Progression In Prostate Cancer Patients Research Articles

Identification macrophage signatures in prostate cancer by single-cell sequencing and machine learning

BackgroundThe tumor microenvironment (TME) encompasses a variety of cells that influence immune responses and tumor growth, with tumor-associated macrophages (TAM) being a crucial component of the TME. TAM can guide prostate cancer in different directions in response to various external stimuli.MethodsFirst, we downloaded prostate cancer single-cell sequencing data and second-generation sequencing data from multiple public databases. From these data, we identified characteristic genes associated with TAM clusters. We then employed machine learning techniques to select the most accurate TAM gene set and developed a TAM-related risk label for prostate cancer. We analyzed the tumor-relatedness of the TAM-related risk label and different risk groups within the population. Finally, we validated the accuracy of the prognostic label using single-cell sequencing data, qPCR, and WB assays, among other methods.ResultsIn this study, the TAM_2 cell cluster has been identified as promoting the progression of prostate cancer, possibly representing M2 macrophages. The 9 TAM feature genes selected through ten machine learning methods and demonstrated their effectiveness in predicting the progression of prostate cancer patients. Additionally, we have linked these TAM feature genes to clinical pathological characteristics, allowing us to construct a nomogram. This nomogram provides clinical practitioners with a quantitative tool for assessing the prognosis of prostate cancer patients.ConclusionThis study has analyzed the potential relationship between TAM and PCa and established a TAM-related prognostic model. It holds promise as a valuable tool for the management and treatment of PCa patients.

Deep reinforcement learning identifies personalized intermittent androgen deprivation therapy for prostate cancer.

The evolution of drug resistance leads to treatment failure and tumor progression. Intermittent androgen deprivation therapy (IADT) helps responsive cancer cells compete with resistant cancer cells in intratumoral competition. However, conventional IADT is population-based, ignoring the heterogeneity of patients and cancer. Additionally, existing IADT relies on pre-determined thresholds of prostate-specific antigen to pause and resume treatment, which is not optimized for individual patients. To address these challenges, we framed a data-driven method in two steps. First, we developed a time-varied, mixed-effect and generative Lotka-Volterra (tM-GLV) model to account for the heterogeneity of the evolution mechanism and the pharmacokinetics of two ADT drugs Cyproterone acetate and Leuprolide acetate for individual patients. Then, we proposed a reinforcement-learning-enabled individualized IADT framework, namely, I$^{2}$ADT, to learn the patient-specific tumor dynamics and derive the optimal drug administration policy. Experiments with clinical trial data demonstrated that the proposed I$^{2}$ADT can significantly prolong the time to progression of prostate cancer patients with reduced cumulative drug dosage. We further validated the efficacy of the proposed methods with a recent pilot clinical trial data. Moreover, the adaptability of I$^{2}$ADT makes it a promising tool for other cancers with the availability of clinical data, where treatment regimens might need to be individualized based on patient characteristics and disease dynamics. Our research elucidates the application of deep reinforcement learning to identify personalized adaptive cancer therapy.

GRP78 promotes bone metastasis of prostate cancer by regulating bone microenvironment through Sonic hedgehog signaling.

Bone metastasis is the leading cause of tumor-related deaths in patients with prostate cancer (PCa). The interactions between PCa and the bone microenvironment form a vicious cycle. However, the complex molecular mechanism by which PCa regulates the bone microenvironment remains unclear. To determine the role of glucose-regulated protein (GRP78) in bone metastasis and growth, we established intracardiac injection and tibial injection models, and performed their histological staining. To assess the effect of GRP78 on the differentiation of osteoblasts and osteoclasts, we performed cell co-culture, enzyme-linked immunosorbent assay, alizarin red staining, and tartrate-resistant acid phosphatase staining. We found that GRP78 is upregulated in PCa tissues and that its upregulation is associated with PCa progression in patients. Functional experiments showed that GRP78 overexpression in PCa cells considerably promotes bone metastasis and induces bone microstructure changes. Silencing GRP78 substantially inhibits the migration and invasion of PCa cells in vitro and bone metastasis and tumor growth in vivo. Mechanistically, GRP78 promotes the migration and invasion of PCa cells via the Sonic hedgehog (Shh) signaling pathway. Cell co-culture showed that GRP78 promotes the differentiation of osteoblasts and osteoclasts through Shh signaling. Our findings suggest that tumor-bone matrix interactions owing to GRP78-activated paracrine Shh signaling by PCa cells regulate the differentiation of osteoblasts and osteoclasts. This process promotes bone metastasis and the proliferation of PCa cells in the bone microenvironment. Targeting the GRP78/Shh axis can serve as a therapeutic strategy to prevent bone metastasis and improve the quality of life of patients with PCa.

P073 - The Wolverhampton Assessment Tool (WAT): An objective and reproducible PRO to monitor wellbeing and detect clinical progression in prostate cancer patients

P073 - The Wolverhampton Assessment Tool (WAT): An objective and reproducible PRO to monitor wellbeing and detect clinical progression in prostate cancer patients

Semaphorin 3C promotes de novo steroidogenesis in prostate cancer cells.

Intratumoral androgen biosynthesis contributes to castration-resistant prostate cancer progression in patients treated with androgen deprivation therapy. The molecular mechanisms by which castration-resistant prostate cancer acquires the capacity for androgen biosynthesis to bypass androgen deprivation therapy are not entirely known. Here, we show that semaphorin 3C, a secreted signaling protein that is highly expressed in castration-resistant prostate cancer, can promote steroidogenesis by altering the expression profile of key steroidogenic enzymes. Semaphorin 3C not only upregulates enzymes required for androgen synthesis from dehydroepiandrosterone or de novo from cholesterol but also simultaneously downregulates enzymes involved in the androgen inactivation pathway. These changes in gene expression correlate with increased production of androgens induced by semaphorin 3C in prostate cancer model cells. Moreover, semaphorin 3C upregulates androgen synthesis in LNCaP cell-derived xenograft tumors, likely contributing to the enhanced in vivo tumor growth rate post castration. Furthermore, semaphorin 3C activates sterol regulatory element-binding protein, a transcription factor that upregulates enzymes involved in the synthesis of cholesterol, a sole precursor for de novo steroidogenesis. The ability of semaphorin 3C to promote intratumoral androgen synthesis may be a key mechanism contributing to the reactivation of the androgen receptor pathway in castration-resistant prostate cancer, conferring continued growth under androgen deprivation therapy. These findings identify semaphorin 3C as a potential therapeutic target for suppressing intratumoral steroidogenesis.

Prognostic utility of RECIP 1.0 with manual and AI-based segmentations in biochemically recurrent prostate cancer from [68Ga]Ga-PSMA-11 PET images

PurposeThis study aimed to (i) validate the Response Evaluation Criteria in PSMA (RECIP 1.0) criteria in a cohort of biochemically recurrent (BCR) prostate cancer (PCa) patients and (ii) determine if this classification could be performed fully automatically using a trained artificial intelligence (AI) model.MethodsOne hundred ninety-nine patients were imaged with [68Ga]Ga-PSMA-11 PET/CT once at the time of biochemical recurrence and then a second time a median of 6.0 months later to assess disease progression. Standard-of-care treatments were administered to patients in the interim. Whole-body tumour volume was quantified semi-automatically (TTVman) in all patients and using a novel AI method (TTVAI) in a subset (n = 74, the remainder were used in the training process of the model). Patients were classified as having progressive disease (RECIP-PD), or non-progressive disease (non RECIP-PD). Association of RECIP classifications with patient overall survival (OS) was assessed using the Kaplan-Meier method with the log rank test and univariate Cox regression analysis with derivation of hazard ratios (HRs). Concordance of manual and AI response classifications was evaluated using the Cohen’s kappa statistic.ResultsTwenty-six patients (26/199 = 13.1%) presented with RECIP-PD according to semi-automated delineations, which was associated with a significantly lower survival probability (log rank p < 0.005) and higher risk of death (HR = 3.78 (1.96–7.28), p < 0.005). Twelve patients (12/74 = 16.2%) presented with RECIP-PD according to AI-based segmentations, which was also associated with a significantly lower survival (log rank p = 0.013) and higher risk of death (HR = 3.75 (1.23–11.47), p = 0.02). Overall, semi-automated and AI-based RECIP classifications were in fair agreement (Cohen’s k = 0.31).ConclusionRECIP 1.0 was demonstrated to be prognostic in a BCR PCa population and is robust to two different segmentation methods, including a novel AI-based method. RECIP 1.0 can be used to assess disease progression in PCa patients with less advanced disease.This study was registered with the Australian New Zealand Clinical Trials Registry (ACTRN12615000608561) on 11 June 2015.

RWD55 Predicting Metastatic Disease Progression in Prostate Cancer Patients Using Machine Learning of PSA Kinetics

Although only 5% of patients with prostate cancer (PCA) have metastases at diagnosis, approximately 20% of those with early stage disease have recurrence with metastases, often years later. Changes in prostate specific antigen (PSA) levels can predict recurrence. A machine learning approach to serum PSA lab kinetics, after diagnosis of localized PCA, was used to forecast progression with metastases.

Impact of an Expanded Definition of Family History on Outcomes of Active Surveillance for Prostate Cancer.

Despite family history being an established risk factor for prostate cancer, the role of a broader definition of family history inclusive of not just prostate cancer but other genetically related malignancies has not been investigated in the active surveillance population. Here, we evaluate the impact of an expanded definition of family history on active surveillance outcomes. Patients undergoing active surveillance for prostate cancer at Massachusetts General Hospital from 1997-2019 with detailed data available on family cancer history were identified. Primary outcome was biopsy progression-free survival, and secondary outcomes were treatment-free survival, adverse pathological features at prostatectomy, and biochemical recurrence after treatment. Statistical analyses were conducted using the Kaplan-Meier method and Cox regression. Among 855 evaluable patients, 300 (35.1%) patients had any family history of prostate cancer, and 95 (11.1%) had a family history of related malignancies suggestive of a hereditary cancer syndrome. Family history of prostate cancer alone was not associated with biopsy progression, whereas family history suggestive of a hereditary cancer syndrome was associated with a significantly increased risk of biopsy progression (HR 1.43, 95%CI 1.01-2.02), independent of other known clinicopathological risk factors in multivariable analysis. Similarly, family history suggestive of a hereditary cancer syndrome was associated with significantly lower treatment-free survival (HR 1.58, 95%CI 1.14-2.18) in multivariable analysis. No significant association was found between family history and adverse features on surgical pathology or biochemical recurrence. An expanded family history suggestive of a hereditary cancer syndrome is an independent predictor of biopsy progression during active surveillance. Men with such a family history may still be offered active surveillance but should be counseled regarding the higher risk of disease progression.

Time series radiomics for the prediction of prostate cancer progression in patients on active surveillance

Serial MRI is an essential assessment tool in prostate cancer (PCa) patients enrolled on active surveillance (AS). However, it has only moderate sensitivity for predicting histopathological tumour progression at follow-up, which is in part due to the subjective nature of its clinical reporting and variation among centres and readers. In this study, we used a long short-term memory (LSTM) recurrent neural network (RNN) to develop a time series radiomics (TSR) predictive model that analysed longitudinal changes in tumour-derived radiomic features across 297 scans from 76 AS patients, 28 with histopathological PCa progression and 48 with stable disease. Using leave-one-out cross-validation (LOOCV), we found that an LSTM-based model combining TSR and serial PSA density (AUC 0.86 [95% CI: 0.78–0.94]) significantly outperformed a model combining conventional delta-radiomics and delta-PSA density (0.75 [0.64–0.87]; p = 0.048) and achieved comparable performance to expert-performed serial MRI analysis using the Prostate Cancer Radiologic Estimation of Change in Sequential Evaluation (PRECISE) scoring system (0.84 [0.76–0.93]; p = 0.710). The proposed TSR framework, therefore, offers a feasible quantitative tool for standardising serial MRI assessment in PCa AS. It also presents a novel methodological approach to serial image analysis that can be used to support clinical decision-making in multiple scenarios, from continuous disease monitoring to treatment response evaluation.Key Points•LSTM RNN can be used to predict the outcome of PCa AS using time series changes in tumour-derived radiomic features and PSA density.•Using all available TSR features and serial PSA density yields a significantly better predictive performance compared to using just two time points within the delta-radiomics framework.•The concept of TSR can be applied to other clinical scenarios involving serial imaging, setting out a new field in AI-driven radiology research.

Commentary on "Clinical implications of endogenous testosterone density in prostate cancer progression in patients with favorable low and intermediate risk treated with radical prostatectomy".

Commentary on "Clinical implications of endogenous testosterone density in prostate cancer progression in patients with favorable low and intermediate risk treated with radical prostatectomy".

Clinical implications of endogenous testosterone density on prostate cancer progression in patients with very favorable low and intermediate risk treated with radical prostatectomy.

We tested the association between endogenous testosterone density (ETD; the ratio between endogenous testosterone [ET] and prostate volume) and prostate cancer (PCa) aggressiveness in very favorable low- and intermediate-risk PCa patients who underwent radical prostatectomy (RP). Only patients with prostate-specific antigen (PSA) within 10 ng ml -1 , clinical stage T1c, and International Society of Urological Pathology (ISUP) grade group 1 or 2 were included. Preoperative ET levels up to 350 ng dl -1 were classified as abnormal. Tumor quantitation density factors were evaluated as the ratio between percentage of biopsy-positive cores and prostate volume (biopsy-positive cores density, BPCD) and the ratio between percentage of cancer invasion at final pathology and prostate weight (tumor load density, TLD). Disease upgrading was coded as ISUP grade group >2, and progression as recurrence (biochemical and/or local and/or distant). Risk associations were evaluated by multivariable Cox and logistic regression models. Of 320 patients, 151 (47.2%) had intermediate-risk PCa. ET (median: 402.3 ng dl -1 ) resulted abnormal in 111 (34.7%) cases (median ETD: 9.8 ng dl -1 ml -1 ). Upgrading and progression occurred in 109 (34.1%) and 32 (10.6%) cases, respectively. Progression was predicted by ISUP grade group 2 (hazard ratio [HR]: 2.290; P = 0.029) and upgrading (HR: 3.098; P = 0.003), which was associated with ISUP grade group 2 (odds ratio [OR]: 1.785; P = 0.017) and TLD above the median (OR: 2.261; P = 0.001). After adjustment for PSA density and body mass index (BMI), ETD above the median was positively associated with BPCD (OR: 3.404; P < 0.001) and TLD (OR: 5.238; P < 0.001). Notably, subjects with abnormal ET were more likely to have higher BPCD (OR: 5.566; P = 0.002), as well as TLD (OR: 14.998; P = 0.016). Independently by routinely evaluated factors, as ETD increased, BPCD and TLD increased, but increments were higher for abnormal ET levels. In very favorable cohorts, ETD may further stratify the risk of aggressive PCa.

SC136 - MRI-derived precise scores for predicting pathologically-confirmed progression in prostate cancer patients on active surveillance

SC136 - MRI-derived precise scores for predicting pathologically-confirmed progression in prostate cancer patients on active surveillance

Fatty Acid Signaling Impacts Prostate Cancer Lineage Plasticity in an Autocrine and Paracrine Manner.

Simple SummaryA high-fat diet is implicated in prostate cancer progression in patients. Prostate-cancer-associated fibroblasts play an important role in promoting tumor progression and therapeutic resistance to androgen-receptor-signaling inhibitors, such as enzalutamide. We investigated the mechanism of saturated fatty acids’ impact on prostate cancer reprogramming. Our work demonstrates that the tumor microenvironment defines the biology of prostate cancer progression induced by saturated fatty acids. This study also provides relevant data to potentially improve prognosis for patients with high fat intake through the inhibition of the identified signaling pathways.Prostate cancer (PCa) affects an estimated 250,000 men every year and causes 34,000 deaths annually. A high-fat diet and obesity are associated with PCa progression and mortality. This study’s premise was the novel observation of crosstalk between PCa epithelia and cancer-associated fibroblasts (CAF) in response to palmitate-mediated lineage plasticity. We found that cholesterol activated canonical Hedgehog (Hh) signaling by increasing cilium Gli activity in PCa cells, while palmitate activated Hh independent of Gli. Exogenous palmitate activated SOX2, a known mediator of lineage plasticity, in PCa cells cocultured with CAF. Stroma-derived Wnt5a was upregulated in CAF while cocultured with PCa cells and treated with palmitate. Wnt5a knockdown in CAF inhibited Hh and SOX2 expression in PCa cells from cocultures. These findings supported our proposed mechanism of a high-fat diet promoting Hh signaling-mediated transformation within the tumor microenvironment. SOX2 and Wnt5a expression were limited by the CD36 neutralizing antibody. Mice xenografted with PCa epithelia and CAF tumors were fed a high-fat diet, leading to elevated SOX2 expression and lineage plasticity reprogramming compared to mice fed an isocaloric rodent diet. CD36 inhibition with enzalutamide elevated apoptosis by TUNEL, but limited proliferation and SOX2 expression compared to enzalutamide alone. This study revealed a mechanism for a high-fat diet to affect prostate cancer progression. We found that saturated fat induced lineage plasticity reprogramming of PCa by interaction with CAF through Wnt5a and Hh signaling.

Enzalutamide Monotherapy vs Active Surveillance in Patients With Low-risk or Intermediate-risk Localized Prostate Cancer

There are few published studies prospectively assessing pharmacological interventions that may delay prostate cancer progression in patients undergoing active surveillance (AS). To compare the efficacy and safety of enzalutamide monotherapy plus AS vs AS alone in patients with low-risk or intermediate-risk prostate cancer. The ENACT study was a phase 2, open-label, randomized clinical trial conducted from June 2016 to August 2020 at 66 US and Canadian sites. Eligible patients were 18 years or older, had received a diagnosis of histologically proven low-risk or intermediate-risk localized prostate cancer within 6 months of screening, and were undergoing AS. Patients were monitored during 1 year of treatment and up to 2 years of follow-up. Data analysis was conducted in February 2021. Randomized 1:1 to enzalutamide, 160 mg, monotherapy for 1 year or continued AS, as stratified by cancer risk and follow-up biopsy type. The primary end point was time to pathological or therapeutic prostate cancer progression (pathological, ≥1 increase in primary or secondary Gleason pattern or ≥15% increased cancer-positive cores; therapeutic, earliest occurrence of primary therapy for prostate cancer). Secondary end points included incidence of a negative biopsy result, percentage of cancer-positive cores, and incidence of a secondary rise in serum prostate-specific antigen (PSA) levels at 1 and 2 years, as well as time to PSA progression. Adverse events were monitored to assess safety. A total of 114 patients were randomized to treatment with enzalutamide plus AS and 113 to AS alone; baseline characteristics were similar between treatment arms (mean [SD] age, 66.1 [7.8] years; 1 Asian individual [0.4%], 21 Black or African American individuals [9.3%], 1 Hispanic individual [0.4%], and 204 White individuals [89.9%]). Enzalutamide significantly reduced the risk of prostate cancer progression by 46% vs AS (hazard ratio, 0.54; 95% CI, 0.33-0.89; P = .02). Compared with AS, odds of a negative biopsy result were 3.5 times higher; there was a significant reduction in the percentage of cancer-positive cores and the odds of a secondary rise in serum PSA levels at 1 year with treatment with enzalutamide; no significant difference was observed at 2 years. Treatment with enzalutamide also significantly delayed PSA progression by 6 months vs AS (hazard ratio, 0.71; 95% CI, 0.53-0.97; P = .03). The most commonly reported adverse events during enzalutamide treatment were fatigue (62 [55.4%]) and gynecomastia (41 [36.6%]). Three patients in the enzalutamide arm died; none were receiving the study drug at the time of death. No deaths were considered treatment-related. The results of this randomized clinical trial suggest that enzalutamide monotherapy was well-tolerated and demonstrated a significant treatment response in patients with low-risk or intermediate-risk localized prostate cancer. Enzalutamide may provide an alternative treatment option for patients undergoing AS. ClinicalTrials.gov Identifier: NCT02799745.

An extracellular vesicle-based assay for noninvasive detection of metastases and monitoring prostate cancer.

e17004 Background: Optimizing outcomes in prostate cancer (PCa) requires timely detect of metastatic progression of prostate cancer patients. We aim to optimize an extracellular vesicle (EV)-based Digital Scoring Assay for detecting PCa metastasis and noninvasive monitoring disease progression. Methods: PCa EV Digital Scoring Assay was developed by combining EV Click Chip, a nanotechnology-enabled microfluidic device for purifying PCa-derived EV and reverse-transcription droplet digital PCR for profiling disease-relevant mRNAs. A panel of 11 PCa-relevant mRNA markers were selected from The Tissue Atlas and a blood-based biomarker study. Plasma samples from 20 localized, 20 metastatic PCa patients, and serial plasma from three PCa patients were used to assess the performance of PCa EV Digital Scoring Assay with the 11-gene panel. mRNA expression of the panel was computed using weighted Z score method. ROC analysis was applied to discriminate localized from metastatic PCa. Results: After optimization, the capability of EV Click Chips (92.5 ± 5.4%) for capturing PCa-derived EVs from artificial plasma samples spiked with EVs outperformed ultracentrifugation (41.0 ± 3.2%) or precipitation methods (34.9± 2.2%; P&lt; 0.001). Strong signals of the 11-gene panel, i.e., ACP3, FOLH1, HOXB13, KLK2, KLK3, KLK4, MSMB, RLN1, SLC45A3, STEAP2, and TMPRSS2, were detected from three PCa cells (LNCaP, C4-2B, and 22Rv1) and their derived EVs, while rare signals were detected in either WBCs or EVs purified from male healthy donor. In the clinical study, the Z scores calculated from the 11-gene panel were significantly higher in metastatic than localized PCa with an area under the ROC curve of 0.88 (95% CI: 0.78-0.98). Finally, longitudinal analyses of three PCa patients with clinical progression, response, and stable diseases, respectively, showed the Z scores can precisely reflect the disease status even when it is undetectable by imaging. Conclusions: We demonstrate a sensitive PCa EV Digital Scoring Assay to identify metastatic PCa and dynamically monitor disease states in a noninvasive manner. This assay may augment current imaging tools for timely detection of PCa progression and provide a means to better personalized care.

Comparative performance of MRI-derived PRECISE scores and delta-radiomics models for the prediction of prostate cancer progression in patients on active surveillance

ObjectivesTo compare the performance of the PRECISE scoring system against several MRI-derived delta-radiomics models for predicting histopathological prostate cancer (PCa) progression in patients on active surveillance (AS).MethodsThe study included AS patients with biopsy-proven PCa with a minimum follow-up of 2 years and at least one repeat targeted biopsy. Histopathological progression was defined as grade group progression from diagnostic biopsy. The control group included patients with both radiologically and histopathologically stable disease. PRECISE scores were applied prospectively by four uro-radiologists with 5–16 years’ experience. T2WI- and ADC-derived delta-radiomics features were computed using baseline and latest available MRI scans, with the predictive modelling performed using the parenclitic networks (PN), least absolute shrinkage and selection operator (LASSO) logistic regression, and random forests (RF) algorithms. Standard measures of discrimination and areas under the ROC curve (AUCs) were calculated, with AUCs compared using DeLong’s test.ResultsThe study included 64 patients (27 progressors and 37 non-progressors) with a median follow-up of 46 months. PRECISE scores had the highest specificity (94.7%) and positive predictive value (90.9%), whilst RF had the highest sensitivity (92.6%) and negative predictive value (92.6%) for predicting disease progression. The AUC for PRECISE (84.4%) was non-significantly higher than AUCs of 81.5%, 78.0%, and 80.9% for PN, LASSO regression, and RF, respectively (p = 0.64, 0.43, and 0.57, respectively). No significant differences were observed between AUCs of the three delta-radiomics models (p-value range 0.34–0.77).ConclusionsPRECISE and delta-radiomics models achieved comparably good performance for predicting PCa progression in AS patients.Key Points• The observed high specificity and PPV of PRECISE are complemented by the high sensitivity and NPV of delta-radiomics, suggesting a possible synergy between the two image assessment approaches.• The comparable performance of delta-radiomics to PRECISE scores applied by expert readers highlights the prospective use of the former as an objective and standardisable quantitative tool for MRI-guided AS follow-up.• The marginally superior performance of parenclitic networks compared to conventional machine learning algorithms warrants its further use in radiomics research.

Diosgenin attenuates tumor growth and metastasis in transgenic prostate cancer mouse model by negatively regulating both NF-κB/STAT3 signaling cascades

Prostate cancer (PCa) is a common disease among men especially in the old age. The deregulated activation of oncogenic and pro-survival transcription factors has been linked with tumor progression in PCa patients. The consequence of diosgenin treatment on NF-κB/STAT3 activation in PCa cells as well as transgenic mouse model was determined. We also validated the hypothesis of targeting these transcription factors using in silico proteomics simulation model. Diosgenin abrogated NF-κB/STAT3 activation and this action was caused as a result of suppression of protein kinases and reporter gene activity that led to a substantial reduction in the expression of various tumorigenic gene products. In vivo, diosgenin (2% w/w) when mixed in diet and fed to mice abrogated tumor progression in transgenic mice. Diosgenin was also detected in serum and was well absorbed orally. Overall, our data highlights the promising efficacy of diosgenin in PCa therapy.

P0914 - Predicting early biochemical progression in prostate cancer patients staged with PSMA PET and multiparametric magnetic resonance imaging

P0914 - Predicting early biochemical progression in prostate cancer patients staged with PSMA PET and multiparametric magnetic resonance imaging

5α-Reductase Inhibitors Could Prevent the Clinical and Pathological Progression of Prostate Cancer: A Meta-analysis.

To explore the efficacy of 5-ARIs in PCA (Prostate Cancer). Searching through the major medical databases such as PubMed, Science Citation Index, EMBASE, Medline, Web of Science, Cochrane Library for all published studies in English until 2018. The following search terms were used: "Finasteride", "dutasteride", "5α reductase inhibitors", "5-ARIs", "prostate cancer", "prostate neoplasm" and the additional related studies were manually searched. Newcastle-Ottawa Scale (NOS) assessed the qualities of studies, and the outcome measures were observed by RR or OR with 95% CIs. We included 9 eligible studies for analyses from 2011 to 2017. We found that 5-ARIs group may have fewer progression (OR = 0.48 95%CI: 0.37-0.61 P < 0.00001, I2=4% p = 0.39) and lower pathological progression (OR = 0.46; 95%CI: 0.29-0.73; p = 0.001, I2=0% p = 0.45), compared with control groups. However, the OS did not show significant difference between two groups (OR=1.10; 95%CI:0.90-1.35; P = 0.35, I2 = 93% P < .00001 ). The use of 5-ARIs could prevent progression in PCA patients both clinical and pathological.

Radiomics analysis of 18F-Choline PET/CT in the prediction of disease outcome in high-risk prostate cancer: an explorative study on machine learning feature classification in 94 patients.

The aim of this study was (1) to investigate the application of texture analysis of choline PET/CT images in prostate cancer (PCa) patients and (2) to propose a machine-learning radiomics model able to select PET features predictive of disease progression in PCa patients with a same high-risk class at restaging. Ninety-four high-risk PCa patients who underwent restaging Cho-PET/CT were analyzed. Follow-up data were recorded for a minimum of 13 months after the PET/CT scan. PET images were imported in LIFEx toolbox to extract 51 features from each lesion. A statistical system based on correlation matrix and point-biserial-correlation coefficient has been implemented for features reduction and selection, while Discriminant analysis (DA) was used as a method for features classification in a whole sample and sub-groups for primary tumor or local relapse (T), nodal disease (N), and metastatic disease (M). In the whole group, 2 feature (HISTO_Entropy_log10; HISTO_Energy_Uniformity) results were able to discriminate the occurrence of disease progression at follow-up, obtaining the best performance in DA classification (sensitivity 47.1%, specificity 76.5%, positive predictive value (PPV) 46.7%, and accuracy 67.6%). In the sub-group analysis, the best performance in DA classification for T was obtained by selecting 3 features (SUVmin; SHAPE_Sphericity; GLCM_Correlation) with a sensitivity of 91.6%, specificity 84.1%, PPV 79.1%, and accuracy 87%; for N by selecting 2 features (HISTO = _Energy Uniformity; GLZLM_SZLGE) with a sensitivity of 68.1%, specificity 91.4%, PPV 83%, and accuracy 82.6%; and for M by selecting 2 features (HISTO_Entropy_log10 - HISTO_Entropy_log2) with a sensitivity 64.4%, specificity 74.6%, PPV 40.6%, and accuracy 72.5%. This machine learning model demonstrated to be feasible and useful to select Cho-PET features for T, N, and M with valuable association with high-risk PCa patients' outcomes. • Artificial intelligence applications are feasible and useful to select Cho-PET features. • Our model demonstrated the presence of specific features for T, N, and M with valuable association with high-risk PCa patients' outcomes. • Further prospective studies are necessary to confirm our results and to develop the application of artificial intelligence in PET imaging of PCa.