Cancer of the Prostate Risk Assessment (CAPRA) Preoperative Score Versus Postoperative Score (CAPRA-S): ability to predict cancer progression and decision-making regarding adjuvant therapy after radical prostatectomy

Novel Multiparametric Magnetic Resonance Imaging-Based Deep Learning and Clinical Parameter Integration for the Prediction of Long-Term Biochemical Recurrence-Free Survival in Prostate Cancer after Radical Prostatectomy

Radical prostatectomy (RP) is the main treatment of prostate cancer (PCa). Biochemical recurrence (BCR) following RP remains the first sign of aggressive disease; hence, better assessment of potential long-term post-RP BCR-free survival is crucial. Our study aimed to evaluate a combined clinical-deep learning (DL) model using multiparametric magnetic resonance imaging (mpMRI) for predicting long-term post-RP BCR-free survival in PCa. A total of 437 patients with PCa who underwent mpMRI followed by RP between 2008 and 2009 were enrolled; radiomics features were extracted from T2-weighted imaging, apparent diffusion coefficient maps, and contrast-enhanced sequences by manually delineating the index tumors. Deep features from the same set of imaging were extracted using a deep neural network based on pretrained EfficentNet-B0. Here, we present a clinical model (six clinical variables), radiomics model, DL model (DLM-Deep feature), combined clinical-radiomics model (CRM-Multi), and combined clinical-DL model (CDLM-Deep feature) that were built using Cox models regularized with the least absolute shrinkage and selection operator. We compared their prognostic performances using stratified fivefold cross-validation. In a median follow-up of 61 months, 110/437 patients experienced BCR. CDLM-Deep feature achieved the best performance (hazard ratio [HR] = 7.72), followed by DLM-Deep feature (HR = 4.37) or RM-Multi (HR = 2.67). CRM-Multi performed moderately. Our results confirm the superior performance of our mpMRI-derived DL algorithm over conventional radiomics.

Does surgical delay for radical prostatectomy affect patient pathological outcome? A retrospective analysis from a Canadian cohort

INTRODUCTION

We sought to assess the impact of surgical wait time (SWT) to robot-assisted radical prostatectomy (RARP) on final pathological outcome.

METHODS

A retrospective review of RARP patient records operated between 2006 and 2015 was conducted. SWT was defined as period from prostate biopsy to surgery. Primary outcome was the impact on postoperative Cancer of the Prostate Risk Assessment (CAPRA-S) score. Patients were stratified according to D'Amico risk categories. Univariate analysis (UVA) and multivariable (MVA) analysis with a generalized linear model was used to evaluate the effect of SWT and other predictive factors on pathological outcome in individual risk group and on the overall sample.

RESULTS

A total of 835 patients were eligible for analysis. Mean SWT was significantly different between the three D'Amico groups, with mean SWT of 180.22 days (95% confidence interval [CI] 169.03; 191.41), 159.14 days (95% CI 152.38; 165.90), and 138.96 days (95% CI 124.60; 153.33) for low-, intermediate-, and high-risk groups, respectively (p<0.001). After stratification by D'Amico risk group, no significant association was observed between SWT and CAPRA-S score in the three risk categories on UVA and MVA. Predictors of higher CAPRA-S score in the multivariable model in the overall cohort were: older age (p=0.014), biopsy Gleason score (p<0.001), percentage of positive cores (p<0.001), and clinical stage (p<0.001).

CONCLUSIONS

In the present study evaluating SWT for RARP in a Canadian socialized system, increased delay for surgery does not appear to impact the pathological outcome. Further studies are required to evaluate the impact of wait time on biochemical recurrence-free survival, cancer-specific survival, and overall survival.

18F Fluorocholine Dynamic Time-of-Flight PET/MR Imaging in Patients with Newly Diagnosed Intermediate- to High-Risk Prostate Cancer: Initial Clinical-Pathologic Comparisons

Purpose To investigate the initial clinical value of fluorine 18 (¹⁸F) fluorocholine (FCH) dynamic positron emission tomography (PET)/magnetic resonance (MR) imaging by comparing its parameters with clinical-pathologic findings in patients with newly diagnosed intermediate- to high-risk prostate cancer (PCa) who plan to undergo radical prostatectomy. Materials and Methods The institutional review board approved the study protocol, and informed written consent was obtained from all subjects for this HIPAA-compliant study. Twelve men (mean age ± standard deviation, 61.7 years ± 8.4; range, 46-74 years) with untreated intermediate- to high-risk PCa characterized according to Cancer of the Prostate Risk Assessment (CAPRA) underwent preoperative FCH dynamic PET/MR imaging followed by radical prostatectomy between April and November 2015. PET/MR imaging parameters including average and maximum K1 (delivery rate constant) and standardized uptake values (SUVs) and Prostate Imaging Reporting and Data System (PI-RADS) version 2 scores were measured and compared with clinical-pathologic characteristics. For statistical analysis, the Spearman rank correlation and Mann-Whitney U tests were performed. Results Of the PET parameters, maximum SUV of primary tumors showed significant correlations with several clinical-pathologic parameters including serum prostate-specific antigen level (ρ = 0.71, P = .01), pathologic stage (ρ = 0.59, P = .043), and postsurgical CAPRA score (ρ = 0.72, P = .008). The overall PI-RADS score showed significant correlations with pathologic tumor volume (ρ = 0.81, P < .001), percentage of tumor cells with Gleason scores greater than 3 (ρ = 0.59, P = .02), and postsurgical CAPRA score (ρ = 0.58, P = .046). The high-risk postsurgical CAPRA score patient group had a significantly higher maximum SUV than did the intermediate-risk group. Combined PET and MR imaging showed improved sensitivity (88%) for prediction of pathologic extraprostatic extension compared with that with MR imaging (50%) and PET (75%) performed separately. Conclusion Maximum SUVs and PI-RADS scores from FCH PET/MR imaging show good correlation with clinical-pathologic characteristics, such as postsurgical CAPRA score, which are related to prognosis in patients with newly diagnosed intermediate- to high-risk PCa. ^© RSNA, 2016 Online supplemental material is available for this article.

External Validation of the Cancer of the Prostate Risk Assessment Postsurgical Score for Prediction of Disease Recurrence after Radical Prostatectomy

Objective. The cancer of the prostate risk assessment (CAPRA-S) postsurgical score predicts recurrence, metastasis, and cancer-specific survival after radical prostatectomy (RP). We evaluated the relation between CAPRA-S score and biochemical recurrence (BCR) in prostate cancer after RP in our clinic. Materials and Methods. This study was performed on 203 patients with prostate carcinoma who underwent open RP and regional lymph node dissection in our clinic between 2008 and 2013. We calculated the CAPRA-S scores including prostate-specific antigen (PSA) at diagnosis, pathology Gleason score, surgical margin, seminal vesicle invasion, extracapsular extension, and lymph node involvement. The patients were divided into 3 risk groups (low, intermediate, and high risk) according to risk scores. Results. Recurrence occurred in 17.8% of the patients (36 patients out of 203 patients) with a median of 11.7-month follow-up. The average recurrence-free survival time is 44.6 months. Surgical margin invasion and seminal vesicle invasion significantly correlated with BCR especially in high risk group (11 and 13 of 15 patients, p < 0.05, resp.). Conclusion. CAPRA-S score can be easily calculated and it is useful in clinical practice in order to timely propose adjuvant therapies after surgery.

Pathologic Outcomes in Men with Low-risk Prostate Cancer Who Are Potential Candidates for Contemporary, Active Surveillance Protocols

The purpose of this study was to determine whether contemporary active surveillance (AS) protocols could sufficiently discriminate significant from indolent tumors in men with low-risk prostate cancer. We retrospectively analyzed 312 patients with low-risk prostate cancer treated with radical prostatectomy. After exclusion of patients with fewer than 10 cores taken at biopsy and those who received neo-adjuvant treatment, 205 subjects satisfied the final inclusion criteria. Five widely accepted AS protocols were employed in this study. A total of 82.0% of the patients met the inclusion criteria of at least one protocol, and 18% did not meet any criteria of published AS protocols. A significant proportion of patients had non-organ-confined disease (8.6% to 10.6%) or a Gleason score of 7 or greater (18.6% to 23.9%) between the different AS criteria. Among patients who did not meet any AS criteria, 32.4% of patients had a pathologically insignificant cancer. Our results indicated a significant adverse pathology in patients who met the contemporary AS protocols. On the other hand, some patients in whom expectant management would be appropriate did not meet any criteria of published AS protocols. None of the clinical or histological criteria reported to date is able to sufficiently discriminate aggressive tumors from indolent ones.

External validation of the CAPRA-S score to predict biochemical recurrence, metastasis and mortality after radical prostatectomy in a European cohort

PURPOSE

The CAPRA-S score predicts prostate cancer recurrence based on pathological information from radical prostatectomy. To our knowledge CAPRA-S has never been externally validated in a European cohort. We independently validated CAPRA-S in a single institution European database.

MATERIALS AND METHODS

The study cohort comprised 14,532 patients treated with radical prostatectomy between January 1992 and August 2012. Prediction of biochemical recurrence, metastasis and cancer specific mortality by CAPRA-S was assessed by Kaplan-Meier analysis and the c-index. CAPRA-S performance to predict biochemical recurrence was evaluated by calibration plot and decision curve analysis.

RESULTS

Median followup was 50.8 months (IQR 25.0-96.0). Biochemical recurrence developed in 20.3% of men at a median of 21.2 months (IQR 7.7-44.9). When stratifying patients by CAPRA-S risk group, estimated 5-year biochemical recurrence-free survival was 91.4%, 70.4% and 29.3% in the low, intermediate and high risk groups, respectively. The CAPRA-S c-index to predict biochemical recurrence, metastasis and cancer specific mortality was 0.80, 0.85 and 0.88, respectively. Metastasis developed in 417 men and 196 men died of prostate cancer.

CONCLUSIONS

The CAPRA-S score was accurate when applied in a European study cohort. It predicted biochemical recurrence, metastasis and cancer specific mortality after radical prostatectomy with a c-index of greater than 0.80. The score can be valuable in regard to decision making for adjuvant therapy.