Radiomics is an emerging field of image analysis with potential applications in patient risk stratification. This study developed and evaluated machine learning models using quantitative radiomic features extracted from multiparametric magnetic resonance imaging (mpMRI) to detect and classify prostate cancer (PCa). In total, 191 patients that underwent prostatic mpMRI and combined targeted and systematic fusion biopsy were retrospectively included. Segmentations of the whole prostate glands and index lesions were performed manually in apparent diffusion coefficient (ADC) maps and T2-weighted MRI. Radiomic features were extracted from regions corresponding to the whole prostate gland and index lesion. The best performing combination of feature setup and classifier was selected to compare its predictive ability of the radiologist’s evaluation (PI-RADS), mean ADC, prostate specific antigen density (PSAD) and digital rectal examination (DRE) using receiver operating characteristic (ROC) analysis. Models were evaluated using repeated 5-fold cross-validation and a separate independent test cohort. In the test cohort, an ensemble model combining a radiomics model, with models for PI-RADS, PSAD and DRE achieved high predictive AUCs for the differentiation of (i) malignant from benign prostatic lesions (AUC = 0.889) and of (ii) clinically significant (csPCa) from clinically insignificant PCa (cisPCa) (AUC = 0.844). Our combined model was numerically superior to PI-RADS for cancer detection (AUC = 0.779; p = 0.054) as well as for clinical significance prediction (AUC = 0.688; p = 0.209) and showed a significantly better performance compared to mADC for csPCa prediction (AUC = 0.571; p = 0.022). In our study, radiomics accurately characterizes prostatic index lesions and shows performance comparable to radiologists for PCa characterization. Quantitative image data represent a potential biomarker, which, when combined with PI-RADS, PSAD and DRE, predicts csPCa more accurately than mADC. Prognostic machine learning models could assist in csPCa detection and patient selection for MRI-guided biopsy.

Extracellular vesicles (EVs) are shed by many different cell types. Their nucleic acids content offers new opportunities for biomarker research in different solid tumors. The role of EV RNA in prostate cancer (PCa) is still largely unknown. EVs were isolated from different benign and malignant prostate cell lines and blood plasma from patients with PCa (n = 18) and controls with benign prostatic hyperplasia (BPH) (n = 7). Nanoparticle tracking analysis (NTA), Western blot, electron microscopy, and flow cytometry analysis were used for the characterization of EVs. Non-coding RNA expression profiling of PC3 metastatic PCa cells and their EVs was performed by next generation sequencing (NGS). miRNAs differentially expressed in PC3 EVs were validated with qRT-PCR in EVs derived from additional cell lines and patient plasma and from matched tissue samples. 92 miRNAs were enriched and 48 miRNAs were depleted in PC3 EVs compared to PC3 cells, which could be confirmed by qRT-PCR. miR-99b-5p was significantly higher expressed in malignant compared to benign EVs. Furthermore, expression profiling showed miR-10a-5p (p = 0.018) and miR-29b-3p (p = 0.002), but not miR-99b-5p, to be overexpressed in plasma-derived EVs from patients with PCa compared with controls. In the corresponding tissue samples, no significant differences in the miRNA expression could be observed. We thus propose that EV-associated miR-10a-5p and miR-29b-3p could serve as potential new PCa detection markers.