70% accuracies to predict BCR and OPR respectively. CONCLUSION: Our results demonstrate the potential to enhance risk classification in primary prostate cancer patients built on PET/MRI radiomics and machine learning without biopsy sampling.

EAU-ESMO consensus statements on the management of advanced and variant bladder cancer-an international collaborative multi-stakeholder effort: under the auspices of the EAU and ESMO Guidelines Committees†.

BACKGROUND: Although guidelines exist for advanced and variant bladder cancer management, evidence is limited/conflicting in some areas and the optimal approach remains controversial. OBJECTIVE: To bring together a large multidisciplinary group of experts to develop consensus statements on controversial topics in bladder cancer management. DESIGN: A steering committee compiled proposed statements regarding advanced and variant bladder cancer management which were assessed by 113 experts in a Delphi survey. Statements not reaching consensus were reviewed; those prioritised were revised by a panel of 45 experts before voting during a consensus conference. SETTING: Online Delphi survey and consensus conference. PARTICIPANTS: The European Association of Urology (EAU), the European Society for Medical Oncology (ESMO), experts in bladder cancer management. OUTCOME MEASUREMENTS AND STATISTICAL ANALYSIS: Statements were ranked by experts according to their level of agreement: 1-3 (disagree), 4-6 (equivocal), 7-9 (agree). A priori (level 1) consensus was defined as ≥70% agreement and ≤15% disagreement, or vice versa. In the Delphi survey, a second analysis was restricted to stakeholder group(s) considered to have adequate expertise relating to each statement (to achieve level 2 consensus). RESULTS AND LIMITATIONS: Overall, 116 statements were included in the Delphi survey. Of these, 33 (28%) statements achieved level 1 consensus and 49 (42%) statements achieved level 1 or 2 consensus. At the consensus conference, 22 of 27 (81%) statements achieved consensus. These consensus statements provide further guidance across a broad range of topics, including the management of variant histologies, the role/limitations of prognostic biomarkers in clinical decision making, bladder preservation strategies, modern radiotherapy techniques, the management of oligometastatic disease and the evolving role of checkpoint inhibitor therapy in metastatic disease. CONCLUSIONS: These consensus statements provide further guidance on controversial topics in advanced and variant bladder cancer management until a time where further evidence is available to guide our approach.

68Ga-PSMA 11 ligand PET imaging in patients with biochemical recurrence after radical prostatectomy - diagnostic performance and impact on therapeutic decision-making.

OBJECTIVE: To evaluate the diagnostic performance of [68Ga]Ga-PSMAHBED-CC conjugate 11 positron emission tomography (PSMA-PET) in the early detection of metastases in patients with biochemical recurrence (BCR) after radical prostatectomy (RP) for clinically non-metastatic prostate cancer, to compare it to CT/MRI alone and to assess its impact on further therapeutic decisions. MATERIAL AND METHODS: We retrospectively assessed 117 consecutive hormone-naïve BCR patients who had 68Ga-PSMA 11 PET/CT (n = 46) or PET/MRI (n = 71) between May 2014 and January 2017. BCR was defined as two PSA rises above 0.2 ng/ml. Two dedicated uro-oncological imaging experts (radiology/nuclear medicine) reviewed separately all images. All results were presented in a blinded sequential fashion to a multidisciplinary tumorboard in order to assess the influence of PSMA-PET imaging on decision-making. RESULTS: The median time from RP to BCR was 36 months (IQR 16-72). Overall, 69 (59%) patients received postoperative radiotherapy. Median PSA level at the time of imaging was 1.04 ng/ml (IQR 0.58-1.87). PSMA-positive lesions were detected in 100 (85.5%) patients. Detection rates were 65% for a PSA value of 0.2 to <0.5 ng/ml, 85.7% for 0.5 to <1, 85.7% for 1 to <2 and 100% for ≥2. PSMA-positive lesions could be confirmed by either histology (16%), PSA decrease in metastasis-directed radiotherapy (45%) or additional information in diffusion-weighted imaging when PET/MRI was performed (18%) in 79% of patients. PSMA-PET detected lesions in 67 patients (57.3%) who had no suspicious correlates according to the RECIST 1.1 criteria on MRI or CT. PSMA-PET changed therapeutic decisions in 74.6% of these 67 patients (p < 0.001), with 86% of them being considered for metastases-directed therapies. CONCLUSIONS: We confirm the high performance of PSMA-PET imaging for the detection of disease recurrence sites in patients with BCR after RP, even at relatively low PSA levels. Moreover, it adds significant information to standard CT/MRI, changing treatment strategies in a significant number of patients.