Biparametric Magnetic Resonance Imaging Research Articles

Prostate158 - An expert-annotated 3T MRI dataset and algorithm for prostate cancer detection

BackgroundThe development of deep learning (DL) models for prostate segmentation on magnetic resonance imaging (MRI) depends on expert-annotated data and reliable baselines, which are often not publicly available. This limits both reproducibility and comparability. MethodsProstate158 consists of 158 expert annotated biparametric 3T prostate MRIs comprising T2w sequences and diffusion-weighted sequences with apparent diffusion coefficient maps. Two U-ResNets trained for segmentation of anatomy (central gland, peripheral zone) and suspicious lesions for prostate cancer (PCa) with a PI-RADS score of ≥4 served as baseline algorithms. Segmentation performance was evaluated using the Dice similarity coefficient (DSC), the Hausdorff distance (HD), and the average surface distance (ASD). The Wilcoxon test with Bonferroni correction was used to evaluate differences in performance. The generalizability of the baseline model was assessed using the open datasets Medical Segmentation Decathlon and PROSTATEx. ResultsCompared to Reader 1, the models achieved a DSC/HD/ASD of 0.88/18.3/2.2 for the central gland, 0.75/22.8/1.9 for the peripheral zone, and 0.45/36.7/17.4 for PCa. Compared with Reader 2, the DSC/HD/ASD were 0.88/17.5/2.6 for the central gland, 0.73/33.2/1.9 for the peripheral zone, and 0.4/39.5/19.1 for PCa. Interrater agreement measured in DSC/HD/ASD was 0.87/11.1/1.0 for the central gland, 0.75/15.8/0.74 for the peripheral zone, and 0.6/18.8/5.5 for PCa. Segmentation performances on the Medical Segmentation Decathlon and PROSTATEx were 0.82/22.5/3.4; 0.86/18.6/2.5 for the central gland, and 0.64/29.2/4.7; 0.71/26.3/2.2 for the peripheral zone. ConclusionsWe provide an openly accessible, expert-annotated 3T dataset of prostate MRI and a reproducible benchmark to foster the development of prostate segmentation algorithms.

Cost-effectiveness analysis of short biparametric magnetic resonance imaging protocol in men at risk of prostate cancer.

To compare the cost-effectiveness of a short biparametric MRI (BP-MRI) with that of contrast-enhanced multiparametric MRI (MP-MRI) for the detection of prostate cancer in men with elevated prostatespecific antigen (PSA) levels. We compared two diagnostic procedures for detection of prostate cancer (Pca), BP-MRI and MP-MRI, in terms of quality-adjusted life years (QALY), incremental costeffectiveness ratio (ICER) and net monetary benefit (NMB) for a hypothetical cohort of 10,000 patients. We compared two scenarios in which different protocols would be used for the early diagnosis of prostate cancer in relation to PSA values. Scenario 1. BP-MRI/MP-MRI yearly if > 3.0 ng/ml, every 2 years otherwise; Scenario 2. BP-MRI/MP-MRI yearly with age-dependent threshold 3.5 ng/ml (50-59 years), 4.5 ng/ml (60-69 years), 6.5 ng/ml (70-79 years). BP-MRI was more effective than the comparator in terms of cost (160.10 € vs 249.99€) QALYs (a mean of 9.12 vs 8.46), ICER (a mean of 232.45) and NMB (a mean of 273.439 vs 251.863). BP-MRI was dominant, being more effective and less expensive, with a lower social cost. Scenario 2 was more cost-effective compared to scenario 1. Our results confirmed the hypothesis that a short bi-parametric MRI protocol represents a cost-efficient procedure, optimizing resources in a policy perspective.

Combination of biparametric magnetic resonance imaging with prostate‐specific antigen density to stratify the risk of significant prostate cancer: Initial biopsy and long‐term follow‐up results

To assess whether the combination of biparametric magnetic resonance imaging with prostate-specific antigen density can properly stratify the risk of significant prostate cancer in patients undergoing prostate biopsies and how this approach affects the detection of prostate cancer during follow-up in patients who do not undergo prostate biopsy. In total, 411 biopsy-naïve patients who had elevated prostate-specific antigen levels and then underwent biparametric magnetic resonance imaging for suspicious prostate cancer were analyzed: 203 patients underwent prostate biopsies, whereas 208 patients did not. Significant prostate cancer detection rates stratified by the combination of Prostate Imaging Reporting and Data System score and prostate-specific antigen density were assessed in patients who underwent prostate biopsies. The cumulative incidence of prostate cancer detection during the follow-up was assessed in patients who omitted biopsy. The negative predictive value for significant prostate cancer was 89% for Prostate Imaging Reporting and Data System scores 1-3, which increased to 97% when prostate-specific antigen density <0.15 ng/ml/cm3 was combined. Among patients who did not undergo biopsy, patients with Prostate Imaging Reporting and Data System scores 1-3 plus prostate-specific antigen density <0.15 ng/ml/cm3 included significantly less cases in which significant prostate cancer was detected during the follow-up, compared with the others (3.2% versus 17% at 36 months). Restriction of prostate biopsies to patients with Prostate Imaging Reporting and Data System scores 4-5 or prostate-specific antigen density ≥0.15 ng/ml/cm3 proved to be the good biopsy strategy, effectively balancing risks and benefits.

A deep learning masked segmentation alternative to manual segmentation in biparametric MRI prostate cancer radiomics

ObjectivesTo determine the value of a deep learning masked (DLM) auto-fixed volume of interest (VOI) segmentation method as an alternative to manual segmentation for radiomics-based diagnosis of clinically significant (CS) prostate cancer (PCa) on biparametric magnetic resonance imaging (bpMRI).Materials and methodsThis study included a retrospective multi-center dataset of 524 PCa lesions (of which 204 are CS PCa) on bpMRI. All lesions were both semi-automatically segmented with a DLM auto-fixed VOI method (averaging < 10 s per lesion) and manually segmented by an expert uroradiologist (averaging 5 min per lesion). The DLM auto-fixed VOI method uses a spherical VOI (with its center at the location of the lowest apparent diffusion coefficient of the prostate lesion as indicated with a single mouse click) from which non-prostate voxels are removed using a deep learning–based prostate segmentation algorithm. Thirteen different DLM auto-fixed VOI diameters (ranging from 6 to 30 mm) were explored. Extracted radiomics data were split into training and test sets (4:1 ratio). Performance was assessed with receiver operating characteristic (ROC) analysis.ResultsIn the test set, the area under the ROC curve (AUCs) of the DLM auto-fixed VOI method with a VOI diameter of 18 mm (0.76 [95% CI: 0.66–0.85]) was significantly higher (p = 0.0198) than that of the manual segmentation method (0.62 [95% CI: 0.52–0.73]).ConclusionsA DLM auto-fixed VOI segmentation can provide a potentially more accurate radiomics diagnosis of CS PCa than expert manual segmentation while also reducing expert time investment by more than 97%.Key Points• Compared to traditional expert-based segmentation, a deep learning mask (DLM) auto-fixed VOI placement is more accurate at detecting CS PCa.• Compared to traditional expert-based segmentation, a DLM auto-fixed VOI placement is faster and can result in a 97% time reduction.• Applying deep learning to an auto-fixed VOI radiomics approach can be valuable.

Early experience in avoiding biopsies for biopsy-naïve men with clinical suspicion of prostate cancer but non-suspicious biparametric magnetic resonance imaging results and prostate-specific antigen density < 0.15ng/mL2: A 2-year follow-up study.

BackgroundOnly limited data have been published on the diagnostic accuracy of combining biparametric (bp) magnetic resonance imaging (MRI) and prostate-specific antigen density (PSAd) to rule out biopsies.PurposeThe purpose is to assess the 2-year risk of being diagnosed with sPCa following the strategy of avoiding immediate biopsies in men with non-suspicious bp MRIs and a PSAd <0.15 ng/mL2.Material and MethodsTwo hundred biopsy-naïve men with clinical suspicion of PCa underwent a pre-biopsy bp MRI from March to July 2019. Of these, 109 men had a Prostate Imaging Reporting and Data System (PI-RADS) score of 1–3 including 77 men with calculated PSAd <0.15 ng/mL2. As a result, no biopsies were performed in these 77 men, who were clinically followed up for at least 2 years and re-examined in case of rising suspicion of sPCa. The remaining 32 men with a calculated PSAd ≥0.15 ng/mL2 underwent systematic biopsies and targeted biopsies of any PI-RADS 3 lesion.ResultsOne of the 77 men (1.3%) had an sPCa diagnosed within 2 years of follow-up. All men were referred back to their general practitioner within 1 year and 9% (7/77) were re-referred to the urology department during follow-up. Among these men, 43% (3/7) continued to have PSA levels that were above their individual thresholds at confirmatory testing and underwent secondary MRI scans.ConclusionsNo biopsies for men with bpMRI results exhibiting maximum PI-RADS 3 and with a PSAd <0.15 ng/mL2 resulted in a 2-year risk of being diagnosed with sPCa of 1.3%.

Biparametric magnetic resonance imaging assessment for detection of muscle-invasive bladder cancer: a systematic review and meta-analysis.

To investigate if removing DCE from the Vesical Imaging Reporting and Data System (VI-RADS) influences the diagnostic accuracy of muscle-invasive bladder cancer (MIBC). We also explored using different reference standards on the MRI diagnostic performance. We searched the Cochrane Library, Embase, and PubMed databases to June 26, 2021. Pooled biparametric MRI (bpMRI, T2WI+DWI) and multiparametric MRI (mpMRI, T2WI+DWI+DCE) sensitivities and specificities and the diagnostic performances of these methods for MIBC were compared using different reference standards. Seventeen studies with 2344 patients were finally included, of which 7 studies, including 1041 patients, reported the diagnostic performance of bpMRI. VI-RADS showed sensitivities and specificities of 0.91 (95% CI 0.87-0.94) and 0.86 (95% CI 0.77-0.91) at cutoff scores of 3, and 0.85 (95% CI 0.77-0.90) and 0.93 (95% CI 0.89-0.96) at cutoff scores of 4. BpMRI showed sensitivities and specificities of 0.90 (95% CI 0.69-0.97) and 0.90 (95% CI 0.81-0.95), and 0.84 (95% CI 0.78-0.88) and 0.97 (95% CI 0.87-0.99), respectively, for cutoff scores of 3 and 4. The sensitivities of bpMRI vs mpMRI for MIBC were not significantly different, but bpMRI was more specific than mpMRI at cutoff scores of 3 (p = 0.02) and 4 (p = 0.02). The VI-RADS studies using primary transurethral resection of bladder tumors (TURBT) as the reference standard had significantly higher sensitivities (p < 0.001) than those using secondary TURBT or radical cystectomy as the reference. BpMRI and conventional VI-RADS had similar diagnostic efficacies for MIBC. Since MRI overestimated MIBC diagnoses using primary TURBT as the reference standard, we recommend using secondary TURBT as the reference standard. • Biparametric MRI without DCE had similar diagnostic efficacies for MIBC compared with conventional VI-RADS. • The sensitivity of VI-RADS was overestimated when referring to the primary TURBT results. • Biparametric MRI comprised of T2WI and DWI could be used for detecting MIBC in clinical practice.

MRI as a screening tool for prostate cancer: current evidence and future challenges

PurposeProstate cancer (PCa) screening, which relies on prostate-specific antigen (PSA) testing, is a contentious topic that received negative attention due to the low sensitivity and specificity of PSA to detect clinically significant PCa. In this context, due to the higher sensitivity and specificity of magnetic resonance imaging (MRI), several trials investigate the feasibility of “MRI-only” screening approaches, and question if PSA testing may be replaced within prostate cancer screening programs.MethodsThis narrative review discusses the current literature and the outlook on the potential of MRI-based PCa screening.ResultsSeveral prospective randomized population-based trials are ongoing. Preliminary study results appear to favor the “MRI-only” approach. However, MRI-based PCa screening programs face a variety of obstacles that have yet to be fully addressed. These include the increased cost of MRI, lack of broad availability, differences in MRI acquisition and interpretation protocols, and lack of long-term impact on cancer-specific mortality. Partly, these issues are being addressed by shorter and simpler MRI approaches (5–20 min bi-parametric MRI), novel quality indicators (PI-QUAL) and the implementation of radiomics (deep learning, machine learning).ConclusionAlthough promising preliminary results were reported, MRI-based PCa screening still lack long-term data on crucial endpoints such as the impact of MRI screening on mortality. Furthermore, the issues of availability, cost-effectiveness, and differences in MRI acquisition and interpretation still need to be addressed.

One-Day Prostate Cancer Diagnosis: Biparametric Magnetic Resonance Imaging and Digital Pathology by Fluorescence Confocal Microscopy.

In this prospective observational study, we tested the feasibility and efficacy of a novel one-day PCa diagnosis path based on biparametric magnetic resonance (bpMRI) and digital pathology by fluorescence confocal microscopy (FCM). Patients aged 55–70 years scheduled for PBx due to increased PSA levels (3–10 ng/mL) and/or abnormal digitorectal examination were enrolled. All patients underwent bpMRI and PBx with immediate FCM evaluation of biopsy cores. Patients were asked to fill out a dedicated Patient Satisfaction Questionnaire. Patients’ satisfaction rates and concordance between digital pathology and standard HE evaluation were the outcomes of interest. Twelve patients completed our one-day PCa diagnosis path. BpMRI showed suspicious lesions in 7 patients. Digital pathology by FCM identified PCa in 5 (41.7%) of the 12 patients. Standard pathology confirmed the diagnosis made through digital pathology in all the cases. At a per patient level, high concordance between the methods was achieved in Gleason Grading (4 out of 5 patients). The level of agreement in the number of positive cores was lower but did not affect the choice of treatment in any of the 5 PCa cases. At a per core level, the agreement was very high for the diagnosis of anyPCa (96.2%) and csPCa (97.3%), with a k coefficient of 0.90 and 0.92, respectively (near perfect agreement). In conclusion, one-day PCa diagnosis by FCM represents a feasible, reliable, and fast diagnostic method that provides significant advantages in optimizing time and resources, leading to patients having a higher quality standard of care perception.

MRI Based Radiomics Compared With the PI-RADS V2.1 in the Prediction of Clinically Significant Prostate Cancer: Biparametric vs Multiparametric MRI.

PurposeTo compare the performance of radiomics to that of the Prostate Imaging Reporting and Data System (PI-RADS) v2.1 scoring system in the detection of clinically significant prostate cancer (csPCa) based on biparametric magnetic resonance imaging (bpMRI) vs. multiparametric MRI (mpMRI).MethodsA total of 204 patients with pathological results were enrolled between January 2018 and December 2019, with 142 patients in the training cohort and 62 patients in the testing cohort. The radiomics model was compared with the PI-RADS v2.1 for the diagnosis of csPCa based on bpMRI and mpMRI by using receiver operating characteristic (ROC) curve analysis.ResultsThe radiomics model based on bpMRI and mpMRI signatures showed high predictive efficiency but with no significant differences (AUC = 0.975 vs 0.981, p=0.687 in the training cohort, and 0.953 vs 0.968, p=0.287 in the testing cohort, respectively). In addition, the radiomics model outperformed the PI-RADS v2.1 in the diagnosis of csPCa regardless of whether bpMRI (AUC = 0.975 vs. 0.871, p= 0.030 for the training cohort and AUC = 0.953 vs. 0.853, P = 0.024 for the testing cohort) or mpMRI (AUC = 0.981 vs. 0.880, p= 0.030 for the training cohort and AUC = 0.968 vs. 0.863, P = 0.016 for the testing cohort) was incorporated.ConclusionsOur study suggests the performance of bpMRI- and mpMRI-based radiomics models show no significant difference, which indicates that omitting DCE imaging in radiomics can simplify the process of analysis. Adding radiomics to PI-RADS v2.1 may improve the performance to predict csPCa.

Evaluation of clinically significant prostate cancer using biparametric magnetic resonance imaging: An evolving concept.

Multiparametric magnetic resonance imaging (mp-MRI) of prostate involves a combination of T2-weighted imaging, diffusion-weighted imaging, and dynamic contrast-enhanced (DCE) scans. However, controversy exists in the literature regarding the true value of DCE in the detection of clinically significant (CS) prostate cancer (PCa). The aim of this study is to compare the role of biparametric MRI (bp-MRI) and mp-MRI in the detection of CS PCa. Thirty-six patients with raised serum prostate-specific antigen levels were included. Bp-MRI was performed in all patients, whereas mp-MRI was performed in 30 cases only. The findings were characterized on the basis of prostate imaging reporting and data system (PI-RADS) v2 grading. PI-RADS v2 score of 3 or more was considered CS PCa. All patients underwent transrectal ultrasound-guided biopsy. Gleason score >6 was considered CS. Statistical analysis was done using the SPSS software and results interpreted. CS PCa was observed in 31 cases on histopathology. On bp-MRI, CS PCa was seen in 31 patients. Five cases of PI-RADS v2 score 3 were seen on bp-MRI and 3 of them were upgraded to PI-RADS 4 on DCE images. One case of PI-RADS 3 had low Gleason score on biopsy, whereas 1 case of PI-RADS 2 had CS PCa on biopsy. No significant difference was observed between bp-MRI and mp-MRI in the detection of CS PCa. Both bp-MRI and mp-MRI have high sensitivity, specificity, and diagnostic accuracy and were nearly identical in the detection of CS PCa with no significant advantage of DCE images.

Predictors of upgrading from low-grade cancer at prostatectomy in men with biparametric magnetic resonance imaging.

IntroductionProstate-specific antigen (PSA) density has previously been identified as a predictor of histological upgrading at radical prostatectomy, but how information from pre-treatment biparametric magnetic resonance imaging (bpMRI) contributes needs further clarification. The objective of this register-based study was to identify predictors of upgrading at prostatectomy in men with Grade group (GG) 1 and pre-treatment bpMRI.Material and methodsThis single-center study included men with GG 1 cancer on prediagnostic biopsy, who underwent bpMRI and robotic-assisted radical prostatectomy (RARP) between March 2014 and September 2019. We estimated logistic regression models to explore predictors for upgrading. The explored potential predictors were age, PSA density, tumor stage and Prostate Imaging Reporting and Data System (PI-RADS) score (dichotomised 1–3 versus 4–5).ResultsUpgrading was observed in 56% (73/130) of the men. PSA density was the only significant predictor for upgrading (unadjusted OR = 1.7, 95% CI 1.2; 2.4 adjusted OR = 1.7, 95% CI 1.2; 2.5). The probability of upgrading was lower for men with a PIRADS 1–3 than for PIRADS 4–5, but the difference was not statistically significant (adjusted OR 0.4, 95% CI 0.2; 1.1, p = 0.082). Among men with PI-RADS 1–3, the probability increased with increasing PSA density (p = 0.036). With PI-RADS 4–5 the probability of upgrading was high over the entire PSA density range.ConclusionsPSA density is a clinically important factor to predict upgrading from GG1 when bpMRI shows PI-RADS 1–3. In men with PI-RADS 4–5 on bpMRI, the probability of an undetected GG 2–5 cancer is high regardless of the PSA density.

A narrative review of biparametric MRI (bpMRI) implementation on screening, detection, and the overall accuracy for prostate cancer.

Prostate cancer is the most common malignancy in American men following skin cancer, with approximately one in eight men being diagnosed during their lifetime. Over the past several decades, the treatment of prostate cancer has evolved rapidly, so too has screening. Since the mid-2010s, magnetic resonance imaging (MRI)–guided biopsies or ‘targeted biopsies’ has been a rapidly growing topic of clinical research within the field of urologic oncology. The aim of this publication is to provide a review of biparametric MRI (bpMRI) utilization for the diagnosis of prostate cancer and a comparison to multiparametric MRI (mpMRI). Through single-centered studies and meta-analysis across all identified pertinent published literature, bpMRI is an effective tool for the screening and diagnosis of prostate cancer. When compared with the diagnostic accuracy of mpMRI, bpMRI identifies prostate cancer at comparable rates. In addition, when omitting dynamic contrast-enhanced (DCE) protocol to the MRI, patients incur reduced costs and shorter imaging time while providers can offer more tests to their patient population.

Efficacy of 68Ga-PSMA-11 PET/CT with biparametric MRI in diagnosing prostate cancer and predicting risk stratification: a comparative study.

This retrospective study aimed to investigate the efficacy of the combined application of biparametric magnetic resonance imaging (bpMRI) and 68Ga-PSMA-11 positron emission computed tomography/computed tomography (bpMRI/PET) in the qualitative diagnosis of intermediate- to high-risk prostate cancer (PCa). The 105 patients with suspected PCa included in the study underwent bpMRI and PET/CT. BpMRI examinations included conventional sequences and diffusion-weighted imaging (DWI) sequences. Major lesions were qualitatively diagnosed according to the Prostate Imaging Reporting and Data System (PI-RADS). A PET/CT scan was started 60 min after intravenous 68Ga-PSMA-11 injection. The area with the highest radioactivity on PET/CT images was defined as the major lesion, and the maximum standard uptake value (SUVmax) was measured. All cases were confirmed by biopsy and pathology. Receiver operating characteristic curve (ROC) analysis was performed on the data to calculate sensitivity, specificity, and the Youden index. Of the 105 patients, 68 patients were diagnosed with PCa, and 37 patients had benign prostatic lesions. With a PI-RADS score ≥3 as the diagnostic threshold, the accuracy of bpMRI in identifying benign and malignant prostate lesions was similar to that of PET/CT (SUVmax threshold ≥10.9), and the Youden indices were 0.60 and 0.64, respectively. The sensitivity and specificity of bpMRI in the differential diagnosis of intermediate- to high-risk PCa versus low-risk PCa or benign lesions were 63% and 88%, respectively, and the Youden index was 0.51. With an SUVmax ≥12.9 as the diagnostic threshold, the sensitivity and specificity of PET/CT in the differential diagnosis of intermediate- to high-risk PCa versus low-risk PCa or benign lesions were 74% and 94%, respectively, and the Youden index was 0.68. The sensitivity and specificity of bpMRI/PET in diagnosing PCa were 94% and 81%, respectively, and the Youden index was 0.75. The sensitivity and specificity of bpMRI/PET in the differential diagnosis of intermediate- to high-risk PCa versus low-risk PCa or benign lesions were 80% and 88%, respectively, and the Youden index was 0.68. The combined application of bpMRI and PET improves the accuracy of the qualitative diagnosis of prostate lesions, and its diagnostic efficacy for risk stratification in patients with intermediate- to high-risk PCa is similar to that of PET/CT and higher than that of bpMRI alone.

Head-to-head comparison of biparametric versus multiparametric MRI of the prostate before robot-assisted transperineal fusion prostate biopsy.

PurposeProstate biparametric magnetic resonance imaging (bpMRI) including T2-weighted imaging (T2WI) and diffusion-weighted imaging (DWI) might be an alternative to multiparametric MRI (mpMRI, including dynamic contrast imaging, DCE) to detect and guide targeted biopsy in patients with suspected prostate cancer (PCa). However, there is no upgrading peripheral zone PI-RADS 3 to PI-RADS 4 without DCE in bpMRI. The aim of this study was to evaluate bpMRI against mpMRI in biopsy-naïve men with elevated prostate-specific antigen (PSA) scheduled for robot-assisted-transperineal fusion-prostate biopsy (RA-TB).MethodsRetrospective single-center-study of 563 biopsy-naïve men (from 01/2015 to 09/2018, mean PSA 9.7 ± 6.5 ng/mL) with PI-RADSv2.1 conform mpMRI at 3 T before RA-TB. Clinically significant prostate cancer (csPCa) was defined as ISUP grade ≥ 2 in any core. Two experienced readers independently evaluated images according to PI-RADSv2.1 criteria (separate readings for bpMRI and mpMRI sequences, 6-month interval). Reference standard was histology from RA-TB.ResultsPI-RADS 2 was scored in 5.1% of cases (3.4% cancer/3.4% csPCa), PI-RADS 3 in 16.9% (32.6%/3.2%), PI-RADS 4 in 57.6% (66.1%/58.3%) and PI-RADS 5 in 20.4% of cases (79.1%/74.8%). For mpMRI/bpMRI test comparison, sensitivity was 99.0%/97.1% (p < 0.001), specificity 47.5%/61.2% (p < 0.001), PPV 69.5%/75.1% (p < 0.001) and NPV 97.6%/94.6% (n.s.). csPCa was considered gold standard. 35 cases without cancer were upgraded to PI-RADS 4 (mpMRI) and six PI-RADS 3 cases with csPCa were not upgraded (bpMRI).ConclusionIn patients planned for RA-TB with elevated PSA and clinical suspicion for PCa, specificity was higher in bpMRI vs. mpMRI, which could solve constrains regarding time and contrast agent.

Predicting the Grade of Prostate Cancer Based on a Biparametric MRI Radiomics Signature.

Purpose This study aimed to investigate the value of biparametric magnetic resonance imaging (bp-MRI)-based radiomics signatures for the preoperative prediction of prostate cancer (PCa) grade compared with visual assessments by radiologists based on the Prostate Imaging Reporting and Data System Version 2.1 (PI-RADS V2.1) scores of multiparametric MRI (mp-MRI). Methods This retrospective study included 142 consecutive patients with histologically confirmed PCa who were undergoing mp-MRI before surgery. MRI images were scored and evaluated by two independent radiologists using PI-RADS V2.1. The radiomics workflow was divided into five steps: (a) image selection and segmentation, (b) feature extraction, (c) feature selection, (d) model establishment, and (e) model evaluation. Three machine learning algorithms (random forest tree (RF), logistic regression, and support vector machine (SVM)) were constructed to differentiate high-grade from low-grade PCa. Receiver operating characteristic (ROC) analysis was used to compare the machine learning-based analysis of bp-MRI radiomics models with PI-RADS V2.1. Results In all, 8 stable radiomics features out of 804 extracted features based on T2-weighted imaging (T2WI) and ADC sequences were selected. Radiomics signatures successfully categorized high-grade and low-grade PCa cases (P < 0.05) in both the training and test datasets. The radiomics model-based RF method (area under the curve, AUC: 0.982; 0.918), logistic regression (AUC: 0.886; 0.886), and SVM (AUC: 0.943; 0.913) in both the training and test cohorts had better diagnostic performance than PI-RADS V2.1 (AUC: 0.767; 0.813) when predicting PCa grade. Conclusions The results of this clinical study indicate that machine learning-based analysis of bp-MRI radiomic models may be helpful for distinguishing high-grade and low-grade PCa that outperformed the PI-RADS V2.1 scores based on mp-MRI. The machine learning algorithm RF model was slightly better.

Deep Learning Reconstruction Enables Highly Accelerated Biparametric MR Imaging of the Prostate.

Early diagnosis and treatment of prostate cancer (PCa) can be curative; however, prostate-specific antigen is a suboptimal screening test for clinically significant PCa. While prostate magnetic resonance imaging (MRI) has demonstrated value for the diagnosis of PCa, the acquisition time is too long for a first-line screening modality. To accelerate prostate MRI exams, utilizing a variational network (VN) for image reconstruction. Retrospective. One hundred and thirteen subjects (train/val/test: 70/13/30) undergoing prostate MRI. 3.0 T; a T2 turbo spin echo (TSE) T2-weighted image (T2WI) sequence in axial and coronal planes, and axial echo-planar diffusion-weighted imaging (DWI). Four abdominal radiologists evaluated the image quality of VN reconstructions of retrospectively under-sampled biparametric MRIs (bp-MRI), and standard bp-MRI reconstructions for 20 test subjects (studies). The studies included axial and coronal T2WI, DWI B50 seconds/mm2 and B1000 seconds/mm (4-fold T2WI, 3-fold DWI), all of which were evaluated separately for image quality on a Likert scale (1: non-diagnostic to 5: excellent quality). In another 10 test subjects, three readers graded lesions on bp-MRI-which additionally included calculated B1500 seconds/mm2 , and apparent diffusion coefficient map-according to the Prostate Imaging Reporting and Data System (PI-RADS v2.1), for both VN and standard reconstructions. Accuracy of PI-RADS ≥3 for clinically significant cancer was computed. Projected scan time of the retrospectively under-sampled biparametric exam was also computed. One-sided Wilcoxon signed-rank test was used for comparison of image quality. Sensitivity, specificity, positive predictive value, and negative predictive value were calculated for lesion detection and grading. Generalized estimating equation with cluster effect was used to compare differences between standard and VN bp-MRI. A P-value of <0.05 was considered statistically significant. Three of four readers rated no significant difference for overall quality between the standard and VN axial T2WI (Reader 1: 4.00 ± 0.56 (Standard), 3.90 ± 0.64 (VN) P=0.33; Reader 2: 4.35 ± 0.74 (Standard), 3.80 ± 0.89 (VN) P=0.003; Reader 3: 4.60 ± 0.50 (Standard), 4.55 ± 0.60 (VN) P=0.39; Reader 4: 3.65 ± 0.99 (Standard), 3.60 ± 1.00 (VN) P=0.38). All four readers rated no significant difference for overall quality between standard and VN DWI B1000 seconds/mm2 (Reader 1: 2.25 ± 0.62 (Standard), 2.45 ± 0.75 (VN) P=0.96; Reader 2: 3.60 ± 0.92 (Standard), 3.55 ± 0.82 (VN) P=0.40; Reader 3: 3.85 ± 0.72 (Standard), 3.55 ± 0.89 (VN) P=0.07; Reader 4: 4.70 ± 0.76 (Standard); 4.60 ± 0.73 (VN) P=0.17) and three of four readers rated no significant difference for overall quality between standard and VN DWI B50 seconds/mm2 (Reader 1: 3.20 ± 0.70 (Standard), 3.40 ± 0.75 (VN) P=0.98; Reader 2: 2.85 ± 0.81 (Standard), 3.00 ± 0.79 (VN) P=0.93; Reader 3: 4.45 ± 0.72 (Standard), 4.05 ± 0.69 (VN) P=0.02; Reader 4: 4.50 ± 0.69 (Standard), 4.45 ± 0.76 (VN) P=0.50). In the lesion evaluation study, there was no significant difference in the number of PI-RADS ≥3 lesions identified on standard vs. VN bp-MRI (P=0.92, 0.59, 0.87) with similar sensitivity and specificity for clinically significant cancer. The average scan time of the standard clinical biparametric exam was 11.8minutes, and this was projected to be 3.2minutes for the accelerated exam. Diagnostic accelerated biparametric prostate MRI exams can be performed using deep learning methods in <4 minutes, potentially enabling rapid screening prostate MRI. 3 TECHNICAL EFFICACY: Stage 5.

Outcome of 5-year follow-up in men with negative findings on initial biparametric MRI

BackgroundWe assessed the 5-year risk of being diagnosed with significant prostate cancer following a low-suspicion biparametric magnetic resonance imaging result. MethodsThe study population was derived from a prospective database used to assess the diagnostic accuracy of biparametric magnetic resonance imaging for significant prostate cancer detection in 1020 biopsy-naïve men. Significant prostate cancer was defined as any core with Gleason grade group ≥3 or a maximum cancerous core length greater than 50% of Gleason grade group 2. A secondary definition of significant prostate cancer was also included: any core with prostate cancer Gleason grade group ≥2. Of the 1020 men, 305 had a low-suspicion biparametric magnetic resonance imaging result (Prostate Imaging Reporting and Data System score of 1 or 2) but four men were excluded from follow-up. Thus, the final study population consisted of 301 men, who were clinically followed-up from inclusion (November 2015 to June 2017) until 1 June 2021. FindingsOverall, 1·7% (5/301) of the study population had significant prostate cancer diagnosed within 5 years (median 1480 days, Interquartile Range (1587–1382)) of their low-suspicion result and corresponding set of biopsies. When the secondary definition of significant prostate cancer was applied, this increased to 5% (15/301) of the study population. InterpretationThe 5-year risk of being diagnosed with significant prostate cancer after a prebiopsy low-suspicion prebiopsy biparametric magnetic resonance imaging result was 1·7%.

How to read biparametric MRI in men with a clinical suspicious of prostate cancer: Pictorial review for beginners with public access to imaging, clinical and histopathological database.

Prostate Magnetic Resonance Imaging (MRI) is increasingly being used in men with a clinical suspicion of prostate cancer (PCa). Performing prostate MRI without the use of an intravenous contrast (IV) agent in men with a clinical suspicion of PCa can lead to reduced MRI scan time. Enabling a large array of different medical providers (from mid-level to specialized radiologists) to evaluate and potentially report prostate MRI in men with a clinical suspicion of PCa with a high accuracy could be one way to enable wide adoption of prostate MRI in men with a clinical suspicion of PCa. The aim of this pictorial review is to provide an insight into acquisition, quality control and reporting of prostate MRI performed without IV contrast agent in men with a clinical suspicion of PCa, aimed specifically at radiologists starting reporting prostate MRI, urologists, urology/radiology residents and mid-level medical providers without experience in reporting prostate MRI. Free public access (http://petiv.utu.fi/improd/and http://petiv.utu.fi/multiimprod/) to complete datasets of 161 and 338 men is provided. The imaging datasets are accompanied by clinical, laboratory and histopathological findings. Several topics are simplified in order to provide a solid base for the development of skills needed for an unsupervised review and potential reporting of prostate MRI in men with a clinical suspicion of PCa. The current review represents the first step towards enabling a large array of different medical providers to review and report accurately prostate MRI performed without IV contrast agent in men with a clinical suspicion of PCa.

Single-center versus multi-center biparametric MRI radiomics approach for clinically significant peripheral zone prostate cancer

ObjectivesTo investigate a previously developed radiomics-based biparametric magnetic resonance imaging (bpMRI) approach for discrimination of clinically significant peripheral zone prostate cancer (PZ csPCa) using multi-center, multi-vendor (McMv) and single-center, single-vendor (ScSv) datasets.MethodsThis study’s starting point was a previously developed ScSv algorithm for PZ csPCa whose performance was demonstrated in a single-center dataset. A McMv dataset was collected, and 262 PZ PCa lesions (9 centers, 2 vendors) were selected to identically develop a multi-center algorithm. The single-center algorithm was then applied to the multi-center dataset (single–multi-validation), and the McMv algorithm was applied to both the multi-center dataset (multi–multi-validation) and the previously used single-center dataset (multi–single-validation). The areas under the curve (AUCs) of the validations were compared using bootstrapping.ResultsPreviously the single–single validation achieved an AUC of 0.82 (95% CI 0.71–0.92), a significant performance reduction of 27.2% compared to the single–multi-validation AUC of 0.59 (95% CI 0.51–0.68). The new multi-center model achieved a multi–multi-validation AUC of 0.75 (95% CI 0.64–0.84). Compared to the multi–single-validation AUC of 0.66 (95% CI 0.56–0.75), the performance did not decrease significantly (p value: 0.114). Bootstrapped comparison showed similar single-center performances and a significantly different multi-center performance (p values: 0.03, 0.012).ConclusionsA single-center trained radiomics-based bpMRI model does not generalize to multi-center data. Multi-center trained radiomics-based bpMRI models do generalize, have equal single-center performance and perform better on multi-center data.

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.