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.
All biopsy techniques allow detection of clinically significant tumors with a median error of 2-3 mm. Elastic image fusion appears to be the most precise technique, independent of prostate volume, target size or location.
• Significant prostate cancer using zoomed ultra-high b-value DWI was detected. • Diagnostic performance among readers with different degrees of experience was good. • mp- MRI of the prostate using a comprehensive non-contrast protocol is clinically feasible.
Radiomics may increase the diagnostic accuracy of medical imaging for localized and metastatic RCC (mRCC). A systematic review and meta-analysis was performed. Doing so, we comprehensively searched literature databases until May 2020. Studies investigating the diagnostic value of radiomics in differentiation of localized renal tumors and assessment of treatment response to ST in mRCC were included and assessed with respect to their quality using the radiomics quality score (RQS). A total of 113 out of 1098 identified studies met the criteria and were included in qualitative synthesis. Median RQS of all studies was 13.9% (5.0 points, IQR 0.25–7.0 points), and RQS increased over time. Thirty studies were included into the quantitative synthesis: For distinguishing angiomyolipoma, oncocytoma or unspecified benign tumors from RCC, the random effects model showed a log odds ratio (OR) of 2.89 (95%-CI 2.40–3.39, p < 0.001), 3.08 (95%-CI 2.09–4.06, p < 0.001) and 3.57 (95%-CI 2.69–4.45, p < 0.001), respectively. For the general discrimination of benign tumors from RCC log OR was 3.17 (95%-CI 2.73–3.62, p < 0.001). Inhomogeneity of the available studies assessing treatment response in mRCC prevented any meaningful meta-analysis. The application of radiomics seems promising for discrimination of renal tumor dignity. Shared data and open science may assist in improving reproducibility of future studies.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.