Multiparametric MRI for Prostate Cancer Characterization: Combined Use of Radiomics Model with PI-RADS and Clinical Parameters

Abstract

<jats:p>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.</jats:p>

Associations between Statin/Omega3 Usage and MRI-Based Radiomics Signatures in Prostate Cancer

“…Based on MRI used in the routine management of prostate cancer, radiomics is well posited to study these heterogeneities as well as to assess the heterogeneity among different patients. While still in an early stage of development as a discipline, radiomics has found success in prostate cancer diagnosis, risk characterization, genomic association, and prognosis prediction, offering a noninvasive and repeatable approach in these applications [ 18 , 19 , 20 , 21 , 22 , 24 , 25 , 27 , 40 ]. With recent research, epidemiological, and clinical development in prostate cancer, risk stratification has become an increasingly central theme in prostate cancer management.…”

“…In prostate cancer, like in many other cancer sites, radiomics has found success in detecting and diagnosing tumors, characterizing index lesions, predicting tumor aggressiveness, evaluating treatment response and prognosis, and associating with tumor genomics [ 17 , 18 , 19 , 20 , 21 , 22 , 23 , 24 , 25 , 26 , 27 ]. However, to the best of our knowledge, radiomics has never been explored as a potential tool to investigate the relationship between medication exposure and prostate cancer.…”

Magnetic Resonance Imaging Based Radiomic Models of Prostate Cancer: A Narrative Review

“…In addition to radiomic features, clinical and molecular variables can readily be included in the eventual prediction model. Such details are thought to benefit predictions of the GS [ 86 ] but are also included in the radiogenomic studies. In these cases, imaging features are modeled to predict molecular characteristics (e.g., androgen resistance) or are combined with multiple biological features (e.g., genomics, proteomics, and metabolomics) to better predict a PCa’s potential aggressiveness.…”

“…MRI radiomics have demonstrated the potential to discern the PCa grade [ 23 , 24 , 86 , 87 , 88 ] or guide management approaches [ 45 , 89 ] from the abundance of clinical data acquired at each scan. However, reproducibility is a significant issue at different stages of the radiomics pipeline, with few studies investigating this question [ 41 , 78 ].…”

Evaluation of a multiparametric MRI radiomic-based approach for stratification of equivocal PI-RADS 3 and upgraded PI-RADS 4 prostatic lesions

“…Radiomics, the extraction of multiple quantitative imaging features from medical images, represents an attractive tool which could overcome the clinical challenge associated with radiologist uncertainties related to PI-RADS 3 lesions and PI-RADS 3 upgraded to PI-RADS 4 lesions. Radiomic tool has been widely explored in the field of PCa and led to promising results, but especially in studies aiming at differentiating between normal and cancerous prostatic tissue, characterizing PCa lesions in terms of aggressiveness according to Gleason Score (GS), and also comparing diagnostic power of radiomic features with that of PI-RADS scoring 16 – 22 . However, to our knowledge, only Giambelluca et al 23 applied radiomic approach to stratify PI-RADS 3 lesions, and there are any studies aiming at investigating the power of radiomics in stratify PI-RADS 3 upgraded to PI-RADS 4.…”