Assessing Prostate Cancer Aggressiveness Research Articles

Transfer Learning with Pretrained Convolutional Neural Network for Automated Gleason Grading of Prostate Cancer Tissue Microarrays.

The Gleason grading system has been the most effective prediction for prostate cancer patients. This grading system provides this possibility to assess prostate cancer's aggressiveness and then constitutes an important factor for stratification and therapeutic decisions. However, determining Gleason grade requires highly-trained pathologists and is time-consuming and tedious, and suffers from inter-pathologist variability. To remedy these limitations, this paper introduces an automatic methodology based on transfer learning with pretrained convolutional neural networks (CNNs) for automatic Gleason grading of prostate cancer tissue microarray (TMA). Fifteen pretrained (CNNs): Efficient Nets (B0-B5), NasNetLarge, NasNetMobile, InceptionV3, ResNet-50, SeResnet 50, Xception, DenseNet121, ResNext50, and inception_resnet_v2 were fine-tuned on a dataset of prostate carcinoma TMA images. Six pathologists separately identified benign and cancerous areas for each prostate TMA image by allocating benign, 3, 4, or 5 Gleason grade for 244 patients. The dataset was labeled by these pathologists and majority vote was applied on pixel-wise annotations to obtain a unified label. Results showed the NasnetLarge architecture is the best model among them in the classification of prostate TMA images of 244 patients with accuracy of 0.93 and area under the curve of 0.98. Our study can act as a highly trained pathologist to categorize the prostate cancer stages with more objective and reproducible results.

3D-Vision-Transformer Stacking Ensemble for Assessing Prostate Cancer Aggressiveness from T2w Images.

Vision transformers represent the cutting-edge topic in computer vision and are usually employed on two-dimensional data following a transfer learning approach. In this work, we propose a trained-from-scratch stacking ensemble of 3D-vision transformers to assess prostate cancer aggressiveness from T2-weighted images to help radiologists diagnose this disease without performing a biopsy. We trained 18 3D-vision transformers on T2-weighted axial acquisitions and combined them into two- and three-model stacking ensembles. We defined two metrics for measuring model prediction confidence, and we trained all the ensemble combinations according to a five-fold cross-validation, evaluating their accuracy, confidence in predictions, and calibration. In addition, we optimized the 18 base ViTs and compared the best-performing base and ensemble models by re-training them on a 100-sample bootstrapped training set and evaluating each model on the hold-out test set. We compared the two distributions by calculating the median and the 95% confidence interval and performing a Wilcoxon signed-rank test. The best-performing 3D-vision-transformer stacking ensemble provided state-of-the-art results in terms of area under the receiving operating curve (0.89 [0.61-1]) and exceeded the area under the precision-recall curve of the base model of 22% (p < 0.001). However, it resulted to be less confident in classifying the positive class.

Predicting absolute benefit in risk of metastasis of androgen deprivation therapy added to radiation therapy in patients with newly diagnosed prostate cancer using Prolaris.

5030 Background: Most patients would defer using androgen deprivation therapy (ADT) with radiation therapy (RT) when the number-needed-to-treat (NNT) exceeds 25 persons to prevent 1 from developing metastasis, corresponding to an absolute benefit of 4%.1 However, no tools for estimating personalized NNT or absolute benefit from ADT exist. We aimed to quantify personalized absolute benefit and NNT for persons receiving ADT added to single modality RT. Methods: The clinical cell-cycle risk (CCR) score combines the University of California, San Francisco’s Cancer of the Prostate Risk Assessment and the cell cycle progression molecular score to accurately assess prostate cancer aggressiveness. The effect of ADT added to RT was modeled using a 10-year risk of metastasis as a function of continuous CCR score for patients treated with RT alone. The relative benefit of ADT added to RT to reduce distant metastasis was modeled using published data from The Meta-Analysis of Randomized trials in Cancer of the Prostate (MARCAP) which utilized several prospectively randomized RT±ADT trials.2 The average absolute benefit was calculated for patients with CCR scores above and below a prespecified multimodality treatment threshold (MTT) using the distribution of scores in a cohort of patients commercially tested by Myriad Genetics. Results: The commercially tested cohort consisted of 56,485 patients spanning all National Comprehensive Cancer Network risk categories (33.7% very low/low risk, 29.8% favorable intermediate risk, 25.6% unfavorable intermediate risk, 11.0% high/very high risk), with 87.2% having CCR scores at or below the MTT and 12.7% with CCR scores above the threshold. The average absolute benefit of ADT treatment was 0.86% (NNT=116) for patients with CCR scores below the MTT and 8.2% (NNT=12) for patients with CCR scores above the MTT. Patients with CCR scores at precisely the MTT had a predicted absolute benefit of 3.7% (NNT=27). Conclusions: The Prolaris test can accurately predict an individual's benefit of adding ADT to RT, and the risk threshold is consistent with patient attitudes about when to use or omit ADT. 1. Spratt DE, Tward JD: IJROBP 108:899-902, 2020. 2. Kishan AU, Sun Y, Hartman H, et al. Lancet Oncol 23:304-316, 2022.

Sequential multiblock partial least squares discriminant analysis for assessing prostate cancer aggressiveness with multiparametric magnetic resonance imaging

In current radiology practice, multi-parametric magnetic resonance imaging (mpMRI) has recently become a key tool in diagnostic and therapeutic decisions. Although it is based on the subjective assessment of T2-weighted images, as well as perfusion-weighted and diffusion-weighted sequences, further quantitative parameters can also be derived from them for improving lesion phenotyping. Despite these parameters are usually exploited in a univariate way, ignoring the benefits of a real multivariate approach, still it is the gold standard imaging technique to assess prostate cancer location and probability of malignancy. In this paper, pharmacokinetic (perfusion) and exponential (diffusion) clinical models, as well as latent variable-based multivariate statistical models like multivariate curve resolution-alternating least squares (MCR-ALS), have been calculated and analyzed with sequential multi block-partial least squares discriminant analysis (SMB-PLS-DA) including technique-block differentiation, in order to better assess for cancer aggressiveness based on Gleason scales. The best prediction result was achieved by the ordered combination of diffusion blocks (MCR-ALS and exponential models) and normalized T2 values. The perfusion blocks did not improve the results obtained by diffusion and T2-weighted based parameters alone, so they can be removed from the SMB-PLS-DA model.

Multi-Site Concordance of Diffusion-Weighted Imaging Quantification for Assessing Prostate Cancer Aggressiveness.

BackgroundDiffusion‐weighted imaging (DWI) is commonly used to detect prostate cancer, and a major clinical challenge is differentiating aggressive from indolent disease.PurposeTo compare 14 site‐specific parametric fitting implementations applied to the same dataset of whole‐mount pathologically validated DWI to test the hypothesis that cancer differentiation varies with different fitting algorithms.Study TypeProspective.PopulationThirty‐three patients prospectively imaged prior to prostatectomy.Field Strength/Sequence3 T, field‐of‐view optimized and constrained undistorted single‐shot DWI sequence.AssessmentDatasets, including a noise‐free digital reference object (DRO), were distributed to the 14 teams, where locally implemented DWI parameter maps were calculated, including mono‐exponential apparent diffusion coefficient (MEADC), kurtosis (K), diffusion kurtosis (DK), bi‐exponential diffusion (BID), pseudo‐diffusion (BID*), and perfusion fraction (F). The resulting parametric maps were centrally analyzed, where differentiation of benign from cancerous tissue was compared between DWI parameters and the fitting algorithms with a receiver operating characteristic area under the curve (ROC AUC).Statistical TestLevene's test, P < 0.05 corrected for multiple comparisons was considered statistically significant.ResultsThe DRO results indicated minimal discordance between sites. Comparison across sites indicated that K, DK, and MEADC had significantly higher prostate cancer detection capability (AUC range = 0.72–0.76, 0.76–0.81, and 0.76–0.80 respectively) as compared to bi‐exponential parameters (BID, BID*, F) which had lower AUC and greater between site variation (AUC range = 0.53–0.80, 0.51–0.81, and 0.52–0.80 respectively). Post‐processing parameters also affected the resulting AUC, moving from, for example, 0.75 to 0.87 for MEADC varying cluster size.Data ConclusionWe found that conventional diffusion models had consistent performance at differentiating prostate cancer from benign tissue. Our results also indicated that post‐processing decisions on DWI data can affect sensitivity and specificity when applied to radiological–pathological studies in prostate cancer.Level of Evidence1Technical EfficacyStage 3

High-level expression of protein tyrosine phosphatase non-receptor 12 is a strong and independent predictor of poor prognosis in prostate cancer

BackgroundProtein tyrosine phosphatase non-receptor 12 (PTPN12) is ubiquitously tyrosine phosphatase with tumor suppressive properties.MethodsPTPN12 expression was analyzed by immunohistochemistry on a tissue microarray with 13,660 clinical prostate cancer specimens.ResultsPTPN12 staining was typically absent or weak in normal prostatic epithelium but seen in the majority of cancers, where staining was considered weak in 26.5%, moderate in 39.9%, and strong in 4.7%. High PTPN12 staining was associated with high pT category, high classical and quantitative Gleason grade, lymph node metastasis, positive surgical margin, high Ki67 labeling index and early prostate specific antigen recurrence (p < 0.0001 each). PTPN12 staining was seen in 86.4% of TMPRSS2:ERG fusion positive but in only 58.4% of ERG negative cancers. Subset analyses discovered that all associations with unfavorable phenotype and prognosis were markedly stronger in ERG positive than in ERG negative cancers but still retained in the latter group. Multivariate analyses revealed an independent prognostic impact of high PTPN12 expression in all cancers and in the ERG negative subgroup and to a lesser extent also in ERG positive cancers. Comparison with 12 previously analyzed chromosomal deletions revealed that high PTPN12 expression was significantly associated with 10 of 12 deletions in ERG negative and with 7 of 12 deletions in ERG positive cancers (p < 0.05 each) indicating that PTPN12 overexpression parallels increased genomic instability in prostate cancer.ConclusionsThese data identify PTPN12 as an independent prognostic marker in prostate cancer. PTPN12 analysis, either alone or in combination with other biomarkers might be of clinical utility in assessing prostate cancer aggressiveness.

Assessing Prostate Cancer Aggressiveness with Hyperpolarized Dual-Agent 3D Dynamic Imaging of Metabolism and Perfusion.

New magnetic resonance (MR) molecular imaging techniques offer the potential for noninvasive, simultaneous quantification of metabolic and perfusion parameters in tumors. This study applied a three-dimensional dynamic dual-agent hyperpolarized 13C magnetic resonance spectroscopic imaging approach with 13C-pyruvate and 13C-urea to investigate differences in perfusion and metabolism between low- and high-grade tumors in the transgenic adenocarcinoma of mouse prostate (TRAMP) transgenic mouse model of prostate cancer. Dynamic MR data were corrected for T1 relaxation and RF excitation and modeled to provide quantitative measures of pyruvate to lactate flux (kPL ) and urea perfusion (urea AUC) that correlated with TRAMP tumor histologic grade. kPL values were relatively higher for high-grade TRAMP tumors. The increase in kPL flux correlated significantly with higher lactate dehydrogenase activity and mRNA expression of Ldha, Mct1, and Mct4 as well as with more proliferative disease. There was a significant reduction in perfusion in high-grade tumors that associated with increased hypoxia and mRNA expression of Hif1α and Vegf and increased ktrans , attributed to increased blood vessel permeability. In 90% of the high-grade TRAMP tumors, a mismatch in perfusion and metabolism measurements was observed, with low perfusion being associated with increased kPL This perfusion-metabolism mismatch was also associated with metastasis. The molecular imaging approach we developed could be translated to investigate these imaging biomarkers for their diagnostic and prognostic power in future prostate cancer clinical trials. Cancer Res; 77(12); 3207-16. ©2017 AACR.

Utility of computed diffusion-weighted MRI for predicting aggressiveness of prostate cancer.

To investigate the value of computed (c) diffusion-weighted imaging (DWI) in assessing prostate cancer aggressiveness. Fifty-five patients with peripheral zone prostate cancer who underwent prebiopsy 1.5T magnetic resonance imaging (including native DWI at b-values of 0 and 1000 s/mm2 ) were included. cDWI signal intensities of peripheral zone prostate cancer and nonmalignant prostate tissue were measured. Association between changes in monoexponentially calculated cDWI signals according to different b-values and primary Gleason grades were assessed. The cDWI signal intensity of prostate cancer was lower at b = 0 s/mm2 and higher at b = 1000 s/mm2 compared to nonmalignant prostate tissue. The b-value at which the signal intensities of prostate cancer and nonmalignant prostate tissue were equal was defined as the "iso-b-value." On multivariate analysis, only the iso-b-value was a significant predictor of primary Gleason grade 4/5 cancer (P = 0.001). The area under the curve (AUC) of the iso-b-value for diagnosing primary Gleason grade 4/5 cancer was 0.94, and significantly higher than that of the tumor apparent diffusion coefficient (ADC) value with an AUC of 0.68 (P < 0.001). cDWI with iso-b-value-based semiquantitative analysis was found to be useful for predicting the aggressiveness of prostate cancer and may potentially outperform tumor ADC measurements in this setting. 3 Technical Efficacy: Stage 2 J. MAGN. RESON. IMAGING 2017;46:490-496.

MO-DE-207B-02: Assessment and Localization of Aggressiveness in Prostate Cancer Using Dynamic Contrast Enhanced-MRI

Purpose: To automatically assess prostate cancer aggressiveness and to map areas of high risk based on quantitative features from Dynamic Contrast Enhanced-MRI (DCE-MRI). Methods: Fifty-seven patients with DCE-MRI acquired on 3T Discovery MR750 GE were retrospectively analyzed. Prostate, peripheral zone (PZ) and gluteus maximus (DCEGM) were manually contoured. Unsupervised pattern recognition was used to decompose the DCE data in prostate as the product W.H of k weight maps W and k patterns H, k=3. A well-perfused pattern (quick wash-in) Hwp was identified along with its weight map Wwp. Voxels with weight Wwp>60% determined a well-perfused volume ROIwp. Six quantitative features F were extracted from SROI=mean(ROIwp) and normalized by SGM =mean(DCEGM). Map of aggressiveness for feature F was constructed as F-map = (F(SROI, SGM)/mean(Wwp(ROIwp)))*Wwp and validated using 30 positive biopsy targets from 15 patients with MR-US guided biopsies. The relationship between features and Gleason Score (GS) was investigated using Spearman correlation coefficient and Kruskal-Wallis test. Results: For 39 patients with PZ lesion, the volume of ROIwp and GS were significantly correlated. Three features were found statistically significant: late_AUC_ratio (ρ=0.32,p=0.049), early_AUFC_ratio (ρ=0.34,p=0.036) and wash-out_ratio (ρ=0.42,p=0.008), and three features were marginally significant: early_AUC_ratio (ρ=0.28,p=0.090), wash-in_ratio (ρ =0.28,p=0.090) and late_AUFC_ratio (ρ=0.29,p=0.074). For 30 targeted biopsies four features F were significantly correlated with GS: early_AUC_ratio (ρ= 0.57,p<0.001), wash-in_ratio (ρ=0.50,p=0.002), early_AUFC_ratio (ρ= 0.56,p=0.001), and wash-out ratio (ρ=0.34,p=0.045). AUC for indolent/aggressive for these features were 0.92 for early_AUC_ratio (p=0.018), 0.85 for wash-in_ratio (p=0.053), 0.95 for early_AUFC_ratio (p=0.012), and 0.88 for wash-out_ratio (p=0.032). F-maps were validated plotting F and F-map values for targeted biopsies: R2 correlation coefficients between F and F-map were larger than 0.85 for all features. Regression slope values were between 0.90 and 1.12. Conclusion: Quantitative features from DCE-MRI, normalized by muscle are able to assess aggressiveness and map the areas of risk in the prostate.

A novel live cell platform diagnostic utilizing phenotypic biomarkers for assessing prostate cancer aggressiveness.

e16567Background: A novel tissue based biomarker panel is developed to objectively assess disease aggressiveness and invasive potential of Prostate Cancer (CaP). The biomarker diagnostic platform i...

The expanding landscape of diffusion-weighted MRI in prostate cancer.

The added value of diffusion-weighted magnetic resonance imaging (DW-MRI) for the detection, localization, and staging of primary prostate cancer has been extensively reported in original studies and meta-analyses. More recently, DW-MRI and related techniques have been used to noninvasively assess prostate cancer aggressiveness and estimate its biological behavior. The present article aims to summarize the potential applications of DW-MRI for noninvasive optimization of pretherapeutic risk assessment, patient management decisions, and evaluation of treatment response.

Current role of multiparametric magnetic resonance imaging for prostate cancer.

Multiparametric magnetic resonance imaging (mp-MRI) has shown promising results in diagnosis, localization, risk stratification and staging of clinically significant prostate cancer, and targeting or guiding prostate biopsy. mp-MRI consists of T2-weighted imaging (T2WI) combined with several functional sequences including diffusion-weighted imaging (DWI), perfusion or dynamic contrast-enhanced imaging (DCEI) and spectroscopic imaging. Recently, mp-MRI has been used to assess prostate cancer aggressiveness and to identify anteriorly located tumors before and during active surveillance. Moreover, recent studies have reported that mp-MRI is a reliable imaging modality for detecting local recurrence after radical prostatectomy or external beam radiation therapy. Because assessment on mp-MRI can be subjective, use of the newly developed standardized reporting Prostate Imaging and Reporting Archiving Data System (PI-RADS) scoring system and education of specialist radiologists are essential for accurate interpretation. This review focuses on the current place of mp-MRI in prostate cancer and its evolving role in the management of prostate cancer.

A novel live cell platform utilizing phenotypic biophysical and molecular biomarkers for assessing prostate cancer aggressiveness.

e16031 Background: Overdiagnosis and overtreatment of prostate cancer is a problem that requires the need for a diagnostic test that can predict cancer aggressiveness and metastatic potential. Cell...

Multiparametric magnetic resonance imaging for prostate cancer: A review and update for urologists.

Recently, imaging of prostate cancer has greatly advanced since the introduction of multiparametric magnetic resonance imaging (mpMRI). mpMRI consists of T2-weighted sequences combined with several functional sequences including diffusion-weighted imaging, dynamic contrast-enhanced imaging, and/or magnetic resonance spectroscopy imaging. Interest has been growing in mpMRI because no single MRI sequence adequately detects and characterizes prostate cancer. During the last decade, the role of mpMRI has been expanded in prostate cancer detection, staging, and targeting or guiding prostate biopsy. Recently, mpMRI has been used to assess prostate cancer aggressiveness and to identify anteriorly located tumors before and during active surveillance. Moreover, recent studies have reported that mpMRI is a reliable imaging modality for detecting local recurrence after radical prostatectomy or external beam radiation therapy. In this regard, some urologic clinical practice guidelines recommended the use of mpMRI in the diagnosis and management of prostate cancer. Because mpMRI is the evolving reference standard imaging modality for prostate cancer, urologists should acquire cutting-edge knowledge about mpMRI. In this article, we review the literature on the use of mpMRI in urologic practice and provide a brief description of techniques. More specifically, we state the role of mpMRI in prostate biopsy, active surveillance, high-risk prostate cancer, and detection of recurrence after radical prostatectomy.

PSA enzymatic activity: A new biomarker for assessing prostate cancer aggressiveness

With the advent of widespread prostate-specific antigen (PSA) testing in recent decades, prostate cancer (PCa) has emerged as the most frequently diagnosed non-skin cancer among men in the U.S. and Europe. Greater screening rates coupled with improved detection methods have caused a controversial upsurge in the number of men undergoing prostate biopsy and subsequent treatment. However, current diagnostic techniques generally suffer from limited ability to identify which seemingly indolent cancers are biologically aggressive. We collected prostatic fluid from 778 post-radical prostatectomy specimens and randomly selected samples from both the clinically confirmed aggressive (n = 50) and non-aggressive (n = 50) prostate cancer populations. We measured the level of proteolytic enzyme activity of PSA (aPSA) in each sample and used receiver operating characteristic (ROC) analysis to correlate aPSA levels with prostate cancer aggressiveness. We found aPSA in prostatic fluid to be inversely proportional to disease stage, such that patients with the most aggressive PCa have on average significantly reduced aPSA compared to those with less aggressive disease. Significantly, our results suggest that many (22% in our study population) of the diagnosed patients with non-aggressive PCa could have averted or delayed radical prostatectomy. Given the high level of debate surrounding PSA screening effectiveness [3-5] and the recent U.S. Preventative Services Task Force recommendation to discontinue PSA screening [6], our results provide renewed hope that a clinical monitoring tool may emerge that truly refines PCa treatment decision-making.

Spermine and Citrate as Metabolic Biomarkers for Assessing Prostate Cancer Aggressiveness

Separating indolent from aggressive prostate cancer is an important clinical challenge for identifying patients eligible for active surveillance, thereby reducing the risk of overtreatment. The purpose of this study was to assess prostate cancer aggressiveness by metabolic profiling of prostatectomy tissue and to identify specific metabolites as biomarkers for aggressiveness. Prostate tissue samples (n = 158, 48 patients) with a high cancer content (mean: 61.8%) were obtained using a new harvesting method, and metabolic profiles of samples representing different Gleason scores (GS) were acquired by high resolution magic angle spinning magnetic resonance spectroscopy (HR-MAS). Multivariate analysis (PLS, PLS-DA) and absolute quantification (LCModel) were used to examine the ability to predict cancer aggressiveness by comparing low grade (GS = 6, n = 30) and high grade (GS≥7, n = 81) cancer with normal adjacent tissue (n = 47). High grade cancer tissue was distinguished from low grade cancer tissue by decreased concentrations of spermine (p = 0.0044) and citrate (p = 7.73·10−4), and an increase in the clinically applied (total choline+creatine+polyamines)/citrate (CCP/C) ratio (p = 2.17·10−4). The metabolic profiles were significantly correlated to the GS obtained from each tissue sample (r = 0.71), and cancer tissue could be distinguished from normal tissue with sensitivity 86.9% and specificity 85.2%. Overall, our findings show that metabolic profiling can separate aggressive from indolent prostate cancer. This holds promise for the benefit of applying in vivo magnetic resonance spectroscopy (MRS) within clinical MR imaging investigations, and HR-MAS analysis of transrectal ultrasound-guided biopsies has a potential as an additional diagnostic tool.

Hepsin is Highly Over Expressed in and a New Candidate for a Prognostic Indicator in Prostate Cancer

Other cDNA microarray studies have shown that hepsin is one of the highly over expressed genes in prostate cancer tissue compared with nonmalignant and benign prostatic hyperplasia tissue. We quantitatively analyzed hepsin gene expression with real-time polymerase chain reaction and calculated its relationships with clinicopathological parameters in a large cohort of samples. Matched prostate tissue samples from the cancerous and noncancerous parts of the same prostates were obtained from 90 patients with prostate cancer who underwent radical prostatectomy. Quantitative reverse transcriptase-polymerase chain reaction was performed using LightCycler Fast Start DNA Master SYBR Green I on a LightCycler (Roche Diagnostics GmbH, Mannheim, Germany) system. The ratio of hepsin-to-beta-actin (a housekeeping gene) was used to normalize data. Hepsin over expression in cancerous compared with noncancerous tissue was found in 81 of the 90 patient samples (90%, p <0.001). In 48 patients (53%) hepsin over expression was more than 10-fold in cancerous tissue. The ratio of cancerous-to-noncancerous hepsin expression was significantly higher in the 39 patients with grade 3 tumors compared with the 51 with grade 2 tumors (median 15.5 vs 9.6, p = 0.031). For the prognosis a cutoff at the 75th percentile provided a significant difference between patients at lower risk (pT2, G2 and Gleason score less than 7) and higher risk (pT3/4, G3 and Gleason score 7 or greater) for relapse. This report of the quantitative analysis of hepsin expression, which is the first to our knowledge, shows strong and significant over expression in prostate cancer tissue. Hepsin expression may be a new prognostic marker that could be used for assessing prostate cancer aggressiveness.