A transparent, lightweight and sustainable Green Learning AI model for prostate cancer detection on MRI.

The aim of this study is to evaluate the impact of radiologist and urologist variability on detection of prostate cancer (PCa) and clinically significant prostate cancer (csPCa) with magnetic resonance imaging (MRI)-transrectal ultrasound (TRUS) fusion prostate biopsies. The Prospective Loyola University MRI (PLUM) Prostate Biopsy Cohort (January 2015 to December 2020) was used to identify men receiving their first MRI and MRI/TRUS fusion biopsy for suspected PCa. Clinical, MRI and biopsy data were stratified by radiologist and urologist to evaluate variation in Prostate Imaging-Reporting and Data System (PI-RADS) grading, lesion number and cancer detection. Multivariable logistic regression (MVR) models and area under the curve (AUC) comparisons assessed the relative impact of individual radiologists and urologists. A total of 865 patients (469 biopsy-naïve) were included across 5 urologists and 10 radiologists. Radiologists varied with grading 15.4% to 44.8% of patients with MRI lesions as PI-RADS 3. PCa detection varied significantly by radiologist, from 34.5% to 66.7% (p= 0.003) for PCa and 17.2% to 50% (p= 0.001) for csPCa. Urologists' PCa diagnosis rates varied between 29.2% and 55.8% (p= 0.013) and between 24.6% and 39.8% (p= 0.36) for csPCa. After adjustment for case-mix on MVR, a fourfold to fivefold difference in PCa detection was observed between the highest-performing and lowest-performing radiologist (OR 0.22, 95%CI 0.10-0.47, p< 0.001). MVR demonstrated improved AUC for any PCa and csPCa detection when controlling for radiologist variation (p= 0.017 and p= 0.038), but controlling for urologist was not significant (p= 0.22 and p= 0.086). Any PCa detection (OR 1.64, 95%CI 1.06-2.55, p= 0.03) and csPCa detection (OR 1.57, 95%CI 1.00-2.48, p= 0.05) improved over time (2018-2020 vs. 2015-2017). Variability among radiologists in PI-RADS grading is a key area for quality improvement significantly impacting the detection of PCa and csPCa. Variability for performance of MRI-TRUS fusion prostate biopsies exists by urologist but with less impact on overall detection of csPCa.

Simple SummaryThe selection of proper candidates for prostate biopsy after magnetic resonance imaging (MRI) has usually been studied in the overall population with suspected prostate cancer (PCa). However, the performance of these tools can change regarding the Prostate Imaging-Reporting and Data System (PI-RADS) categories. We compared three different tools: PSA density, MRI-ERSPC risk calculator and Proclarix in 567 men with suspected PCa (PSA > 3 ng/mL and/or abnormal rectal examination) in one academic institution. All patients underwent multiple transrectal ultrasound guided biopsies after a multiparametric MRI was performed. We concluded that in the overall population, MRI-ERSPC RC outperformed PSA density and Proclarix, whereas in patients with lesions PI-RADS < 3 Proclarix was better than the other tools. However, no tool guaranteed 100% detection of clinically significant PCa in PI-RADS 4 and 5.Tools to properly select candidates for prostate biopsy after magnetic resonance imaging (MRI) have usually been analyzed in overall populations with suspected prostate cancer (PCa). However, the performance of these tools can change regarding the Prostate Imaging-Reporting and Data System (PI-RADS) categories due to the different incidence of clinically significant PCa (csPCa). The objective of the study was to analyze PSA density (PSAD), MRI-ERSPC risk calculator (RC), and Proclarix to properly select candidates for prostate biopsy regarding PI-RADS categories. We performed a head-to-head analysis of 567 men with suspected PCa, PSA > 3 ng/mL and/or abnormal rectal examination, in whom two to four core transrectal ultrasound (TRUS) guided biopsies to PI-RADS ≥ three lesions and/or 12-core TRUS systematic biopsies were performed after 3-tesla mpMRI between January 2018 and March 2020 in one academic institution. The overall detection of csPCa was 40.9% (6% in PI-RADS < 3, 14.8% in PI-RADS 3, 55.3% in PI-RADS 4, and 88.9% in PI-RADS 5). MRI-ERSPC model exhibited a net benefit over PSAD and Proclarix in the overall population. Proclarix outperformed PSAD and MRI-ERSPC RC in PI-RADS ≤ 3. PSAD outperformed MRI-ESRPC RC and Proclarix in PI-RADS > 3, although none of them exhibited 100% sensitivity for csPCa in this setting. Therefore, tools to properly select candidates for prostate biopsy after MRI must be analyzed regarding the PI-RADS categories. While MRI-ERSPC RC outperformed PSAD and Proclarix in the overall population, Proclarix outperformed in PI-RADS ≤ 3, and no tool guaranteed 100% detection of csPCa in PI-RADS 4 and 5.

BackgroundMultiparametric magnetic resonance imaging (mpMRI) improves detection of clinically significant prostate cancer (csPCa), but the subjective Prostate Imaging Reporting and Data System (PI-RADS) system and quantitative apparent diffusion coefficient (ADC) are inconsistent. Restriction spectrum imaging (RSI) is an advanced diffusion-weighted MRI technique that yields a quantitative imaging biomarker for csPCa called the RSI restriction score (RSIrs). ObjectiveTo evaluate RSIrs for automated patient-level detection of csPCa. Design, setting, and participantsWe retrospectively studied all patients (n = 151) who underwent 3 T mpMRI and RSI (a 2-min sequence on a clinical scanner) for suspected prostate cancer at University of California San Diego during 2017–2019 and had prostate biopsy within 180 d of MRI. InterventionWe calculated the maximum RSIrs and minimum ADC within the prostate, and obtained PI-RADS v2.1 from medical records. Outcome measurements and statistical analysisWe compared the performance of RSIrs, ADC, and PI-RADS for the detection of csPCa (grade group ≥2) on the best available histopathology (biopsy or prostatectomy) using the area under the curve (AUC) with two-tailed α = 0.05. We also explored whether the combination of PI-RADS and RSIrs might be superior to PI-RADS alone and performed subset analyses within the peripheral and transition zones. Results and limitationsAUC values for ADC, RSIrs, and PI-RADS were 0.48 (95% confidence interval: 0.39, 0.58), 0.78 (0.70, 0.85), and 0.77 (0.70, 0.84), respectively. RSIrs and PI-RADS were each superior to ADC for patient-level detection of csPCa (p < 0.0001). RSIrs alone was comparable with PI-RADS (p = 0.8). The combination of PI-RADS and RSIrs had an AUC of 0.85 (0.78, 0.91) and was superior to either PI-RADS or RSIrs alone (p < 0.05). Similar patterns were seen in the peripheral and transition zones. ConclusionsRSIrs is a promising quantitative marker for patient-level csPCa detection, warranting a prospective study. Patient summaryWe evaluated a rapid, advanced prostate magnetic resonance imaging technique called restriction spectrum imaging to see whether it could give an automated score that predicted the presence of clinically significant prostate cancer. The automated score worked about as well as expert radiologists’ interpretation. The combination of the radiologists’ scores and automated score might be better than either alone.

To compare the diagnostic performance of transperineal targeted biopsy (TB) or systematic biopsy (SB) alone based on combined TB+SB and radical prostatectomy (RP) specimen for detecting prostate cancer (PCa) according to the prostate imaging reporting and data system (PI-RADS) score. This study included 1077 men who underwent transperineal bi-parametric (bp) magnetic resonance imaging (MRI)-ultrasound (US) fusion TB+SB (bpMRI-US FTSB) between April 2019 and March 2022. To compare the performance of each modality (TB, SB, and combined TB+SB) with the RP specimen (as the standard) for detecting PCa and clinically significant PCa (csPCa), receiver operating characteristic (ROC) curves were plotted. PCa was detected in 581 of 1077 men (53.9%) using bpMRI-US FTSB. CsPCa was detected in 383 of 1077 men (35.6%), 17 of 285 (6.0%) with PI-RADS 0 to 2, 35 of 277 (12.6%) with PI-RADS 3, 134 of 274 (48.9%) with PI-RADS 4, and 197 of 241 (81.7%) with PI-RADS 5, respectively. The additional diagnostic value of TB vs. SB compared to combined TB+SB for diagnosing csPCa were 4.3% vs. 3.2% (p=0.844), 20.4% vs 5.1% (p<0.001), and 20.3% vs. 0.7% (p<0.001) with PI-RADS 3, 4, and 5, respectively. TB alone showed no significant difference in diagnostic performance for csPCa with combined TB+SB based on RP specimens in patients with PI-RADS 5 (p=0.732). A need for addition of SB to TB in patients with PI-RADS 3 and 4 lesions, however, TB alone may be performed without affecting the management of patients with PI-RADS 5.

PD36-11 A NOVEL LIGHTWEIGHT MACHINE LEARNING MODEL FOR AUTOMATED RECLASSIFICATION OF THE INDEX LESION ON BIPARAMETRIC PROSTATE MRI

Background Gallium 68 (68Ga) prostate-specific membrane antigen (PSMA) PET/MRI may improve detection of clinically significant prostate cancer (CSPC). Purpose To compare the sensitivity and specificity of 68Ga-PSMA PET/MRI with multiparametric MRI for detecting CSPC. Materials and Methods Men with prostate specific antigen levels of 2.5-20 ng/mL prospectively underwent 68Ga-PSMA PET/MRI, including multiparametric MRI sequences, between June 2019 and March 2020. Imaging was evaluated independently by two radiologists by using the Prostate Imaging Reporting and Data System (PI-RADS) version 2.1. Sensitivity and specificity for CSPC (International Society of Urological Pathology grade group ≥ 2) were compared for 68Ga-PSMA PET/MRI and multiparametric MRI by using the McNemar test. Decision curve analysis compared the net benefit of each imaging strategy. Results Ninety-nine men (median age, 67 years; interquartile range, 62-71 years) were included; 79% (78 of 99) underwent biopsy. CSPC was detected in 32% (25 of 78). For CSPC, specificity was higher for 68Ga-PSMA PET/MRI than multiparametric MRI (76% [95% CI: 62, 86] vs 49% [95% CI: 35, 63], respectively; P < .001). Sensitivity was similar (88% [95% CI: 69, 98] vs 92% [95% CI: 74, 99], respectively; P > .99). For PI-RADS 3 lesions, specificity was also higher for 68Ga-PSMA PET/MRI than for multiparametric MRI: 86% (95% CI: 73, 95) versus 59% (95% CI: 43, 74), respectively (P = .002). Decision curve analysis showed that biopsies targeted to PSMA uptake increased the net benefit of multiparametric MRI only among PI-RADS 3 lesions. The net benefit of targeted biopsy for a PI-RADS 3 lesion with PSMA uptake was higher across all threshold probabilities over 8%. The net benefit of targeted biopsy was similar for PI-RADS 4 and 5 lesions, regardless of PSMA uptake. Conclusions Gallium 68 prostate-specific membrane antigen PET/MRI improved specificity for clinically significant prostate cancer compared with multiparametric MRI, particularly in Prostate Imaging Reporting and Data System grade 3 lesions. © RSNA, 2021 Online supplemental material is available for this article. See also the editorial by Williams and Estes in this issue.

Our aim was to evaluate whether combining the maximum restriction score derived from restriction spectrum imaging (RSIrsmax) with deep learning (DL) models can enhance patient-level detection of clinically significant prostate cancer (csPCa) in comparison to Prostate Imaging-Reporting and Data System (PI-RADS) or RSIrsmax alone. A total of 1892 patients from seven institutions who underwent imaging between January 2016 and March 2024 were included on the basis of magnetic resonance imaging (MRI) findings and biopsy-confirmed prostate cancer diagnosis. Two DL architectures, 3D-DenseNet and 3D-DenseNet+RSI (incorporating RSIrsmax), were developed and trained using biparametric MRI and RSI data using a leave-one-center-out validation approach. RSI is a rapid sequence that requires only 2-3min to acquire. Model performance was evaluated in a biopsy-confirmed subset of 876 patients, with subgroup analyses stratified by site and scanner vendor. Receiver operating characteristic (ROC) and precision recall curves and forest plots (I2 for heterogeneity) were generated, and the area under the ROC curve (AUC) and sensitivity, were compared, as well as specificity at fixed sensitivity of 0.90. Calibration, decision-curve, and reclassification analyses (net reclassification improvement and integrated discrimination improvement) were performed. Codes used in developing the DL model are available on GitHub (https://github.com/ESONG1999/Deep-learning-AI-and-RSI-for-patient-level-detection-of-csPCa-on-MRI). Neither RSIrsmax nor the best DL model combined with RSIrsmax significantly outperformed PI-RADS interpretation by expert radiologists. However, when combined with PI-RADS, both approaches significantly improved patient-level csPCa detection, with AUCs of 0.78 (95% confidence interval [CI] 0.75-0.81; p<0.001) for RSIrsmax+PI-RADS and 0.80 (95% CI 0.77-0.82; p<0.001) for the best DL model+PI-RADS, versus 0.75 (95% CI 0.71-0.78) for PI-RADS alone. The absolute gain in specificity at fixed sensitivity of 0.90 was 0.04 (95% CI 0.04-0.04) for RSIrsmax+PI-RADS, and 0.03 (95% CI 0.03-0.04) for DL+PI-RADS. Both RSIrsmax and the best DL model demonstrated comparable performance to PI-RADS alone. Addition of either model to PI-RADS significantly enhanced patient-level detection of csPCa in comparison to PI-RADS alone. Limitations include biopsy as an imperfect reference, the exclusion of hip implant cases, lack of external calibration, limited RSI availability, and missing case-level information for individual radiologists and their expertise. We looked at whether adding advanced scan data (ASD) and artificial intelligence (AI) models to radiologist assessments of MRI (magnetic resonance imaging) scans was better in detecting aggressive prostate cancer (PCa). We found that adding AI models or ASD to standard scan scores improved cancer detection in comparison to standard scores alone. The results suggest that combining radiologist expertise with AI and ASD may help in earlier identification of more patients with csPCa.

Purpose To determine the diagnostic accuracy for clinically significant prostate cancer achieved with abbreviated biparametric prostate magnetic resonance (MR) imaging in comparison with full multiparametric contrast material-enhanced prostate MR imaging in men with elevated prostate-specific antigen (PSA) and negative transrectal ultrasonography (US)-guided biopsy findings; to determine the significant cancer detection rate of biparametric versus full multiparametric contrast-enhanced MR imaging and between-reader agreement for interpretation of biparametric MR imaging. Materials and Methods In this institutional review board-approved retrospective review of prospectively acquired data, men with PSA greater than or equal to 3 ng/mL after negative transrectal US-guided biopsy findings underwent state-of-the-art, full multiparametric contrast-enhanced MR imaging at 3.0-T including high-spatial-resolution structural imaging in several planes, diffusion-weighted imaging at 0, 800, 1000, and 1400 mm2/sec, and dynamic contrast-enhanced MR imaging, obtained without endorectal coil within 34 minutes 19 seconds. One of four radiologists with different levels of expertise (1-9 years) first reviewed only a fraction of the full multiparametric contrast-enhanced MR images, consisting of single-plane (axial) structural imaging (T2-weighted turbo spin-echo and diffusion-weighted imaging), acquired within 8 minutes 45 seconds (referred to as biparametric MR imaging), and established a diagnosis according to the Prostate Imaging Reporting and Data System (PI-RADS) version 2; only thereafter, the remaining full multiparametric contrast-enhanced MR images were read. Men with PI-RADS categories 3-5 underwent MR-guided targeted biopsy. Men with PI-RADS categories 1-2 remained in urologic follow-up for at least 2 years, with rebiopsy (transrectal US-guided or transperineal saturation) where appropriate. McNemar test was used to compare diagnostic accuracies. To investigate between-reader agreement, biparametric MR images of 100 patients were read independently by all three radiologists. Results A total of 542 men, aged 64.8 years ± 8.2 (median PSA, 7 ng/mL), were included. Biparametric MR imaging helped detect clinically significant prostate cancer in 138 men. Full multiparametric contrast-enhanced MR imaging allowed detection of one additional clinically significant prostate cancer (a stage pT2a, intermediate-risk cancer with a Gleason score of 3+4) and caused 11 additional false-positive diagnoses. Diagnostic accuracy for detection of clinically significant cancer of biparametric MR imaging (89.1%, 483 of 542) was similar to that of full multiparametric contrast-enhanced MR imaging (87.2%, 473 of 542). Between-reader agreement of biparametric MR imaging interpretation was substantial (κ = 0.81). Conclusion Biparametric MR imaging allows detection of clinically significant prostate cancer missed by transrectal US-guided biopsy. Biparametric prostate MR imaging takes less than 9 minutes examination time, works without contrast agent injection, and offers a diagnostic accuracy and cancer detection rate that are equivalent to those of conventional full multiparametric contrast-enhanced MR imaging protocols. © RSNA, 2017.

To evaluate magnetic resonance imaging (MRI)-targeted biopsy (MRI-TB) performance in detecting clinically significant prostate cancer (csPCa) with a Prostate Imaging Reporting and Data System (PI-RADS) score of ≥3 peripheral zone (PZ) lesions using multiparametric MRI (mpMRI)-histopathology correlation. This retrospective study included 141 patients with 187 PZ lesions who underwent mpMRI followed by both MRI-TB and transrectal ultrasound-guided systematic biopsy (SB) between December 2021 and December 2024. All mpMRI scans were evaluated by a board-certified experienced radiologist in accordance with the PI-RADS version 2.1 criteria. The csPCa detection rates of SB, MRI-TB, and combined biopsy (CB) were compared. Statistical analyses included McNemar's test, Fisher's exact test, and the Mann-Whitney U test. A P value <0.05 was considered statistically significant. Among the 141 patients (187 PI-RADS ≥3 PZ lesions), patients with csPCa exhibited significantly higher prostate-specific antigen (PSA) levels (15.3 vs. 8.2 ng/mL; P = 0.02), lower prostate volume (52.4 vs. 78.6 mL; P < 0.001), and three-fold higher PSA density (PSAD) (0.30 vs. 0.10 ng/mL/mL; P < 0.001) than non-csPCa cases. Notably, PSAD > 0.15 ng/mL/mL occurred in 78% of patients with csPCa vs. 18% in non-csPCa cases (P < 0.001). Moreover, MRI-TB detected significantly more csPCa than SB (17.7% vs. 10.7% of lesions; P < 0.001), with maximal advantage in PI-RADS 4 lesions (20.7% vs. 10.9%; P = 0.004). By contrast, CB did not significantly increase csPCa detection over MRI-TB alone (19.8% vs. 17.7%; P = 0.125). Chronic prostatitis (CP) (34.0% of benign cases) confounded PI-RADS specificity. For csPCa detection in PI-RADS ≥3 PZ lesions, particularly PI-RADS 4, MRI-TB outperforms SB. For PI-RADS 5, SB and MRI-TB showed equivalent efficacy. However, MRI-TB alone suffices for PI-RADS ≥4 lesions or PSAD >0.15 ng/mL/mL, whereas CB remains preferable for PI-RADS 3. The high CP prevalence underscores the need for adjunctive biomarkers to improve specificity. MRI-TB optimizes csPCa detection for PI-RADS ≥4 PZ lesions, reducing reliance on SBs. A PSAD threshold >0.15 ng/mL/mL effectively stratifies biopsy necessity, and high CP prevalence (34% of benign cases) underscores the need for adjunct biomarkers to improve specificity in PI-RADS 3-4 lesions.

MP55-18 A NOVEL MACHINE LEARNING FRAMEWORK TO AUTOMATED CHARACTERIZE PROSTATE IMAGING REPORTING AND DATA SYSTEM (PIRADS) ON MRI

Objective: Combining Prostate Imaging-Reporting and Data System (PI-RADS) with prostate-specific antigen density (PSAD) may improve the detection of clinically significant prostate cancer (csPCa) while reducing unnecessary biopsies. This study aimed to evaluate csPCa detection rates using PI-RADS and PSAD, identify optimal PSAD cutoffs, and assess biopsy strategies to optimize csPCa detection and reduce unnecessary procedures within a South Korean cohort. Methods: This multicenter retrospective study included 3117 biopsy-naïve patients from 2 tertiary hospitals in South Korea (2020-2025) who underwent magnetic resonance imaging–based transperineal prostate biopsy. Patients were stratified into PI-RADS groups (1-2, 3, 4-5) and PSAD categories (&lt;0.10, 0.10-0.15, 0.15-0.20, and ≥0.20). Receiver-operating characteristic (ROC) curve analyses validated PSAD cut-offs, and biopsy strategies were compared for csPCa detection and biopsy avoidance. Results: The overall csPCa detection rate was 47.1%. PI-RADS 4-5 patients had high detection rates across all PSAD levels (20.1%-76.5%), while PI-RADS 1-2 and 3 patients with PSAD ≥ 0.15 showed elevated rates (15.2%-16.9% and 25.0%-35.7%, respectively). ROC curve analyses identified optimal PSAD cut-offs of 0.155 (area under the ROC curve (AUC), 0.708) for PI-RADS 1-2 and 0.145 (AUC, 0.749) for PI-RADS 3. The proposed strategy (PI-RADS ≥ 4 or PI-RADS 1-2 or 3 with PSAD ≥ 0.15) outperformed other strategies, avoiding 448 (14.4%) biopsies, missing 28 (1.9%) csPCa cases, and achieving a negative predictive value of 93.8%. Conclusion: Integrating PI-RADS with PSAD enhances risk stratification for csPCa, maintaining high diagnostic accuracy while reducing unnecessary procedures. Cite this article as: Lee SJ, Shin DH, Kim HY. Multicenter study on integrating prostate magnetic resonance imaging with prostate-specific antigen density for risk-adapted biopsy strategy in a South Korean cohort. Urol Res Pract. 2026, 52, 0014, doi: 10.5152/tud.2026.26014.

The potential of deep learning to support radiologist prostate magnetic resonance imaging (MRI) interpretation has been demonstrated. The aim of this study was to evaluate the effects of increased and diversified training data (TD) on deep learning performance for detection and segmentation of clinically significant prostate cancer-suspicious lesions. In this retrospective study, biparametric (T2-weighted and diffusion-weighted) prostate MRI acquired with multiple 1.5-T and 3.0-T MRI scanners in consecutive men was used for training and testing of prostate segmentation and lesion detection networks. Ground truth was the combination of targeted and extended systematic MRI-transrectal ultrasound fusion biopsies, with significant prostate cancer defined as International Society of Urological Pathology grade group greater than or equal to 2. U-Nets were internally validated on full, reduced, and PROSTATEx-enhanced training sets and subsequently externally validated on the institutional test set and the PROSTATEx test set. U-Net segmentation was calibrated to clinically desired levels in cross-validation, and test performance was subsequently compared using sensitivities, specificities, predictive values, and Dice coefficient. One thousand four hundred eighty-eight institutional examinations (median age, 64 years; interquartile range, 58-70 years) were temporally split into training (2014-2017, 806 examinations, supplemented by 204 PROSTATEx examinations) and test (2018-2020, 682 examinations) sets. In the test set, Prostate Imaging-Reporting and Data System (PI-RADS) cutoffs greater than or equal to 3 and greater than or equal to 4 on a per-patient basis had sensitivity of 97% (241/249) and 90% (223/249) at specificity of 19% (82/433) and 56% (242/433), respectively. The full U-Net had corresponding sensitivity of 97% (241/249) and 88% (219/249) with specificity of 20% (86/433) and 59% (254/433), not statistically different from PI-RADS (P > 0.3 for all comparisons). U-Net trained using a reduced set of 171 consecutive examinations achieved inferior performance (P < 0.001). PROSTATEx training enhancement did not improve performance. Dice coefficients were 0.90 for prostate and 0.42/0.53 for MRI lesion segmentation at PI-RADS category 3/4 equivalents. In a large institutional test set, U-Net confirms similar performance to clinical PI-RADS assessment and benefits from more TD, with neither institutional nor PROSTATEx performance improved by adding multiscanner or bi-institutional TD.

Effects of the lesion size on clinically significant prostate cancer detection rates in PI-RADS category 3-5 lesions

The objective of this study was to investigate the correlation between Prostate Imaging Reporting and Data System (PIRADS) scores obtained from multiparametric magnetic resonance imaging (mpMRI) and histopathological outcomes, including Gleason grades and adverse prognostic factors, in patients undergoing prostate biopsy for suspected prostate cancer.This retrospective study included 195 patients who underwent mpMRI and transrectal ultrasound-guided biopsy. PIRADS scores were assigned based on the PIRADS v2.1 guidelines, and biopsy specimens were evaluated for clinically significant prostate cancer (CSPCa), defined as Gleason score ≥ 7, as well as for adverse features such as Extracapsular Extension (ECE), Lymphovascular invasion (LVI), and Perineural invasion (PNI). Diagnostic accuracy of PIRADS scores was assessed using sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV).Among 195 patients who underwent biopsy, PIRADS 3 lesions had a PPV of 20.00% for CSPCa, with 42.86% negative biopsy results. PIRADS 4 and 5 lesions showed higher PPVs for CSPCa at 71.43% and 86.00%, respectively. The majority of patients with PIRADS 3 lesions had Gleason 6 cancers, while PIRADS 4 and 5 lesions were significantly associated with higher Gleason scores (≥ 7). PIRADS 5 lesions had the highest rates of adverse features, including ECE (38%), LVI (14%), and PNI (24%), compared to PIRADS 4 and 3 lesions. Diagnostic accuracy was highest for PIRADS 4-5 lesions, with a sensitivity of 78%, specificity of 75%, and area under the curve (AUC) of 0.82, while PIRADS 3 lesions had a lower sensitivity (24%) and AUC (0.65).Higher PIRADS scores are significantly associated with an increased Likelihood of CSPCa, more aggressive Gleason grades, and adverse pathological features. PIRADS 4-5 lesions demonstrate high diagnostic accuracy for CSPCa, supporting their use in guiding biopsy decisions and treatment planning. PIRADS 3 lesions, though less predictive, still warrant individualized management, with some cases presenting aggressive disease. These findings reinforce the clinical utility of PIRADS scoring in prostate cancer risk stratification.

Diagnostic Accuracy of Single-plane Biparametric and Multiparametric Magnetic Resonance Imaging in Prostate Cancer: A Randomized Noninferiority Trial in Biopsy-naïve Men