Farshad Moradi

Background: PSMA PET radiomics is a promising tool for primary prostate cancer (PCa) characterisation. However, small single-centre studies and lack of external validation hinder definitive conclusions on the potential of PSMA PET radiomics in the initial workup of PCa. We aimed to validate a radiomics signature in a larger internal cohort and in an external cohort from a separate centre. Methods: One hundred and twenty-seven PCa patients were retrospectively enrolled across two independent hospitals. The first centre (IRCCS San Raffaele Scientific Institute, Centre 1) contributed 62 [⁶⁸Ga]Ga-PSMA-11 PET scans, 20 patients classified as low-grade (ISUP grade < 4), and 42 as high-grade (ISUP grade ≥ 4). The second centre (Stanford University Hospital, Centre 2) provided 65 [⁶⁸Ga]Ga-PSMA-11 PET scans, and 49 low-grade and 16 high-grade patients. A radiomics model previously generated in Centre 1 was tested on the two cohorts separately and afterward on the entire dataset. Then, we evaluated whether the radiomics features selected in the previous investigation could generalise to new data. Several machine learning (ML) models underwent training and testing using 100-fold Monte Carlo cross-validation, independently at both Centre 1 and Centre 2, with a 70–30% train–test split. Additionally, models were trained in one centre and tested in the other, and vice versa. Furthermore, data from both centres were combined for training and testing using Monte Carlo cross-validation. Finally, a new radiomics signature built on this bicentric dataset was proposed. Several performance metrics were computed. Results: The previously generated radiomics signature resulted in an area under the receiver operating characteristic curve (AUC) of 80.4% when tested on Centre 1, while it generalised poorly to Centre 2, where it reached an AUC of 62.7%. When the whole cohort was considered, AUC was 72.5%. Similarly, new ML models trained on the previously selected features yielded, at best, an AUC of 80.9% for Centre 1 and performed at chance for Centre 2 (AUC of 49.3%). A new signature built on this bicentric dataset reached, at best, an average AUC of 91.4% in the test set. Conclusions: The satisfying performance of radiomics models when used in the original development settings, paired with the poor performance otherwise observed, emphasises the need to consider centre-specific factors and dataset characteristics when developing radiomics models. Combining radiomics datasets is a viable strategy to reduce such centre-specific biases, but external validation is still needed.

Prostate-specific membrane antigen (PSMA) PET offers superior accuracy to other imaging modalities in initial staging of prostate cancer and is more likely to affect management. We examined the prognostic value of ⁶⁸Ga-PSMA-11 uptake in primary lesion and presence of metastatic disease on PET in newly diagnosed prostate cancer patients prior to initial therapy. Methods: In a prospective study from April 2016 to December 2020, ⁶⁸Ga-PSMA-11 PET/MRI was done in men with new diagnosis of intermediate or high-grade prostate cancer who were candidates for prostatectomy. Patients were followed up after initial therapy for up to 5 years. We examined the Kendall correlation between PET (intense uptake in primary lesion and presence of metastatic disease) and clinical and pathologic findings (grade group, extraprostatic extension, nodal involvement) relevant for risk stratification, and examined the relationship between PET findings and outcome using Kaplan–Meier analysis. Results: Seventy-three men, 64.0±6.3 years of age were imaged. Seventy-two had focal uptake in prostate and in 20 (27%), PSMA-avid metastatic disease was identified. Uptake correlated with grade group and prostate-specific antigen (PSA). Presence of PSMA metastasis correlated with grade group and pathologic nodal stage. PSMA PET had higher per-patients positivity than nodal dissection in patients with only 5-15 nodes removed (8/41 vs. 3/41) but lower positivity if more than 15 nodes were removed (13/21 vs. 10/21). High uptake in primary (SUV_max>12.5, P = .008) and presence of PSMA metastasis (P = .013) were associated with biochemical failure, and corresponding hazard ratios for recurrence within 2-years (4.93 and 3.95, respectively) were similar or higher than other clinicopathologic prognostic factors. Conclusions:⁶⁸Ga-PSMA-11 PET can risk stratify patients with intermediate or high-grade prostate cancer prior to prostatectomy based on degree of uptake in prostate and presence of metastatic disease.

Opinion statement Neuroendocrine tumors (NETs) are a heterogenous group of neoplasms characterized by varied biological hallmarks and behavior, ranging from indolent to aggressive. For many decades, somatostatin analogues and few targeted therapies were available for NETs and these therapies had minimal response rates. However, there have been a number of recent treatment advances. Peptide receptor radionuclide therapy (PRRT) is a novel approach to treatment of NETs and has changed the landscape of treatment for NETs. It is a form of targeted therapy in which a radiolabeled somatostatin analogue delivers radiation specifically to tumor cells expressing the somatostatin receptor.