Detection of Clinically Significant Prostate Cancer: Short Dual-Pulse Sequence versus Standard Multiparametric MR Imaging-A Multireader Study

Deep Learning-based Unsupervised Domain Adaptation via a Unified Model for Prostate Lesion Detection Using Multisite Biparametric MRI Datasets

Purpose To determine whether the unsupervised domain adaptation (UDA) method with generated images improves the performance of a supervised learning (SL) model for prostate cancer (PCa) detection using multisite biparametric (bp) MRI datasets. Materials and Methods This retrospective study included data from 5150 patients (14 191 samples) collected across nine different imaging centers. A novel UDA method using a unified generative model was developed for PCa detection using multisite bpMRI datasets. This method translates diffusion-weighted imaging (DWI) acquisitions, including apparent diffusion coefficient (ADC) and individual diffusion-weighted (DW) images acquired using various b values, to align with the style of images acquired using b values recommended by Prostate Imaging Reporting and Data System (PI-RADS) guidelines. The generated ADC and DW images replace the original images for PCa detection. An independent set of 1692 test cases (2393 samples) was used for evaluation. The area under the receiver operating characteristic curve (AUC) was used as the primary metric, and statistical analysis was performed via bootstrapping. Results For all test cases, the AUC values for baseline SL and UDA methods were 0.73 and 0.79 (P < .001), respectively, for PCa lesions with PI-RADS score of 3 or greater and 0.77 and 0.80 (P < .001) for lesions with PI-RADS scores of 4 or greater. In the 361 test cases under the most unfavorable image acquisition setting, the AUC values for baseline SL and UDA were 0.49 and 0.76 (P < .001) for lesions with PI-RADS scores of 3 or greater and 0.50 and 0.77 (P < .001) for lesions with PI-RADS scores of 4 or greater. Conclusion UDA with generated images improved the performance of SL methods in PCa lesion detection across multisite datasets with various b values, especially for images acquired with significant deviations from the PI-RADS-recommended DWI protocol (eg, with an extremely high b value). Keywords: Prostate Cancer Detection, Multisite, Unsupervised Domain Adaptation, Diffusion-weighted Imaging, b Value Supplemental material is available for this article. © RSNA, 2024.

Japanese clinical practice guidelines for prostate cancer 2023

This fourth edition of the Japanese Clinical Practice Guidelines for Prostate Cancer 2023 is compiled. It was revised under the leadership of the Japanese Urological Association, with members selected from multiple academic societies and related organizations (Japan Radiological Society, Japanese Society for Radiation Oncology, the Department of EBM and guidelines, Japan Council for Quality Health Care (Minds), Japanese Society of Pathology, and the patient group (NPO Prostate Cancer Patients Association)), in accordance with the Minds Manual for Guideline Development (2020 ver. 3.0). The most important feature of this revision is the adoption of systematic reviews (SRs) in determining recommendations for 14 clinical questions (CQs). Qualitative SRs for these questions were conducted, and the final recommendations were made based on the results through the votes of 24 members of the guideline development group. Five algorithms based on these results were also created. Contents not covered by the SRs, which are considered textbook material, have been described in the general statement. In the general statement, a literature search for 14 areas was conducted; then, based on the general statement and CQs of the Japanese Clinical Practice Guidelines for Prostate Cancer 2016, the findings revealed after the 2016 guidelines were mainly described. This article provides an overview of these guidelines.

Machine learning based prediction of image quality in prostate MRI using rapid localizer images

Purpose

Diagnostic performance of prostate MRI depends on high-quality imaging. Prostate MRI quality is inversely proportional to the amount of rectal gas and distention. Early detection of poor-quality MRI may enable intervention to remove gas or exam rescheduling, saving time. We developed a machine learning based quality prediction of yet-to-be acquired MRI images solely based on MRI rapid localizer sequence, which can be acquired in a few seconds.

Approach

The dataset consists of 213 (147 for training and 64 for testing) prostate sagittal T2-weighted (T2W) MRI localizer images and rectal content, manually labeled by an expert radiologist. Each MRI localizer contains seven two-dimensional (2D) slices of the patient, accompanied by manual segmentations of rectum for each slice. Cascaded and end-to-end deep learning models were used to predict the quality of yet-to-be T2W, DWI, and apparent diffusion coefficient (ADC) MRI images. Predictions were compared to quality scores determined by the experts using area under the receiver operator characteristic curve and intra-class correlation coefficient.

Results

In the test set of 64 patients, optimal versus suboptimal exams occurred in 95.3% (61/64) versus 4.7% (3/64) for T2W, 90.6% (58/64) versus 9.4% (6/64) for DWI, and 89.1% (57/64) versus 10.9% (7/64) for ADC. The best performing segmentation model was 2D U-Net with ResNet-34 encoder and ImageNet weights. The best performing classifier was the radiomics based classifier.

Conclusions

A radiomics based classifier applied to localizer images achieves accurate diagnosis of subsequent image quality for T2W, DWI, and ADC prostate MRI sequences.

Prostate volume analysis in image registration for prostate cancer care: a verification study

Combined magnetic resonance imaging (MRI) and positron emission tomography/computed tomography (PET/CT) may enhance diagnosis, aid surgical planning and intra-operative orientation for prostate biopsy and radical prostatectomy. Although PET-MRI may provide these benefits, PET-MRI machines are not widely available. Image fusion of Prostate specific membrane antigen PET/CT and MRI acquired separately may be a suitable clinical alternative. This study compares CT-MR registration algorithms for urological prostate cancer care. Paired whole-pelvis MR and CT scan data were used (n = 20). A manual prostate CTV contour was performed independently on each patients MR and CT image. A semi-automated rigid-, automated rigid- and automated non-rigid registration technique was applied to align the MR and CT data. Dice Similarity Index (DSI), 95% Hausdorff distance (95%HD) and average surface distance (ASD) measures were used to assess the closeness of the manual and registered contours. The automated non-rigid approach had a significantly improved performance compared to the automated rigid- and semi-automated rigid-registration, having better average scores and decreased spread for the DSI, 95%HD and ASD (all p < 0.001). Additionally, the automated rigid approach had similar significantly improved performance compared to the semi-automated rigid registration across all accuracy metrics observed (all p < 0.001). Overall, all registration techniques studied here demonstrated sufficient accuracy for exploring their clinical use. While the fully automated non-rigid registration algorithm in the present study provided the most accurate registration, the semi-automated rigid registration is a quick, feasible, and accessible method to perform image registration for prostate cancer care by urologists and radiation oncologists now.

Dynamic Contrast-Enhanced Study in the mpMRI of the Prostate-Unnecessary or Underutilised? A Narrative Review

The aim of this review is to summarise recent scientific literature regarding the clinical use of DCE-MRI as a component of multiparametric resonance imaging of the prostate. This review presents the principles of DCE-MRI acquisition and analysis, the current role of DCE-MRI in clinical practice with special regard to its role in presently available categorisation systems, and an overview of the advantages and disadvantages of DCE-MRI described in the current literature. DCE-MRI is an important functional sequence that requires intravenous administration of a gadolinium-based contrast agent and gives information regarding the vascularity and capillary permeability of the lesion. Although numerous studies have confirmed that DCE-MRI has great potential in the diagnosis and monitoring of prostate cancer, its role is still inadequate in the PI-RADS categorisation. Moreover, there have been numerous scientific discussions about abandoning the intravenous application of gadolinium-based contrast as a routine part of MRI examination of the prostate. In this review, we summarised the recent literature on the advantages and disadvantages of DCE-MRI, focusing on an overview of currently available data on bpMRI and mpMRI, as well as on studies providing information on the potential better usability of DCE-MRI in improving the sensitivity and specificity of mpMRI examinations of the prostate.

Multi-parametric MRI for radiotherapy simulation

Magnetic resonance imaging (MRI) has become an important imaging modality in the field of radiotherapy (RT) in the past decade, especially with the development of various novel MRI and image-guidance techniques. In this review article, we will describe recent developments and discuss the applications of multi-parametric MRI (mpMRI) in RT simulation. In this review, mpMRI refers to a general and loose definition which includes various multi-contrast MRI techniques. Specifically, we will focus on the implementation, challenges, and future directions of mpMRI techniques for RT simulation.

Abbreviated Versus Multiparametric Prostate MRI in Active Surveillance for Prostate-Cancer Patients: Comparison of Accuracy and Clinical Utility as a Decisional Tool

(1) Purpose: To compare the diagnostic accuracy between full multiparametric contrast-enhanced prostate MRI (mpMRI) and abbreviated dual-sequence prostate MRI (dsMRI) in men with clinically significant prostate cancer (csPCa) who were candidates for active surveillance. (2) Materials and Methods: Fifty-four patients with a diagnosis of low-risk PCa in the previous 6 months had a mpMRI scan prior to a saturation biopsy and a subsequent MRI cognitive transperineal targeted biopsy (for PI-RADS ≥ 3 lesions). The dsMRI images were obtained from the mpMRI protocol. The images were selected by a study coordinator and assigned to two readers blinded to the biopsy results (R1 and R2). Inter-reader agreement for clinically significant cancer was evaluated with Cohen's kappa. The dsMRI and mpMRI accuracy was calculated for each reader (R1 and R2). The clinical utility of the dsMRI and mpMRI was investigated with a decision-analysis model. (3) Results: The dsMRI sensitivity and specificity were 83.3%, 31.0%, 75.0%, and 23.8%, respectively, for R1 and R2. The mpMRI sensitivity and specificity were 91.7%, 31.0%, 83.3%, and 23.8%, respectively, for R1 and R2. The inter-reader agreement for the detection of csPCa was moderate (k = 0.53) and good (k = 0.63) for dsMRI and mpMRI, respectively. The AUC values for the dsMRI were 0.77 and 0.62 for the R1 and R2, respectively. The AUC values for the mpMRI were 0.79 and 0.66 for R1 and R2, respectively. No AUC differences were found between the two MRI protocols. At any risk threshold, the mpMRI showed a higher net benefit than the dsMRI for both R1 and R2. (4) Conclusions: The dsMRI and mpMRI showed similar diagnostic accuracy for csPCa in male candidates for active surveillance.

The diagnostic performance in clinically significant prostate cancer with PI-RADS version 2.1: simplified bpMRI versus standard mpMRI

OBJECTIVES

To compare the diagnostic performance for the detection of clinically significant prostate cancer (csPCa) between bpMRI with only axial T2WI (simplified bpMRI) and standard-multiparametric MRI (mpMRI).

METHODS

A total of 569 patients who underwent mpMRI followed by biopsy or prostatectomy were enrolled in this retrospective study. According to PI-RADS v2.1, three radiologists (A, B, C) from three centers blinded to clinical variables were assigned scores on lesions with simplified bpMRI and then with mpMRI 2 weeks later. Diagnostic performance of simplified bpMRI was compared with mpMRI using histopathology as reference standard.

RESULTS

For all the three radiologists, the diagnostic sensitivity was significantly higher with mpMRI than with simplified bpMRI (P < 0.001 to P = 0.035); and although specificity was also higher with mpMRI than with simplified bpMRI for radiologist B and radiologist C, it was statistically significant only for radiologist B (P = 0.011, P = 0.359, respectively). On the contrary, for radiologist A, specificity was higher with simplified bpMRI than with mpMRI (P = 0.001). The area under the receiver operating characteristic curve (AUC) was significantly higher for mpMRI than for simplified bpMRI except for radiologist A (radiologist A: 0.903 vs 0.913, P = 0.1542; radiologist B: 0.861 vs 0.834 P = 0.0013; and radiologist C: 0.884 vs 0.848, P = 0.0003). Interobserver reliability of PI-RADS v2.1 showed good agreement for both simplified bpMRI (kappa = 0.665) and mpMRI (kappa = 0.739).

CONCLUSION

Although the detection of csPCa with simplified bpMRI was comparatively lower than that with mpMRI, the diagnostic performance was still high in simplified bpMRI. Our data justify using mpMRI outperforms simplified bpMRI for prostate cancer screening and imply simplified bpMRI as a potential screening tool.

Landmarks in the evolution of prostate biopsy

Approaches and techniques used for diagnostic prostate biopsy have undergone considerable evolution over the past few decades: from the original finger-guided techniques to the latest MRI-directed strategies, from aspiration cytology to tissue core sampling, and from transrectal to transperineal approaches. In particular, increased adoption of transperineal biopsy approaches have led to reduced infectious complications and improved antibiotic stewardship. Furthermore, as image fusion has become integral, these novel techniques could be incorporated into prostate biopsy methods in the future, enabling 3D-ultrasonography fusion reconstruction, molecular targeting based on PET imaging and autonomous robotic-assisted biopsy.

Comparison between biparametric and multiparametric MRI in predicting muscle invasion by bladder cancer based on the VI-RADS

This study aimed to compare the diagnostic validity of biparametric magnetic resonance imaging (bpMRI) with that of multiparametric MRI (mpMRI) based on the Vesicle Imaging-Reporting and Data System (VI-RADS) in predicting muscle invasion by bladder cancer (BCa). We retrospectively examined 357 patients with an initial diagnosis of BCa who underwent preoperative MRI; 257 and 100 patients underwent mpMRI and bpMRI, respectively. Two urogenital radiologists evaluated all bpMRI and mpMRI scans using VI-RADS, and the diagnostic validity of VI-RADS for predicting muscle invasion by BCa was analyzed based on histopathology of the first and/or second transurethral resection of bladder tumors and radical cystectomy. Receiver operating characteristic (ROC) curves were plotted with the calculation of area under the curves (AUCs), and the level of significance was P < 0.05. Both groups showed optimal performance with a VI-RADS score ≥ 3. BpMRI showed comparable diagnostic performance to mpMRI (reader 1: AUC, 0.903 [0.827-0.954] vs. 0.935 [0.884-0.968], p = 0.510; and reader 2: AUC, 0.901 [0.814-0.945] vs. 0.915 [0.874-0.946]; p = 0.655). The inter-reader agreement between both readers was excellent (Cohen's kappa value = 0.942 and 0.905 for bpMRI and mpMRI, respectively). This comparative study suggests that bpMRI has comparable diagnostic performance to mpMRI and may be an alternative option to predict muscle invasion by BCa.

Prospectively Accelerated T2-Weighted Imaging of the Prostate by Combining Compressed SENSE and Deep Learning in Patients with Histologically Proven Prostate Cancer

BACKGROUND

To assess the performance of prospectively accelerated and deep learning (DL) reconstructed T2-weighted (T2w) imaging in volunteers and patients with histologically proven prostate cancer (PCa).

METHODS

Prospectively undersampled T2w datasets were acquired with acceleration factors of 1.7 (reference), 3.4 and 4.8 in 10 healthy volunteers and 23 patients with histologically proven PCa. Image reconstructions using compressed SENSE (C-SENSE) and a combination of C-SENSE and DL-based artificial intelligence (C-SENSE AI) were analyzed. Qualitative image comparison was performed using a 6-point Likert scale (overall image quality, noise, motion artifacts, lesion detection, diagnostic certainty); the T2 and PI-RADS scores were compared between the two reconstructions. Additionally, quantitative image parameters were assessed (apparent SNR, apparent CNR, lesion size, line profiles).

RESULTS

All C-SENSE AI-reconstructed images received a significantly higher qualitative rating compared to the C-SENSE standard images. Analysis of the quantitative parameters supported this finding, with significantly higher aSNR and aCNR. The line profiles demonstrated a significantly steeper signal change at the border of the prostatic lesion and the adjacent normal tissue in the C-SENSE AI-reconstructed images, whereas the T2 and PI-RADS scores as well as the lesion size did not differ.

CONCLUSION

In this prospective study, we demonstrated the clinical feasibility of a novel C-SENSE AI reconstruction enabling a 58% acceleration in T2w imaging of the prostate while obtaining significantly better image quality.

Comparison of Multiparametric and Fast MRI Protocols in Detecting Clinically Significant Prostate Cancer and a Detailed Cost Analysis

BACKGROUND

Due to the long acquisition time and high cost of multiparametric magnetic resonance imaging (mpMRI), biparametric and, more recently, fast prostate magnetic resonance imaging (fpMRI) protocols have been described. However, there is insufficient data about the diagnostic performance and cost of fpMRI.

PURPOSE

To compare the diagnostic performances and cost analysis of fpMRI and mpMRI in clinically significant prostate cancer (csPCA).

STUDY TYPE

Retrospective.

POPULATION

A total of 103 patients (63 had csPCA) with a mean age of 66.83 (± 7.22) years were included.

FIELD STRENGTH/SEQUENCE

A 1.5-T; T1- and T2-weighted turbo spin-echo imaging (T1WI and T2WI), echo-planar diffusion-weighted images, and dynamic contrast-enhanced T1W imaging.

ASSESSMENT

Three readers independently evaluated the fpMRI and mpMRI images in different sessions blinded to all patient information. Diagnostic performances of fpMRI and mpMRI were evaluated. Kappa coefficient (κ) was used to determine the interreader and intrareader agreement. A detailed cost analysis was performed for each protocol.

STATISTICAL TESTS

Receiver operating characteristics analysis, area under the curve (AUC), and κ test were used. Diagnostic performance parameters were also calculated.

RESULTS

Of the 63 malignant index lesions (csPCA), 53/63 of those (84.1%) originated from the peripheral zone and 10/63 lesions (15.9%) originated from the transition zone. The AUC values for fpMRI were 0.878 for reader 1, 0.937 for reader 2, and 0.855 for reader 3. For mpMRI, the AUC values were 0.893 for reader 1, 0.94 for reader 2, and 0.862 for reader 3. Inter and intrareader agreements were moderate to substantial (κ range, 0.5-0.79). The total cost per examination was calculated as €12.39 and €30.10 for fpMRI and mpMRI, respectively.

DATA CONCLUSIONS

Fast MRI protocol has similar diagnostic performance with mpMRI in detecting csPCA, and fpMRI can be considered an alternative protocol that could create a lower financial burden on health-care systems.

LEVEL OF EVIDENCE

4 TECHNICAL EFFICACY STAGE: 6.

Radiomic Machine Learning and External Validation Based on 3.0 T mpMRI for Prediction of Intraductal Carcinoma of Prostate With Different Proportion

Purpose

To assess the association of radiomics features based on multiparametric MRI (mpMRI) with the proportion of intraductal carcinoma of prostate (IDC-P) and validate the predictive models.

Materials and Methods

We retrospectively included pre-treatment MR images of prostate cancer (PCa) with IDC components of high proportion (≥10%, hpIDC-P), low proportion (<10%, lpIDC-P), and pure acinar adenocarcinoma (PAC) from our institution for training and internal validation and cooperated cohort for external validation. Normalized images of T2WI, diffusion weighted imaging (DWI) and apparent diffusion coefficient (ADC) map, and dynamic contrast enhanced (DCE) sequences were used for radiomics modeling. The clinical model was built based on serum total prostate specific antigen (tPSA) and Gleason score (GS), and the integrated model was the combination of Rad-score and clinicopathological data. The discrimination ability was assessed by area under the receiver operating characteristic curve (ROC-AUC) in the internal and external validation sets and compared by DeLong test.

Results

Overall, 97 patients with hpIDC-P, 87 lpIDC-P, and 78 PAC were included for training and internal validation, and 11, 16, and 19 patients for external validation. The integrated model for predicting hpIDC-P got the best ROC-AUC of 0.88 (95%CI = 0.83-0.93) in internal and 0.86 (95%CI = 0.72-1.0) in external validation, which both outperformed clinical models (AUC=0.78, 95% CI = 0.72-0.85, AUC=0.69, 95% CI = 0.5-0.85, respectively) based solely on GS, and the radiomics model (AUC=0.85, 95% CI = 0.79-0.91) was slightly inferior to the integrated model and better than the clinical model in internal dataset. The integrated model for predicting lpIDC-P outperformed both radiomics and clinical models in the internal dataset, while slightly inferior to the integrated model for predicting hpIDC-P.

Conclusions

Radiomics signature improved differentiation of both hpIDC-P and lpIDC-P versus PAC when compared with the clinical model based on Gleason score, and was validated in an external cohort.

Current Status of Biparametric MRI in Prostate Cancer Diagnosis: Literature Analysis

The role of multiparametric MRI (mpMRI) in the detection of prostate cancer is well-established. Based on the limited role of dynamic contrast enhancement (DCE) in PI-RADS v2.1, the risk of potential side effects, and the increased cost and time, there has been an increase in studies advocating for the omission of DCE from MRI assessments. Per PI-RADS v2.1, DCE is indicated in the assessment of PI-RADS 3 lesions in the peripheral zone, with its most pronounced effect when T2WI and DWI are of insufficient quality. The aim of this study was to evaluate the methodology and reporting in the literature from the past 5 years regarding the use of DCE in prostate MRI, especially with respect to the indications for DCE as stated in PI-RADS v2.1, and to describe the different approaches used across the studies. We searched for studies investigating the use of bpMRI and/or mpMRI in the detection of clinically significant prostate cancer between January 2017 and April 2022 in the PubMed, Web of Science, and Google Scholar databases. Through the search process, a total of 269 studies were gathered and 41 remained after abstract and full-text screening. The following information was extracted from the eligible studies: general clinical and technical characteristics of the studies, the number of PI-RADS 3 lesions, different definitions of clinically significant prostate cancer (csPCa), biopsy thresholds, reference standard methods, and number and experience of readers. Forty-one studies were included in the study. Only 51% (21/41) of studies reported the prevalence of csPCa in their equivocal lesion (PI-RADS category 3 lesions) subgroups. Of the included studies, none (0/41) performed a stratified sub-analysis of the DCE benefit versus MRI quality and 46% (19/41) made explicit statements about removing MRI scans based on a range of factors including motion, noise, and image artifacts. Furthermore, the number of studies investigating the role of DCE using readers with varying experience was relatively low. This review demonstrates that a high proportion of the studies investigating whether bpMRI can replace mpMRI did not transparently report information inherent to their study design concerning the key indications of DCE, such as the number of clinically insignificant/significant PI-RADS 3 lesions, nor did they provide any sub-analyses to test image quality, with some removing bad quality MRI scans altogether, or reader-experience-dependency indications for DCE. For the studies that reported on most of the DCE indications, their conclusions about the utility of DCE were heavily definition-dependent (with varying definitions of csPCa and of the PI-RADS category biopsy significance threshold). Reporting the information inherent to the study design and related to the specific indications for DCE as stated in PI-RADS v2.1 is needed to determine whether DCE is helpful or not. With most of the recent literature being retrospective and not including the data related to DCE indications in particular, the ongoing dispute between bpMRI and mpMRI is likely to linger.

Abbreviated MR Protocols in Prostate MRI

Prostate MRI is an integral part of the clinical work-up in biopsy-naïve patients with suspected prostate cancer, and its use has been increasing steadily over the last years. To further its general availability and the number of men benefitting from it and to reduce the costs associated with MR, several approaches have been developed to shorten examination times, e.g., by focusing on sequences that provide the most useful information, employing new technological achievements, or improving the workflow in the MR suite. This review highlights these approaches; discusses their implications, advantages, and disadvantages; and serves as a starting point whenever an abbreviated prostate MRI protocol is being considered for implementation in clinical routine.

Diagnostic Accuracy of Abbreviated Bi-Parametric MRI (a-bpMRI) for Prostate Cancer Detection and Screening: A Multi-Reader Study

(1) Background: There is currently limited evidence on the diagnostic accuracy of abbreviated biparametric MRI (a-bpMRI) protocols for prostate cancer (PCa) detection and screening. In the present study, we aim to investigate the performance of a-bpMRI among multiple readers and its potential application to an imaging-based screening setting. (2) Methods: A total of 151 men who underwent 3T multiparametric MRI (mpMRI) of the prostate and transperineal template prostate mapping biopsies were retrospectively selected. Corresponding bpMRI (multiplanar T2WI, DWI, ADC maps) and a-bpMRI (axial T2WI and b 2000 s/mm² DWI only) dataset were derived from mpMRI. Three experienced radiologists scored a-bpMRI, standard biparametric MRI (bpMRI) and mpMRI in separate sessions. Diagnostic accuracy and interreader agreement of a-bpMRI was tested for different positivity thresholds and compared to bpMRI and mpMRI. Predictive values of a-bpMRI were computed for lower levels of PCa prevalence to simulate a screening setting. The primary definition of clinically significant PCa (csPCa) was Gleason ≥ 4 + 3, or cancer core length ≥ 6 mm. (3) Results: The median age was 62 years, the median PSA was 6.8 ng/mL, and the csPCa prevalence was 40%. Using a cut off of MRI score ≥ 3, the sensitivity and specificity of a-bpMRI were 92% and 48%, respectively. There was no significant difference in sensitivity compared to bpMRI and mpMRI. Interreader agreement of a-bpMRI was moderate (AC1 0.58). For a low prevalence of csPCa (e.g., <10%), higher cut offs (MRI score ≥ 4) yield a more favourable balance between the predictive values and positivity rate of MRI. (4) Conclusion: Abbreviated bpMRI protocols could match the diagnostic accuracy of bpMRI and mpMRI for the detection of csPCa. If a-bpMRI is used in low-prevalence settings, higher cut-offs for MRI positivity should be prioritised.

Non-invasive Urine Test for Molecular Classification of Clinical Significance in Newly Diagnosed Prostate Cancer Patients

Objective: To avoid over-treatment of low-risk prostate cancer patients, it is important to identify clinically significant and insignificant cancer for treatment decision-making. However, no accurate test is currently available.

Methods: To address this unmet medical need, we developed a novel gene classifier to distinguish clinically significant and insignificant cancer, which were classified based on the National Comprehensive Cancer Network risk stratification guidelines. A non-invasive urine test was developed using quantitative mRNA expression data of 24 genes in the classifier with an algorithm to stratify the clinical significance of the cancer. Two independent, multicenter, retrospective and prospective studies were conducted to assess the diagnostic performance of the 24-Gene Classifier and the current clinicopathological measures by univariate and multivariate logistic regression and discriminant analysis. In addition, assessments were performed in various Gleason grades/ISUP Grade Groups.

Results: The results showed high diagnostic accuracy of the 24-Gene Classifier with an AUC of 0.917 (95% CI 0.892–0.942) in the retrospective cohort (n = 520), AUC of 0.959 (95% CI 0.935–0.983) in the prospective cohort (n = 207), and AUC of 0.930 (95% 0.912-CI 0.947) in the combination cohort (n = 727). Univariate and multivariate analysis showed that the 24-Gene Classifier was more accurate than cancer stage, Gleason score, and PSA, especially in the low/intermediate-grade/ISUP Grade Group 1–3 cancer subgroups.

Conclusions: The 24-Gene Classifier urine test is an accurate and non-invasive liquid biopsy method for identifying clinically significant prostate cancer in newly diagnosed cancer patients. It has the potential to improve prostate cancer treatment decisions and active surveillance.

A systematic review and meta-analysis of the diagnostic accuracy of biparametric prostate MRI for prostate cancer in men at risk

INTRODUCTION

Multiparametric magnetic resonance imaging (mpMRI), the use of three multiple imaging sequences, typically T2-weighted, diffusion weighted (DWI) and dynamic contrast enhanced (DCE) images, has a high sensitivity and specificity for detecting significant cancer. Current guidance now recommends its use prior to biopsy. However, the impact of DCE is currently under debate regarding test accuracy. Biparametric MRI (bpMRI), using only T2 and DWI has been proposed as a viable alternative. We conducted a contemporary systematic review and meta-analysis to further examine the diagnostic performance of bpMRI in the diagnosis of any and clinically significant prostate cancer.

METHODS

A systematic review of the literature from 01/01/2017 to 06/07/2019 was performed by two independent reviewers using predefined search criteria. The index test was biparametric MRI and the reference standard whole-mount prostatectomy or prostate biopsy. Quality of included studies was assessed by the QUADAS-2 tool. Statistical analysis included pooled diagnostic performance (sensitivity; specificity; AUC), meta-regression of possible covariates and head-to-head comparisons of bpMRI and mpMRI where both were performed in the same study.

RESULTS

Forty-four articles were included in the analysis. The pooled sensitivity for any cancer detection was 0.84 (95% CI, 0.80-0.88), specificity 0.75 (95% CI, 0.68-0.81) for bpMRI. The summary ROC curve yielded a high AUC value (AUC = 0.86). The pooled sensitivity for clinically significant prostate cancer was 0.87 (95% CI, 0.78-0.93), specificity 0.72 (95% CI, 0.56-0.84) and the AUC value was 0.87. Meta-regression analysis revealed no difference in the pooled diagnostic estimates between bpMRI and mpMRI.

CONCLUSIONS

This meta-analysis on contemporary studies shows that bpMRI offers comparable test accuracies to mpMRI in detecting prostate cancer. These data are broadly supportive of the bpMRI approach but heterogeneity does not allow definitive recommendations to be made. There is a need for prospective multicentre studies of bpMRI in biopsy naïve men.

Improving workflow in prostate MRI: AI-based decision-making on biparametric or multiparametric MRI

OBJECTIVES

To develop and validate an artificial intelligence algorithm to decide on the necessity of dynamic contrast-enhanced sequences (DCE) in prostate MRI.

METHODS

This study was approved by the institutional review board and requirement for study-specific informed consent was waived. A convolutional neural network (CNN) was developed on 300 prostate MRI examinations. Consensus of two expert readers on the necessity of DCE acted as reference standard. The CNN was validated in a separate cohort of 100 prostate MRI examinations from the same vendor and 31 examinations from a different vendor. Sensitivity/specificity were calculated using ROC curve analysis and results were compared to decisions made by a radiology technician.

RESULTS

The CNN reached a sensitivity of 94.4% and specificity of 68.8% (AUC: 0.88) for the necessity of DCE, correctly assigning 44%/34% of patients to a biparametric/multiparametric protocol. In 2% of all patients, the CNN incorrectly decided on omitting DCE. With a technician reaching a sensitivity of 63.9% and specificity of 89.1%, the use of the CNN would allow for an increase in sensitivity of 30.5%. The CNN achieved an AUC of 0.73 in a set of examinations from a different vendor.

CONCLUSIONS

The CNN would have correctly assigned 78% of patients to a biparametric or multiparametric protocol, with only 2% of all patients requiring re-examination to add DCE sequences. Integrating this CNN in clinical routine could render the requirement for on-table monitoring obsolete by performing contrast-enhanced MRI only when needed.

Comparison of Sensitivity and Specificity of Biparametric versus Multiparametric Prostate MRI in the Detection of Prostate Cancer in 431 Men with Elevated Prostate-Specific Antigen Levels

(1) Background: the study of dynamic contrast enhancement (DCE) has a limited role in the detection of prostate cancer (PCa), and there is a growing interest in performing unenhanced biparametric prostate-MRI (bpMRI) instead of the conventional multiparametric-MRI (mpMRI). In this study, we aimed to retrospectively compare the performance of the mpMRI, which includes DCE study, and the unenhanced bpMRI, composed of only T2-weighted imaging and diffusion-weighted imaging (DWI), in PCa detection in men with elevated prostate-specific-antigen (PSA) levels. (2) Methods: a 1.5 T MRI, with an endorectal-coil, was performed on 431 men (aged 61.5 ± 8.3 years) with a PSA ≥4.0 ng/mL. The bpMRI and mpMRI tests were independently assessed in separate sessions by two readers with 5 (R1) and 3 (R2) years of experience. The histopathology or ≥2 years follow-up served as a reference standard. The sensitivity and specificity were calculated with their 95% CI, and McNemar’s and Cohen’s κ statistics were used. (3) Results: in 195/431 (45%) of histopathologically proven PCa cases, 62/195 (32%) were high-grade PCa (GS ≥ 7b) and 133/195 (68%) were low-grade PCa (GS ≤ 7a). The PCa could be excluded by histopathology in 58/431 (14%) and by follow-up in 178/431 (41%) of patients. For bpMRI, the sensitivity was 164/195 (84%, 95% CI: 79–89%) for R1 and 156/195 (80%, 95% CI: 74–86%) for R2; while specificity was 182/236 (77%, 95% CI: 72–82%) for R1 and 175/236 (74%, 95% CI: 68–80%) for R2. For mpMRI, sensitivity was 168/195 (86%, 95% CI: 81–91%) for R1 and 160/195 (82%, 95% CI: 77–87%) for R2; while specificity was 184/236 (78%, 95% CI: 73–83%) for R1 and 177/236 (75%, 95% CI: 69–81%) for R2. Interobserver agreement was substantial for both bpMRI (κ = 0.802) and mpMRI (κ = 0.787). (4) Conclusions: the diagnostic performance of bpMRI and mpMRI were similar, and no high-grade PCa was missed with bpMRI.

Accuracy of abbreviated multiparametric MRI-derived protocols in predicting local staging of prostate cancer in men undergoing radical prostatectomy

BACKGROUND

Abbreviated magnetic resonance imaging (aMRI) protocols have emerged as an alternative to multiparametric MRI (mpMRI) to reduce examination time and costs.

PURPOSE

To compare multiple aMRI protocols for predicting pathological stage ≥T3 (≥pT3) prostate cancer (PCa).

MATERIAL AND METHODS

One hundred and eight men undergoing staging mpMRI before radical prostatectomy (RP) were retrospectively evaluated. 3.0-T imaging was performed with a 32-channel surface coil and a protocol including diffusion-weighted imaging (DWI), transverse T2-weighted (tT2W) imaging, coronal T2W (cT2W) imaging, sagittal T2W (sT2) imaging, and dynamic contrast-enhanced (DCE) imaging. Two readers independently assessed whether any MRI observation showed stage ≥T3 on each sequence (reading order: DWI, cT2W, tT2W, sT2W, DCE). Final stage was assessed by matching readers' assignments to pathology, and combining them into eight protocols: DWI + tT2W, DWI + cT2W + tT2W, DWI + tT2W + sT2W, DWI + cT2W + tT2W + sT2W, DWI + tT2W + DCE, DWI + cT2W + tT2W + DCE, DWI + tT2W + sT2W + DCE, and mpMRI. Diagnostic accuracy and inter-reader agreement for aMRI protocols were calculated.

RESULTS

Prevalence of ≥pT3 PCa was 31.5%. Sensitivity, specificity, positive (PPV) and negative predictive value (NPV) of aMRI protocols were comparable to mpMRI for R1. Sensitivity was 74.3% (95% confidence interval [CI] 64.8-72.0) to 77.1% (95% CI 67.9-84.4), and NPV 86.8% (95% CI 78.6-92.3) to 88.1% (95% CI 80.1-93.3). All accuracy measures of the various aMRI protocols were similar to mpMRI also for R2, albeit all slightly lower compared to R1. On a per-protocol basis, there was substantial inter-reader agreement in predicting stage ≥pT3 (k 0.63-0.67).

CONCLUSION

When comparing the diagnostic accuracy of multiple aMRI protocols against mpMRI for predicting stage ≥pT3 PCa, the protocol with the fewest sequences (DWI + tT2W) is apparently equivalent to standard mpMRI.

For men enrolled in active surveillance, pre-biopsy biparametric magnetic resonance imaging significantly reduces the risk of reclassification and disease progression after 1 year

AIMS

To assess the level of disease progression at confirmatory staging biopsies after 1 year of active surveillance (AS) and compare the detection rate of significant prostate cancers (PCas) in patients who underwent pre-biopsy biparametric magnetic resonance imaging (bpMRI) before the first set of diagnostic transrectal ultrasonography-guided biopsies (TRUS-bx) with the detection rate in patients who did not undergo pre-biopsy bpMRI.

MATERIALS AND METHODS

Comparison of two patient groups enrolled in AS. Patients in Group A (n = 127) underwent pre-biopsy bpMRI followed by TRUS-bx ± targeted biopsies. Patients in Group B (n = 127) were enrolled in AS based on biopsy results from TRUS-bx only.

RESULTS

Overall, 6% of the patients in Group A and 20% of the patients in Group B had an upgrade in Gleason grade from insignificant to significant PCa at confirmatory staging biopsies (odds ratio [OR], 3.5; p = .002; 95% confidence interval [CI], 1.6-7.9).

CONCLUSIONS

Patients who underwent pre-biopsy bpMRI before the first set of diagnostic biopsies had a reduced risk of reclassification and disease progression after 1 year of AS. Thus, pre-biopsy bpMRI improves the selection of men who should be enrolled in AS.

Diagnostic Ability of Dynamic Contrast-Enhanced Magnetic Resonance Imaging for Prostate Cancer and Clinically Significant Prostate Cancer in Equivocal Lesions: A Systematic Review and Meta-Analysis

Background

Dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) now has been used to diagnose prostate cancer (PCa). Equivocal lesions are defined as PIRADS category 3 or a Likert scale of 1 to 5 category 3 lesions. Currently, there are no clear recommendations for the management of these lesions. This study aimed to estimate the diagnostic capacity of DCE-MRI for PCa and clinically significant prostate cancer (csPCa) in equivocal lesions.

Materials and methods

Two researchers searched PubMed, Embase and Web of Science to identify studies that met our subject. We searched for articles that mention the accuracy of the diagnosis of DCE-MRI for PCa or csPCa in equivocal lesions and used histopathological results as the reference standard. We used a tool (the Quality Assessment of Diagnostic Accuracy Studies-2 tool) to evaluate the quality of the studies that we screened out. Meta-regression was used to explore the reasons for heterogeneity in results.

Results

Ten articles were eventually included in our study. The sensitivity, specificity and 95% confidence intervals (CI) for DCE-MRI in diagnosing csPCa were 0.67 (95% CI, 0.56–0.76), 0.58 (95% CI, 0.46–0.68). The sensitivity and specificity and 95% CI for DCE-MRI in diagnosing PCa were 0.57 (95% CI, 0.46–0.68), 0.58 (95% CI, 0.45–0.70). The areas under the curve (AUC) of DCE-MRI were 0.67 (95% CI, 0.63–0.71) and 0.60 (95% CI, 0.55–0.64) while diagnosing csPCa and PCa. Through meta-regression, we found that study design, magnetic field strength, the definition of csPCa, and the scoring system were the sources of heterogeneity.

Conclusion

The results of our study indicate that the role of DCE-MRI in equivocal lesions may be limited.

Magnetic Resonance Imaging Based Radiomic Models of Prostate Cancer: A Narrative Review

Simple Summary

The increasing interest in implementing artificial intelligence in radiomic models has occurred alongside advancement in the tools used for computer-aided diagnosis. Such tools typically apply both statistical and machine learning methodologies to assess the various modalities used in medical image analysis. Specific to prostate cancer, the radiomics pipeline has multiple facets that are amenable to improvement. This review discusses the steps of a magnetic resonance imaging based radiomics pipeline. Present successes, existing opportunities for refinement, and the most pertinent pending steps leading to clinical validation are highlighted.

Abstract

The management of prostate cancer (PCa) is dependent on biomarkers of biological aggression. This includes an invasive biopsy to facilitate a histopathological assessment of the tumor’s grade. This review explores the technical processes of applying magnetic resonance imaging based radiomic models to the evaluation of PCa. By exploring how a deep radiomics approach further optimizes the prediction of a PCa’s grade group, it will be clear how this integration of artificial intelligence mitigates existing major technological challenges faced by a traditional radiomic model: image acquisition, small data sets, image processing, labeling/segmentation, informative features, predicting molecular features and incorporating predictive models. Other potential impacts of artificial intelligence on the personalized treatment of PCa will also be discussed. The role of deep radiomics analysis-a deep texture analysis, which extracts features from convolutional neural networks layers, will be highlighted. Existing clinical work and upcoming clinical trials will be reviewed, directing investigators to pertinent future directions in the field. For future progress to result in clinical translation, the field will likely require multi-institutional collaboration in producing prospectively populated and expertly labeled imaging libraries.

Autonomous Detection and Classification of PI-RADS Lesions in an MRI Screening Population Incorporating Multicenter-Labeled Deep Learning and Biparametric Imaging: Proof of Concept

Background: Opportunistic prostate cancer (PCa) screening is a controversial topic. Magnetic resonance imaging (MRI) has proven to detect prostate cancer with a high sensitivity and specificity, leading to the idea to perform an image-guided prostate cancer (PCa) screening; Methods: We evaluated a prospectively enrolled cohort of 49 healthy men participating in a dedicated image-guided PCa screening trial employing a biparametric MRI (bpMRI) protocol consisting of T2-weighted (T2w) and diffusion weighted imaging (DWI) sequences. Datasets were analyzed both by human readers and by a fully automated artificial intelligence (AI) software using deep learning (DL). Agreement between the algorithm and the reports—serving as the ground truth—was compared on a per-case and per-lesion level using metrics of diagnostic accuracy and k statistics; Results: The DL method yielded an 87% sensitivity (33/38) and 50% specificity (5/10) with a k of 0.42. 12/28 (43%) Prostate Imaging Reporting and Data System (PI-RADS) 3, 16/22 (73%) PI-RADS 4, and 5/5 (100%) PI-RADS 5 lesions were detected compared to the ground truth. Targeted biopsy revealed PCa in six participants, all correctly diagnosed by both the human readers and AI. Conclusions: The results of our study show that in our AI-assisted, image-guided prostate cancer screening the software solution was able to identify highly suspicious lesions and has the potential to effectively guide the targeted-biopsy workflow.

Comparison of multiple abbreviated multiparametric MRI-derived protocols for the detection of clinically significant prostate cancer

BACKGROUND

The aim of this paper was to compare the accuracy of multiple abbreviated multiparametric magnetic resonance imaging (mpMRI)-derived protocols in detecting clinically significant prostate cancer (csPCa).

METHODS

One hundred and eight men undergoing staging 3.0T mpMRI with a Prostate Imaging - Reporting and Data System version 2 (PI-RADSv2)-compliant protocol before radical prostatectomy (RP) were retrospectively evaluated. Two readers (R1, R2) independently analyzed mpMRI, assigning a PI-RADSv2 category to each observation as appearing on each examination sequence. A study coordinator assessed final PI-RADSv2 category by combining readers' assignments according to four protocols: short MRI (sMRI) (diffusion-weighted imaging + axial T2-weighted imaging), contrast-enhanced short MRI (cesMRI) (sMRI + dynamic contrast-enhanced [DCE] imaging), biparametric MRI (diffusion-weighted imaging + multiplanar T2-weigthed imaging), and mpMRI. Using RP pathology as the reference standard for csPCa, we calculated the per-lesion cancer detection rate (CDR) and false discovery rate (FDR) for each MRI protocol (cut-off PI-RADSv2 category ≥3), and the per-PI-RADSv2 category prevalence of csPCa and false positives.

RESULTS

Pathology after RP found 142 csPCas with median International Society of Urogenital Pathology grade group 2, and stage ≤pT2c in 68.6% of cases. CDR was comparable across the four MRI protocols (74.6% to 75.3% for R1, and 68.3% for R2). FDR was comparable as well (14.4%-14.5% for R1 and 11.1% for R2). sMRI was the minimum protocol equaling mpMRI in terms of CDR, although cesMRI, similarly to mpMRI, was associated with fewer PI-RADSv2 category 3 assignments and higher prevalence of csPCa within PI-RADSv2 category 3 observations (66.7% versus 76.9% for R1, and 100% versus 91.7% for R2, respectively).

CONCLUSIONS

Among multiple abbreviated mpMRI-derived protocols, cesMRI was the one equaling mpMRI in terms of csPCa detection and minimizing PI-RADSv2 category 3 assignments.

Additional Value of Dynamic Contrast-enhanced Sequences in Multiparametric Prostate Magnetic Resonance Imaging: Data from the PROMIS Study

BACKGROUND

Multiparametric magnetic resonance imaging (MP-MRI) is established in the diagnosis of prostate cancer, but the need for enhanced sequences has recently been questioned.

OBJECTIVE

To assess whether dynamic contrast-enhanced imaging (DCE) improves accuracy over T2 and diffusion sequences.

DESIGN, SETTING, AND PARTICIPANTS

PROMIS was a multicentre, multireader trial, with, in this part, 497 biopsy-naïve men undergoing standardised 1.5T MP-MRI using T2, diffusion, and DCE, followed by a detailed transperineal prostate mapping (TPM) biopsy at 5 mm intervals. Likert scores of 1-5 for the presence of a significant tumour were assigned in strict sequence, for (1) T2 + diffusion and then (2) T2 + diffusion + dynamic contrast-enhanced images.

OUTCOME MEASUREMENTS AND STATISTICAL ANALYSIS

For the primary analysis, the primary PROMIS outcome measure (Gleason score ≥4 + 3 or ≥6 mm maximum cancer length) on TPM was used, and an MRI score of ≥3 was considered positive.

RESULTS AND LIMITATIONS

Sensitivity without and with DCE was 94% and 95%, specificity 37% and 38%, positive predictive value 51% and 51%, and negative predictive value 90% and 91%, respectively (p >  0.05 in each case). The number of patients avoiding biopsy (scoring 1-2) was similar (123/497 vs 121/497, p =  0.8). The number of equivocal scores (3/5) was slightly higher without DCE (32% vs 28% p =  0.031). The proportion of MRI equivocal (3/5) and positive (4-5) cases showing significant tumours were similar (23% and 71% vs 20% and 69%). No cases of dominant Gleason 4 or higher were missed with DCE, compared with a single case with T2 + diffusion-weighted imaging. No attempt was made to correlate lesion location on MRI and histology, which may be considered a limitation. Radiologists were aware of the patient's prostate-specific antigen.

CONCLUSIONS

Contrast adds little when MP-MRI is used to exclude significant prostate cancer.

PATIENT SUMMARY

An intravenous injection of contrast may not be necessary when magnetic resonance imaging is used as a test to rule out significant tumours in the prostate.

Contrast Medium or No Contrast Medium for Prostate Cancer Diagnosis. That Is the Question

The benefits and drawbacks of the dynamic contrast-enhanced MRI sequence for prostate cancer diagnosis are increasingly being recognized, with many centers adopting the biparametric (bp) MRI approach as the default initial approach. The abandonment of the routine use of contrast medium requires an assessment of the loss of diagnostic power against the gains in operational logistics, costs, time, capacity, and side effects. It is the balance of these factors weighted against the clinical priorities of patients that determines which patient groups can safely avoid dynamic contrast enhancement. Although systematic reviews and individual studies are broadly supportive of the bpMRI approach, the pathway impacts for men with suspected cancer using the bpMRI approach are still not well documented for clinical practice. Robust prospectively acquired data for bpMRI regarding biopsy avoidance, detection of clinically significant and insignificant cancers, and for increasing the precision of tumor grade and volume are needed. There is a requirement for prospective, randomized, or blinded head-to-head, multicenter studies, addressing the noninferiority of biopsy yields prompted by bpMRI and multiparametric MRI approaches. These studies should more precisely define patient groups where the benefits and harms of contrast enhancement are aligned to their clinical priorities. Only then can we be confident in recommending bpMRI as an initial diagnostic approach for prostate cancer diagnosis. Level of Evidence 1 Technical Efficacy Stage 5.

Is dynamic contrast enhancement still necessary in multiparametric magnetic resonance for diagnosis of prostate cancer: a systematic review and meta-analysis

Background

The purpose of this study is to systematically review the literatures assessing the value of dynamic contrast enhancement (DCE) in the multiparametric magnetic resonance imaging (mpMRI) for the diagnosis of prostate cancer (PCa).

Methods

We searched Embase, PubMed and Web of science until January 2019 to extract articles exploring the possibilities whether the pre-biopsy biparametric magnetic resonance imaging (bpMRI) can replace the position of mpMRI in the diagnosis of PCa. The sensitivity and specificity of bpMRI were all included. The study quality was assessed by QUADAS-2. Bivariate random effects meta-analyses and a hierarchical summary receiver operating characteristic plot were performed for further study through Revman 5 and Stata12.

Results

After searching, we acquired 752 articles among which 45 studies with 5,217 participants were eligible for inclusion. The positive likelihood ratio for the detection of PCa was 2.40 (95% CI: 1.50–3.80) and the negative likelihood ratio was 0.31 (95% CI: 0.18–0.53). The sensitivity and specificity were 0.77 (95% CI: 0.73–0.81) and 0.81 (95% CI: 0.76–0.85) respectively. Based on our result, pooled specificity demonstrated little difference between bpMRI and mpMRI [bpMRI, 0.81 (95% CI, 0.76–0.85); mpMRI, 0.82 (95% CI, 0.72–0.88); P=0.169]. The sensitivity, however, indicated a significant difference between these two groups [bpMRI, 0.77 (95% CI, 0.73–0.81); mpMRI, 0.84 (95% CI, 0.78–0.89); P=0.001].

Conclusions

bpMRI with high b-value is a sensitive tool for diagnosing PCa. Consistent results were found in multiple subgroup analysis.

Biparametric versus multiparametric magnetic resonance imaging of the prostate: detection of clinically significant cancer in a perfect match group

Background

Biparametric (bp) magnetic resonance imaging (MRI) could be an alternative MRI for the detection of the clinically significant prostate cancer (csPCa).

Purpose

To compare the accuracies of prostate cancer detection and localization between prebiopsy bpMRI and postbiopsy multiparametric MRI (mpMRI) taken on different days, using radical prostatectomy specimens as the reference standards.

Material and methods

Data of 41 total consecutive patients who underwent the following examinations and procedures between September 2015 and March 2017 were collected: (1) magnetic resonance- and/or ultrasonography-guided biopsy after bpMRI; (2) postbiopsy mpMRI; and (3) radical prostatectomy with csPCa. Two radiologists scored suspected lesions on bpMRI and mpMRI independently using Prostate Imaging Reporting and Data System version 2. The diagnostic accuracy of detecting csPCa and the Dice similarity coefficient were obtained. Apparent diffusion coefficient (ADC) ratios were also obtained for quantitative comparison between bpMRI and mpMRI.

Results

Diagnostic accuracies on bpMRI and mpMRI were 0.83 and 0.82 for reader 1; 0.80 and 0.82 for reader 2. There are no significantly different values of diagnostic sensitivities or specificities between the readers or between MRI protocols. Intra-observer Dice similarity coefficient was significantly lower in reader 2, compared to that in reader 1 between the two MRI protocols. The range of mean ADC ratio was 0.281-0.635. There was no statistically significant difference in the ADC ratio between bpMRI and mpMRI.

Conclusions

Diagnostic performance of bpMRI without dynamic contrast enhancement MRI is not significantly different from mpMRI with dynamic contrast enhancement MRI in the detection of csPCa.

MRI combined with PSA density in detecting clinically significant prostate cancer in patients with PSA serum levels of 4∼10ng/mL: Biparametric versus multiparametric MRI

PURPOSE

To compare the performance of biparametric magnetic resonance imaging (bpMRI) to that of multiparametric MRI (mpMRI) in combination with prostate-specific antigen density (PSAD) in detecting clinically significant prostate cancer (csPCa) in patients with PSA serum levels of 4∼10ng/mL.

MATERIALS AND METHODS

A total of 123 men (mean age, 66.3±8.9 [SD]; range: 42-83 years) with PSA serum levels of 4∼10ng/mL with suspected csPCa were included. All patients underwent mpMRI at 3 Tesla and transrectal ultrasound-guided prostate biopsy in their clinical workup and were followed-up for >1 year when no csPCa was found at initial biopsy. The mpMRI images were reinterpreted according to the Prostate Imaging Reporting and Data System (PI-RADS, v2.1) twice in two different sessions using either mpMRI sequences or bpMRI sequences. The patients were divided into 2 groups according to whether csPCa was detected. The PI-RADS (mpMRI or bpMRI) categories and PSAD were used in combination to detect csPCa. Receiver operating characteristic (ROC) curve and decision curve analyses were performed to compare the efficacy of the different models (mpMRI, bpMRI, PSAD, mpMRI+PSAD and bpMRI+PSAD).

RESULTS

Thirty-seven patients (30.1%, 37/123) had csPCa. ROC analysis showed that bpMRI (AUC=0.884 [95% confidence interval (CI): 0.814-0.935]) outperformed mpMRI (AUC=0.867 [95% CI: 0.794-0.921]) (P=0.035) and that bpMRI and mpMRI performed better than PSAD (0.682 [95% CI: 0.592-0.763]) in detecting csPCa; bpMRI+PSAD (AUC=0.907 [95% CI: 0.841-0.952]) performed similarly to mpMRI+PSAD (AUC=0.896 [95% CI: 0.828-0.944]) (P=0.151) and bpMRI (P=0.224). The sensitivity and specificity were 81.1% (95% CI: 64.8-92.0%) and 88.4% (95% CI: 79.7-94.3%), respectively for bpMRI, and 83.8% (95% CI: 68.0-93.8%) and 80.2% (95% CI: 70.2-88.0%), respectively for mpMRI (P>0.999 for sensitivity and P=0.016 for specificity). Among the 5 decision models, the decision curve analysis showed that all models (except for PSAD) achieved a high net benefit.

CONCLUSION

In patients with PSA serum levels of 4∼10ng/mL, bpMRI and bpMRI combined with PSAD achieve better performance than mpMRI in detecting csPCa; bpMRI has a higher specificity than mpMRI, which could decrease unnecessary biopsy, and may serve as a potential alternative to mpMRI to optimize clinical workup.

Multiparametric MRI and auto-fixed volume of interest-based radiomics signature for clinically significant peripheral zone prostate cancer

Objectives

To create a radiomics approach based on multiparametric magnetic resonance imaging (mpMRI) features extracted from an auto-fixed volume of interest (VOI) that quantifies the phenotype of clinically significant (CS) peripheral zone (PZ) prostate cancer (PCa).

Methods

This study included 206 patients with 262 prospectively called mpMRI prostate imaging reporting and data system 3–5 PZ lesions. Gleason scores > 6 were defined as CS PCa. Features were extracted with an auto-fixed 12-mm spherical VOI placed around a pin point in each lesion. The value of dynamic contrast-enhanced imaging(DCE), multivariate feature selection and extreme gradient boosting (XGB) vs. univariate feature selection and random forest (RF), expert-based feature pre-selection, and the addition of image filters was investigated using the training (171 lesions) and test (91 lesions) datasets.

Results

The best model with features from T2-weighted (T2-w) + diffusion-weighted imaging (DWI) + DCE had an area under the curve (AUC) of 0.870 (95% CI 0.980–0.754). Removal of DCE features decreased AUC to 0.816 (95% CI 0.920–0.710), although not significantly (p = 0.119). Multivariate and XGB outperformed univariate and RF (p = 0.028). Expert-based feature pre-selection and image filters had no significant contribution.

Conclusions

The phenotype of CS PZ PCa lesions can be quantified using a radiomics approach based on features extracted from T2-w + DWI using an auto-fixed VOI. Although DCE features improve diagnostic performance, this is not statistically significant. Multivariate feature selection and XGB should be preferred over univariate feature selection and RF. The developed model may be a valuable addition to traditional visual assessment in diagnosing CS PZ PCa.

Key Points

• T2-weighted and diffusion-weighted imaging features are essential components of a radiomics model for clinically significant prostate cancer; addition of dynamic contrast-enhanced imaging does not significantly improve diagnostic performance.

• Multivariate feature selection and extreme gradient outperform univariate feature selection and random forest.

• The developed radiomics model that extracts multiparametric MRI features with an auto-fixed volume of interest may be a valuable addition to visual assessment in diagnosing clinically significant prostate cancer.

Electronic supplementary material

The online version of this article (10.1007/s00330-019-06488-y) contains supplementary material, which is available to authorized users.

Detection of Extraprostatic Extension of Cancer on Biparametric MRI Combining Texture Analysis and Machine Learning: Preliminary Results

RATIONALE AND OBJECTIVES

Extraprostatic extension of disease (EPE) has a major role in risk stratification of prostate cancer patients. Currently, pretreatment local staging is performed with MRI, while the gold standard is represented by histopathological analysis after radical prostatectomy. Texture analysis (TA) is a quantitative postprocessing method for data extraction, while machine learning (ML) employs artificial intelligence algorithms for data classification. Purpose of this study was to assess whether ML algorithms could predict histopathological EPE using TA features extracted from unenhanced MR images.

MATERIALS AND METHODS

Index lesions from biparametric MRI examinations of 39 patients with prostate cancer who underwent radical prostatectomy were manually segmented on both T2-weighted images and ADC maps for TA data extraction. Combinations of different feature selection methods and ML classifiers were tested, and their performance was compared to a baseline accuracy reference.

RESULTS

The classifier showing the best performance was the Bayesian Network, using the dataset obtained by the Subset Evaluator feature selection method. It showed a percentage of correctly classified instances of 82%, an area under the curve of 0.88, a weighted true positive rate of 0.82 and a weighted true negative rate of 0.80.

CONCLUSION

A combined ML and TA approach appears as a feasible tool to predict histopathological EPE on biparametric MR images.

Comparison of bi- and multiparametric magnetic resonance imaging to select men for active surveillance

Background

Active surveillance of men with prostate cancer relies on accurate risk assessments because it aims to avoid or delay invasive therapies and reduce overtreatment.

Purpose

To compare the diagnostic performance of pre-biopsy biparametric magnetic resonance imaging (MRI) with confirmatory multiparametric MRI in selecting men for active surveillance.

Material and Methods

The study population included biopsy-naïve men with clinical suspicion of prostate cancer undergoing biparametric MRI followed by combined (standard plus MRI targeted) biopsies. Men diagnosed with prostate cancer who were subsequently enrolled in active surveillance and underwent a confirmatory multiparametric MRI within three months of diagnosis were included in the study. Discrepancies between the pre-biopsy biparametric MRI and the confirmatory multiparametric MRI were assessed.

Results

Overall, 101 men (median age = 64 years; median prostate-specific-antigen level = 6.3 ng/mL) were included. Nine patients were re-biopsied after multiparametric MRI for the following reasons: suspicion of targeting error (three patients); a new suspicious lesion detected by multiparametric MRI (five patients); and an increase in tumor volume (one patient) compared with biparametric MRI. Confirmatory biopsies showed a Gleason grade group (GG) upgrade of ≥2 in 4/6 patients with suspicion of more advanced disease (missed suspicious lesion, increase in tumor volume) on multiparametric MRI. However, although multiparametric MRI subsequently detected a GG ≥ 2 prostate cancer lesion missed by biparametric MRI in 4% (4/101) of included men, the difference did not reach statistical significance (McNemar, P = 0.133).

Conclusion

Biparametric MRI could be used to select men eligible for active surveillance and a confirmatory multiparametric MRI performed shortly after inclusion seems unnecessary.

Model-free prostate cancer segmentation from dynamic contrast-enhanced MRI with recurrent convolutional networks: A feasibility study

Dynamic contrast enhanced (DCE) magnetic resonance imaging (MRI) is a method of temporal imaging that is commonly used to aid in prostate cancer (PCa) diagnosis and staging. Typically, machine learning models designed for the segmentation and detection of PCa will use an engineered scalar image called K^trans to summarize the information in the DCE time-series images. This work proposes a new model that amalgamates the U-net and the convGRU neural network architectures for the purpose of interpreting DCE time-series in a temporal and spatial basis for segmenting PCa in MR images. Ultimately, experiments show that the proposed model using the DCE time-series images can outperform a baseline U-net segmentation model using K^trans. However, when other types of scalar MR images are considered by the models, no significant advantage is observed for the proposed model.

Prostate cancer detection with biparametric magnetic resonance imaging (bpMRI) by readers with different experience: performance and comparison with multiparametric (mpMRI)

PURPOSE

To study the detection of clinically significant prostate cancer (PCa) by readers with different experience, comparing performance with biparametric magnetic resonance imaging (bmMRI) and with the reference multiparametric (mpMRI).

METHODS

Retrospective analysis of 68 patients with mpMRI of the prostate at 1.5 Tesla using a 32 phased-array coil. Forty-five patients (cases) underwent radical prostatectomy, whereas 23 (controls) had a negative prostate biopsy and ≥ 2.5 years of negative follow-up. Six observers (two with 1000 cases interpreted, two with 300, two with 100) performed the analysis first with bpMRI including diffusion-weighted imaging (DWI), apparent diffusion coefficient (ADC) maps and T2-weighted (T2W) imaging in three planes and, after 1 month, with mpMRI, adding dynamic contrast enhancement (DCE). The performance was quantified by sensitivity (SNS), specificity (SPC) and area under the curve (AUC) of the ROC (Receiver Operating Characteristics) procedure.

RESULTS

Concordance within observers of equivalent experience was good (weighted Cohen's k ≈ 0.7). The two expert readers performed as well in bpMRI as in mpMRI (SNS = 0.91-0.96, AUC = 0.86-0.93; p ≥ 0.10); readers with 300 cases performed well in mpMRI, but significantly worse in bpMR: SNS = 0.58 versus 0.91 (p < 0.0001) and AUC = 0.73 versus 0.86 (p = 0.01); the limited experience of readers with 100 cases showed in mpMRI (SNS = 0.71; AUC = 0.77) and even more in bpMRI (SNS = 0.50; AUC = 0.68).

CONCLUSION

The study revealed the impact of the readers' experience when using bpMRI. The bpMRI without contrast media was a valid alternative for expert readers, whereas less experienced ones needed DCE to significantly boost SNS and AUC. Results indicate 700-800 cases as threshold for reliable interpretation with bpMRI.

Diagnostic Accuracy of a MR Protocol Acquired with and without Endorectal Coil for Detection of Prostate Cancer: A Multicenter Study

Introduction

The purpose of this study was to compare diagnostic accuracy of a prostate multiparametric magnetic resonance imaging (mpMRI) protocol for detection of prostate cancer between images acquired with and without en-dorectal coil (ERC).

Materials

This study was approved by the regional ethics committee. Between 2014 and 2015, 33 patients (median age 51.3 years; range 42.1-77.3 years) who underwent prostate-MRI at 3T scanners at 2 different institutions, acquired with (mpMRI_ERC) and without (mpMRI_PPA) ERC and who received radical prostatectomy, were included in this retrospective study. Two expert readers (R1, R2) attributed a PI-RADS version 2 score for the most suspect (i. e. index) lesion for mpMRI_PPA and mpMRI_ERC. Sensitivity and positive predictive value for detection of index lesions were assessed using 2 × 2 contingency tables. Differences between groups were tested using the McNemar test. Whole-mount histopathology served as reference standard.

Results

On a quadrant-basis cumulative sensitivity ranged between 0.61-0.67 and 0.76-0.88 for mpMRI_PPA and mpMRI_ERC protocols, respectively (p > 0.05). Cumulative positive predictive value ranged between 0.80-0.81 and 0.89-0.91 for mpMRI_PPA and mpMRI_ERC protocols, respectively. The differences were not statistically significant for R1 (p = 0.267) or R2 (p = 0.508).

Conclusion

Our results suggest that there may be no significant differences for detection of prostate cancer between images acquired with and without an ERC.

Comparison between multiparametric MRI with and without post - contrast sequences for clinically significant prostate cancer detection

Background:

Dynamic-contrast enhanced (DCE) sequence is used to increase detection of small lesions, based on increased vascularization. However, literature is controversy about the real incremental value of DCE in detection of clinically significant (CS) prostate cancer (PCa), since absence of enhancement does not exclude cancer, and enhancement alone is not definitive for tumor. Purpose: To test the hypothesis that DCE images do not increase CS PCa detection on MRI prior to biopsy, comparing exams without and with contrast sequences. Material and Materials and Methods: All men who come to our institution to perform MRI on a 3T scanner without a prior diagnosis of CS PCa were invited to participate in this study. Reference standard was transrectal prostate US with systematic biopsy and MRI/US fusion biopsy of suspicious areas. Radiologists read the MRI images prospectively and independently (first only sequences without contrast, and subsequently the entire exam) and graded them on 5-points scale of cancer suspicion.

Results:

102 patients were included. Overall detection on biopsy showed CS cancer in 43 patients (42.2%), clinically non-significant cancer in 11 (10.8%) and negative results in 48 patients (47%). Positivities for CS PCa ranged from 8.9% to 9.8% for low suspicion and 75.0% to 88.9% for very high suspicion. There was no statistical difference regarding detection of CS PCa (no statistical difference was found when compared accuracies, sensitivities, specificities, PPV and NPV in both types of exams). Inter-reader agreement was 0.59.

Conclusion:

Exams with and without contrast-enhanced sequences were similar for detection of CS PCa on MRI.

Evolution of prostate MRI: from multiparametric standard to less-is-better and different-is better strategies

Multiparametric magnetic resonance imaging (mpMRI) has become the standard of care to achieve accurate and reproducible diagnosis of prostate cancer. However, mpMRI is quite demanding in terms of technical rigour, patient's tolerability and safety, expertise in interpretation, and costs. This paper reviews the main technical strategies proposed as less-is-better solutions for clinical practice (non-contrast biparametric MRI, reduction of acquisition time, abbreviated protocols, computer-aided diagnosis systems), discussing them in the light of the available evidence and of the concurrent evolution of Prostate Imaging Reporting and Data System (PI-RADS). We also summarised research results on those advanced techniques representing an alternative different-is-better line of the still ongoing evolution of prostate MRI (quantitative diffusion-weighted imaging, quantitative dynamic contrast enhancement, intravoxel incoherent motion, diffusion tensor imaging, diffusional kurtosis imaging, restriction spectrum imaging, radiomics analysis, hybrid positron emission tomography/MRI).

68Ga-PSMA-11 PET/MR Detects Local Recurrence Occult on mpMRI in Prostate Cancer Patients After HIFU

High-intensity focused ultrasound (HIFU) is a promising new modality for the treatment of localized prostate cancer (PCa). Follow-up of patients is recommended with biopsies and multiparametric MRI (mpMRI). However, mpMRI in the postinterventional setting is often false-negative. It was our aim to investigate if the new tracer targeting the prostate-specific membrane antigen (⁶⁸Ga-PSMA-11) could be used to localize recurrent disease with PET/MR in patients with discrepant findings between mpMRI and template biopsies. Methods: Interim analysis was performed of the first 10 patients scanned between September 2016 and May 2018 with positive template biopsy and negative mpMRI after HIFU from an ongoing clinical trial (NCT02265159). All patients underwent ⁶⁸Ga-PSMA-11 PET/MRI within 3 mo. Four prostatic quadrants were defined, and for every quadrant suspicion for recurrence was rated on a 5-point Likert scale from definitely no recurrence (1) to highly suspected of recurrence (5), with 4 used as a cutoff for suspected disease based on PET/MRI by a masked reader. ⁶⁸Ga-PSMA-11 uptake of suspected lesions and background areas was measured with the SUV_max The apparent diffusion coefficient values of lesions and background were given for each segment. PET/MRI scans were compared with the template biopsy results, including corresponding Gleason scores (GS), number of positive cores, and tumor length. Results: The quadrant-based sensitivity, specificity, and positive and negative predictive values for PET/MRI were 55%, 100%, 100%, and 85%, respectively. Patient-based PET/MRI was negative in 4 cases with GS 3 + 4 and a tumor length between 0.1 and 3 mm. All tumor lesions with GS 4 + 3 or higher were detected on PET/MRI. Conclusion: Our preliminary results indicate that ⁶⁸Ga-PSMA-11-PET/MR has the potential to localize PCa recurrence after HIFU occult on mpMRI.

Prospective comparison of a fast 1.5-T biparametric with the 3.0-T multiparametric ESUR magnetic resonance imaging protocol as a triage test for men at risk of prostate cancer

OBJECTIVE

To compare prospectively the diagnostic performance of a biparametric (T2-weighted imaging [T2WI] and diffusion-weighted imaging [DWI]) 1.5-T fast magnetic resonance imaging (fMRI) protocol with the standard 3.0-T multiparametric MRI (mpMRI) protocol of the European Society of Urological Imaging (ESUR) in men referred for a prostate biopsy.

PATIENTS AND METHODS

Ninety patients with a prostate cancer (PCa) risk of ≥10% according to the SWOP calculator 4 underwent first fMRI and then the reference mpMRI. Patients with Prostate Imaging Reporting and Data System (PI-RADS) v.2 lesions ≥3/5 on the mpMRI were scheduled for MRI/ultrasonography (US) fusion-guided prostate biopsy. Performance of fMRI was assessed using receiver-operating characteristic curve analysis and mpMRI as reference. Calculation of inter-technique agreement on PI-RADS v.2 score by Cohen's κ.

RESULTS

The diagnostic accuracy of fMRI shown by the lesion-based analysis was excellent: area under the curve (AUC) 0.961 (P < 0.001), sensitivity 95%, specificity 97%, positive predictive value (PPV) 99%, negative predictive value (NPV) 89%. The patient-based analysis showed an AUC for fMRI of 0.975 (P < 0.001), a sensitivity of 98%, a specificity of 97%, a PPV of 98% and an NPV of 97%. Agreement on the PI-RADS score between both protocols was found to be good (κ = 0.78 [0.57; 0.99]); fMRI missing PI-RADS 4 lesions in three patients. Biopsy results showed no cancer in two patients (two cores per nodule) and Gleason 6 cancer in one patient. There was only one false-positive fMRI, with a PI-RADS score of 4, whose biopsy was negative.

CONCLUSION

In the triage of men with a high risk of PCa for prostate biopsy, an f MRI protocol (1.5-T magnet, T2WI + DWI, <15 min) may safely replace the traditional ESUR 3.0-T mpMRI protocol, saving time and contrast injection.

Diagnostic Performance of Biparametric MRI for Detection of Prostate Cancer: A Systematic Review and Meta-Analysis

OBJECTIVE

The purpose of this study was to perform a systematic review and meta-analysis to estimate the diagnostic performance of biparametric MRI (bpMRI) for detection of prostate cancer (PCa).

MATERIALS AND METHODS

Two independent reviewers performed a systematic review of the literature published from January 2000 to July 2017 by using predefined search terms. The standard of pathologic reference was established at prostatectomy or prostate biopsy. The numbers of true- and false-positive and true- and false-negative results were extracted. The Quality Assessment of Diagnostic Accuracy Studies tool was used to assess the quality of the selected studies. Statistical analysis included pooling of diagnostic accuracy, meta-regression, subgroup analysis, head-to-head comparison, and identification of publication bias.

RESULTS

Thirty-three studies were used for general data pooling. The overall sensitivity was 0.81 (95% CI, 0.76-0.85), and overall specificity was 0.77 (95% CI, 0.69-0.84). As for clinically relevant PCa, bpMRI maintained high diagnostic value (AUC, 0.85; 95% CI, 0.82-0.88). There was no evidence of publication bias (p = 0.67). From head-to-head comparison for detection of PCa, multiparametric MRI (mpMRI) had significantly higher pooled sensitivity (0.85; 95% CI, 0.78-0.93) than did bpMRI (0.80; 95% CI, 0.71-0.90) (p = 0.01). However, the pooled specificity values were not significantly different (mpMRI, 0.77 [95% CI, 0.58-0.95]; bpMRI, 0.80 [95% CI, 0.64-0.96]; p = 0.82).

CONCLUSION

The results of this meta-analysis suggest that bpMRI has high diagnostic accuracy in the detection of PCa and maintains a high detection rate for clinically relevant PCa. However, owing to high heterogeneity among the included studies, caution is needed in applying the results of the meta-analysis.

Combined Analysis of Biparametric MRI and Prostate-Specific Antigen Density: Role in the Prebiopsy Diagnosis of Gleason Score 7 or Greater Prostate Cancer

OBJECTIVE

The objective of our study was to investigate the diagnostic performance of prebiopsy biparametric MRI (bpMRI) and prostate-specific antigen density (PSAD) for Gleason score (GS) 7 or greater prostate cancer (PCa).

MATERIALS AND METHODS

Sixty-eight consecutive patients who underwent prebiopsy bpMRI and biopsy were included. Pathologic results of systemic and targeted biopsies were the reference standard. Qualitative analyses comprised Prostate Imaging Reporting and Data System version 2 (PI-RADSv2) and modified PI-RADSv2 (mPI-RADSv2). Quantitative analyses comprised mean apparent diffusion coefficient (ADC) of tumor, 10th percentile ADC of tumor, mean ADC ratio (ADCR) between benign tissues and PCa, and 10th percentile ADCR between benign tissues and PCa. The AUCs of the following combined models for GS 7 or greater PCa were investigated: model 1, PSAD and PI-RADSv2; model 2, PSAD and mPI-RADSv2; model 3, PSAD and mean ADC; model 4, PSAD and 10th percentile ADC; model 5, PSAD and mean ADCR; and model 6, PSAD and 10th percentile ADCR.

RESULTS

The rate of GS 7 or greater PCa was 45.6% (31/68). AUCs of bpMRI parameters were 0.816 for PI-RADSv2, 0.838 for mPI-RADSv2, 0.820 for mean ADC, 0.823 for 10th percentile ADC, 0.780 for mean ADCR, and 0.763 for 10th percentile ADCR (p > 0.05 in all comparisons), whereas AUCs of prostate-specific antigen (PSA)-based parameters were 0.650 for PSA and 0.745 for PSAD (PSA vs PSAD, p = 0.017). AUCs of the combined models from 1 to 6 were 0.860, 0.880, 0.837, 0.844, 0.811, and 0.806, respectively, for biopsy GS 7 or greater PCa (p > 0.05 in all comparisons).

CONCLUSION

Combined analysis of prebiopsy bpMRI and PSAD is useful for identifying GS 7 or greater PCa.