Prostate Region-Wise Imaging Biomarker Profiles for Risk Stratification and Biochemical Recurrence Prediction

SIMPLE SUMMARY: In prostate cancer (PCa), an accurate patient risk stratification, as well as the awareness of a possible biochemical recurrence (BCR) event, are crucial to individualize treatment decisions. Magnetic resonance imaging (MRI) is commonly used in the diagnosis, risk stratification, localization, and staging of PCa. Likewise, radiomics, which allows the extraction of quantitative parameters from medical images, has attracted increased attention in recent years. A combination of both strategies may be useful for predicting important clinical outcomes in these patients. In patients with localized PCa receiving neoadjuvant androgen deprivation therapy and radiotherapy, we explore the existence of putative prostate region-wise imaging biomarker (radiomic, diffusion, and/or perfusion features) profiles extracted from MRIs in order to discriminate patients according to their risk or the appearance of BCR 10 years after diagnosis, as well as to determine their predictive value alone or in combination with clinical variables. ABSTRACT: Background: Identifying prostate cancer (PCa) patients with a worse prognosis and a higher risk of biochemical recurrence (BCR) is essential to guide treatment choices. Here, we aimed to identify possible imaging biomarker (perfusion/diffusion + radiomic features) profiles extracted from MRIs that were able to discriminate patients according to their risk or the occurrence of BCR 10 years after diagnosis, as well as to evaluate their predictive value with or without clinical data. Methods: Patients with localized PCa receiving neoadjuvant androgen deprivation therapy and radiotherapy were retrospectively evaluated. Imaging features were extracted from MRIs for each prostate region or for the whole gland. Univariate and multivariate analyses were conducted. Results: 128 patients (mean [range] age, 71 [50–83] years) were included. Prostate region-wise imaging biomarker profiles mainly composed of radiomic features allowed discriminating risk groups and patients experiencing BCR. Heterogeneity-related radiomic features were increased in patients with worse prognosis and with BCR. Overall, imaging biomarkers profiles retained good predictive ability (AUC values superior to 0.725 in most cases), which generally improved when clinical data were included (particularly evident for the prediction of the BCR, with AUC values ranging from 0.841 to 0.877 for combined models and sensitivity values above 0.960) and when models were built per prostate region vs. the whole gland. Conclusions: Prostate region-aware imaging profiles enable identification of patients with worse prognosis and with a higher risk of BCR, retaining higher predictive values when combined with clinical variables.