Predictor Of Biochemical Recurrence Research Articles

Development and Validation of a Multimodality Model Based on Whole-Slide Imaging and Biparametric MRI for Predicting Postoperative Biochemical Recurrence in Prostate Cancer.

Purpose To develop and validate a machine learning multimodality model based on preoperative MRI, surgical whole-slide imaging (WSI), and clinical variables for predicting prostate cancer (PCa) biochemical recurrence (BCR) following radical prostatectomy (RP). Materials and Methods In this retrospective study (September 2015 to April 2021), 363 male patients with PCa who underwent RP were divided into training (n = 254; median age, 69 years [IQR, 64-74 years]) and testing (n = 109; median age, 70 years [IQR, 65-75 years]) sets at a ratio of 7:3. The primary end point was biochemical recurrence-free survival. The least absolute shrinkage and selection operator Cox algorithm was applied to select independent clinical variables and construct the clinical signature. The radiomics signature and pathomics signature were constructed using preoperative MRI and surgical WSI data, respectively. A multimodality model was constructed by combining the radiomics signature, pathomics signature, and clinical signature. Using Harrell concordance index (C index), the predictive performance of the multimodality model for BCR was assessed and compared with all single-modality models, including the radiomics signature, pathomics signature, and clinical signature. Results Both radiomics and pathomics signatures achieved good performance for BCR prediction (C index: 0.742 and 0.730, respectively) on the testing cohort. The multimodality model exhibited the best predictive performance, with a C index of 0.860 on the testing set, which was significantly higher than all single-modality models (all P ≤ .01). Conclusion The multimodality model effectively predicted BCR following RP in patients with PCa and may therefore provide an emerging and accurate tool to assist postoperative individualized treatment. Keywords: MR Imaging, Urinary, Pelvis, Comparative Studies Supplemental material is available for this article. © RSNA, 2024.

Limited prognostic role of routine serum markers (AP, CEA, LDH and NSE) in oligorecurrent prostate cancer patients undergoing PSMA-radioguided surgery

IntroductionWe evaluated the prognostic role of pre-salvage prostate-specific membrane antigen–radioguided surgery (PSMA-RGS) serum levels of alkaline phosphatase (AP), carcinoembryonic antigen (CEA), lactate dehydrogenase (LDH), and neuron-specific enolase (NSE).Materials and methodsPatients who consecutively underwent PSMA-RGS for prostate cancer (PCa) oligorecurrence between January 2019 and January 2022 were selected. Biomarkers were assessed one day before surgery. Cox regression and logistic regression models tested the relationship between biochemical recurrence-free survival (BFS), 6- and 12-month biochemical recurrence (BCR), and several independent variables, including biomarkers.Results153 consecutive patients were analyzed. In the univariable Cox regression analysis, none of the biomarkers achieved predictor status (AP: hazard ratio [HR] = 1.03, 95% CI 0.99, 1.01; p = 0.19; CEA: HR = 1.73, 95% CI 0.94, 1.21; p = 0.34; LDH: HR = 1.01, 95% CI 1.00, 1.01; p = 0.05; NSE: HR = 1.02, 95% CI 0.98, 1.06; p = 0.39). The only independent predictor of BFS was the number of positive lesions on PSMA PET (HR = 1.17, 95% CI 1.02, 1.30; p = 0.03).The number of positive lesions was confirmed as independent predictor for BCR within 6 and 12 months (BCR < 6 months: odds ratio [OR] = 1.1, 95% CI 1.0, 1.3; p = 0.04; BCR < 12 months: OR = 1.1, 95% CI 1.0, 1.3; p = 0.04).ConclusionThe assessment of AP, CEA, LDH, and NSE before salvage PSMA-RGS showed no prognostic impact. Further studies are needed to identify possible predictors that will optimize patient selection for salvage PSMA-RGS.

Long-Term Oncological Outcomes after Nerve-Sparing Robot-Assisted Radical Prostatectomy for High-Risk Localized Prostate Cancer: A Single-Center, Two-Arm Prospective Study.

To compare the oncological outcomes of patients with high-risk localized prostate cancer undergoing nerve-sparing and non-nerve-sparing robot-assisted radical prostatectomy (RARP). Between November 2002 and December 2018, we prospectively recorded the data of patients undergoing RARP for high-risk localized prostate cancer (PCa) at our tertiary referral center. NSS (nerve-sparing surgery) was carefully offered on the basis of the preoperative clinical characteristics of the patients and an intraoperative assessment. The patients were stratified into two groups: nerve-sparing and non-nerve-sparing groups (yes/no). Radical prostatectomies were performed by 10 surgeons with a robot-assisted technique using a daVinci® surgical system. The primary oncological outcome evaluated was biochemical recurrence (BCR). The secondary oncological outcomes assessed were positive surgical margins (PSMs) and cancer-specific survival (CSS). A total of 779 patients were included in the study: 429 (55.1%) underwent NSS while 350 (44.9%) underwent non-NSS. After a mean (±SD) follow-up of 192 (±14) months, 328 (42.1%) patients developed BCR; no significant difference was found between the NSS and non-NSS groups (156 vs. 172; p = 0.09). Both our univariable and multivariable analyses found that the nerve-sparing approach was not a predictor of BCR (p > 0.05). Kaplan-Mayer survival curves for BCR showed no significant difference among the non-NSS, unilateral NSS, and bilateral NSS groups (log rank test = 0.6). PSMs were reported after RARPs for 254 (32.6%) patients, with no significant difference between the NSS and non-NSS group (143 vs. 111; p = 0.5). In the subgroup of 15 patients who died during the follow-up period, mean (±SD) CSS was 70.5 (±26.1) months, with no significant difference between the NSS and non-NSS groups (mean CSS: 70.3 vs. 70.7 months). NSS does not appear to negatively impact the oncological outcomes of patients with high-risk PCa. Randomized clinical trials are needed to confirm our promising findings.

Explainable and visualizable machine learning models to predict biochemical recurrence of prostate cancer.

Machine learning (ML) models presented an excellent performance in the prognosis prediction. However, the black box characteristic of ML models limited the clinical applications. Here, we aimed to establish explainable and visualizable ML models to predict biochemical recurrence (BCR) of prostate cancer (PCa). A total of 647 PCa patients were retrospectively evaluated. Clinical parameters were identified using LASSO regression. Then, cohort was split into training and validation datasets with a ratio of 0.75:0.25 andBCR-related features were included in Cox regression and five ML algorithm to construct BCR prediction models. The clinical utility of each model wasevaluated by concordance index (C-index) values and decision curve analyses (DCA). Besides, Shapley Additive Explanation (SHAP) values were used to explain the features in the models. We identified 11 BCR-related features using LASSO regression, then establishing five ML-based models, including random survival forest (RSF), survival support vector machine (SSVM), survival Tree (sTree), gradient boosting decision tree (GBDT), extreme gradient boosting (XGBoost), and a Cox regression model, C-index were 0.846 (95%CI 0.796-0.894), 0.774 (95%CI 0.712-0.834), 0.757 (95%CI 0.694-0.818), 0.820 (95%CI 0.765-0.869), 0.793 (95%CI 0.735-0.852), and 0.807 (95%CI 0.753-0.858), respectively. The DCA showed that RSF model had significant advantages over all models. In interpretability of ML models, the SHAP value demonstrated the tangible contribution of each feature in RSF model. Our score system provide reference for the identification for BCR, and the crafting of a framework for making therapeutic decisions for PCa on a personalized basis.

Salvage Androgen Deprivation Therapy as Potential Treatment for Recurrence after Robot-Assisted Radical Prostatectomy.

The efficacy of intermittent androgen deprivation therapy (ADT) for biochemical recurrence (BCR) after robot-assisted radical prostatectomy (RARP) is unknown, and its usefulness in Japanese practice needs to be investigated. We conducted a retrospective analysis of 85 patients who underwent RARP and were selected for intermittent ADT for postoperative recurrence at Kanazawa University Hospital between 2009 and 2019. Intermittent ADT was administered for 2 years. If prostate-specific antigen levels increased post-treatment, intermittent ADT was reinitiated. The median follow-up period was 47 months. The 73 patients had completed the initial course of ADT, and 12 were under initial ADT. The 5-year castration-resistant prostate-cancer-free survival rates, cancer-specific survival, and overall survival were 92.7%, 98.3%, and 94.7%, respectively. A subgroup analysis of 69 patients who completed intermittent ADT was conducted to evaluate the BCR rate following initial ADT. The 5-year BCR-free survival rate was 53.2%. Multivariate analysis identified testosterone ≤ 0.03 ng/mL during ADT as the sole predictor of BCR after ADT. Salvage intermittent ADT may be an effective treatment option for BCR after RARP. In addition, it would be useful to confirm strong testosterone suppression as a criterion for transition to intermittent therapy.

Pretreatment prostate-specific antigen density as a predictor of biochemical recurrence in patients with prostate cancer: a meta-analysis

BackgroundA consensus has not been reached on the value of prostate-specific antigen density (PSAD) as a predictor of biochemical recurrence of prostate cancer. This meta-analysis aimed to evaluate the association between PSAD and biochemical recurrence of prostate cancer after primary treatment.MethodsTwo authors systematically searched PubMed, Web of Science, and Embase databases (up to August September 10, 2023) to identify studies that assessed the value of pretreatment PSAD in predicting biochemical recurrence after primary treatment (radical prostatectomy or radiotherapy) of prostate cancer. A random effect model was used to pool adjusted hazard ratios (HR) with 95% confidence intervals (CI) for biochemical recurrence.ResultsNine studies with 4963 patients were eligible for the meta-analysis. The reported prevalence of biochemical recurrence ranged from 4 to 55.1%. For patients with higher PSAD compared to those with low PSAD, the pooled HR of biochemical recurrence was 1.59 (95% CI 1.21–2.10). Subgroup analysis showed that the pooled HR of biochemical recurrence was 1.80 (95% CI 1.34–2.42) for patients who received radical prostatectomy, and 0.98 (95% CI 0.66–1.45) for patients who received radiotherapy.ConclusionsElevated pretreatment PSAD may be an independent predictor for biochemical recurrence of prostate cancer after radical prostatectomy. Determining PSAD could potentially improve the prediction of biochemical recurrence in patients with prostate cancer.

Significance of the cribriform morphology area ratio for biochemical recurrence in Gleason score 4 + 4 prostate cancer patients following robot-assisted radical prostatectomy.

In prostate cancer, histological cribriform patterns are categorized as Gleason pattern 4, and recent studies have indicated that their size and percentage are associated with the risk of biochemical recurrence (BCR). However, these studies included a mixture of cases with various Gleason scores (GSs). We therefore examined the prognostic value of the area and percentage of cribriform patterns in patients with GS 4 + 4 prostate cancer. We investigated 108 patients with GS 4 + 4 prostate cancer who underwent robot-assisted radical prostatectomy (RARP). After digitally scanning the hematoxylin and eosin-stained slides, we measured the area of the entire cancer and cribriform patterns. Predictive factors for BCR were explored using log-rank test and Cox proportional hazard model analyses. Sixty-seven (62.0%) patients had a cribriform pattern in RARP specimens, and 32 (29.6%) experienced BCR. The median total cancer area, cribriform pattern area, and percentage of cribriform pattern area (% cribriform) were 427.70 mm2 (interquartile range [IQR], 171.65-688.53 mm2 ), 8.85 mm2 (IQR, 0-98.83 mm2 ), and 2.44% (IQR, 0%-33.70%), respectively. Univariate analyses showed that higher preoperative serum prostate-specific antigen (PSA) levels, positive resection margins, advanced pathological T stage, extraprostatic extension, larger total cancer area, larger cribriform morphology area, and higher % cribriform values were significantly associated with BCR. A multivariate analysis demonstrated that the PSA level (hazard ratio [HR], 1.061; 95% confidence interval [CI], 1.011-1.113; p = 0.017) and % cribriform (HR, 1.018; 95% CI, 1.005-1.031; p = 0.005) were independent predictors of BCR. An increased % cribriform value was associated with BCR in patients with GS 4 + 4 prostate cancer following RARP.

Stroma-specific gene expression signature identifies prostate cancer subtype with high recurrence risk

Current prognostic tools cannot clearly distinguish indolent and aggressive prostate cancer (PC). We hypothesized that analyzing individual contributions of epithelial and stromal components in localized PC (LPC) could improve risk stratification, as stromal subtypes may have been overlooked due to the emphasis on malignant epithelial cells. Hence, we derived molecular subtypes of PC using gene expression analysis of LPC samples from prostatectomy patients (cohort 1, n = 127) and validated these subtypes in two independent prostatectomy cohorts (cohort 2, n = 406, cohort 3, n = 126). Stroma and epithelium-specific signatures were established from laser-capture microdissection data and non-negative matrix factorization was used to identify subtypes based on these signatures. Subtypes were functionally characterized by gene set and cell type enrichment analyses, and survival analysis was conducted. Three epithelial (E1-E3) and three stromal (S1-S3) PC subtypes were identified. While subtyping based on epithelial signatures showed inconsistent associations to biochemical recurrence (BCR), subtyping by stromal signatures was significantly associated with BCR in all three cohorts, with subtype S3 indicating high BCR risk. Subtype S3 exhibited distinct features, including significantly decreased cell-polarity and myogenesis, significantly increased infiltration of M2-polarized macrophages and CD8 + T-cells compared to subtype S1. For patients clinically classified as CAPRA-S intermediate risk, S3 improved prediction of BCR. This study demonstrates the potential of stromal signatures in identification of clinically relevant PC subtypes, and further indicated that stromal characterization may enhance risk stratification in LPC and may be particularly promising in cases with high prognostic ambiguity based on clinical parameters.

Identification of a 9-gene signature to enhance biochemical recurrence prediction in primary prostate cancer: A benchmarking study using ten machine learning methods and twelve patient cohorts

Prostate cancer (PCa) is a prevalent malignancy among men worldwide, and biochemical recurrence (BCR) after radical prostatectomy (RP) is a critical turning point commonly used to guide the development of treatment strategies for primary PCa. However, the clinical parameters currently in use are inadequate for precise risk stratification and informing treatment choice. To address this issue, we conducted a study that collected transcriptomic data and clinical information from 1662 primary PCa patients across 12 multicenter cohorts globally. We leveraged 101 algorithm combinations that consisted of 10 machine learning methods to develop and validate a 9-gene signature, named BCR SCR, for predicting the risk of BCR after RP. Our results demonstrated that BCR SCR generally outperformed 102 published prognostic signatures. We further established the clinical significance of these nine genes in PCa progression at the protein level through immunohistochemistry on Tissue Microarray (TMA). Moreover, our data showed that patients with higher BCR SCR tended to have higher rates of BCR and distant metastasis after radical radiotherapy. Through drug target prediction analysis, we identified nine potential therapeutic agents for patients with high BCR SCR. In conclusion, the newly developed BCR SCR has significant translational potential in accurately stratifying the risk of patients who undergo RP, monitoring treatment courses, and developing new therapies for the disease.

Pre-surgical 68Ga-PSMA-11 PET for biochemical recurrence risk assessment: A surrogate of pelvic lymph node dissection? Follow-up analysis of a multicenter prospective phase 3 imaging trial.

285 Background: To compare the prognostic value of presurgical PSMA-PET and pelvic lymph nodes invasion (pN1) for biochemical recurrence (BCR) free-survival (FS) in patients with intermediate-risk to high-risk prostate cancer (PCa) treated with radical prostatectomy (RP) and pelvic lymph node dissection. Methods: This is a follow-up study of the surgery cohort included in the multicenter prospective phase 3 imaging trial (n=277; NCT03368547, NCT02611882, NCT02919111). Each 68Ga-PSMA-11-PET scan was read by three blinded independent readers. Local histopathology risk score (CAPRA-S (Cancer of the Prostate Risk Assessment) score without pN data), PSMA-PET extra-prostatic disease (N1/M1), and pN were used to assess risk of BCR. Patients were followed up after RP by the local investigators using electronic medical records. BCR was defined by a prostate-specific antigen (PSA) level ≥0.2 ng/ml after RP or an initiation of PCa specific secondary treatment (&gt;6 months after surgery). Univariate, multivariate Cox model, and c-statistic index were performed to assess the prognostic value of PSMA-PET, LNI and its added value to Local histopathology risk score. Results: From December 2015 to December 2019, 277 patients underwent surgery after PSMA-PET. Clinical follow-up was obtained in 240/277 (87%) patients. Median follow-up from surgery was 32.4 (IQR 23.3-42.9) months. Ninety-one/240 BCR events (38%) were observed. PSMA-PET N1/M1 and pN1 were found in 41/240 (17%) and 67/240 (28%) patients respectively. Local histopathology risk score, PSMA-PET and pN were significant univariate predictors of BCR. Only Local histopathology risk score and PSMA PET were significant in multivariate analysis (HR [95% CI] 1.4 (1.2-1.5) p&lt;0.0001) and (1.7 (1-2.9) p=0.03). Prognostic value of model combining local histopathology and PSMA-PET was not significantly different than model combining local histopathology and pN (c-statistic 0.74 (0.69-0.79) vs 0.73 (0.68-0.78); p= 0.69). In patient group with low-risk Local histopathology score and PSMA-PET N0-M0 only 4/109 (5%) were pN1. In patients with high-risk local histopathology score, a PSMA-PET N1/M1 was associated with a significant lower BCR-FS than a PSMA-PET N0-M0 (median survival (95% CI) 32.7 (14.9-NR) vs 8 (3.2-15.5) p= 0.001). pN1 was found in respectively 25/34 (74%) and 34/90 (38%). Conclusions: Combination of pre-surgical PSMA-PET and Local histopathology was not statistically different than the reference standard, i.e local histopathology and pN to predict BCR-FS. Interestingly rate of discrepancy with pN was low among patient with low histopathology risk and PSMA-PET (N0-M0) and patient with high histopathology risk and PSMA-PET (N1/M1). Clinical trial information: NCT03368547 , NCT02611882 , NCT02919111 .

Quantification of collagen content and stromal cellularity within reactive stroma is predictive of prostate cancer biochemical recurrence and specific death

Semiquantitative reactive stromal grading has been shown to be a predictor of biochemical recurrence and prostate cancer (PCa) specific death. It has been extensively validated. In this study we tested novel technologies to introduce quantitative measures of host response, in particular collagen content and stromal cellularity. We use 3 large retrospective cohorts, the Baylor College of Medicine cohort, the Brady cohort and the Pound cohort. Slides were stained and digitized using image deconvolution and analyzed using image segmentation and image analyses. PicroSirius red stain histochemical stains were used for collagen quantification. Area of cancer and stroma were measured independently, without regard to quality of stroma. Cellularity, in each compartment, was measured using image deconvolution, image segmentation and image analysis. Two biomarkers were tested in 3 independent cohorts with two endpoints, biochemical recurrence and prostate cancer specific death. Stromal cellularity (qCollCell) and stromal collagen area (qCollArea) are independently predictive biochemical recurrence in the Hopkins Brady cohort, particularly in Gleason 6–7 patients. Multivariate analysis demonstrated that increased stroma cellularity (qCollCell) was a significant predictor of PCa specific death, when compared to an established model of PCa, in the Baylor cohort. Stromal collagen (qCollArea) independently predicts PCa-specific death in the Hopkins Pound cohort. The introduction of a computerized quantitative test of the host response increases the probability that this test will be reproducible in other cohorts. The ability to improve prediction of prostate cancer specific death might lie in the study of the host and its response.

Anti-Müllerian hormone: a novel biomarker for aggressive prostate cancer? Emerging evidence from a prospective study of radical prostatectomies.

Prostate cancer patients are a heterogeneous group as regards the aggressiveness of the disease. The relationship of steroid hormones with the aggressiveness of prostate cancer is unclear. It is known that the anti-Müllerian hormone (AMH) inhibits prostate cancer cell lines in vitro. The aim of this study is to investigate the relationship of AMH and steroid hormones with the aggressiveness of prostate cancer. This was a prospective study of consecutive radical prostatectomy patients. We measured the following hormones: total testosterone, sex hormone-binding globulin, albumin, luteinizing hormone, follicle-stimulating hormone, estradiol, dehydroepiandrosterone sulfate, androstenedione, and AMH. The minimum follow-up after radical prostatectomy was 5years. For the aggressiveness of prostate cancer, we considered the following three variables: post-operative Gleason score (GS) ≥ 8, TNM pΤ3 disease, and prostate-specific antigen (PSA) biochemical recurrence (BCR). In total, 91 patients were enrolled. The mean age and PSA were 64.8years and 9.3ng/dl, respectively. The median post-operative GS was 7. Low AMH blood levels were correlated with higher post-operative GS (p = 0.001), as well as with PSA BCR (p = 0.043). With pT3 disease, only albumin was (negatively) correlated (p = 0.008). ROC analysis showed that AMH is a good predictor of BCR (AUC 0.646, 95% CI 0.510-0.782, p = 0.043); a cutoff value of 3.06ng/dl had a positive prognostic value of 71.4% and a negative prognostic value of 63.3% for BCR. Cox regression analysis showed that AMH is a statistically significant and independent prognostic marker for BCR (p = 0.013). More precisely, for every 1ng/ml of AMH rise, the probability for PSA BCR decreases by 20.8% (HR = 0.792). Moreover, in Kaplan-Meier analysis, disease-free survival is more probable in patients with AMΗ ≥ 3.06ng/ml (p = 0.004). Low AMH blood levels were correlated with aggressive prostate cancer in this radical prostatectomy cohort of patients. Therefore, AMH could be a prognostic biomarker for the aggressiveness of the disease.

Development and validation of a circulating tumor cells-related signature focusing on biochemical recurrence and immunotherapy response in prostate cancer

BackgroundStudies have shown that the circulating tumor cells (CTCs) play a key role for invasion and formation of distant metastases in prostate cancer (PCa). However, few CTCs-related genes (CRGs) have been developed for biochemical recurrence (BCR) prediction and clinical applications of PCa patients. Materials and methodsBioinformatics analysis with public PCa datasets were used to investigate the relationship between the differentially expressed CRGs and BCR. Lasso-COX regression analysis was used to constructed and validated a CRGs-based BCR prediction signature for PCa. Single-cell data were used to validate the expression levels of signature genes in different cell types and then explored the cell-cell communication relationships. Finally, the expression levels of signature genes were verified and the CRGs involved in immunotherapy response were further identified. ResultsThirteen CRGs were differentially expressed and closely associated with BCR in PCa. Then we constructed and validated a BCR prediction signature for PCa patients based on 3 differentially expressed CRGs (EMID1, SPP1 and UBE2C), and the signature was an independent factor to predict BCR for PCa. Single-cell data showed the specific expression patterns of the signature genes, while the SPP1 pathway plays an important role in cell-cell communication. Further analyses suggested UBE2C was highly expressed in BCR group and high expression of UBE2C had a better response for patients who received immunotherapy. Moreover, the expression levels of UBE2C in CTCs were higher than other cells and tissues, indicated that UBE2C may affect the BCR event of PCa patients through CTCs. ConclusionOur findings demonstrated that CRGs were significantly associated with BCR and immunotherapy efficacy in PCa and CRGs may influence the BCR event through CTCs.

Prediction of biochemical recurrence after laparoscopic radical prostatectomy

BackgroundRadical prostatectomy (RP) has been considered primary treatment for localized prostate cancer. Biochemical recurrence (BCR) occur approximately 20–30% in five year after RP. We aim to develop a novel nomogram to predict BCR-free survival (BCRFS) and performed external validation using a validation cohort that may help clinicians to make better decision for tailoring adjuvant treatment to specific group of patients.Materials and methodsThis retrospective cohort study included 370 localized and regional prostate cancer patients who underwent laparoscopic radical prostatectomy (LRP) in Songklanagarind hospital between January 2010 and December 2019, the patients were divided into two groups (primary cohort and validation cohort). BCR-free survival was created using Kaplan-Meier curve. Predictive factors for BCR were identified with univariable and multivariable analysis using Cox proportional hazards model. Predictive nomogram was created using these identified factors and developed for the prediction of biochemical recurrence free survival (BCRFS) at 1 and 5 years after LRP.ResultsFor primary Songklanagarind cohort, BCR was found in 105 patients (44.7%). Overall 1-year BCR-free survival was 52.8%, and 5-year BCR-free survival was 45.7% with median time to BCR of 18.1 months. Multivariable analysis identified unfavorable factor to BCRRF which are high initial serum PSA (> 20) (p < 0.001; HR 3.2), ISUP Gleason grade group > = 3 (p 0.033; HR 2.2), positive surgical margins (p 0.046; HR 1.5), and seminal vesicle involvement (p < 0.001; HR 5.2) and using for develop a novel nomogram to predict BCR. Concordance index 0.78.ConclusionProstate cancer patients with unfavorable factors, including high initial PSA (> 20), ISUP Gleason grade group > = 3, positive margin and extra-prostatic tumor extension are considered high risks and independent predictors of biochemical recurrence. This predictive models could potentially improve the 1 and 5-year BCR prediction after RP, according to the study’s findings and will aid medical professionals in achieving the goal of clinical prediction and creating a proper management for the localized treatment of prostate cancer underwent laparoscopic radical prostatectomy.

MRI characteristics and oncological follow-up of patients with ISUP grade group 4 or 5 prostate cancer

ObjectivesTo analyze multiparametric MRI (mpMRI) characteristics of patients with International Society of Urological Pathology (ISUP) grade group (GG) 4 or 5 prostate cancer (PC) and to correlate MRI parameters with the occurrence of biochemical recurrence (BCR) after radical prostatectomy (RPE).MethodsIn this single-center cohort study consecutive patients with mpMRI and ISUP GG 4 or 5 PC were retrospectively analyzed. Clinical, MR-guided biopsy, and diagnostic mpMRI parameter were assessed. A subcohort of patients with RPE and follow-up was analyzed separately. A univariate and multivariate analyses were performed to determine parameters that are associated to patients with BCR after RPE.Results145 patients (mean age 70y, median PSA 10.9 ng/ml) were analyzed. 99% had a PI-RADS classification of 4 or 5, 48% revealed MRI T3 stage, and median diameter of the MRI index lesion (IL) was 15 mm. IL showed a median ADC value of 668 ×10−6 mm2/s and exhibited contrast enhancement in 94% of the cases. For patients with follow-up after RPE (n = 82; mean follow-up time 68 ± 27 m), MRI parameters were significantly different for contact length of the IL to the pseudocapsule (LCC), MRI T3 stage, and IL localization (p < 0.05). Higher PSAD and MRI T3 stage were independent parameters for the risk of BCR when incorporating clinical, biopsy, and MRI parameters.ConclusionISUP GG 4 or 5 PC has distinctive characteristics on mpMRI and were detected on MRI in all cases. In addition, higher PSAD and MRI T3 stage were significant predictors for BCR after RPE.

Biological and clinical significance of radiomics features obtained from magnetic resonance imaging preceding pre-carbon ion radiotherapy in prostate cancer based on radiometabolomics.

We aimed to investigate the feasibility of metabolomics to explain the underlying biological implications of radiomics features obtained from magnetic resonance imaging (MRI) preceding carbon ion radiotherapy (CIRT) in patients with prostate cancer and to further explore the clinical significance of radiomics features on the prognosis of patients, based on their biochemical recurrence (BCR) status. Metabolomic results obtained using high-performance liquid chromatography coupled with tandem mass spectrometry of urine samples, combined with pre-RT radiomic features extracted from MRI images, were evaluated to investigate their biological significance. Receiver operating characteristic (ROC) curve analysis was subsequently conducted to examine the correlation between these biological implications and clinical BCR status. Statistical and metabolic pathway analyses were performed using MetaboAnalyst and R software. Correlation analysis revealed that methionine alteration extent was significantly related to four radiomic features (Contrast, Difference Variance, Small Dependence High Gray Level Emphasis, and Mean Absolute Deviation), which were significantly correlated with BCR status. The area under the curve (AUC) for BCR prediction of these four radiomic features ranged from 0.704 to 0.769, suggesting that the higher the value of these four radiomic features, the greater the decrease in methionine levels after CIRT and the lower the probability of BCR. Pre-CIRT MRI radiomic features were associated with CIRT-suppressed metabolites. These radiomic features can be used to predict the alteration in the amplitude of methionine after CIRT and the BCR status, which may contribute to the optimization of the CIRT strategy and deepen the understanding of PCa.

Comparison of MRI-Based Staging and Pathologic Staging for Predicting Biochemical Recurrence of Prostate Cancer After Radical Prostatectomy.

BACKGROUND. Currently most clinical models for predicting biochemical recurrence (BCR) of prostate cancer (PCa) after radical prostatectomy (RP) incorporate staging information from RP specimens, creating a gap in preoperative risk assessment. OBJECTIVE. The purpose of our study was to compare the utility of presurgical staging information from MRI and postsurgical staging information from RP pathology in predicting BCR in patients with PCa. METHODS. This retrospective study included 604 patients (median age, 60 years) with PCa who underwent prostate MRI before RP from June 2007 to December 2018. A single genitourinary radiologist assessed MRI examinations for extraprostatic extension (EPE) and seminal vesicle invasion (SVI) during clinical interpretations. The utility of EPE and SVI on MRI and RP pathology for BCR prediction was assessed through Kaplan-Meier and Cox proportional hazards analyses. Established clinical BCR prediction models, including the University of California San Francisco Cancer of the Prostate Risk Assessment (UCSF-CAPRA) model and the Cancer of the Prostate Risk Assessment Postsurgical (CAPRA-S) model, were evaluated in a subset of 374 patients with available Gleason grade groups from biopsy and RP pathology; two CAPRA-MRI models (CAPRA-S model with modifications to replace RP pathologic staging features with MRI staging features) were also assessed. RESULTS. Univariable predictors of BCR included EPE on MRI (HR = 3.6), SVI on MRI (HR = 4.4), EPE on RP pathology (HR = 5.0), and SVI on RP pathology (HR = 4.6) (all p < .001). Three-year BCR-free survival (RFS) rates for patients without versus with EPE were 84% versus 59% for MRI and 89% versus 58% for RP pathology, and 3-year RFS rates for patients without versus with SVI were 82% versus 50% for MRI and 83% versus 54% for RP histology (all p < .001). For patients with T3 disease on RP pathology, 3-year RFS rates were 67% and 41% for patients without and with T3 disease on MRI. AUCs of CAPRA models, including CAPRA-MRI models, ranged from 0.743 to 0.778. AUCs were not significantly different between CAPRA-S and CAPRA-MRI models (p > .05). RFS rates were significantly different between low- and intermediate-risk groups for only CAPRA-MRI models (80% vs 51% and 74% vs 44%; both p < .001). CONCLUSION. Presurgical MRI-based staging features perform comparably to postsurgical pathologic staging features for predicting BCR. CLINICAL IMPACT. MRI staging can preoperatively identify patients at high BCR risk, helping to inform early clinical decision-making. TRIAL REGISTRATION. ClinicalTrials.gov NCT00026884 and NCT02594202.

Impact of persistent PSA after salvage radical prostatectomy: a multicenter study.

Persistent prostatic specific antigen (PSA) represents a poor prognostic factor for recurrence after radical prostatectomy (RP). However, the impact of persistent PSA on oncologic outcomes in patients undergoing salvage RP is unknown. To investigate the impact of persistent PSA after salvage RP on long-term oncologic outcomes. Patients who underwent salvage RP for recurrent prostate cancer between 2000 and 2021 were identified from twelve high-volume centers. Only patients with available PSA after salvage RP were included. Kaplan-Meier analyses and multivariable Cox regression models were used to test the effect of persistent PSA on biochemical recurrence (BCR), metastasis and any death after salvage RP. Persistent PSA was defined as a PSA-value ≥ 0.1 ng/ml, at first PSA-measurement after salvageRP. Overall, 580 patients were identified. Of those, 42% (n = 242) harbored persistent PSA. Median follow-up after salvage RP was 38 months, median time to salvage RP was 64 months and median time to first PSA after salvage RP was 2.2 months. At 84 months after salvage RP, BCR-free, metastasis-free, and overall survival was 6.6 vs. 59%, 71 vs. 88% and 77 vs. 94% for patients with persistent vs. undetectable PSA after salvage RP (all p < 0.01). In multivariable Cox models persistent PSA was an independent predictor for BCR (HR: 5.47, p < 0.001) and death (HR: 3.07, p < 0.01). Persistent PSA is common after salvage RP and represents an independent predictor for worse oncologic outcomes. Patients undergoing salvage RP should be closely monitored after surgery to identify those with persistent PSA.

Machine Learning for the Prediction of Biochemical Recurrence in Patients Treated with Radical Prostatectomy.

Biochemical recurrence (BCR) occurs in about 40% of patients with prostate cancer following radical prostatectomy (RP). Our goal was to develop a machine learning model for the prediction of BCR five-years after RP, to improve patient prognostication. Patients treated with RP at a tertiary care medical center between 1990 and 2017 were included. A gradient boosted decision trees-based machine learning model modified to handle survival data was trained on 80% of the dataset. The model's performance was evaluated on the remaining 20%. Input variables were age at surgery, prostate specific antigen (PSA) at diagnosis (in ng/mL), pathologic Gleason grade group (GG), pathologic T stage (organ confined disease vs. extracapsular extension (ECE) vs. seminal vesicle invasion (SVI)), lymph node involvement, and surgical margin status. Model performance was assessed using time-dependent area under curve of the receiver operator curve (AUC). The full dataset included 11,139 patients, of whom 1,153 (10%) developed BCR. Median age at surgery was 59 and PSA at diagnosis was 5.4 ng/mL. Only 1,080 (9.7%) patients had GG 3, and 707 (6.3%) GG 4 and 5. 1,366 (12%) patients had positive surgical margins and 134 (1.2%) had lymph node involvement. Most patients had organ confined disease with EPE and SVI diagnosed in 2,759 (25%) and 392 (3.5%) patients, respectively. Median follow-up was 5 years and median time to BCR was 4 years. When validated on the hold-out set of 2,228 patients, the model shows a time-dependent AUC of 0.82 (95% CI 0.78 - 0.86) for BCR at t = 5 years. Our machine learning model can be used to estimate risk of BCR following RP and shows exceptional performance, with implications on patient prognostication and follow-up. We are currently working on validating its performance on an external dataset.

An MRI-Based Convolutional Neural Network to Predict Biochemical Recurrence Following Radiotherapy for Intermediate and High-Risk Localized Prostate Cancer.

The risk of biochemical recurrence (BCR) following radiotherapy (RT) for localized prostate cancer (LPCa) varies considerably within risk stratification groups defined by classic clinical and pathologic variables; there is an unmet need for low-cost tools that more robustly predict BCR and allow for individualized therapy. Published imaging-based algorithms for BCR prediction after RT are limited to hand-crafted radiomics and/or small cohorts. We aimed to develop a deep learning model to predict BCR at 5 years after RT for intermediate and high risk LPCa using pre-treatment T2-weighted (T2W) MRI. Patients with intermediate and high risk LPCa treated with radical RT at our institution between 2010 and 2015 were included. We excluded those who did not have a pre-treatment T2W-MRI and those with less than 5 years of follow-up. The Phoenix definition for BCR was used. The dataset (DS1) was split into training (70%), validation (20%), and test (10%) sets using a stratified technique. A U-Net model for prostate segmentation was trained and tested on a separate annotated prostate T2W-MRI dataset (DS2) of 225 patients from our institution. The U-Net model was then used to segment the whole prostate gland on the MRI images of DS1, and the segmented images were fed into four 2D convolutional neural networks (CNNs) using different network architectures and regularization techniques (VGG blocks with batch normalization, dropout, and max pooling layers) to predict BCR at 5 years. The CNNs were evaluated using the area under the receiver operating characteristic curve (AUC) on the test set. For benchmarking, three machine learning classifiers (Random Forest, Logistic Regression, and Support Vector Machines) were developed using the 5 most important features selected by Mean Decrease in Impurity from a set of 18 clinical variables. A total of 189 patients were included in DS1. Androgen deprivation therapy (ADT) was received by 83.6% of patients. BCR was identified in 26% of the cases. The Dice score for the U-Net segmentation model was 78% on the test set of DS2. The AUC achieved by the different CNNs for predicting BCR ranged between 0.53 and 0.75. The best performing CNN consisted of 3 convolutional layers, the first two followed by max-pooling layers, a flattening layer, a dense layer, and an output layer with softmax activation function. The best clinical model was a Random Forest algorithm with an AUC of 0.70. The selected clinical variables by decreasing feature importance were: age, time to nadir PSA, pre-treatment PSA, percentage of positive biopsy cores at diagnosis, and nadir PSA. We developed a deep learning model based on pre-treatment T2W-MRI to predict BCR at 5 years following radical RT for intermediate and high-risk LPCa. This CNN outperformed a model based on clinical variables and warrants further validation in external cohorts.