Zonal adjusted PSA density improves prostate cancer detection rates compared with PSA in Taiwanese males with PSA < 20 ng/ml

Research on the mean maximum Young's modulus value as a new diagnostic parameter for prostate cancer

Ultrasound-based shear wave elastography (SWE) can non-invasively assess prostate tissue stiffness for the diagnosis of prostate cancer (PCa). So far, there is no widely recognized standard for the detection process and calculation method of Young's modulus value in transrectal SWE ultrasound imaging (TSWEUI). In our study, the mean maximum Young's modulus value (m-Emax) of the maximum cross-section of prostate is obtained by calculating the mean of 12 measured Emax in the four quadrants. This retrospective study included 209 suspected malignant prostate disease patients with pathological results in our hospital. Among the 209 patients, 75 patients completed TSWEUI, and 63 of the 75 patients completed magnetic resonance imaging (MRI). The area under the receiver operating characteristic (ROC) curve (AUC) of 75 patients for m-Emax was 0.754. The prostate volume, prostate-specific antigen, and m-Emax were used to develop a nomogram (AUC = 0.868). The nomogram could effectively predict the probability of PCa, thereby reducing the needle biopsy rate for diagnosing PCa. The AUC of 63 patients was not statistically different between m-Emax (AUC = 0.717) and MRI (AUC = 0.787) (P = 0.361). These indicate that m-Emax can be used as an innovative parameter in TSWEUI to diagnosis PCa. TSWEUI is more cost-effective than MRI in diagnosing PCa.

Transition-zone PSA-density calculated from MRI deep learning prostate zonal segmentation model for prediction of clinically significant prostate cancer

PURPOSE

To develop a deep learning (DL) zonal segmentation model of prostate MR from T2-weighted images and evaluate TZ-PSAD for prediction of the presence of csPCa (Gleason score of 7 or higher) compared to PSAD.

METHODS

1020 patients with a prostate MRI were randomly selected to develop a DL zonal segmentation model. Test dataset included 20 cases in which 2 radiologists manually segmented both the peripheral zone (PZ) and TZ. Pair-wise Dice index was calculated for each zone. For the prediction of csPCa using PSAD and TZ-PSAD, we used 3461 consecutive MRI exams performed in patients without a history of prostate cancer, with pathological confirmation and available PSA values, but not used in the development of the segmentation model as internal test set and 1460 MRI exams from PI-CAI challenge as external test set. PSAD and TZ-PSAD were calculated from the segmentation model output. The area under the receiver operating curve (AUC) was compared between PSAD and TZ-PSAD using univariate and multivariate analysis (adjusts age) with the DeLong test.

RESULTS

Dice scores of the model against two radiologists were 0.87/0.87 and 0.74/0.72 for TZ and PZ, while those between the two radiologists were 0.88 for TZ and 0.75 for PZ. For the prediction of csPCa, the AUCs of TZPSAD were significantly higher than those of PSAD in both internal test set (univariate analysis, 0.75 vs. 0.73, p < 0.001; multivariate analysis, 0.80 vs. 0.78, p < 0.001) and external test set (univariate analysis, 0.76 vs. 0.74, p < 0.001; multivariate analysis, 0.77 vs. 0.75, p < 0.001 in external test set).

CONCLUSION

DL model-derived zonal segmentation facilitates the practical measurement of TZ-PSAD and shows it to be a slightly better predictor of csPCa compared to the conventional PSAD. Use of TZ-PSAD may increase the sensitivity of detecting csPCa by 2-5% for a commonly used specificity level.

Comparison of quantitative parameters and radiomic features as inputs into machine learning models to predict the Gleason score of prostate cancer lesions

INTRODUCTION

The classification of prostate cancer (PCa) lesions using Prostate Imaging Reporting and Data System (PI-RADS) suffers from poor inter-reader agreement. This study compared quantitative parameters or radiomic features from multiparametric magnetic resonance imaging (mpMRI) or positron emission tomography (PET), as inputs into machine learning (ML) to predict the Gleason scores (GS) of detected lesions for improved PCa lesion classification.

METHODS

20 biopsy-confirmed PCa subjects underwent imaging before radical prostatectomy. A pathologist assigned GS from tumour tissue. Two radiologists and one nuclear medicine physician delineated the lesions on the mpMR and PET images, yielding 45 lesion inputs. Seven quantitative parameters were extracted from the lesions, namely T2-weighted (T2w) image intensity, apparent diffusion coefficient (ADC), transfer constant (K^TRANS), efflux rate constant (K_ep), and extracellular volume ratio (V_e) from mpMR images, and SUV_mean and SUV_max from PET images. Eight radiomic features were selected out of 109 radiomic features from T2w, ADC and PET images. Quantitative parameters or radiomic features, with risk factors of age, prostate-specific antigen (PSA), PSA density and volume, of 45 different lesion inputs were input in different combinations into four ML models - Decision Tree (DT), Support Vector Machine (SVM), k-Nearest-Neighbour (kNN), Ensembles model (EM).

RESULTS

SUV_max yielded the highest accuracy in discriminating detected lesions. Among the 4 ML models, kNN yielded the highest accuracies of 0.929 using either quantitative parameters or radiomic features with risk factors as input.

CONCLUSIONS

ML models' performance is dependent on the input combinations and risk factors further improve ML classification accuracy.

Assessment of Prostate Volume and Prostate-specific Antigen Density With the Segmentation Method on Magnetic Resonance Imaging

BACKGROUND/AIM

This study aimed to compare the prostate volume (PV) and prostate-specific antigen density (PSAD) obtained using the ellipsoid volume formula or segmentation methods on magnetic resonance imaging (MRI) and further predict prostate cancer (PCa).

PATIENTS AND METHODS

Retrospectively, the enrolled patients underwent prostate MRI and had PSA levels between 4 and 10 ng/ml. The PV was measured with both the ellipsoid volume formula (PVe) and the segmentation method (PVs). The transitional zone volume (TZV) was measured with the segmentation method. The PSADe, PSADs, and PSAD_TZV were calculated. Bland-Altman plots were used to compare the agreements. ROC curve analysis was used to compare the diagnostic accuracies to predict PCa. The results were also compared between the PCa and the no-PCa groups, and among tumors with different locations and different Gleason scores (GS).

RESULTS

Seventy-six of the 117 enrolled patients were classified into the PCa group. There were high agreements between PVs and PVe as well as between PSADs and PSADe, while several outliers were mainly due to post-transurethral resection of the prostate changes and irregular hyperplastic nodules. The diagnostic accuracy of PSADe (AUC: 0.732) was slightly higher than that of PSADs (AUC: 0.729) and PSAD_TZV (AUC: 0.715). The PSADe and PSADs were not different among different tumor locations but were higher in GS ≥7 lesions (both p=0.006).

CONCLUSION

The segmentation method can be an alternative method to measure PV and calculate PSAD before prostate biopsy, particularly in post-transurethral resection of the prostate patients or those with irregular hyperplastic nodules.

Prebiopsy bpMRI and hematological parameter-based risk scoring model for predicting outcomes in biopsy-naive men with PSA 4-20 ng/mL

Excessive prostate biopsy is a common problem for clinicians. Although some hematological and bi-parametric magnetic resonance imaging (bpMRI) parameters might help increase the rate of positive prostate biopsies, there is a lack of studies on whether their combination can further improve clinical detection efficiency. We retrospectively enrolled 394 patients with PSA levels of 4-20 ng/mL who underwent prebiopsy bpMRI during 2010-2021. Based on bpMRI and hematological indicators, six models and a nomogram were constructed to predict the outcomes of biopsy. Furthermore, we constructed and evaluated a risk scoring model based on the nomogram. Age, prostate-specific antigen (PSA) density (PSAD), systemic immune-inflammation index, cystatin C level, and the Prostate Imaging Reporting and Data System (PI-RADS) v2.1 score were significant predictors of prostate cancer (PCa) on multivariable logistic regression analyses (P < 0.05) and the five parameters were used to construct the XYFY nomogram. The area under the receiver operating characteristic (ROC) curve (AUC) of the nomogram was 0.916. Based on the nomogram, a risk scoring model (XYFY risk model) was constructed and then we divided the patients into low-(XYFY score: < 95), medium-(XYFY score: 95-150), and, high-risk (XYFY score: > 150) groups. The predictive values for diagnosis of PCa and clinically-significant PCa among the three risk groups were 3.0%(6/201), 41.8%(51/122), 91.5%(65/71); 0.5%(1/201), 19.7%(24/122), 60.6%(43/71), respectively. In conclusion, in this study, we used hematological and bpMRI parameters to establish and internally validate a XYFY risk scoring model for predicting the biopsy outcomes for patients with PSA levels of 4-20 ng/mL and this risk model would support clinical decision-making and reduce excessive biopsies.

Prostate zones and cancer: lost in transition?

Localized prostate cancer shows great clinical, genetic and environmental heterogeneity; however, prostate cancer treatment is currently guided solely by clinical staging, serum PSA levels and histology. Increasingly, the roles of differential genomics, multifocality and spatial distribution in tumorigenesis are being considered to further personalize treatment. The human prostate is divided into three zones based on its histological features: the peripheral zone (PZ), the transition zone (TZ) and the central zone (CZ). Each zone has variable prostate cancer incidence, prognosis and outcomes, with TZ prostate tumours having better clinical outcomes than PZ and CZ tumours. Molecular and cell biological studies can improve understanding of the unique molecular, genomic and zonal cell type features that underlie the differences in tumour progression and aggression between the zones. The unique biology of each zonal tumour type could help to guide individualized treatment and patient risk stratification.

The Role of PSA Density among PI-RADS v2.1 Categories to Avoid an Unnecessary Transition Zone Biopsy in Patients with PSA 4-20 ng/mL

Objective

To evaluate the role of prostate-specific antigen density (PSAD) in different Prostate Imaging Reporting and Data System version 2.1 (PI-RADS v2.1) categories to avoid an unnecessary biopsy in transition zone (TZ) patients with PSA ranging from 4 to 20 ng/mL.

Materials and Methods

In this retrospective and single-center study, 333 biopsy-naïve patients with TZ lesions who underwent biparametric magnetic resonance imaging (bp-MRI) were analyzed from January 2016 to March 2020. Multivariate logistic regression analyses were performed to determine independent predictors of clinically significant prostate cancer (cs-PCa). The receiver operating characteristic (ROC) curve was used to compare diagnostic performance.

Results

PI-RADS v2.1 and PSAD were the independent predictors for TZ cs-PCa in patients with PSA 4-20 ng/mL. 0.9% (2/213), 10.0% (7/70), and 48.0% (24/50) of PI-RADS v2.1 score 1-2, 3, and 4-5 had TZ cs-PCa. However, for patients with PI-RADS v2.1 score 1-2, there were no obvious changes in the detection of TZ cs-PCa (0.8% (1/129), 1.3% (1/75), and 0.0% (0/9)) combining with different PSAD stratification (PSAD < 0.15, 0.15-0.29, and ≥0.30 ng/mL/mL). For patients with PI-RADS v2.1 score ≥ 3, the TZ cs-PCa detection rate significantly varied according to different PSAD stratification. A PI-RADS v2.1 score 3 and PSAD < 0.15 and 0.15-0.29 ng/mL/mL had 8.6% (3/35) and 3.7% (1/27) of TZ cs-PCa, while a PI-RADS v2.1 score 3 and PSAD ≥ 0.30 ng/mL/mL had a higher TZ cs-PCa detection rate (37.5% (3/8)). A PI-RADS v2.1 score 4-5 and PSAD <0.15 ng/mL/mL had no cs-PCa (0.0% (0/9)). In contrast, a PI-RADS v2.1 score 4-5 and PSAD 0.15-0.29 and ≥0.30 ng/mL/mL had the highest cs-PCa detection rate (50.0% (10/20), 66.7% (14/21)). It showed the highest AUC in the combination of PI-RADS v2.1 and PSAD (0.910), which was significantly higher than PI-RADS v2.1 (0.889, P = 0.039) or PSAD (0.803, P < 0.001).

Conclusions

For TZ patients with PSA 4-20 ng/mL, PI-RADS v2.1 score ≤ 2 can avoid an unnecessary biopsy regardless of PSAD. PI-RADS v2.1 score ≥ 3 may avoid an unnecessary biopsy after combining with PSAD. PI-RADS v2.1 combined with PSAD could significantly improve diagnostic performance.

The Reproducibility of Deep Learning-Based Segmentation of the Prostate Gland and Zones on T2-Weighted MR Images

Volume of interest segmentation is an essential step in computer-aided detection and diagnosis (CAD) systems. Deep learning (DL)-based methods provide good performance for prostate segmentation, but little is known about the reproducibility of these methods. In this work, an in-house collected dataset from 244 patients was used to investigate the intra-patient reproducibility of 14 shape features for DL-based segmentation methods of the whole prostate gland (WP), peripheral zone (PZ), and the remaining prostate zones (non-PZ) on T2-weighted (T2W) magnetic resonance (MR) images compared to manual segmentations. The DL-based segmentation was performed using three different convolutional neural networks (CNNs): V-Net, nnU-Net-2D, and nnU-Net-3D. The two-way random, single score intra-class correlation coefficient (ICC) was used to measure the inter-scan reproducibility of each feature for each CNN and the manual segmentation. We found that the reproducibility of the investigated methods is comparable to manual for all CNNs (14/14 features), except for V-Net in PZ (7/14 features). The ICC score for segmentation volume was found to be 0.888, 0.607, 0.819, and 0.903 in PZ; 0.988, 0.967, 0.986, and 0.983 in non-PZ; 0.982, 0.975, 0.973, and 0.984 in WP for manual, V-Net, nnU-Net-2D, and nnU-Net-3D, respectively. The results of this work show the feasibility of embedding DL-based segmentation in CAD systems, based on multiple T2W MR scans of the prostate, which is an important step towards the clinical implementation.

Deep Learning Whole-Gland and Zonal Prostate Segmentation on a Public MRI Dataset

BACKGROUND

Prostate volume, as determined by magnetic resonance imaging (MRI), is a useful biomarker both for distinguishing between benign and malignant pathology and can be used either alone or combined with other parameters such as prostate-specific antigen.

PURPOSE

This study compared different deep learning methods for whole-gland and zonal prostate segmentation.

STUDY TYPE

Retrospective.

POPULATION

A total of 204 patients (train/test = 99/105) from the PROSTATEx public dataset.

FIELD STRENGTH/SEQUENCE

A 3 T, TSE T₂ -weighted.

ASSESSMENT

Four operators performed manual segmentation of the whole-gland, central zone + anterior stroma + transition zone (TZ), and peripheral zone (PZ). U-net, efficient neural network (ENet), and efficient residual factorized ConvNet (ERFNet) were trained and tuned on the training data through 5-fold cross-validation to segment the whole gland and TZ separately, while PZ automated masks were obtained by the subtraction of the first two.

STATISTICAL TESTS

Networks were evaluated on the test set using various accuracy metrics, including the Dice similarity coefficient (DSC). Model DSC was compared in both the training and test sets using the analysis of variance test (ANOVA) and post hoc tests. Parameter number, disk size, training, and inference times determined network computational complexity and were also used to assess the model performance differences. A P < 0.05 was selected to indicate the statistical significance.

RESULTS

The best DSC (P < 0.05) in the test set was achieved by ENet: 91% ± 4% for the whole gland, 87% ± 5% for the TZ, and 71% ± 8% for the PZ. U-net and ERFNet obtained, respectively, 88% ± 6% and 87% ± 6% for the whole gland, 86% ± 7% and 84% ± 7% for the TZ, and 70% ± 8% and 65 ± 8% for the PZ. Training and inference time were lowest for ENet.

DATA CONCLUSION

Deep learning networks can accurately segment the prostate using T₂ -weighted images.

EVIDENCE LEVEL

4 TECHNICAL EFFICACY: Stage 2.