Positive Predictive Value of Prostate Imaging Reporting and Data System Version 2 for the Detection of Clinically Significant Prostate Cancer: A Systematic Review and Meta-analysis

Risk Stratification of Patients Candidate to Radical Prostatectomy Based on Clinical and Multiparametric Magnetic Resonance Imaging Parameters: Development and External Validation of Novel Risk Groups

BACKGROUND

Despite the key importance of magnetic resonance imaging (MRI) parameters, risk classification systems for biochemical recurrence (BCR) in prostate cancer (PCa) patients treated with radical prostatectomy (RP) are still based on clinical variables alone.

OBJECTIVE

We aimed at developing and validating a novel classification integrating clinical and radiological parameters.

DESIGN, SETTING, AND PARTICIPANTS

A retrospective multicenter cohort study was conducted between 2014 and 2020 across seven academic international referral centers. A total of 2565 patients treated with RP for PCa were identified.

OUTCOME MEASUREMENTS AND STATISTICAL ANALYSIS

Early BCR was defined as two prostate-specific antigen (PSA) values of ≥0.2 ng/ml within 3 yr after RP. Kaplan-Meier and Cox regressions tested time and predictors of BCR. Development and validation cohorts were generated from the overall patient sample. A model predicting early BCR based on Cox-derived coefficients represented the basis for a nomogram that was validated externally. Predictors consisted of PSA, biopsy grade group, MRI stage, and the maximum diameter of lesion at MRI. Novel risk categories were then identified. The Harrel's concordance index (c-index) compared the accuracy of our risk stratification with the European Association of Urology (EAU), Cancer of the Prostate Risk Assessment (CAPRA), and International Staging Collaboration for Cancer of the Prostate (STAR-CAP) risk groups in predicting early BCR.

RESULTS AND LIMITATIONS

Overall, 200 (8%), 1834 (71%), and 531 (21%) had low-, intermediate-, and high-risk disease according to the EAU risk groups. The 3-yr overall BCR-free survival rate was 84%. No differences were observed in the 3-yr BCR-free survival between EAU low- and intermediate-risk groups (88% vs 87%; p = 0.1). The novel nomogram depicted optimal discrimination at external validation (c-index 78%). Four new risk categories were identified based on the predictors included in the Cox-based nomogram. This new risk classification had higher accuracy in predicting early BCR (c-index 70%) than the EAU, CAPRA, and STAR-CAP risk classifications (c-index 64%, 63%, and 67%, respectively).

CONCLUSIONS

We developed and externally validated four novel categories based on clinical and radiological parameters to predict early BCR. This novel classification exhibited higher accuracy than the available tools.

PATIENT SUMMARY

Our novel and straightforward risk classification outperformed currently available preoperative risk tools and should, therefore, assist physicians in preoperative counseling of men candidate to radical treatment for prostate cancer.

Cancer detection rates of the PI-RADSv2.1 assessment categories: systematic review and meta-analysis on lesion level and patient level

BACKGROUND

The Prostate Imaging Reporting and Data System, version 2.1 (PI-RADSv2.1) standardizes reporting of multiparametric MRI of the prostate. Assigned assessment categories are a risk stratification algorithm, higher categories indicate a higher probability of clinically significant cancer compared to lower categories. PI-RADSv2.1 does not define these probabilities numerically. We conduct a systematic review and meta-analysis to determine the cancer detection rates (CDR) of the PI-RADSv2.1 assessment categories on lesion level and patient level.

METHODS

Two independent reviewers screen a systematic PubMed and Cochrane CENTRAL search for relevant articles (primary outcome: clinically significant cancer, index test: prostate MRI reading according to PI-RADSv2.1, reference standard: histopathology). We perform meta-analyses of proportions with random-effects models for the CDR of the PI-RADSv2.1 assessment categories for clinically significant cancer. We perform subgroup analysis according to lesion localization to test for differences of CDR between peripheral zone lesions and transition zone lesions.

RESULTS

A total of 17 articles meet the inclusion criteria and data is independently extracted by two reviewers. Lesion level analysis includes 1946 lesions, patient level analysis includes 1268 patients. On lesion level analysis, CDR are 2% (95% confidence interval: 0-8%) for PI-RADS 1, 4% (1-9%) for PI-RADS 2, 20% (13-27%) for PI-RADS 3, 52% (43-61%) for PI-RADS 4, 89% (76-97%) for PI-RADS 5. On patient level analysis, CDR are 6% (0-20%) for PI-RADS 1, 9% (5-13%) for PI-RADS 2, 16% (7-27%) for PI-RADS 3, 59% (39-78%) for PI-RADS 4, 85% (73-94%) for PI-RADS 5. Higher categories are significantly associated with higher CDR (P < 0.001, univariate meta-regression), no systematic difference of CDR between peripheral zone lesions and transition zone lesions is identified in subgroup analysis.

CONCLUSIONS

Our estimates of CDR demonstrate that PI-RADSv2.1 stratifies lesions and patients as intended. Our results might serve as an initial evidence base to discuss management strategies linked to assessment categories.

Prostate Imaging and Data Reporting System Version 2 as a Radiology Performance Metric: An Analysis of 18 Abdominal Radiologists

PURPOSE

To determine expected trained provider performance dispersion in Prostate Imaging and Data Reporting System version 2 (PI-RADS v2) positive predictive values (PPVs).

METHODS

This single-center quality assurance retrospective cohort study evaluated 5,556 consecutive prostate MRIs performed on 4,593 patients. Studies were prospectively interpreted from October 8, 2016, to July 31, 2020, by 18 subspecialty-trained abdominal radiologists (1-22 years' experience; median MRIs per radiologist: 232, first-to-third quartile range [Q1-Q3]: 128-440; 13 interpreted at least 30 MRIs with a reference standard). Maximum prospectively reported whole-gland PI-RADS v2 score was compared to post-MRI biopsy histopathology obtained within 2 years. The primary outcome was PPV of MRI by provider stratified by maximum whole-gland PI-RADS v2 score.

RESULTS

Median provider-level PPVs for the radiologists who interpreted ≥30 MRIs with a reference standard were PI-RADS 3 (22.1%; Q1-Q3: 10.0%-28.6%), PI-RADS 4 (49.2%; Q1-Q3: 41.4%-50.0%), PI-RADS 5 (81.8%; Q1-Q3: 77.1%-84.4%). Overall, the maximum whole-gland PI-RADS v2 score was PI-RADS 1 to 2 (34.6% [1,925]), PI-RADS 3 (8.5% [474]), PI-RADS 4 (21.0% [1,166]), PI-RADS 5 (18.3% [1,018]), no PI-RADS score (17.5% [973]). System-level (all providers) PPVs for maximum PI-RADS v2 scores were 20.0% (95% confidence interval [CI]: 15.7%-24.9%) for PI-RADS 3, 48.5% (95% CI: 44.8%-52.2%) for PI-RADS 4, and 80.1% for PI-RADS 5 (95% CI: 75.7%-83.9%).

CONCLUSION

Subspecialty-trained abdominal radiologists with a wide range of experience can obtain consistent positive predictive values for PI-RADS v2 scores of 3 to 5. These data can be used for quality assurance benchmarking.

Artificial Intelligence in Magnetic Resonance Imaging-based Prostate Cancer Diagnosis: Where Do We Stand in 2021?

CONTEXT

Men suspected of harboring prostate cancer (PCa) increasingly undergo multiparametric magnetic resonance imaging (mpMRI) and mpMRI-guided biopsy. The potential of mpMRI coupled to artificial intelligence (AI) methods to detect and classify PCa before decision-making requires investigation.

OBJECTIVE

To review the literature for studies addressing the diagnostic performance of combined mpMRI and AI approaches to detect and classify PCa, and to provide selection criteria for relevant articles having clinical significance.

EVIDENCE ACQUISITION

We performed a nonsystematic search of the English language literature using the PubMed-MEDLINE database up to October 30, 2020. We included all original studies addressing the diagnostic accuracy of mpMRI and AI to detect and classify PCa with histopathological analysis as a reference standard.

EVIDENCE SYNTHESIS

Eleven studies assessed AI and mpMRI approaches for PCa detection and classification based on a ground truth that referred to the entire prostate either with radical prostatectomy specimens (RPS) or relocalization of positive systematic and/or targeted biopsy. Seven studies retrospectively annotated cancerous lesions onto mpMRI identified in whole-mount sections from RPS, three studies used a backward projection of histological prostate biopsy information, and one study used a combined cohort of both approaches. All studies cross-validated their data sets; only four used a test set and one a multisite validation scheme. Performance metrics for lesion detection ranged from 87.9% to 92% at a threshold specificity of 50%. The lesion classification accuracy of the algorithms was comparable to that of the Prostate Imaging-Reporting and Data System.

CONCLUSIONS

For an algorithm to be implemented into radiological workflows and to be clinically applicable, it must be trained with a ground truth labeling that reflects histopathological information for the entire prostate and it must be externally validated. Lesion detection and classification performance metrics are promising but require prospective implementation and external validation for clinical significance.

PATIENT SUMMARY

We reviewed the literature for studies on prostate cancer detection and classification using magnetic resonance imaging (MRI) and artificial intelligence algorithms. The main application is in supporting radiologists in interpreting MRI scans and improving the diagnostic performance, so that fewer unnecessary biopsies are carried out.

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.