Impact of PI-RADS Category 3 lesions on the diagnostic accuracy of MRI for detecting prostate cancer and the prevalence of prostate cancer within each PI-RADS category: A systematic review and meta-analysis

Clinical-imaging metrics for the diagnosis of prostate cancer in PI-RADS 3 lesions

OBJECTIVE

To explore the feasibility and efficacy of clinical-imaging metrics in the diagnosis of prostate cancer (PCa) and clinically significant prostate cancer (csPCa) in prostate imaging-reporting and data system (PI-RADS) category 3 lesions.

METHODS

A retrospective analysis was conducted on lesions diagnosed as PI-RADS 3. They were categorized into benign, non-csPCa and csPCa groups. Apparent diffusion coefficient (ADC), T2-weighted imaging signal intensity (T2WISI), coefficient of variation of ADC and T2WISI, prostate-specific antigen density (PSAD), ADC density (ADCD), prostate-specific antigen lesion volume density (PSAVD) and ADC lesion volume density (ADCVD) were measured and calculated. Univariate and multivariate analyses were used to identify risk factors associated with PCa and csPCa. Receiver operating characteristic curve (ROC) and decision curves were utilized to assess the efficacy and net benefit of independent risk factors.

RESULTS

Among 202 patients, 133 had benign prostate disease, 25 non-csPCa and 44 csPCa. Age, PSA and lesion location showed no significant differences (P > 0.05) among the groups. T2WISI and coefficient of variation of ADC (ADCcv) were independent risk factors for PCa in PI-RADS 3 lesions, yielding an area under the curve (AUC) of 0.68. ADC was an independent risk factor for csPCa in PI-RADS 3 lesions, yielding an AUC of 0.65. Decision curve analysis showed net benefit for patients at certain probability thresholds.

CONCLUSIONS

T2WISI and ADCcv, along with ADC, respectively showed considerable promise in enhancing the diagnosis of PCa and csPCa in PI-RADS 3 lesions.

PI-RADS upgrading as the strongest predictor for the presence of clinically significant prostate cancer in patients with initial PI-RADS-3 lesions

PURPOSE

Unclear lesions on multiparametric magnetic resonance tomography (mpMRI) are challenging for the indication of biopsy in patients with clinical suspicion of prostate cancer (PCa). The aim of this study is the validation of the detection rate of clinically significant PCa (csPCa) in patients with PI-RADS 3 findings and to determine the appropriate follow-up strategy.

METHODS

In this retrospective single-center study, patients with maximum PI-RADS 3 lesions underwent targeted MRI/ultrasound-fusion biopsy (tPbx) combined with systematic 12-core biopsy (sPbx) and follow-up mpMRI with further control biopsy. We assessed the evolution of MRI findings (PI-RADS, volume of the lesion), clinical parameters and histopathology in follow-up MRI and biopsies. The primary objective is the detection rate of csPCa, defined as ISUP ≥ 2 findings.

RESULTS

A total of 126 patients (median PSA 6.65 ng/ml; median PSA-density (PSAD) 0.13 ng/ml2) were included. The initial biopsy identified low-risk PCa in 24 cases (19%). During follow-up biopsy, 22.2% of patients showed PI-RADS upgrading (PI-RADS > 3), and 29 patients (23%) exhibited a tumor upgrading. Patients with PI-RADS upgrading had a higher risk of csPCa compared to those without PI-RADS upgrading (42.9% vs. 9.18%, p < 0.05). PI-RADS upgrading was identified as an independent predictor for csPCa in follow-up biopsy (OR 16.20; 95% CI 1.17-224.60; p = 0.038).

CONCLUSION

Patients with stable PI-RADS 3 findings may not require a follow-up biopsy. Instead, it is advisable to schedule an MRI, considering that PI-RADS upgrading serves as an independent predictor for csPCa.

Artificial intelligence as diagnostic aiding tool in cases of Prostate Imaging Reporting and Data System category 3: the results of retrospective multi-center cohort study

PURPOSE

To study the effect of artificial intelligence (AI) on the diagnostic performance of radiologists in interpreting prostate mpMRI images of the PI-RADS 3 category.

METHODS

In this multicenter study, 16 radiologists were invited to interpret prostate mpMRI cases with and without AI. The study included a total of 87 cases initially diagnosed as PI-RADS 3 by radiologists without AI, with 28 cases being clinically significant cancers (csPCa) and 59 cases being non-csPCa. The study compared the diagnostic efficacy between readings without and with AI, the reading time, and confidence levels.

RESULTS

AI changed the diagnosis in 65 out of 87 cases. Among the 59 non-csPCa cases, 41 were correctly downgraded to PI-RADS 1-2, and 9 were incorrectly upgraded to PI-RADS 4-5. For the 28 csPCa cases, 20 were correctly upgraded to PI-RADS 4-5, and 5 were incorrectly downgraded to PI-RADS 1-2. Radiologists assisted by AI achieved higher diagnostic specificity and accuracy than those without AI [0.695 vs 0.000 and 0.736 vs 0.322, both P < 0.001]. Sensitivity with AI was not significantly different from that without AI [0.821 vs 1.000, P = 1.000]. AI reduced reading time significantly compared to without AI (mean: 351 seconds, P < 0.001). The diagnostic confidence score with AI was significantly higher than that without AI (Cohen Kappa: -0.016).

CONCLUSION

With the help of AI, there was an improvement in the diagnostic accuracy of PI-RADS category 3 cases by radiologists. There is also an increase in diagnostic efficiency and diagnostic confidence.

Prostate MRI and PSMA-PET in the Primary Diagnosis of Prostate Cancer

Over the last years, prostate magnetic resonance imaging (MRI) has gained a key role in the primary diagnosis of clinically significant prostate cancer (csPCa). While a negative MRI can avoid unnecessary prostate biopsies and the overdiagnosis of indolent cancers, a positive examination triggers biopsy samples targeted to suspicious imaging findings, thus increasing the diagnosis of csPCa with a sensitivity and negative predictive value of around 90%. The limitations of MRI, including suboptimal positive predictive values, are fueling debate on how to stratify biopsy decisions and management based on patient risk and how to correctly estimate it with clinical and/or imaging findings. In this setting, "next-generation imaging" imaging based on radiolabeled Prostate-Specific Membrane Antigen (PSMA)-Positron Emission Tomography (PET) is expanding its indications both in the setting of primary staging (intermediate-to-high risk patients) and primary diagnosis (e.g., increasing the sensitivity of MRI or acting as a problem-solving tool for indeterminate MRI cases). This review summarizes the current main evidence on the role of prostate MRI and PSMA-PET as tools for the primary diagnosis of csPCa, and the different possible interaction pathways in this setting.

PI-RADS 3 lesions: a critical review and discussion of how to improve management

Since the publication of PI-RADS v1 in 2012, the debate regarding the question of how to manage PI-RADS 3 lesions has been mostly unsolved. However, based on our review of the current literature we discuss possible solutions and improvements to the original classification, factors such as PSAD (Prostate Specific Antigen Density), age, and tumor volume, in the decision of whether to proceed with a biopsy or not.

An Apparent Diffusion Coefficient-Based Machine Learning Model Can Improve Prostate Cancer Detection in the Grey Area of the Prostate Imaging Reporting and Data System Category 3: A Single-Centre Experience

The Prostate Imaging and Reporting Data System (PI-RADS) has a key role in the management of prostate cancer (PCa). However, the clinical interpretation of PI-RADS 3 score lesions may be challenging and misleading, thus postponing PCa diagnosis to biopsy outcome. Multiparametric magnetic resonance imaging (mpMRI) radiomic analysis may represent a stand-alone noninvasive tool for PCa diagnosis. Hence, this study aims at developing a mpMRI-based radiomic PCa diagnostic model in a cohort of PI-RADS 3 lesions. We enrolled 133 patients with 155 PI-RADS 3 lesions, 84 of which had PCa confirmation by fusion biopsy. Local radiomic features were generated from apparent diffusion coefficient maps, and the four most informative were selected using LASSO, the Wilcoxon rank-sum test (p < 0.001), and support vector machines (SVMs). The selected features where augmented and used to train an SVM classifier, externally validated on a holdout subset. Linear and second-order polynomial kernels were exploited, and their predictive performance compared through receiver operating characteristics (ROC)-related metrics. On the test set, the highest performance, equally for both kernels, was specificity = 76%, sensitivity = 78%, positive predictive value = 80%, and negative predictive value = 74%. Our findings substantially improve radiologist interpretation of PI-RADS 3 lesions and let us advance towards an image-driven PCa diagnosis.

Multivariable stratification of PI-RADS version 2.1 categories for the risk of false-positive target biopsy: Impact on prostate biopsy decisions

PURPOSE

To identify clinical and multiparametric magnetic resonance imaging (mpMRI) factors predicting false positive target biopsy (FP-TB) of prostate imaging reporting and data system version 2.1 (PI-RADSv2.1) ≥ 3 findings.

METHOD

We retrospectively included 221 men with and without previous negative prostate biopsy who underwent 3.0 T/1.5 T mpMRI for suspicious clinically significant prostate cancer (csPCa) between April 2019-July 2021. A study coordinator revised mpMRI reports provided by one of two radiologists (experience of > 1500/>500 mpMRI examinations, respectively) and matched them with the results of transperineal systematic biopsy plus fusion target biopsy (TB) of PI-RADSv2.1 ≥ 3 lesions or PI-RADSv2.1 ≤ 2 men with higher clinical risk. A multivariable model was built to identify features predicting FP-TB of index lesions, defined as the absence of csPCa (International Society of Urogenital Pathology [ISUP] ≥ 2). The model was internally validated with the bootstrap technique, receiving operating characteristics (ROC) analysis, and decision analysis.

RESULTS

Features significantly associated with FP-TB were age < 65 years (odds ratio [OR] 2.77), prostate-specific antigen density (PSAD) < 0.15 ng/mL/mL (OR 2.45), PI-RADS 4/5 category vs. category 3 (OR 0.15/0.07), and multifocality (OR 0.46), with a 0.815 area under the curve (AUC) in assessing FP-TB. When adjusting PI-RADSv2.1 categorization for the model, mpMRI showed 87.5% sensitivity and 79.9% specificity for csPCa, with a greater net benefit in triggering biopsy compared to unadjusted categorization or adjustment for PSAD only at decision analysis, from threshold probability ≥ 15%.

CONCLUSION

Adjusting PI-RADSv2.1 categories for a multivariable risk of FP-TB is potentially more effective in triggering TB of index lesions than unadjusted PI-RADS categorization or adjustment for PSAD alone.

The use of 68 Ga-PSMA PET/CT to stratify patients with PI-RADS 3 lesions according to clinically significant prostate cancer risk

BACKGROUND

Prostate imaging reporting and data system (PI-RADS) category 3 lesions represent a "gray zone," having an equivocal risk of presenting as clinically significant prostate cancer (csPCa). ⁶⁸ Ga-labelled prostate-specific membrane antigen (⁶⁸ Ga-PSMA) positron emission tomography/computed tomography (PET/CT) has been identified as a diagnostic tool that can help to predict cases of primary PCa. We aimed to explore diagnostic value of ⁶⁸ Ga-PSMA PET/CT for csPCa in PI-RADS 3 lesions to aid in decision-making and avoid unnecessary biopsies.

METHODS

A total of 78 men with PI-RADS 3 lesions who underwent both ⁶⁸ Ga-PSMA PET/CT and transrectal ultrasound/magnetic resonance imaging (MRI) fusion-guided biopsy were enrolled. Images were analyzed by respective physicians who were blinded to the pathological results. Receiver operating characteristic (ROC) curve analysis and decision curve analysis were used to evaluate the diagnostic performance of univariate and multivariate analyses.

RESULTS

A total of 26/78 men had pathologically confirmed csPCa. A lower ADCT/ADCCLP (0.65 vs. 0.71, p = 0.018), smaller prostate volume (25.27 vs. 42.79 ml, p < 0.001), lower free prostate-specific antigen/total prostate-specific antigen (0.11 vs. 0.16, p < 0.001), higher PSA level (13.45 vs. 7.90 ng/ml, p = 0.001), higher PSA density (0.40 vs. 0.16 ng/ml² , p < 0.001), higher SUVmax (9.80 vs. 4.40, p < 0.001) and SUVT/BGp (2.41 vs. 1.00, p < 0.001) were associated with csPCa. ROC analysis illustrated the improvement in SUVmax and SUVT/BGp compared with all independent and combined clinical features as well as multiparametric magnetic resonance imaging (mpMRI) features for csPCa detection. The net benefits of SUVmax and SUVT/BGp were superior to those of other features, respectively. With cutoff values of 5.0 for SUVmax and 1.4 for SUVT/BGp, the diagnostic sensitivity and specificity for csPCa were 96.2%, 100% and 80.8%, 84.6%, respectively.

CONCLUSION

⁶⁸ Ga-PSMA PET/CT is potentially capable of stratifying men with PI-RADS 3 lesions according to the presence of csPCa and has better performance than the model established based on clinical and mpMRI features.

Natural History of Patients with Prostate MRI Likert 1-3 and Development of RosCaP: a Multivariate Risk Score for Clinically Significant Cancer

INTRODUCTION

Clinically significant prostate cancer (csCaP) with Gleason ≥3 + 4 is found in 10% negative prebiopsy multiparametric (mp) MRI cases and varies widely for equivocal mpMRI cases. The objective of this study was to investigate long-term outcomes of patients with negative and equivocal mpMRIs and to develop a predictive score for csCaP risk stratification in this group.

PATIENTS AND METHODS

Patients who underwent an upfront mpMRI between May 2015 and March 2018 with an MRI score Likert 1 to 3 were included in the study. Patients had either a CaP diagnosis at MRI-targeted biopsy or were not diagnosed and attended follow-up in the community. Outcomes were analysed through the Kaplan-Meier estimator and Cox Model. Regression coefficients of significant variables were used to develop a Risk of significant Cancer of the Prostate score (RosCaP).

RESULTS

At first assessment 281/469 patients had mpMRI only and 188/469 mpMRI and biopsy, 26 csCaP were found at biopsy, including 10/26 in Likert 3 patients. 12/371 patients discharged without CaP after first assessment were diagnosed with csCaP during a median of 34.2 months' follow-up, 11/12 diagnosis occurred in patients omitting initial biopsy. csCaP diagnosis-free survival was 95.7% in the MRI group and 99.1% in the biopsy group. From these outcomes, a continuous RosCaP score was developed: RosCaP = 0.083 x Age - 0.202 x (1/PSA Density) + 0.786 (if Likert 3), and 4 risk classes were proposed. Limitations include retrospective design and absence of external validation.

CONCLUSION

Age, PSA Density and MRI Likert score were significantly associated to the risk of csCaP and utilised to devise the novel RosCap predictive score focused to support risk assessment in patients with negative or equivocal mpMRI results.

68Ga-PSMA-11 PET/MRI versus multiparametric MRI in men referred for prostate biopsy: primary tumour localization and interreader agreement

Background

Magnetic resonance imaging (MRI) is recommended by the European Urology Association guidelines as the standard modality for imaging-guided biopsy. Recently positron emission tomography with prostate-specific membrane antigen (PSMA PET) has shown promising results as a tool for this purpose. The aim of this study was to compare the accuracy of positron emission tomography with prostate-specific membrane antigen/magnetic resonance imaging (PET/MRI) using the gallium-labeled prostate-specific membrane antigen (⁶⁸Ga-PSMA-11) and multiparametric MRI (mpMRI) for pre-biopsy tumour localization and interreader agreement for visual and semiquantitative analysis. Semiquantitative parameters included apparent diffusion coefficient (ADC) and maximum lesion diameter for mpMRI and standardized uptake value (SUV_max) and PSMA-positive volume (PSMA_vol) for PSMA PET/MRI.

Results

Sensitivity and specificity were 61.4% and 92.9% for mpMRI and 66.7% and 92.9% for PSMA PET/MRI for reader one, respectively. RPE was available in 23 patients and 41 of 47 quadrants with discrepant findings. Based on RPE results, the specificity for both imaging modalities increased to 98% and 99%, and the sensitivity improved to 63.9% and 72.1% for mpMRI and PSMA PET/MRI, respectively. Both modalities yielded a substantial interreader agreement for primary tumour localization (mpMRI kappa = 0.65 (0.52–0.79), PSMA PET/MRI kappa = 0.73 (0.61–0.84)). ICC for SUV_max, PSMA_vol and lesion diameter were almost perfect (≥ 0.90) while for ADC it was only moderate (ICC = 0.54 (0.04–0.78)). ADC and lesion diameter did not correlate significantly with Gleason score (ρ = 0.26 and ρ = 0.16) while SUV_max and PSMA_vol did (ρ =  − 0.474 and ρ =  − 0.468).

Conclusions

PSMA PET/MRI has similar accuracy and reliability to mpMRI regarding primary prostate cancer (PCa) localization. In our cohort, semiquantitative parameters from PSMA PET/MRI correlated with tumour grade and were more reliable than the ones from mpMRI.

Supplementary Information

The online version contains supplementary material available at 10.1186/s41824-022-00135-4.

Diagnostic value of combining PI-RADS v2.1 with PSAD in clinically significant prostate cancer

PURPOSE

To investigate the diagnostic value of the Prostate Imaging Reporting and Data System version 2.1 (PI-RADS v2.1) for clinically significant prostate cancer (CsPCa). We also aimed to combine PI-RADS v2.1 with prostate-specific antigen (PSA) derivatives to improve the predictive value of CsPCa.

METHODS

We retrospectively collected relevant data who underwent standard MRI examinations of the prostate and subjected to a prostate biopsy at Shenzhen People's hospital from November 2014 to November 2019. Included 125 cases of CsPCa and 383 cases of non-CsPCa. All cases were scored using the PI-RADS v2.1. The clinical data collected included age, PSA, free PSA/total PSA, prostate volume and PSA density (PSAD). A univariate analysis was performed to identify statistically significant indicators. Logistic regression was used to analyze the predictive value of the multi-parameter combination on CsPCa.

RESULTS

Except age, the difference in all of indicators between the CsPCa group and non-CsPCa group was statistically significant. The PI-RADS score and PSAD value had the highest diagnostic value. Logistic regression analysis revealed that the PI-RADS score and PSAD value were independent predictors of CsPCa, with a regression model AUC of 0.935. CsPCa detection rates were low when the PI-RADS score ≤ 2 or the PI-RADS score = 3 and the PSAD value ≤ 0.33 ng/ml/ml.

CONCLUSION

Combining the PI-RADS score and PSAD value improved the predictive performance of CsPCa. Patients with a PI-RADS score ≤ 2 or a PI-RADS score = 3 and a PSAD value ≤ 0.33 ng/ml/ml can avoid an unnecessary biopsy.

Development of a nomogram combining multiparametric magnetic resonance imaging and PSA-related parameters to enhance the detection of clinically significant cancer across different region

OBJECTIVE

Prostate cancer (PCa) is the most prevalent cancer among males. This study attempted to develop a clinically significant prostate cancer (csPCa) risk nomogram including Prostate Imaging-Reporting and Data System (PI-RADS) score and other clinical indexes for initial prostate biopsy in light of the different prostate regions, and internal validation was further conducted.

PATIENTS AND METHODS

A retrospective study was performed including 688 patients who underwent ultrasound-guided transperineal magnetic resonance imaging fusion prostate biopsy from December 2016 to July 2019. We constructed nomograms combining PI-RADS score and clinical variables (prostate-specific antigen [PSA], prostate volume (PV), age, free/total PSA, and PSA density) through univariate and multivariate logistic regression to identify patients eligible for biopsy. The performance of the predictive model was evaluated by bootstrap resampling. The area under the curve (AUC) of the receiver-operating characteristic (ROC) analysis was appointed to quantify the accuracy of the primary nomogram model for csPCa. Calibration curves were used to assess the agreement between the biopsy specimen and the predicted probability of the new nomogram. The χ² test was also applied to evaluate the heterogeneity between fusion biopsy and systematic biopsy based on different PI-RADS scores and prostate regions.

RESULTS

A total of 320 of 688 included patients were diagnosed with csPCa. csPCa was defined as Gleason score ≥7. The ROC and concordance-index both presented good performance. The nomogram reached an AUC of 0.867 for predicting csPCa at the peripheral zone; meanwhile, AUC for transitional and apex zones were 0.889 and 0.757, respectively. Statistical significance was detected between fusion biopsy and systematic biopsy for PI-RADS score >3 lesions and lesions at the peripheral and transitional zones.

CONCLUSION

We produced a novel nomogram predicting csPCa in patients with suspected imaging according to different locations. Our results indicated that PI-RADS score combined with other clinical parameters showed a robust predictive capacity for csPCa before prostate biopsy. The new nomogram, which incorporates prebiopsy data including PSA, PV, age, and PI-RADS score, can be helpful for clinical decision-making to avoid unnecessary biopsy.

Radiomics in prostate cancer: an up-to-date review

Prostate cancer (PCa) is the most common worldwide diagnosed malignancy in male population. The diagnosis, the identification of aggressive disease, and the post-treatment follow-up needs a more comprehensive and holistic approach. Radiomics is the extraction and interpretation of images phenotypes in a quantitative manner. Radiomics may give an advantage through advancements in imaging modalities and through the potential power of artificial intelligence techniques by translating those features into clinical outcome prediction. This article gives an overview on the current evidence of methodology and reviews the available literature on radiomics in PCa patients, highlighting its potential for personalized treatment and future applications.

Comparison of different thresholds of PSA density for risk stratification of PI-RADSv2.1 categories on prostate MRI

OBJECTIVES

To compare the effect of different PSA density (PSAD) thresholds on the accuracy for clinically significant prostate cancer (csPCa) of the Prostate Imaging Reporting And Data System v.2.1 (PI-RADSv2.1).

METHODS

We retrospectively included 123 biopsy-naïve men who underwent multiparametric magnetic resonance imaging (mpMRI) and transperineal mpMRI-targeted and systematic prostate biopsy between April 2019 and October 2020. mpMRI, obtained on a 3.0T magnet with a PI-RADSv2.1-compliant protocol, was read by two radiologists (>1500/>500 mpMRI examinations). csPCa was defined as International Society of Urogenital Pathology grading group ≥2. Receiver operating characteristic analysis was used to calculate per-index lesion sensitivity, specificity, and area under the curve (AUC) of PI-RADSv.2.1 categories after adjusting for PSAD ≥0.10,≥0.15, and ≥0.20 ng/mL ml^-1. Per-adjusted category cancer detection rate (CDR) was calculated, and decision analysis performed to compare PSAD-adjusted PI-RADSv.2.1 categories as a biopsy trigger.

RESULTS

csPCa prevalence was 43.9%. PSAD-adjustment increased the CDR of PI-RADSv2.1 category 4. Sensitivity/specificity/AUC were 92.6%/53.6%/0.82 for unadjusted PI-RADS, and 85.2%/72.4%/0.84, 62.9%/85.5%/0.83, and 92.4%/53.6%/0.82 when adjusting PI-RADS categories for a 0.10, 0.15, and 0.20 ng/ml ml^-1 PSAD threshold, respectively. Triggering biopsy for PI-RADS four lesions and PSAD ≥0.10 ng/mL ml^-1 was the strategy with greatest net benefit at 30 and 40% risk probability (0.307 and 0.271, respectively).

CONCLUSIONS

PI-RADSv2.1 category four with PSAD ≥0.10 ng/mL ml^-1 was the biopsy-triggering cut-off with the highest net benefit in the range of expected prevalence for csPCa.

ADVANCES IN KNOWLEDGE

0.10 ng/mL ml^-1 is the PSAD threshold with higher clinical utility in stratifying the risk for prostate cancer of PI-RADSv.2.1 categories.

Simplified PI-RADS (S-PI-RADS) for biparametric MRI to detect and manage prostate cancer: What urologists need to know

Biparametric magnetic resonance imaging (bpMRI) of the prostate has emerged as an alternative to multiparametric MRI (mpMRI) for the detection of clinically significant prostate cancer (csPCa). However, while the Prostate Imaging Reporting and Data System (PI-RADS) is widely known for mpMRI, a proper PI-RADS for bpMRI has not yet been adopted. In this review, we report the current status and the future directions of bpMRI, and propose a simplified PI-RADS (S-PI-RADS) that could help radiologists and urologists in the detection and management of PCa.

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

Simple Summary

The increasing interest in implementing artificial intelligence in radiomic models has occurred alongside advancement in the tools used for computer-aided diagnosis. Such tools typically apply both statistical and machine learning methodologies to assess the various modalities used in medical image analysis. Specific to prostate cancer, the radiomics pipeline has multiple facets that are amenable to improvement. This review discusses the steps of a magnetic resonance imaging based radiomics pipeline. Present successes, existing opportunities for refinement, and the most pertinent pending steps leading to clinical validation are highlighted.

Abstract

The management of prostate cancer (PCa) is dependent on biomarkers of biological aggression. This includes an invasive biopsy to facilitate a histopathological assessment of the tumor’s grade. This review explores the technical processes of applying magnetic resonance imaging based radiomic models to the evaluation of PCa. By exploring how a deep radiomics approach further optimizes the prediction of a PCa’s grade group, it will be clear how this integration of artificial intelligence mitigates existing major technological challenges faced by a traditional radiomic model: image acquisition, small data sets, image processing, labeling/segmentation, informative features, predicting molecular features and incorporating predictive models. Other potential impacts of artificial intelligence on the personalized treatment of PCa will also be discussed. The role of deep radiomics analysis-a deep texture analysis, which extracts features from convolutional neural networks layers, will be highlighted. Existing clinical work and upcoming clinical trials will be reviewed, directing investigators to pertinent future directions in the field. For future progress to result in clinical translation, the field will likely require multi-institutional collaboration in producing prospectively populated and expertly labeled imaging libraries.