BACKGROUND: In this work, we compare input level, feature level and decision level data fusion techniques for automatic detection of clinically significant prostate lesions (csPCa).
METHODS: Multiple deep learning CNN architectures were developed using the Unet as the baseline. The CNNs use both multiparametric MRI images (T2W, ADC, and High b-value) and quantitative clinical data (prostate specific antigen (PSA), PSA density (PSAD), prostate gland volume & gross tumor volume (GTV)), and only mp-MRI images (n = 118), as input. In addition, co-registered ground truth data from whole mount histopathology images (n = 22) were used as a test set for evaluation.
RESULTS: The CNNs achieved for early/intermediate / late level fusion a precision of 0.41/0.51/0.61, recall value of 0.18/0.22/0.25, an average precision of 0.13 / 0.19 / 0.27, and F scores of 0.55/0.67/ 0.76. Dice Sorensen Coefficient (DSC) was used to evaluate the influence of combining mpMRI with parametric clinical data for the detection of csPCa. We compared the DSC between the predictions of CNN\'s trained with mpMRI and parametric clinical and the CNN\'s trained with only mpMRI images as input with the ground truth. We obtained a DSC of data 0.30/0.34/0.36 and 0.26/0.33/0.34 respectively. Additionally, we evaluated the influence of each mpMRI input channel for the task of csPCa detection and obtained a DSC of 0.14 / 0.25 / 0.28.
CONCLUSIONS: The results show that the decision level fusion network performs better for the task of prostate lesion detection. Combining mpMRI data with quantitative clinical data does not show significant differences between these networks (p = 0.26/0.62/0.85). The results show that CNNs trained with all mpMRI data outperform CNNs with less input channels which is consistent with current clinical protocols where the same input is used for PI-RADS lesion scoring.
BACKGROUND: The trial was registered retrospectively at the German Register for Clinical Studies (DRKS) under proposal number Nr. 476/14 & 476/19.

OBJECTIVE: To evaluate the difference in the diagnostic efficacy of 18F-PSMA-1007 PET/CT and pelvic MRI in primary prostate cancer, as well as the correlation between the two methods and histopathological parameters and serum PSA levels.
METHODS: A total of 41 patients with suspected prostate cancer who underwent 18F-PSMA-1007 PET/CT imaging in our department from 2018 to 2023 were retrospectively collected. All patients underwent 18F-PSMA-1007 PET/CT and MRI scans. The sensitivity, PPV and diagnostic accuracy of MRI and 18F-PSMA-1007 PET/CT in the diagnosis of prostate cancer were calculated after comparing the results of MRI and 18F-PSMA-1007 PET/CT with biopsy. The Spearman test was used to calculate the correlation between 18F-PSMA-1007 PET/CT, MRI parameters, histopathological indicators, and serum PSA levels.
RESULTS: Compared with histopathological results, the sensitivity, PPV and diagnostic accuracy of 18F-PSMA-1007 PET/CT in the diagnosis of prostate cancer were 95.1%, 100.0% and 95.1%, respectively. The sensitivity, PPV and diagnostic accuracy of MRI in the diagnosis of prostate cancer were 82.9%, 100.0% and 82.9%, respectively. There was a mild to moderately positive correlation between Gleason (Gs) score, Ki-67 index, serum PSA level and 18F-PSMA-1007 PET/CT parameters (p < 0.05). There was a moderately negative correlation between the expression of AMACR (P504S) and 18F-PSMA-1007 PET/CT parameters (p < 0.05). The serum PSA level and the Gs score were moderately positively correlated with the MRI parameters (p < 0.05). There was no correlation between histopathological parameters and MRI parameters (p > 0.05).
CONCLUSIONS: Compared with MRI, 18F-PSMA-1007 PET/CT has higher sensitivity and diagnostic accuracy in the detection of malignant prostate tumors. In addition, the Ki-67 index and AMACR (P504S) expression were only correlated with 18F-PSMA-1007 PET/CT parameters. Gs score and serum PSA level were correlated with 18F-PSMA-1007 PET/CT and MRI parameters. 18F-PSMA-1007 PET/CT examination can provide certain reference values for the clinical diagnosis, evaluation, and treatment of malignant prostate tumors.

UNASSIGNED: Tobacco contains harmful carcinogens that have been associated with cancers. Some studies have associated tobacco smoking with prostate cancer (PCa). The relationship between alcohol consumption as a risk factor for prostate cancer has been debated. Some studies associated alcohol consumption with increased risk of PCa, associating alcohol consumption with higher-grade cancers and poorer prognosis. Other studies have found a minimal relationship with PCa, with some even suggesting that alcohol consumption may even be protective. This study evaluates the association between smoking and alcohol consumption in prostate cancer patients.
UNASSIGNED: This is a retrospective study on one hundred and fifty-two patients diagnosed with prostate cancer with a known history of both smoking and or alcohol consumption managed over a 9year period from January 2012 to December 2020 from three Urology referrals hospitals. Patients with incomplete history were excluded. Their data such as age, a history of cigarette smoking, prostate-specific antigen level, prostate biopsy histopathology reports, and Gleason\'s grade were extracted. This was coded into Microsoft Excel and analyzed with SPSS version 20. The results were analyzed and presented in tables and charts.
UNASSIGNED: One hundred and thirty-five patients had a premorbid history of smoking and alcohol consumption with a mean age of 69 years and a modal age in the 70-79-year age group. Fifty-three (39.3%) of the patients had a history of cigarette smoking, ninety-four (69.6%) had a history of alcohol consumption. In comparison, fifty-one (37.8%) had a history of cigarette smoking and alcohol consumption. The high-risk Gleason\'s 8-10 prostate cancer was commoner among smokers than nonsmokers. There was no statistically significant association between cigarette smoking and alcohol consumption alone and combined with PCa.
UNASSIGNED: The high-risk Gleason\'s 8-10 prostate cancer was commoner among smokers than nonsmokers. There was no statistically significant association between cigarette smoking and alcohol consumption and the risk of prostate cancer.

OBJECTIVE: The Gleason score (GS) and positive needles are crucial aggressive indicators of prostate cancer (PCa). This study aimed to investigate the usefulness of magnetic resonance imaging (MRI) radiomics models in predicting GS and positive needles of systematic biopsy in PCa.
METHODS: A total of 218 patients with pathologically proven PCa were retrospectively recruited from 2 centers. Small-field-of-view high-resolution T2-weighted imaging and post-contrast delayed sequences were selected to extract radiomics features. Then, analysis of variance and recursive feature elimination were applied to remove redundant features. Radiomics models for predicting GS and positive needles were constructed based on MRI and various classifiers, including support vector machine, linear discriminant analysis, logistic regression (LR), and LR using the least absolute shrinkage and selection operator. The models were evaluated with the area under the curve (AUC) of the receiver-operating characteristic.
RESULTS: The 11 features were chosen as the primary feature subset for the GS prediction, whereas the 5 features were chosen for positive needle prediction. LR was chosen as classifier to construct the radiomics models. For GS prediction, the AUC of the radiomics models was 0.811, 0.814, and 0.717 in the training, internal validation, and external validation sets, respectively. For positive needle prediction, the AUC was 0.806, 0.811, and 0.791 in the training, internal validation, and external validation sets, respectively.
CONCLUSIONS: MRI radiomics models are suitable for predicting GS and positive needles of systematic biopsy in PCa. The models can be used to identify aggressive PCa using a noninvasive, repeatable, and accurate diagnostic method.

Prostate cancer (PCa) is the most prevalent non-cutaneous cancer in men. Early PCa detection has been made possible by the adoption of screening methods based on the serum prostate-specific antigen and Gleason score (GS). The aim of this study was to correlate gene expression with the differentiation level of prostate adenocarcinomas, as indicated by GS. We used data from The Cancer Genome Atlas (TCGA) and included 497 prostate cancer patients, 52 of which also had normal tissue sample sequencing data. Gene ontology analysis revealed that higher GSs were associated with greater responses to DNA damage, telomere lengthening, and cell division. Positive correlation was found with transcription factor activator of the adenovirus gene E2 (E2F) and avian myelocytomatosis viral homolog (MYC) targets, G2M checkpoints, DNA repair, and mitotic spindles. Immune cell deconvolution revealed high M0 macrophage counts and an increase in M2 macrophages dependent on the GS. The molecular pathways most correlated with GSs were cell cycle, RNA transport, and calcium signaling (depleted). A combinatorial approach identified a set of eight genes able to differentiate by k-Nearest Neighbors (kNN) between normal tissues, low-Gleason tissues, and high-Gleason tissues with high accuracy. In conclusion, our study could be a step forward to better understanding the link between gene expression and PCa progression and aggressiveness.

We aimed to retrospectively review outcomes in patients with high-risk prostate cancer and a Gleason score ≤ 6 following modern radiotherapy. We analyzed the outcomes of 1374 patients who had undergone modern radiotherapy, comprising a high-risk low grade [HRLG] group (Gleason score ≤ 6; n = 94) and a high-risk high grade [HRHG] group (Gleason score ≥ 7, n = 1125). We included 955 patients who received brachytherapy with or without external beam radio-therapy (EBRT) and 264 who received modern EBRT (intensity-modulated radiotherapy [IMRT] or stereotactic body radiotherapy [SBRT]). At a median follow-up of 60 (2-177) months, actuarial 5-year biochemical failure-free survival rates were 97.8 and 91.8% (p = 0.017), respectively. The frequency of clinical failure in the HRLG group was less than that in the HRHG group (0% vs 5.4%, p = 0.012). The HRLG group had a better 5-year distant metastasis-free survival than the HRHG group (100% vs 96.0%, p = 0.035). As the HRLG group exhibited no clinical failure and better outcomes than the HRHG group, the HRLG group might potentially be classified as a lower-risk group.

Multi-criteria optimization (MCO) function has been available on commercial radiotherapy (RT) treatment planning systems to improve plan quality; however, no study has compared Eclipse and RayStation MCO functions for prostate RT planning. The purpose of this study was to compare prostate RT MCO plan qualities in terms of discrepancies between Pareto optimal and final deliverable plans, and dosimetric impact of final deliverable plans. In total, 25 computed tomography datasets of prostate cancer patients were used for Eclipse (version 16.1) and RayStation (version 12A) MCO-based plannings with doses received by 98% of planning target volume having 76 Gy prescription (PTV76D98%) and 50% of rectum (rectum D50%) selected as trade-off criteria. Pareto optimal and final deliverable plan discrepancies were determined based on PTV76D98% and rectum D50% percentage differences. Their final deliverable plans were compared in terms of doses received by PTV76 and other structures including rectum, and PTV76 homogeneity index (HI) and conformity index (CI), using a t-test. Both systems showed discrepancies between Pareto optimal and final deliverable plans (Eclipse: -0.89% (PTV76D98%) and -2.49% (Rectum D50%); RayStation: 3.56% (PTV76D98%) and -1.96% (Rectum D50%)). Statistically significantly different average values of PTV76D98%,HI and CI, and mean dose received by rectum (Eclipse: 76.07 Gy, 0.06, 1.05 and 39.36 Gy; RayStation: 70.43 Gy, 0.11, 0.87 and 51.65 Gy) are noted, respectively (p < 0.001). Eclipse MCO-based prostate RT plan quality appears better than that of RayStation.

OBJECTIVE: Percentage of positive cores involved on a systemic prostate biopsy has been established as a risk factor for adverse oncologic outcomes and is a National Comprehensive Cancer Network (NCCN) independent parameter for unfavorable intermediate-risk disease. Most data from a radiation standpoint was published in an era of conventional fractionation. We explore whether the higher biological dose delivered with SBRT can mitigate this risk factor.
METHODS: A large single institutional database was interrogated to identify all patients diagnosed with localized prostate cancer (PCa) treated with 5-fraction SBRT without ADT. Pathology results were reviewed to determine detailed core involvement as well as Gleason score (GS). High-volume biopsy core involvement was defined as ≥ 50%. Weighted Gleason core involvement was reviewed, giving higher weight to higher-grade cancer. The PSA kinetics and oncologic outcomes were analyzed for association with core involvement.
RESULTS: From 2009 to 2018, 1590 patients were identified who underwent SBRT for localized PCa. High-volume core involvement was a relatively rare event observed in 19% of our cohort, which was observed more in patients with small prostates (p < 0.0001) and/or intermediate-risk disease (p = 0.005). Higher PSA nadir was observed in those patients with low-volume core involvement within the intermediate-risk cohort (p = 0.004), which was confirmed when core involvement was analyzed as a continuous variable weighted by Gleason score (p = 0.049). High-volume core involvement was not associated with biochemical progression (p = 0.234).
CONCLUSIONS: With a median follow-up of over 4 years, biochemical progression was not associated with pretreatment high-volume core involvement for patients treated with 5-fraction SBRT alone. In the era of prostate SBRT and MRI-directed prostate biopsies, the use of high-volume core involvement as an independent predictor of unfavorable intermediate risk disease should be revisited.

UNASSIGNED: The purpose of this study was to investigate the clinical significance of serum high sensitive C-reactive protein/albumin ratio in primary prostate biopsy.
UNASSIGNED: Retrospective analysis was done on the clinical data of 1679 patients who had their first transrectal or perineal prostate biopsy at our situation from 2010 to 2018. Prostate cancer (PCa) and benign prostatic hyperplasia (BPH) were the pathologic diagnoses in 819 and 860 cases, respectively. A comparison was made between the HAR differences between PCa and BPH patients as well as the positive prostate biopsy rate differences between groups with increased and normal HAR. The results of the prostate biopsy were examined using logistic regression, and a model for predicting prostate cancer was created. The receiver characteristic curve (ROC) was used to determine the model\'s prediction effectiveness. The clinical models integrated into HAR were evaluated for their potential to increase classification efficacy using net reclassification improvement (NRI) and integrated discrimination improvement (IDI). According to the Gleason score (GS) categorization system, prostate cancer patients were separated into low, middle, and high GS groups. The differences in HAR between the various groups were then compared. The prevalence of high GSPCa and metastatic PCa in normal populations and the prevalence of higher HAR in prostate cancer patients were compared using the chi-square test.
UNASSIGNED: Patients with PCa had a median HAR (upper quartile to lower quartile) of 0.0379 (10-3), patients with BPH had a median HAR (0.0137 (10-3)), and the difference was statistically significant (p<0.05). Patients with increased HAR and the normal group, respectively, had positive prostate biopsy rates of 52% (435/839)and 46% (384/840), and the difference was statistically significant (p<0.05). Logistic regression analysis showed that HAR (OR=3.391, 95%CI 2.082 ~ 4.977, P < 0.05), PSA density (PSAD) (OR=7.248, 95%CI 5.005 ~ 10.495, P < 0.05) and age (OR=1.076, 95%CI 1.056 ~ 1.096, P < 0.05) was an independent predictor of prostate biopsy results. Two prediction models are built: a clinical model based on age and PSAD, and a prediction model that adds HAR to the clinical model. The two models\' ROC had area under the curves (AUC) of 0.814 (95%CI 0.78-0.83) and 0.815 (95%CI 0.79-0.84), respectively. When compared to a single blood total PSA (tPSA) with an AUC of 0.746 (95%CI 0.718-0.774), they were all superior. Nevertheless, there was no statistically significant difference (p<0.05) between the two models. We assessed the prediction model integrated into HAR\'s capacity to increase classification efficiency using NRI and IDI, and we discovered that NRI>0, IDI>0, and the difference was statistically significant (P>0.05).There was a statistically significant difference in HAR between various GS groups for individuals who had prostate cancer as a consequence of biopsy (p<0.05). The incidence of high GS and metastatic patients was statistically significantly greater (p<0.05) in the HAR elevated group (90.1%and 39.3%, respectively) than in the HAR normal group (84.4% and 12.0%).
UNASSIGNED: Prostate biopsy results that were positive were impacted by HAR, an independent factor that increased with the rate of PCa discovery. Patients with elevated HAR had a greater risk of high GS as well as metastatic PCa among those with recently diagnosed prostate cancer through prostate biopsy.

Prostate cancer (PCa) is one of the most common cancers in men worldwide, and its timely diagnosis and treatment are becoming increasingly important. MRI is in increasing use to diagnose cancer and to distinguish between non-clinically significant and clinically significant PCa, leading to more precise diagnosis and treatment. The purpose of this study is to present a radiomics-based method for determining the Gleason score (GS) for PCa using tumour heterogeneity on multiparametric MRI (mp-MRI).
Twenty-six patients with biopsy-proven PCa were included in this study. The quantitative T2 values, apparent diffusion coefficient (ADC) and signal enhancement rates (α) were calculated using multi-echo T2 images, diffusion-weighted imaging (DWI) and dynamic contrast-enhanced MRI (DCE-MRI), for the annotated region of interests (ROI). After texture feature analysis, ROI range expansion and feature filtering was performed. Then obtained data were put into support vector machine (SVM), K-Nearest Neighbor (KNN) and other classifiers for binary classification.
The highest classification accuracy was 73.96% for distinguishing between clinically significant (Gleason 3 + 4 and above) and non-significant cancers (Gleason 3 + 3) and 83.72% for distinguishing between Gleason 3 + 4 from Gleason 4 + 3 and above, which was achieved using initial ROIs drawn by the radiologists. The accuracy improved when using expanded ROIs to 80.67% using SVM and 88.42% using Bayesian classification for distinguishing between clinically significant and non-significant cancers and Gleason 3 + 4 from Gleason 4 + 3 and above, respectively.
Our results indicate the research significance and value of this study for determining the GS for prostate cancer using the expansion of the ROI region.