Establishment of Korean prostate cancer database by the Korean Urological Oncology Society

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.

Establishment of Prospective Registry of Active Surveillance for Prostate Cancer: The Korean Urological Oncology Society Database

PURPOSE

To establish a prospective registry for the active surveillance (AS) of prostate cancer (PC) using the Korean Urological Oncology Society (KUOS) database and to present interim analysis.

MATERIALS AND METHODS

The KUOS registry of AS for PC (KUOS-AS-PC) was organized in May 2019 and comprises multiple institutions nationwide. The eligibility criteria were as follows: patients with (1) pathologically proven PC; (2) pre-biopsy prostate-specific antigen (PSA) ≤20 ng/mL; (3) International Society of Urological Pathology (ISUP) grade 1 or 2 (no cribriform pattern 4); (4) clinical T stage ≤T2c; (5) positive core ratio ≤50%; and (6) maximal cancer involvement in the core ≤50%. Detailed longitudinal clinical information, including multi-parametric magnetic resonance imaging and disease-specific outcomes, was recorded.

RESULTS

From May 2019 to June 2021, 296 patients were enrolled, and 284 were analyzed. The mean±standard deviation (SD) age at enrollment was 68.7±8.2 years. The median follow-up period was 11.2 months (5.9-16.8 mo). Majority of patients had pre-biopsy PSA ≤10 ng/mL (91.2%), PSA density <0.2 ng/mL² (79.7%), ISUP grade group 1 (94.4%), single positive core (65.7%), maximal cancer involvement in the core ≤20% (78.1%), and clinical T stage of T1c or lower (72.9%). Fifty-two (18.3%) discontinued AS for various reasons. Interventions included radical prostatectomy (80.8%), transurethral prostatectomy (5.8%), primary androgen deprivation therapy (5.8%), radiation (5.8%), and focal therapy (1.9%). The mean±SD time to intervention was 8.9±5.2 months. The reasons for discontinuation included pathologic reclassification (59.6%), patient preference (25.0%), and radiologic reclassification (9.6%). Two (4.8%) patients with pathologic Gleason score upgraded to ISUP grade group 4, no biochemical recurrence.

CONCLUSIONS

The KUOS established a successful prospective database of PC patients undergoing AS in Korea, named the KUOS-AS-PC registry.

Population-wide impacts of aspirin, statins, and metformin use on prostate cancer incidence and mortality

We evaluated the association between aspirin, statins, and metformin use and prostate cancer (PC) incidence and mortality using a large population-based dataset. 388,760 men who participated in national health screening program in Korea during 2002–2003 were observed from 2004 to 2013. Hazard ratios of aspirin, statins, and metformin use for PC incidence and PC mortality were calculated with adjustment for simultaneous drug use. Cumulative use of each drug was inserted as time-dependent variable with 2-year time windows. Aspirin use ≥ 1.5 year (per 2-year) was associated with borderline decrease in PC mortality when compared to non-users (adjusted hazard ratio [aHR] 0.71, 95% confidence interval [CI] 0.50–1.02). Statins use was not associated with either PC incidence or PC mortality. Metformin ever-use was associated with decreased PC incidence compared with non-diabetics (aHR 0.86, 95% CI 0.77–0.96). Diabetics who were not using metformin or using low cumulative doses had higher PC mortality than non-diabetics (aHR 2.01, 95% CI 1.44–2.81, and aHR 1.70, 95% CI 1.07–2.69, respectively). However, subjects with higher cumulative doses of metformin did not show increased PC mortality. In conclusion, metformin use was associated with lower PC incidence. Use of aspirin and that of metformin among diabetic patients were associated with lower PC mortality.

Deep Learning with Quantitative Features of Magnetic Resonance Images to Predict Biochemical Recurrence of Radical Prostatectomy: A Multi-Center Study

Simple Summary

Biochemical recurrence after radical prostatectomy is vitally important for long-term oncological control and subsequent treatment of these patients. We applied radiomic technique to extract features from MR images of prostate cancer patients, and used deep learning algorithm to establish a predictive model for biochemical recurrence with high accuracy. The model was validated in 2 indepented cohorts with superior predictive value than traditional stratification systems. With the aid of this model, we are able to distinghuish patients with higher risk of developing biochemical recurrence at early stage, thus providing a window to initiate neoadjuvant or adjuvant therapies for prostate cancer patients.

Abstract

Biochemical recurrence (BCR) occurs in up to 27% of patients after radical prostatectomy (RP) and often compromises oncologic survival. To determine whether imaging signatures on clinical prostate magnetic resonance imaging (MRI) could noninvasively characterize biochemical recurrence and optimize treatment. We retrospectively enrolled 485 patients underwent RP from 2010 to 2017 in three institutions. Quantitative and interpretable features were extracted from T2 delineated tumors. Deep learning-based survival analysis was then applied to develop the deep-radiomic signature (DRS-BCR). The model’s performance was further evaluated, in comparison with conventional clinical models. The model achieved C-index of 0.802 in both primary and validating cohorts, outweighed the CAPRA-S score (0.677), NCCN model (0.586) and Gleason grade group systems (0.583). With application analysis, DRS-BCR model can significantly reduce false-positive predictions, so that nearly one-third of patients could benefit from the model by avoiding overtreatments. The deep learning-based survival analysis assisted quantitative image features from MRI performed well in prediction for BCR and has significant potential in optimizing systemic neoadjuvant or adjuvant therapies for prostate cancer patients.

Radium-223 in Asian patients with castration-resistant prostate cancer with symptomatic bone metastases: A single-arm phase 3 study

Aim

Radium‐223, a targeted alpha therapy, is approved widely for the treatment of patients with metastatic castrate‐resistant prostate cancer, based on a pivotal phase 3 study in predominantly white patients. We investigated the efficacy and safety of radium‐223 in Asian patients with castrate‐resistant prostate cancer and metastatic bone disease.

Methods

This multicenter, prospective, single‐arm, open‐label phase 3 trial evaluated the efficacy and safety of the standard radium‐223 regimen (55 kBq/kg every 4 weeks for six cycles) in patients from Asian countries. The primary endpoints were the safety and overall survival.

Results

A total of 226 patients were enrolled and received at least one dose of radium‐223. Median overall survival was 14.0 months (95% confidence interval [CI], 11.2–17.4). Median time to total alkaline phosphatase and prostate‐specific antigen progression were 7.5 (95% CI, 6.8–7.7) and 3.6 (95% CI, 3.1–3.7) months, respectively. Median skeletal‐related event‐free survival was 26.0 months (95% CI, 12.6–not reached). Grade ≥3 treatment‐emergent adverse events were reported in 103 (46%) of 226 patients, with anemia being the most common event (34 [15%] patients). Grade ≥3 drug‐related treatment‐emergent adverse events occurred in 39 (17%) of 226 patients. Serious treatment‐emergent adverse events were reported in 65 (29%) of 226 patients. Seven (3%) patients had an adverse event leading to death; none were considered to be related to radium‐223.

Conclusion

The results of this study support the use of the standard radium‐223 regimen for the treatment of Asian patients with castrate‐resistant prostate cancer and symptomatic bone metastases.

Trends in Prostate Cancer Prevalence and Radical Prostatectomy Rate according to Age Structural Changes in South Korea between 2005 and 2015

PURPOSE

Radical prostatectomy (RP) is one of main treatments for prostate cancer (Pca). The prevalence of Pca has been decreasing in recent reports. However, no study has reported trends in Pca prevalence or RP rate according to age structural changes. The objective of this study was to investigate trends in Pca prevalence and frequency of RP according to age structural change.

MATERIALS AND METHODS

We evaluated trends in Pca prevalence and RP rate using National Health Insurance Data from 2005 to 2015. Relationships for Pca prevalence and RP rate with age structural change were also determined. Primary outcomes included trends in Pca prevalence and RP rates according to age groups, comparing those before and after 2011.

RESULTS

Pca prevalence tended to increase before 2011 and decreased after 2011 in persons in the 60-years age group. RP rate increased pattern before 2011 and decreased after 2011 in age groups of 50s, 60s, and over 70s. Pca prevalence and age structural change showed a significantly positive relationship in all age groups, except for the age group under 40 years. RP rate and age structural change also showed a significantly positive relationship in all age groups.

CONCLUSION

Age structural change can affect the decreasing trend in Pca prevalence and RP rate in South Korea. Future studies are needed to validate this result.