The contemporary concept of significant versus insignificant prostate cancer. Eur Urol. 2011;60:291-303. [PMID: 21601982 DOI: 10.1016/j.eururo.2011.05.006]

Comparison of Multiparametric MRI and the Combination of PSMA Plus MRI for the Intraprostatic Diagnosis of Prostate Cancer: A Systematic Review and Meta-Analysis

PURPOSE

The aim of this study was to perform a head-to-head comparison of multiparametric MRI (mpMRI) and the combination of prostate-specific membrane antigen (PSMA) PET plus MRI (PSMA + MRI) for detecting intraprostatic clinically significant prostate cancer (csPCa).

PATIENTS AND METHODS

Relevant databases were searched through November 2023. Only studies directly comparing mpMRI and PSMA + MRI (PET/MRI or PET/CT + mpMRI) were included. A meta-analysis with a random-effects model was used to estimate pooled sensitivity, specificity, and area under the curve for each approach.

RESULTS

A total of 19 studies were included. On a patient-level analysis, PSMA + MRI had higher sensitivity (9 studies) than mpMRI for csPCa detection (96% [95% confidence interval (CI): 92%, 98%] vs 89% [95% CI: 81%, 94%]; P = 0.04). The patient-level specificity (4 studies) of PSMA + MRI was 55% (95% CI: 31%-76%) compared with 50% (95% CI: 44%-57%) of mpMRI ( P = 0.67). Region-level sensitivity (10 studies) was 85% (95% CI: 74%-92%) for PSMA + MRI and 71% (95% CI: 58%-82%) for mpMRI ( P = 0.09), whereas specificity (4 studies) was 87% (95% CI: 76%-94%) and 90% (95% CI: 82%-95%), respectively ( P = 0.59). Lesion-level sensitivity and specificity were similar between modalities with pooled data from less than 4 studies.

CONCLUSIONS

PSMA + MRI had superior pooled sensitivity and similar specificity for the detection of csPCa compared with mpMRI in this meta-analysis of head-to-head studies.

The predictive impact of hematological inflammatory markers in detecting prostate cancer in patients with PI-RADS 3 lesions on multiparametric magnetic resonance imaging

BACKGROUND

The diagnostic accuracy of suspicious lesions that are classified as PI-RADS 3 in multiparametric prostate magnetic-resonance imaging (mpMRI) is controversial. This study aims to assess the predictive capacity of hematological inflammatory markers such as neutrophil-lymphocyte ratio (NLR), pan-immune-inflammation value (PIV), and systemic immune-response index (SIRI) in detecting prostate cancer in PI-RADS 3 lesions.

METHODS

276 patients who underwent mpMRI and subsequent prostate biopsy after PI-RADS 3 lesion detection were included in the study. According to the biopsy results, the patients were distributed to two groups as prostate cancer (PCa) and no cancer (non-PCa). Data concerning age, PSA, prostate volume, PSA density, PI-RADS 3 lesion size, prostate biopsy results, monocyte counts (109/L), lymphocyte counts (109/L), platelet counts (109/L), neutrophils count (109/L) were recorded from the complete blood count. From these data; PIV value is obtained by monocyte × neutrophil × platelet/lymphocyte, NLR by neutrophil/lymphocyte, and SIRI by monocyte number × NLR.

RESULTS

Significant variations in neutrophil, lymphocyte, and monocyte levels between PCa and non-PCa patient groups were detected (p = 0.009, p = 0.001, p = 0.005 respectively, p < 0.05). NLR, PIV, and SIRI exhibited significant differences, with higher values in PCa patients (p = 0.004, p = 0.001, p < 0.001 respectively, p < 0.05). The area under curve of SIRI was 0.729, with a cut-off value of 1.20 and with a sensitivity 57.70%, and a specificity of 68.70%.

CONCLUSION

SIRI outperformed NLR and PIV in detecting PCa in PI-RADS 3 lesions, showcasing its potential as a valuable biomarker. Implementation of this parameter to possible future nomograms has the potential to individualize and risk-stratify the patients in prostate biopsy decision.

Sialic acid blockade inhibits the metastatic spread of prostate cancer to bone

BACKGROUND

Bone metastasis is a common consequence of advanced prostate cancer. Bisphosphonates can be used to manage symptoms, but there are currently no curative treatments available. Altered tumour cell glycosylation is a hallmark of cancer and is an important driver of a malignant phenotype. In prostate cancer, the sialyltransferase ST6GAL1 is upregulated, and studies show ST6GAL1-mediated aberrant sialylation of N-glycans promotes prostate tumour growth and disease progression.

METHODS

Here, we monitor ST6GAL1 in tumour and serum samples from men with aggressive prostate cancer and using in vitro and in vivo models we investigate the role of ST6GAL1 in prostate cancer bone metastasis.

FINDINGS

ST6GAL1 is upregulated in patients with prostate cancer with tumours that have spread to the bone and can promote prostate cancer bone metastasis in vivo. The mechanisms involved are multi-faceted and involve modification of the pre-metastatic niche towards bone resorption to promote the vicious cycle, promoting the development of M2 like macrophages, and the regulation of immunosuppressive sialoglycans. Furthermore, using syngeneic mouse models, we show that inhibiting sialylation can block the spread of prostate tumours to bone.

INTERPRETATION

Our study identifies an important role for ST6GAL1 and α2-6 sialylated N-glycans in prostate cancer bone metastasis, provides proof-of-concept data to show that inhibiting sialylation can suppress the spread of prostate tumours to bone, and highlights sialic acid blockade as an exciting new strategy to develop new therapies for patients with advanced prostate cancer.

FUNDING

Prostate Cancer Research and the Mark Foundation For Cancer Research, the Medical Research Council and Prostate Cancer UK.

The association between patient and disease characteristics, and the risk of disease progression in patients with prostate cancer on active surveillance

PURPOSE

The objective of this study was to identify and assess patient and disease characteristics associated with an increased risk of disease progression in men with prostate cancer on active surveillance.

METHODS

We studied patients with low-risk (ISUP GG1) or favorable intermediate-risk (ISUP GG2) PCa. All patients had at least one repeat biopsy. Disease progression was the primary outcome of this study, based on pathological upgrading. Univariate and multivariate Cox proportional hazard analyses were used to evaluate the association between covariates and disease progression.

RESULTS

In total, 240 men were included, of whom 198 (82.5%) were diagnosed with low-risk PCa and 42 (17.5%) with favorable intermediate-risk PCa. Disease progression was observed in 42.9% (103/240) of men. Index lesion > 10 mm (HR = 2.85; 95% CI 1.74-4.68; p < 0.001), MRI (m)T-stage 2b/2c (HR = 2.52; 95% CI 1.16-5.50; p = 0.02), highest PI-RADS score of 5 (HR 3.05; 95% CI 1.48-6.28; p = 0.002) and a higher PSA level (HR 1.06; 95% CI 1.01-1.11; p = 0.014) at baseline were associated with disease progression on univariate analysis. Multivariate analysis showed no significant baseline predictors of disease progression.

CONCLUSION

In AS patients with low-risk or favorable intermediate-risk PCa, diameter of index lesion, MRI (m)T-stage, height of the PI-RADS score and the PSA level at baseline are significant predictors of disease progression to first repeat biopsy.

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

INTRODUCTION

Prostate cancer (PCa) ranks second among prevalent cancers in men, necessitating effective screening tools such as multiparametric magnetic resonance imaging (mpMRI) with the prostate imaging reporting and data system (PI-RADS) classification. This study explores the impact of lesion volume on clinically significant prostate cancer (csPCa) detection rates in PI-RADS 3-5 lesions, aiming to contribute insights into the underexplored relationship between lesion size and csPCa detection.

MATERIALS AND METHODS

A retrospective analysis was conducted on data from 754 patients undergoing mpMRI-guided transrectal ultrasound (TRUS) prostate biopsy between January 2016 and 2023. Patients with PI-RADS 3, 4, and 5 lesions were included. Lesion size and PI-RADS categories were assessed through mpMRI, followed by MR fusion biopsy.

RESULTS

Of the patients, 33.7%, 52.3%, and 14.1% had PI-RADS 3, 4, and 5 lesions, respectively. Lesion sizes correlated significantly with csPCa detection in PI-RADS 4 and 5 categories. For PI-RADS 3 lesions, no significant differences in csPCa rates were observed based on lesion size. However, in PI-RADS 4 and 5 groups, larger lesions showed higher csPCa rates.

CONCLUSION

This study suggests that subgroup categorizations based on lesion volume could predict clinically significant PCa with high accuracy, potentially reducing unnecessary biopsies and associated overtreatment. Future research should further explore the relationship between lesion size and csPCa, clarifying discussions regarding the inclusion of systematic biopsies in diagnostic protocols.

Preliminary evaluation for ultrasound-guided targeted prostate biopsy using a portable surgical robot: Ex vivo results

BACKGROUND

Robotic systems are increasingly used to enhance clinical outcomes in prostate intervention. To evaluate the clinical value of the proposed portable robot, the robot-assisted and robot-targeted punctures were validated experimentally.

METHOD

The robot registration utilising the electromagnetic tracker achieves coordinate transformation from the ultrasound (US) image to the robot. Subsequently, Transrectal ultrasound (TRUS)-guided phantom trials were conducted for robot-assisted, free-hand, and robot-targeted punctures.

RESULTS

The accuracy of robot registration was 0.95 mm, and the accuracy of robot-assisted, free-hand, and robot-targeted punctures was 2.38 ± 0.64 mm, 3.11 ± 0.72 mm, and 3.29 ± 0.83 mm sequentially.

CONCLUSION

The registration method has been successfully applied to robot-targeted puncture. Current results indicate that the accuracy of robot-targeted puncture is slightly inferior to that of manual operations. Moreover, in manual operation, robot-assisted puncture improves the accuracy of free-hand puncture. Accuracy superior to 3.5 mm demonstrates the clinical applicability of both robot-assisted and robot-targeted punctures.

Genome-wide methylation profiling of diagnostic tumor specimens identified DNA methylation markers associated with metastasis among men with untreated localized prostate cancer

BACKGROUND

We used a genome-wide discovery approach to identify methylation markers associated with metastasis in men with localized prostate cancer (PCa), as better identification of those at high risk of metastasis can inform treatment decision-making.

METHODS

We identified men with localized PCa at Kaiser Permanente California (January 1, 1997-December 31, 2006) who did not receive curative treatment and followed them for 10 years to determine metastasis status. Cases were chart review-confirmed metastasis, and controls were matched using density sampling. We extracted DNA from the cancerous areas in the archived diagnostic tissue blocks. We used Illumina's Infinium MethylationEPIC BeadChip for methylation interrogation. We used conditional logistic regression and Bonferroni's correction to identify methylation markers associated with metastasis. In a separate validation cohort (2007), we evaluated the added predictive utility of the methylation score beyond clinical risk score.

RESULTS

Among 215 cases and 404 controls, 31 CpG sites were significantly associated with metastasis status. Adding the methylation score to the clinical risk score did not meaningfully improve the c-statistic (0.80-0.81) in the validation cohort, though the score itself was statistically significant (p < 0.01). In the validation cohort, both clinical risk score alone and methylation marker score alone are well calibrated for predicted 10-year metastasis risks. Adding the methylation score to the clinical risk score only marginally improved predictive risk calibration.

CONCLUSION

Our findings do not support the use of these markers to improve clinical risk prediction. The methylation markers identified may inform novel hypothesis in the roles of these genetic regions in metastasis development.

3-D Transducer Mounted Shear Wave Absolute Vibro-Elastography: Proof of Concept

Quantitative tissue stiffness characterization using ultrasound (US) has been shown to improve prostate cancer (PCa) detection in multiple studies. Shear wave absolute vibro-elastography (SWAVE) allows quantitative and volumetric assessment of tissue stiffness using external multifrequency excitation. This article presents a proof of concept of a first-of-a-kind 3-D hand-operated endorectal SWAVE system designed to be used during systematic prostate biopsy. The system is developed with a clinical US machine, requiring only an external exciter that can be mounted directly to the transducer. Subsector acquisition of radio frequency (RF) data allows imaging of shear waves with a high effective frame rate (up to 250 Hz). The system was characterized using eight different quality assurance phantoms. Due to the invasive nature of prostate imaging, at this early stage of development, validation of in vivo human tissue was instead carried out by intercostally scanning the livers of n = 7 healthy volunteers. The results are compared with 3-D magnetic resonance elastography (MRE) and an existing 3-D SWAVE system with a matrix array transducer (M-SWAVE). High correlations were found with MRE (99% in phantoms, 94% in liver data) and with M-SWAVE (99% in phantoms, 98% in liver data).

Deep Learning Algorithm for Tumor Segmentation and Discrimination of Clinically Significant Cancer in Patients with Prostate Cancer

BACKGROUND

We investigated the feasibility of a deep learning algorithm (DLA) based on apparent diffusion coefficient (ADC) maps for the segmentation and discrimination of clinically significant cancer (CSC, Gleason score ≥ 7) from non-CSC in patients with prostate cancer (PCa).

METHODS

Data from a total of 149 consecutive patients who had undergone 3T-MRI and been pathologically diagnosed with PCa were initially collected. The labelled data (148 images for GS6, 580 images for GS7) were applied for tumor segmentation using a convolutional neural network (CNN). For classification, 93 images for GS6 and 372 images for GS7 were used. For external validation, 22 consecutive patients from five different institutions (25 images for GS6, 70 images for GS7) representing different MR machines were recruited.

RESULTS

Regarding segmentation and classification, U-Net and DenseNet were used, respectively. The tumor Dice scores for internal and external validation were 0.822 and 0.7776, respectively. As for classification, the accuracies of internal and external validation were 73 and 75%, respectively. For external validation, diagnostic predictive values for CSC (sensitivity, specificity, positive predictive value and negative predictive value) were 84, 48, 82 and 52%, respectively.

CONCLUSIONS

Tumor segmentation and discrimination of CSC from non-CSC is feasible using a DLA developed based on ADC maps (b2000) alone.

Learning-based needle tip tracking in 2D ultrasound by fusing visual tracking and motion prediction

Visual trackers are the most commonly adopted approach for needle tip tracking in ultrasound (US)-based procedures. However, they often perform unsatisfactorily in biological tissues due to the significant background noise and anatomical occlusion. This paper presents a learning-based needle tip tracking system, which consists of not only a visual tracking module, but also a motion prediction module. In the visual tracking module, two sets of masks are designed to improve the tracker's discriminability, and a template update submodule is used to keep up to date with the needle tip's current appearance. In the motion prediction module, a Transformer network-based prediction architecture estimates the target's current position according to its historical position data to tackle the problem of target's temporary disappearance. A data fusion module then integrates the results from the visual tracking and motion prediction modules to provide robust and accurate tracking results. Our proposed tracking system showed distinct improvement against other state-of-the-art trackers during the motorized needle insertion experiments in both gelatin phantom and biological tissue environments (e.g. 78% against <60% in terms of the tracking success rate in the most challenging scenario of "In-plane-static" during the tissue experiments). Its robustness was also verified in manual needle insertion experiments under varying needle velocities and directions, and occasional temporary needle tip disappearance, with its tracking success rate being >18% higher than the second best performing tracking system. The proposed tracking system, with its computational efficiency, tracking robustness, and tracking accuracy, will lead to safer targeting during existing clinical practice of US-guided needle operations and potentially be integrated in a tissue biopsy robotic system.

Detection of intraductal carcinoma in prostate cancer patients with small tumor volume

OBJECTIVES

The purpose of this study was to investigate intraductal carcinoma of the prostate (intraductal carcinoma) and significant cancer (SC) in patients with small tumor volume (<0.5 cm³ ) in prostatectomy specimens.

METHODS

Data from 639 patients undergoing radical prostatectomy between April 2006 and December 2017 at Chiba University Hospital and 2 affiliated institutions were retrospectively reviewed. Tumor volume in prostatectomy specimens was measured, and with a tumor volume of less than 0.5 cm³ , the presence of intraductal carcinoma and SC was examined. SC was defined as one that did not meet the definition of pathological insignificant cancer (organ-confined cancer, Grade Group 1, tumor volume < 0.5 cm³ ). The number of patients who met four active surveillance (AS) protocols was also examined.

RESULTS

A total of 83 patients with tumor volume < 0.5 cm³ were identified in this study population (SC: 43 patients [52%], intraductal carcinoma: 5 patients [6%]). The median follow-up was 34.6 months (range: 18-57 months). Four (5%) developed biochemical recurrence. The number of positive biopsy cores ≥ 2 was an independent predictor of SC in patients with tumor volume < 0.5 cm³ (hazard ratio: 4.39; 95% confidence interval: 1.67-11.56; p = 0.003). In tumor volume < 0.5 cm³ , tumor volume was significantly correlated with the International Society of Urological Pathology Grade Group (1 vs. 4-5, p = 0.002) and the presence of intraductal carcinoma (p = 0.004). In intraductal carcinoma-positive cases, four of five patients (80%) had the predictor of SC, which was two or more positive biopsy cores. Of the four AS protocols, the criteria for Prostate Cancer Research International: Active Surveillance were met most frequently in 46 cases (55%) of tumor volume less than 0.5 cm³ if targeted biopsy by magnetic resonance imaging was available.

CONCLUSION

The results of the present study suggest that intraductal carcinoma was present even in cases with small tumor volumes. Grade Group and intraductal carcinoma showed a positive correlation with tumor volume.

Toward mechatronic MRI-guided focal laser ablation of the prostate: Robust registration for improved needle delivery

BACKGROUND

Multiparametric MRI (mpMRI) is an effective tool for detecting and staging prostate cancer (PCa), guiding interventional therapy, and monitoring PCa treatment outcomes. MRI-guided focal laser ablation (FLA) therapy is an alternative, minimally invasive treatment method to conventional therapies, which has been demonstrated to control low-grade, localized PCa while preserving patient quality of life. The therapeutic success of FLA depends on the accurate placement of needles for adequate delivery of ablative energy to the target lesion. We previously developed an MR-compatible mechatronic system for prostate FLA needle guidance and validated its performance in open-air and clinical 3T in-bore experiments using virtual targets.

PURPOSE

To develop a robust MRI-to-mechatronic system registration method and evaluate its in-bore MR-guided needle delivery accuracy in tissue-mimicking prostate phantoms.

METHODS

The improved registration multifiducial assembly houses thirty-six aqueous gadolinium-filled spheres distributed over a 7.3 × 7.3 × 5.2 cm volume. MRI-guided needle guidance accuracy was quantified in agar-based tissue-mimicking prostate phantoms on trajectories (N = 44) to virtual targets covering the mechatronic system's range of motion. 3T gradient-echo recalled (GRE) MRI images were acquired after needle insertions to each target, and the air-filled needle tracks were segmented. Needle guidance error was measured as the shortest Euclidean distance between the target point and the segmented needle trajectory, and angular error was measured as the angle between the targeted trajectory and the segmented needle trajectory. These measurements were made using both the previously designed four-sphere registration fiducial assembly on trajectories (N = 7) and compared with the improved multifiducial assembly using a Mann-Whitney U test.

RESULTS

The median needle guidance error of the system using the improved registration fiducial assembly at a depth of 10 cm was 1.02 mm with an interquartile range (IQR) of 0.42-2.94 mm. The upper limit of the one-sided 95% prediction interval of needle guidance error was 4.13 mm. The median (IQR) angular error was 0.0097 rad (0.0057-0.015 rad) with a one-sided 95% prediction interval upper limit of 0.022 rad. The median (IQR) positioning error using the previous four-sphere registration fiducial assembly was 1.87 mm (1.77-2.14 mm). This was found to be significantly different (p = 0.0012) from the median (IQR) positioning error of 0.28 mm (0.14-0.95 mm) using the new registration fiducial assembly on the same trajectories. No significant difference was detected between the medians of the angular errors (p = 0.26).

CONCLUSION

This is the first study presenting an improved registration method and validation in tissue-mimicking phantoms of our remotely actuated MR-compatible mechatronic system for delivery of prostate FLA needles. Accounting for the effects of needle deflection, the system was demonstrated to be capable of needle delivery with an error of 4.13 mm or less in 95% of cases under ideal conditions, which is a statistically significant improvement over the previous method. The system will next be validated in a clinical setting.

Tumor Location and a Tumor Volume over 2.8 cc Predict the Prognosis for Japanese Localized Prostate Cancer

(1) Objective: Our study investigated the prognostic value of tumor volume and location in prostate cancer patients who received radical prostatectomy (RP). (2) Methods: The prognostic significance of tumor volume and location, together with other clinical factors, was studied using 557 patients who received RP. (3) Results: The receiver operating characteristic (ROC) curve identified the optimal cutoff value of tumor volume as 2.8 cc for predicting biochemical recurrence (BCR). Cox regression analysis revealed that a tumor in the posterior area (p = 0.031), peripheral zone (p = 0.0472), and tumor volume ≥ 2.8 cc (p < 0.0001) were predictive factors in univariate analysis. After multivariate analysis, tumor volume ≥ 2.8 cc (p = 0.0225) was an independent predictive factor for BCR. Among them, a novel risk model was established using tumor volume and location in the posterior area and peripheral zone. The progression-free survival (PFS) of patients who met the three criteria (unfavorable group) was significantly worse than other groups (p ≤ 0.001). Furthermore, multivariate analysis showed that the unfavorable risk was an independent prognostic factor for BCR. The prognostic significance of our risk model was observed in low- to intermediate-risk patients, although it was not observed in high-risk patients. (4) Conclusion: Tumor volume (≥2.8 cc) and localization (posterior/peripheral zone) may be a novel prognostic factor in patients undergoing RP.

Comparison of Computed Diffusion-Weighted Imaging b2000 and Acquired Diffusion-Weighted Imaging b2000 for Detection of Prostate Cancer

Purpose

To compare the sensitivity of tumor detection and inter-observer agreement between acquired diffusion-weighted imaging (aDWI) b2000 and computed DWI (cDWI) b2000 in patients with prostate cancer (PCa).

Materials and Methods

Eighty-eight patients diagnosed with PCa by radical prostatectomy and having undergone pre-operative 3 Tesla-MRI, including DWI (b, 0, 100, 1000, 2000 s/mm2), were included in the study. cDWI b2000 was obtained from aDWI b0, b100, and b1000. Two independent reviewers performed a review of the aDWI b2000 and cDWI b2000 images in random order at 4-week intervals. A region of interest was drawn for the largest tumor on each dataset, and a Prostate Imaging-Reporting and Data System (PI-RADS) score based on PI-RADS v2.1 was recorded. Histologic topographic maps served as the reference standard.

Results

The study population's Gleason scores were 6 (n = 16), 7 (n = 53), 8 (n = 9), and 9 (n = 10). According to the reviewers, the sensitivities of cDWI b2000 and aDWI b2000 showed no significant differences (for reviewer 1, both 94% [83/88]; for reviewer 2, both 90% [79/88]; p = 1.000, respectively). The kappa values of cDWI b2000 and aDWI b2000 for the PI-RADS score were 0.422 (95% confidence interval [CI], 0.240-0.603) and 0.495 (95% CI, 0.308-0.683), respectively.

Conclusion

cDWI b2000 showed comparable sensitivity with aDWI b2000, in addition to sustained moderate inter-observer agreement, in the detection of PCa.

Knowledge, attitudes, and practices of active surveillance in prostate cancer among urologists: a real-life survey from Brazil

Background

Active surveillance (AS) is the preferred treatment for patients with very low-and low-risk prostate cancer (PCa), but it is underperformed worldwide. This study aimed to report knowledge, attitudes, and practices (KAP) of AS for PCa among urologists in Brazil.

Methods

This cross-sectional study used a questionnaire with 50 questions divided into participant characteristics, knowledge regarding inclusion criteria for AS, follow-up, intervention triggers, acceptance, and practice for an index patient. Data analysis comprises absolute and relative frequencies of the variables. After that, a logistic regression was performed in order to verify possible patterns of answers provided by the respondents in the index patient questionnaire.

Results

Questionnaires were sent through the SurveyMonkey® platform to 5,015 urologists using email addresses and through social media. A total of 600 (12%) questionnaires returned and 413 (8.2%) were completed and included in the analysis. Only 53% of urologists adopt AS for low- and very-low-risk PCa. Inclusion criteria were patients with age > 50 years (32.2%), prostate specific antigen (PSA) < 10 ng/mL (87.2%), T1 clinical stage (80.4%), Biopsy Gleason score ≤ 6, positive cores ≤ 2 (44.3%), positive core involvement < 50% (45.3%), and magnetic resonance imaging findings (38.7%). The PSA doubling time was still used by 60.3%. Confirmatory biopsy (55.9%), PSA level (36.6%), and digital rectal examination (34.4%) were considered by most urologists for follow-ups. Patient preference (85.7%), upgrade of Gleason score (73.4%), and increased number of positive cores (66.8%) were associated with conversion to definitive treatment. In an index patient, non-acceptance and active treatment request were the most cited reasons for not performing AS.

Conclusion

There is significant variability in the KAP of AS in Brazil, which indicates the need to reinforce AS, its inclusion and follow-up criteria, and the benefits for physicians and the general population.

Trial registration: Not applicable.

Supplementary Information

The online version contains supplementary material available at 10.1186/s12894-022-01036-1.

Prostate MRI percentage tumor involvement or "PI-RADS percent" as a predictor of adverse surgical pathology

BACKGROUND

This study assesses magnetic resonance imaging (MRI) prostate % tumor involvement or "PI-RADs percent" as a predictor of adverse pathology (AP) after surgery for localized prostate cancer (PCa). Two separate variables, "All PI-RADS percent" (APP) and "Highest PI-RADS percent" (HPP), are defined as the volume of All PI-RADS 3-5 score lesions on MRI and the volume of the Highest PI-RADS 3-5 score lesion each divided by TPV, respectively.

METHOD

An analysis was done of an IRB approved prospective cohort of 557 patients with localized PCa who had targeted biopsy of MRI PIRADs 3-5 lesions followed by RARP from April 2015 to May 2020 performed by a single surgeon at a single center. AP was defined as ISUP GGG ≥3, pT stage ≥T3 and/or LNI. Univariate and multivariable analyses were used to evaluate APP and HPP at predicting AP with other clinical variables such as Age, PSA at surgery, Race, Biopsy GGG, mpMRI ECE and mpMRI SVI. Internal and External Validation demonstrated predicted probabilities versus observed probabilities.

RESULTS

AP was reported in 44.5% (n = 248) of patients. Multivariable regression showed both APP (odds ratio [OR]: 1.10, 95% confidence interval [CI]: 1.04-1.14, p = 0.0007) and HPP (OR: 1.10; 95% CI: 1.04-1.16; p = 0.0007) were significantly associated with AP with individual area under the operating curves (AUCs) of 0.6142 and 0.6229, respectively, and AUCs of 0.8129 and 0.8124 when incorporated in models including preoperative PSA and highest biopsy GGG.

CONCLUSIONS

Increasing PI-RADS Percent was associated with a higher risk of AP, and both APP and HPP may have clinical utility as predictors of AP in GGG 1 and 2 patients being considered for AS.

PATIENT SUMMARY

Using PIRADs percent to predict AP for presurgical patients may help risk stratification, and for low and low volume intermediate risk patients, may influence treatment decisions.

A comparative study of transperineal software-assisted magnetic resonance/ultrasound fusion biopsy and transrectal cognitive fusion biopsy of the prostate

BACKGROUND

The advantages and disadvantages of transperineal and transrectal biopsies remain controversial in the era of prostate targeted biopsy. In this study, we compared the cancer detection and complication rates of transperineal magnetic resonance/ultrasound (MR/US) fusion biopsy and transrectal cognitive fusion biopsy of the prostate.

METHODS

This was a comparative study of two prospectively collected cohorts. Men with clinically suspected prostate cancer and prostate imaging reporting and data system (PI-RADS) score ≥ 3 lesions on multi-parametric magnetic resonance imaging (mpMRI) were enrolled. They underwent either transperineal software fusion biopsy or transrectal cognitive fusion biopsy and systematic biopsy. The detection rates of any prostate cancer and clinically significant prostate cancer (csPC, defined as Gleason score ≥ 3 + 4) and the complication rates between both groups were analysed.

RESULTS

Ninety-two and 85 patients underwent transperineal software fusion and transrectal cognitive fusion biopsies, respectively. The detection rate for any prostate cancer was similar between both groups (60.8% vs. 56.4%, p = 0.659). In terms of csPC detection, transperineal fusion biopsy outperformed transrectal fusion biopsy (52.2% vs. 36.5%, p = 0.036). In multivariate regression analysis, age, PI-RADS score > 3, and transperineal route were significant predictors of csPC. Meanwhile, transperineal biopsy resulted in a higher rate of urinary retention than transrectal biopsy (18.5% vs. 4.7%, p = 0.009). No serious infectious complications were noted, although a patient developed sepsis after transrectal biopsy.

CONCLUSIONS

Transperineal software fusion biopsy provided a higher csPC detection rate than transrectal cognitive fusion biopsy and carried minimal risk for infectious complications in patients with MRI-visible prostate lesions.

Synthetic correlated diffusion imaging hyperintensity delineates clinically significant prostate cancer

Prostate cancer (PCa) is the second most common cancer in men worldwide and the most frequently diagnosed cancer among men in more developed countries. The prognosis of PCa is excellent if detected at an early stage, making early screening crucial for detection and treatment. In recent years, a new form of diffusion magnetic resonance imaging called correlated diffusion imaging (CDI) was introduced, and preliminary results show promise as a screening tool for PCa. In the largest study of its kind, we investigate the relationship between PCa presence and a new variant of CDI we term synthetic correlated diffusion imaging (CDI\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$^s$$\end{document}s), as well as its performance for PCa delineation compared to current standard MRI techniques [T2-weighted (T2w) imaging, diffusion-weighted imaging (DWI), and dynamic contrast-enhanced (DCE) imaging] across a cohort of 200 patient cases. Statistical analyses reveal that hyperintensity in CDI\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$^s$$\end{document}s is a strong indicator of PCa presence and achieves strong delineation of clinically significant cancerous tissue compared to T2w, DWI, and DCE. These results suggest that CDI\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$^s$$\end{document}s hyperintensity may be a powerful biomarker for the presence of PCa, and may have a clinical impact as a diagnostic aid for improving PCa screening.

Prediction of Clinically Significant Cancer Using Radiomics Features of Pre-Biopsy of Multiparametric MRI in Men Suspected of Prostate Cancer

Background: Texture features based on the spatial relationship of pixels, known as the gray-level co-occurrence matrix (GLCM), may play an important role in providing the accurate classification of suspected prostate cancer. The purpose of this study was to use quantitative imaging parameters of pre-biopsy multiparametric magnetic resonance imaging (mpMRI) for the prediction of clinically significant prostate cancer. Methods: This was a prospective study, recruiting 200 men suspected of having prostate cancer. Participants were imaged using a protocol-based 3T MRI in the pre-biopsy setting. Radiomics parameters were extracted from the T2WI and ADC texture features of the gray-level co-occurrence matrix were delineated from the region of interest. Radical prostatectomy histopathology was used as a reference standard. A Kruskal–Wallis test was applied first to identify the significant radiomic features between the three groups of Gleason scores (i.e., G1, G2 and G3). Subsequently, the Holm–Bonferroni method was applied to correct and control the probability of false rejections. We compared the probability of correctly predicting significant prostate cancer between the explanatory GLCM radiomic features, PIRADS and PSAD, using the area under the receiver operation characteristic curves. Results: We identified the significant difference in radiomic features between the three groups of Gleason scores. In total, 12 features out of 22 radiomics features correlated with the Gleason groups. Our model demonstrated excellent discriminative ability (C-statistic = 0.901, 95%CI 0.859–0.943). When comparing the probability of correctly predicting significant prostate cancer between explanatory GLCM radiomic features (Sum Variance T2WI, Sum Entropy T2WI, Difference Variance T2WI, Entropy ADC and Difference Variance ADC), PSAD and PIRADS via area under the ROC curve, radiomic features were 35.0% and 34.4% more successful than PIRADS and PSAD, respectively, in correctly predicting significant prostate cancer in our patients (p < 0.001). The Sum Entropy T2WI score had the greatest impact followed by the Sum Variance T2WI. Conclusion: Quantitative GLCM texture analyses of pre-biopsy MRI has the potential to be used as a non-invasive imaging technique to predict clinically significant cancer in men suspected of having prostate cancer.

Development and Validation of an Artificial Intelligence-Powered Platform for Prostate Cancer Grading and Quantification

IMPORTANCE

The Gleason grading system has been the most reliable tool for the prognosis of prostate cancer since its development. However, its clinical application remains limited by interobserver variability in grading and quantification, which has negative consequences for risk assessment and clinical management of prostate cancer.

OBJECTIVE

To examine the impact of an artificial intelligence (AI)-assisted approach to prostate cancer grading and quantification.

DESIGN, SETTING, AND PARTICIPANTS

This diagnostic study was conducted at the University of Wisconsin-Madison from August 2, 2017, to December 30, 2019. The study chronologically selected 589 men with biopsy-confirmed prostate cancer who received care in the University of Wisconsin Health System between January 1, 2005, and February 28, 2017. A total of 1000 biopsy slides (1 or 2 slides per patient) were selected and scanned to create digital whole-slide images, which were used to develop and validate a deep convolutional neural network-based AI-powered platform. The whole-slide images were divided into a training set (n = 838) and validation set (n = 162). Three experienced academic urological pathologists (W.H., K.A.I., and R.H., hereinafter referred to as pathologists 1, 2, and 3, respectively) were involved in the validation. Data were collected between December 29, 2018, and December 20, 2019, and analyzed from January 4, 2020, to March 1, 2021.

MAIN OUTCOMES AND MEASURES

Accuracy of prostate cancer detection by the AI-powered platform and comparison of prostate cancer grading and quantification performed by the 3 pathologists using manual vs AI-assisted methods.

RESULTS

Among 589 men with biopsy slides, the mean (SD) age was 63.8 (8.2) years, the mean (SD) prebiopsy prostate-specific antigen level was 10.2 (16.2) ng/mL, and the mean (SD) total cancer volume was 15.4% (20.1%). The AI system was able to distinguish prostate cancer from benign prostatic epithelium and stroma with high accuracy at the patch-pixel level, with an area under the receiver operating characteristic curve of 0.92 (95% CI, 0.88-0.95). The AI system achieved almost perfect agreement with the training pathologist (pathologist 1) in detecting prostate cancer at the patch-pixel level (weighted κ = 0.97; asymptotic 95% CI, 0.96-0.98) and in grading prostate cancer at the slide level (weighted κ = 0.98; asymptotic 95% CI, 0.96-1.00). Use of the AI-assisted method was associated with significant improvements in the concordance of prostate cancer grading and quantification between the 3 pathologists (eg, pathologists 1 and 2: 90.1% agreement using AI-assisted method vs 84.0% agreement using manual method; P < .001) and significantly higher weighted κ values for all pathologists (eg, pathologists 2 and 3: weighted κ = 0.92 [asymptotic 95% CI, 0.90-0.94] for AI-assisted method vs 0.76 [asymptotic 95% CI, 0.71-0.80] for manual method; P < .001) compared with the manual method.

CONCLUSIONS AND RELEVANCE

In this diagnostic study, an AI-powered platform was able to detect, grade, and quantify prostate cancer with high accuracy and efficiency and was associated with significant reductions in interobserver variability. These results suggest that an AI-powered platform could potentially transform histopathological evaluation and improve risk stratification and clinical management of prostate cancer.

Diagnostic accuracy of bi-parametric magnetic resonance imaging in suspected prostate cancer: Correlation of scan results with biopsy findings in a series of 266 patients

Objectives:

This study aimed to determine the diagnostic accuracy of bi-parametric magnetic resonance imaging (bpMRI) for clinically significant (CS) prostate cancer (PCa), and to assess the suitability of a new diagnostic pathway using bpMRI and prostate-specific antigen density (PSAd) to determine the need for biopsy.

Methods:

A total of 386 patients referred to one UK cancer centre with suspected PCa across 12 months from 2017 to 2018 underwent bpMRI, with a Prostate Imaging Reporting and Data System (PIRADS) score assigned. Of these, 266 (69%) were biopsied, with 150 CS-PCa (a Gleason score of 7 or a Gleason score of 3 with core length ⩾5 mm) detected: a 57% diagnostic yield. Imaging, PSAd and biopsy results were collated, and a confusion matrix was calculated.

Results:

Twenty-three men with PIRADS 1 were biopsied, with two CS-PCa detected: PSAd M=0.19 ( SD=0.07). Twenty-one men with PIRADS 2 lesions were biopsied, with one CS-PCa detected: PSAd was 0.28. Seventy-five men with PIRADS 3 were biopsied, with 25 CS-PCa detected: PSAd M=0.26 ( SD=0.16). Fifty-seven men with PIRADS 4 were biopsied, with 46 CS-PCa detected: PSAd M=0.26 ( SD=0.16). Ninety men with PIRADS 5 were biopsied, with 83 CS-PCa detected: PSAd M=0.55 ( SD=0.63). Among the 266 biopsied patients, a pathway offering biopsy if PIRADS is ⩾3 or PSAd ⩾0.1 spares 11 (4.2%) biopsies compared to baseline practice, with a sensitivity of 100% and a specificity of 10.1%, for biopsy-detected CS-PCa. The diagnostic yield is 61.8%.

Conclusion:

BpMRI is comparable to multi-parametric MRI for assessing need for biopsy in suspected PCa, albeit with lower specificity. A diagnostic pathway using bpMRI and PSAd can be safely used to avoid biopsy in men at low risk, increasing diagnostic yield of biopsy while reducing overdiagnosis and avoiding the risks and costs associated with gadolinium contrast.

Level of evidence:

Level 4.

HSP90-specific nIR probe identifies aggressive prostate cancers: translation from preclinical models to a human phase I study

A noninvasive test to discriminate indolent prostate cancers from lethal ones would focus treatment where necessary while reducing over-treatment. We exploited the known activity of heat shock protein 90 (Hsp90) as a chaperone critical for the function of numerous oncogenic drivers, including the androgen receptor and its variants, to detect aggressive prostate cancer. We linked a near infrared fluorescing molecule to an HSP90 binding drug and demonstrated that this probe (designated HS196) was highly sensitive and specific for detecting implanted prostate cancer cell lines with greater uptake by more aggressive subtypes. In a phase I human study, systemically administered HS196 could be detected in malignant nodules within prostatectomy specimens. Single-cell RNA sequencing identified uptake of HS196 by malignant prostate epithelium from the peripheral zone (AMACR+ERG+EPCAM+ cells), including SYP+ neuroendocrine cells that are associated with therapeutic resistance and metastatic progression. A theranostic version of this molecule is under clinical testing.

Performance of Deep Learning and Genitourinary Radiologists in Detection of Prostate Cancer Using 3-T Multiparametric Magnetic Resonance Imaging

BACKGROUND

Several deep learning-based techniques have been developed for prostate cancer (PCa) detection using multiparametric magnetic resonance imaging (mpMRI), but few of them have been rigorously evaluated relative to radiologists' performance or whole-mount histopathology (WMHP).

PURPOSE

To compare the performance of a previously proposed deep learning algorithm, FocalNet, and expert radiologists in the detection of PCa on mpMRI with WMHP as the reference.

STUDY TYPE

Retrospective, single-center study.

SUBJECTS

A total of 553 patients (development cohort: 427 patients; evaluation cohort: 126 patients) who underwent 3-T mpMRI prior to radical prostatectomy from October 2010 to February 2018.

FIELD STRENGTH/SEQUENCE

3-T, T2-weighted imaging and diffusion-weighted imaging.

ASSESSMENT

FocalNet was trained on the development cohort to predict PCa locations by detection points, with a confidence value for each point, on the evaluation cohort. Four fellowship-trained genitourinary (GU) radiologists independently evaluated the evaluation cohort to detect suspicious PCa foci, annotate detection point locations, and assign a five-point suspicion score (1: least suspicious, 5: most suspicious) for each annotated detection point. The PCa detection performance of FocalNet and radiologists were evaluated by the lesion detection sensitivity vs. the number of false-positive detections at different thresholds on suspicion scores. Clinically significant lesions: Gleason Group (GG) ≥ 2 or pathological size ≥ 10 mm. Index lesions: the highest GG and the largest pathological size (secondary).

STATISTICAL TESTS

Bootstrap hypothesis test for the detection sensitivity between radiologists and FocalNet.

RESULTS

For the overall differential detection sensitivity, FocalNet was 5.1% and 4.7% below the radiologists for clinically significant and index lesions, respectively; however, the differences were not statistically significant (P = 0.413 and P = 0.282, respectively).

DATA CONCLUSION

FocalNet achieved slightly lower but not statistically significant PCa detection performance compared with GU radiologists. Compared with radiologists, FocalNet demonstrated similar detection performance for a highly sensitive setting (suspicion score ≥ 1) or a highly specific setting (suspicion score = 5), while lower performance in between.

LEVEL OF EVIDENCE

3 TECHNICAL EFFICACY STAGE: 2.

Indication for Active Surveillance in the Era of MRI-Targeted Prostate Biopsies

INTRODUCTION

Active surveillance (AS) strategies were established to avoid overtreatment of low-risk prostate cancer (PCa) patients. Low tumor volume represents one indication criteria; however, applying this criterion after MRI-targeted prostate biopsies may lead to overestimation of tumor volume; wherefore, patients suitable for AS would be exposed to the risk of overtreatment.

METHODS

This retrospective analysis included 318 patients in which PCa was detected by MRI-TRUS fusion prostate biopsy. Classic and extended indication for AS included Gleason 6 and Gleason 3 + 4 cancer, respectively. We assessed the effect of targeted biopsies and temporary rating strategies on eligibility for AS and developed new "composite" algorithms to more accurately assess eligibility for AS.

RESULTS

Forty-four (13.8%) and 60 (18.9%) of the 318 patients qualified for AS according to "classic" and "extended" criteria, respectively. Application of the "composite 1" definition led to AS eligibility of 52 of 248 patients (20.97%) in the classic and of 77 of 248 patients (31.05%) in the "extended" group.

CONCLUSIONS

We could demonstrate that classic algorithms led to ineligibility of patients for AS. We propose a new rating algorithm to improve tumor assessment for a more accurate indication for AS.

Design and validation of an MRI-compatible mechatronic system for needle delivery to localized prostate cancer

PURPOSE

Prostate cancer is the most common non-cutaneous cancer among men in the United States and is the second leading cause of cancer death in American men. (Siegel et al. [2019] CA: A Cancer J Clin.69(1):7-34.) Focal laser ablation (FLA) has the potential to control small tumors while preserving urinary and erectile function by leaving the neurovascular bundles and urethral sphincters intact. Accurate needle guidance is critical to the success of FLA. Multiparametric magnetic resonance images (mpMRI) can be used to identify targets, guide needles, and assess treatment outcomes. The purpose of this work was to design and evaluate the accuracy of an MR-compatible mechatronic system for in-bore transperineal guidance of FLA ablation needles to localized lesions in the prostate.

METHODS

The mechatronic system was constructed entirely of non-ferromagnetic materials, with actuation controlled by piezoelectric motors and optical encoders. The needle guide hangs between independent front and rear two-link arms, which allows for horizontal and vertical translation as well as pitch and yaw rotation of the guide with a 6.0 cm range of motion in each direction. Needles are inserted manually through a chosen hole in the guide, which has been aligned with the target in the prostate. Open-air positioning error was evaluated using an optical tracking system (0.25 mm RMS accuracy) to measure 125 trajectories in free space. Correction of systematic bias in the system was performed using 85 of the trajectories, and the remaining 40 were used to estimate the residual error. The error was calculated as the horizontal and vertical displacement between the axis of the desired and measured trajectories at a typical needle insertion depth of 10 cm. MR-compatibility was evaluated using a grid phantom to assess image degradation due to the presence of the system, and induced force, heating, and electrical interference in the system were assessed qualitatively. In-bore positioning error was evaluated on 25 trajectories.

RESULTS

Open-air mean positioning error at the needle tip was 0.80 ± 0.36 mm with a one-sided 95% confidence interval of 1.40 mm. The mean deviation of needle trajectories from the planned direction was 0.14 ± 0.06^∘ . In the MR bore, the mean positioning error at the needle tip was 2.11 ± 1.05 mm with a one-sided 95% prediction interval of 3.84 mm. The mean angular error was 0.49 ± 0.26^∘ . The system was found to be compatible with the MR environment under the specified gradient-echo sequence parameters used in this study.

CONCLUSION

A complete system for delivering needles to localized prostate tumors was developed and described in this work, and its compatibility with the MR environment was demonstrated. In-bore MRI positioning error was sufficiently small for targeting small localized prostate tumors.

Development of a transperineal prostate biopsy robot guided by MRI-TRUS image

BACKGROUND

In the transrectal ultrasound (TRUS)-guided transperineal prostate biopsy, doctors determine the biopsy target by observing the prostate region in TRUS images. However, ultrasound images with low imaging quality make doctors easy to be interfered when determining the biopsy route, which reduces the biopsy success rate.

METHODS

This paper introduces the guidance method of magnetic resonance image (MRI) registration to ultrasound image and develops a 5-degrees of freedom robot for prostate biopsy guided by MRI-TRUS image. The robot uses a structure attached to the ultrasound probe to reduce the space occupied. By registering the posture relationship between MRI, TRUS image, ultrasonic probe and the robot base, the accurate localization of the suspected lesion area can be achieved with the preoperative MRIs.

RESULTS

The prostate phantom biopsy based on the robotic biopsy system in this paper, the average biopsy error is 1.44 mm, and the maximum biopsy error is 2.23 mm.

CONCLUSIONS

We build a robotic biopsy platform with prostate phantom, and evaluate the biopsy accuracy of MRI-TRUS guided prostate biopsy robot, the results meet clinical prostate biopsy requirements.

The impact of age on pathological insignificant prostate cancer rates in contemporary robot-assisted prostatectomy patients despite active surveillance eligibility

BACKGROUND

To assess insignificant prostate cancer(iPCa) rates after robot-assisted radical prostatectomy (RARP) in contemporary patients who were preoperatively eligible for active surveillance(AS). IPCa indicates no risk of PCa progression.

METHODS

We retrospectively analysed 2,837 RARP patients (2010-2019) who fulfilled at least one AS entry criteria set - Prostate Cancer Research International - Active Surveillance(PRIAS), University of California San Francisco(UCSF), National Comprehensive Cancer Network(NCCN) or University of Toronto. We utilized four different iPCa definitions, (1) based on pT2 and Gleason score ≤6 and also cumulative tumor-volume (2) ≤2.5mL, (3) ≤0.7mL or (4) ≤0.5mL. For each AS set we tested the rates of iPCa and compared between age <70 vs. ≥70 yrs. This was complemented by multivariable logistic regression(LRM) predicting iPCa, adjusted for age and clinical AS variables. Finally, within the subgroup, who had iPCa, we tested rate of those, who were deemed preoperatively AS ineligible.

RESULTS

Between most(PRIAS) and least stringent(TORONTO) AS sets, iPCa(1) was correctly predicted in 70-57%. Similarly, for iPCa definitions 2-4, rates were (2)59-42%, (3)34-19% and (4)27-14%. Senior patients harbored decreased proportions of iPCa. LRM confirmed that advanced age is associated with a lower chance of iPCa. More stringent AS sets lead to higher rates of AS ineligibility, e.g. 53% for PRIAS, despite iPCa.

CONCLUSIONS

AS sets show limited accuracy for stricter iPCa definitions, which further declined with advanced age. Greater AS stringency resulted in more AS ineligible patients despite harboring iPCa. In consequence, patients are at risk for overtreatment. Clinicians must consider age and different AS sets that result in highly variable detection rates of iPCa.

Can mean ADC value and ADC ratio of benign prostate tissue to prostate cancer assist in the prediction of clinically significant prostate cancer within the PI-RADSv2 scoring system?

Background

The aim of this study is to investigate whether quantitative DW metrics can provide additive value to the reliable categorization of lesions within existing PI-RADSv2 guidelines. Fifty-eight patients with clinically suspicious prostate cancer who underwent PR examination, PSA serum levels, sextant TRUS-guided biopsies, and bi-parametric MR imaging were included in the study.

Results

Sixty-six lesions were detected by histopathological analysis of surgical specimens. The mean ADC values were significantly lower in tumor than non-tumor tissue. The mean ADC value inversely correlated with Gleason score of tumors with a significant p value < 0.001.Conversely, a positive relationship was found between the ADC ratio (ADC of benign prostatic tissue to prostate cancer) and the pathologic Gleason score with a significant elevation of the ADC ratio along with an increase of the pathologic Gleason score (p < 0.001). ROC curves constructed for the tumor ADC and ADC ratio helped to distinguish pathologically aggressive (Gleason score ≥ 7) from non-aggressive (Gleason score ≤ 6) tumors and to correlate it with PIRADSv2 scoring to predict the presence of clinically significant PCA (PIRADSv2 DW ≥ 4). The ability of the tumor ADC and ADC ratio to predict highly aggressive tumors (GS> 7) was high (AUC for ADC and ADC ratio, 0.946 and 0.897; p = 0.014 and 0.039, respectively). The ADC cut-off value for GS ≥ 7 was < 0.7725 and for GS ≤ 6 was > 0.8620 with sensitivity and specificity 97 and 94%. The cutoff ADC ratio for predicting (GS > 7) was 1.42 and for GS ≤ 6 was > 1.320 with sensitivity and specificity 97 and 92%. By applying this ADC ratio cut-off value the sensitivity and specificity of reader 1 for correct categorization of PIRADSv2 DW > 4 increased from 90 and 68% to 95 and 90% and that of reader 2 increased from 94 and 88% to 97 and 92%, respectively.

Conclusion

Estimation of DW metrics (ADC and ADC ratio between benign prostatic tissue and prostate cancer) allow the non-invasive assessment of biological aggressiveness of prostate cancer and allow reliable application of the PIRADSv2 scoring to determine clinically significant cancer (DW score > 4) which may contribute in planning initial treatment strategies.

A 3D-2D Hybrid U-Net Convolutional Neural Network Approach to Prostate Organ Segmentation of Multiparametric MRI

OBJECTIVE

Prostate cancer is the most commonly diagnosed cancer in men in the United States with more than 200,000 new cases in 2018. Multiparametric MRI (mpMRI) is increasingly used for prostate cancer evaluation. Prostate organ segmentation is an essential step of surgical planning for prostate fusion biopsies. Deep learning convolutional neural networks (CNNs) are the predominant method of machine learning for medical image recognition. In this study, we describe a deep learning approach, a subset of artificial intelligence, for automatic localization and segmentation of prostates from mpMRI.

MATERIALS AND METHODS

This retrospective study included patients who underwent prostate MRI and ultrasound-MRI fusion transrectal biopsy between September 2014 and December 2016. Axial T2-weighted images were manually segmented by two abdominal radiologists, which served as ground truth. These manually segmented images were used for training on a customized hybrid 3D-2D U-Net CNN architecture in a fivefold cross-validation paradigm for neural network training and validation. The Dice score, a measure of overlap between manually segmented and automatically derived segmentations, and Pearson linear correlation coefficient of prostate volume were used for statistical evaluation.

RESULTS

The CNN was trained on 299 MRI examinations (total number of MR images = 7774) of 287 patients. The customized hybrid 3D-2D U-Net had a mean Dice score of 0.898 (range, 0.890-0.908) and a Pearson correlation coefficient for prostate volume of 0.974.

CONCLUSION

A deep learning CNN can automatically segment the prostate organ from clinical MR images. Further studies should examine developing pattern recognition for lesion localization and quantification.

Value of MRI texture analysis for predicting high-grade prostate cancer

PURPOSE

To explore the potential value of MRI texture analysis (TA) combined with prostate-related biomarkers to predict high-grade prostate cancer (HGPCa).

MATERIALS AND METHODS

Eighty-five patients who underwent MRI scanning, including T2-weighted imaging (T2WI) and diffusion-weighted imaging (DWI) prior to trans-rectal ultrasound (TRUS)-guided core prostate biopsy, were retrospectively enrolled. TA parameters derived from T2WI and DWI, prostate-specific antigen (PSA), and free PSA (fPSA) were compared between the HGPCa and non-high-grade prostate cancer (NHGPCa) groups using independent Student's t-test and the Mann-Whitney U test. Logistic regression and receiver operating characteristic (ROC) curve analyses were performed to assess the predictive value for HGPCa.

RESULTS

Univariate analysis showed that PSA and entropy based on apparent diffusion coefficient (ADC) map differed significantly between the HGPCa and NHGPCa groups and showed higher diagnostic values for HGPCa (area under the curve (AUC) = 82.0% and 80.0%, respectively). Logistic regression and ROC curve analyses revealed that kurtosis, skewness and entropy derived from ADC maps had diagnostic power to predict HGPCa; when the three texture parameters were combined, the area under the ROC curve reached the maximum (AUC = 84.6%; 95% confidence interval (CI): 0.758, 0.935; P = 0.000).

CONCLUSION

TA parameters derived from ADC may be a valuable tool in predicting HGPCa. The combination of specific textural parameters extracted from ADC map may be additional tools to predict HGPCa.

Advances in Prognostic Methylation Biomarkers for Prostate Cancer

There is a major clinical need for accurate biomarkers for prostate cancer prognosis, to better inform treatment strategies and disease monitoring. Current clinically recognised prognostic factors, including prostate-specific antigen (PSA) levels, lack sensitivity and specificity in distinguishing aggressive from indolent disease, particularly in patients with localised intermediate grade prostate cancer. There has therefore been a major focus on identifying molecular biomarkers that can add prognostic value to existing markers, including investigation of DNA methylation, which has a known role in tumorigenesis. In this review, we will provide a comprehensive overview of the current state of DNA methylation biomarker studies in prostate cancer prognosis, and highlight the advances that have been made in this field. We cover the numerous studies into well-established candidate genes, and explore the technological transition that has enabled hypothesis-free genome-wide studies and the subsequent discovery of novel prognostic genes.

Transperineal Versus Transrectal Targeted Biopsy With Use of Electromagnetically-tracked MR/US Fusion Guidance Platform for the Detection of Clinically Significant Prostate Cancer

OBJECTIVE

To compare transperineal (TP-TBx) and transrectal (TR-TBx) targeted prostate biopsy in a prospective non randomized single surgeon series of MR/US fusion-guided targeted biopsy performed using an electromagnetic tracking platform (NCT04026763).

MATERIALS AND METHODS

In this single-institution prospective study, 168 patients who underwent transperineal systematic 12-core biopsy and TP-TBx with electromagnetic tracking (UroNav, Invivo, Gainesville, FL) were compared to 211 patients who underwent a similar procedure by a transrectal approach. Univariate and multivariate analyses were used to assess if biopsy technique impacted all cancer detection rates or clinically significant (Gleason score >3+4) cancer detection rates.

RESULTS

Patients who underwent TP-TBx were older (68 vs 65 y, P = .014), with a slightly higher rate of PI-RADSv2.0 score (39% vs 28%, P = .039) and higher lesion volume on mpMRI (0.54 vs 0.41 cc, P = .039). The rates of CS disease detection by TP-TBx and TR-TBx were 59% and 54%, respectively. In a multivariate analysis adjusting for PSA, previous biopsy status, prostate volume, PI-RADS score, lesion volume, and lesion location, there was no statistically significant difference in likelihood to detect any PCa (OR, 0.98; 95% CI, 0.56-1.71; P = .940) or CS PCa (OR, 0.94, 95% CI, 0.58-1.51; P = .791).

CONCLUSION

Transperineal targeted biopsy with electromagnetic-tracking is comparable to the transrectal fusion-guided approach in the detection of any PCa and csPCa cancer.

Molecular Changes in Tissue Proteome during Prostate Cancer Development: Proof-of-Principle Investigation

(1) Background: Prostate cancer (PCa) is characterized by high heterogeneity. The aim of this study was to investigate molecular alterations underlying PCa development based on proteomics data. (2) Methods: Liquid chromatography coupled to tandem mass spectrometry was conducted for 22 fresh-frozen tissue specimens from patients with benign prostatic hyperplasia (BPH, n = 5) and PCa (n = 17). Mann Whitney test was used to define significant differences between the two groups. Association of protein abundance with PCa progression was evaluated using Spearman correlation, followed by verification through investigating the Prostate Cancer Transcriptome Atlas. Functional enrichment and interactome analysis were carried out using Metascape and String. (3) Results: Proteomics analysis identified 1433 proteins, including 145 proteins as differentially abundant between patients with PCa and BPH. In silico analysis revealed alterations in several pathways and hallmarks implicated in metabolism and signalling, represented by 67 proteins. Among the latter, 21 proteins were correlated with PCa progression at both the protein and mRNA levels. Interactome analysis of these 21 proteins predicted interactions between Myc proto-oncogene (MYC) targets, protein processing in the endoplasmic reticulum, and oxidative phosphorylation, with MYC targets having a central role. (4) Conclusions: Tissue proteomics allowed for characterization of proteins and pathways consistently affected during PCa development. Further validation of these findings is required.

MRI and Active Surveillance for Prostate Cancer

Since the introduction of Prostate-Specific Antigen (PSA) screening, prostate cancer mortality has decreased [...]

Clinical evaluation and disease management of PI-RADS 3 lesions. Analysis from a single tertiary high-volume center

OBJECTIVE

To evaluate the clinical and pathological implications of Prostate Cancer (PCa) patients with a Prostate Imaging - Reporting and Data System (PI-RADS) 3 lesion at multi parametric magnetic resonance imaging (mpMRI).

METHODS

We included 356 patients with a PI-RADS score 3 lesion at mpMRI who underwent prostate biopsy for a suspect of PCa at a single tertiary high-volume centre between 2013 and 2016.We developed Uni- (UVA) and multi variable (MVA) logistic regression analyses assessing the predictors of three endpoints: 1) diagnosis of PCa, 2) active surveillance (AS) criteria and 3) clinically significant (CS) PCa at final pathology.

RESULTS

PCa was diagnosed in 285 patients (80%), out of these 154 (56%) were eligible for AS according to Prostate Cancer Research International Active Surveillance (PRIAS) criteria. Over the 228 (64%) patients who underwent surgery, 93 (40.8%) had a CS disease at final pathology. Hundred and ninety-three (84.6%) had a pT2 disease and 35 (15.4%) had a pT3 disease. The size of the main lesion, age, PSA and prostate volume efficiently predicted PCa at MVA (all p < 0.05). None of our predictors were significantly associated with AS characteristics. Over those patients who underwent surgery, the biopsy Gleason Score (p = 0.007) efficiently predicted a CS PCa at final pathology.

CONCLUSIONS

mpMRI-detected PI-RADS 3 lesions should be sent to a prostate biopsy if other clinical parameters suggest the presence of a PCa. In case of diagnosis of a PCa, patients should undergo confirmatory biopsy before being included in AS protocols to avoid underestimation of a CS disease.

Predicting Insignificant Prostate Cancer: Analysis of the Pathological Outcomes of Candidates for Active Surveillance according to the Pre-International Society of Urological Pathology (Pre-ISUP) 2014 Era Versus the Post-ISUP2014 Era

Purpose

To analyze the difference in the prediction accuracy with an active surveillance (AS) protocol between two eras (pre-International Society of Urological Pathology [pre-ISUP]-2014 vs. post-ISUP2014).

Materials and Methods

We retrospectively analyzed 118 candidates for AS who underwent radical prostatectomy between 2009 and 2017. We divided our patients into two groups (group 1 [n=57], operation date 2009–2015; group 2 [n=61], operation date 2016–2017). Pathologic slides in group 1 were reviewed to distinguish men with cribriform pattern (CP) because the determination of Gleason scores in old era had been based on pre-ISUP2014 classification. Postoperative outcomes in the two eras were analyzed twice: first, all men in group 1 vs. group 2; second, the remaining men after excluding those with CPs in group 1 vs. group 2.

Results

The proportion of men with insignificant prostate cancer (iPCa) was significantly lower in group 1 than in group 2 (36.8% vs. 57.4%, p=0.040). After excluding 11 men with CPs from group 1, those remaining (46 men) were compared again with group 2. In this analysis, the proportion of men with iPCa was similar between the two groups (old vs. contemporary era: 41.3% vs. 57.4%, p=0.146). Nine of 11 men with CP had violated the criteria for iPCa in the earlier comparison.

Conclusions

The accuracy of the AS protocol has been affected by the coexistence of CPs and pure Gleason 6 tumors in the pre-ISUP2014 era. We suggest to use only contemporary (post-ISUP2014) data to analyze the accuracy with AS protocols in future studies.

The utility of intraoperative contrast-enhanced ultrasound in detecting residual disease after focal HIFU for localized prostate cancer

BACKGROUND AND OBJECTIVES

Focal high intensity focused ultrasound (HIFU) is an emerging treatment for selected men with localized prostate cancer. A limitation of HIFU is the absence of a reliable tool to measure treatment effect intraoperatively. Contrast-enhanced ultrasound (CEUS) has been shown to be a promising modality for assessing the extent and boundaries of tissue ablation. The aim of this study was to assess the value of CEUS immediately after focal HIFU.

MATERIALS AND METHODS

Retrospective analysis of a prospectively maintained registry including consecutive men undergoing focal HIFU (Focal One). Candidates for focal HIFU were treatment naive men with ≥10 years life expectancy, prostate-specific antigen (PSA) ≤ 20 ng/ml, TNM primary tumor, regional lymph nodes, distant metastasis stage ≤ T2c N0 M0 with a multiparametric MRI (mpMRI) visible lesion concordant with histologically proven prostate cancer. CEUS evaluation was performed immediately at the end of the procedure. Based on the surgeon's estimation of CEUS imaging, re-HIFU was performed, followed by another CEUS evaluation. To test our hypothesis, the results of the CEUS were compared to the results of early mpMRI to rule out clinically significant cancer. The concordance between the 2 tests was measured using the Cohen's kappa. The best model including relevant predictors was calculated with CEUS or with mpMRI to determine their respective added value.

RESULTS

Of 66 men who underwent HIFU, 32 met eligibility criteria. Bifocal treatment was performed in 1 man, increasing the number of treated lesions to 33. Further ablation based on CEUS was delivered intraoperatively to 13 lesions (39%). The positive biopsy rate for clinically significant cancer in the treated zones was 30% (10/33). The negative predictive value of CEUS and early mpMRI was 71% (95% confidence interval: 59%-82%). Concordance between CEUS and mpMRI was significant with a 72.7% agreement (P = 0.001). The model with CEUS showed the best accuracy with an area under the curve of 0.881.

CONCLUSION

CEUS has a higher added value compared to early mpMRI in ruling out clinically significant cancer after focal HIFU. It should be evaluated whether the use of CEUS intraoperatively enhances the efficacy of focal HIFU.

The decision of targeted, systematic or combined biopsy in a biopsy naïve patient for the diagnosis of prostate cancer, can be made on the basis of multiparametric magnetic resonance imaging

Introduction:

The current trend to implement multiparametric magnetic resonance imaging (mpMRI)-guided targeted biopsy (TB) as primary biopsy for the diagnosis of suspected prostate cancer and to avoid systematic biopsy (SB) is growing. However, concern remains regarding missing clinically significant (Cs) cancer on the normal mpMRI areas of the prostate. Therefore, we compared the normal and abnormal areas from mpMRI at the same prostate biopsy, using simultaneous SB and TB technique.

Methods:

A prospective, comparative effectiveness study included 134 patients initially referred for primary biopsy (from October 2017 to June 2018); 100 men were selected, mean age 68 years, with a median level of prostate specific antigen of 7.6, with average prostate volume of 52 cm3 (T3 disease and prostate imaging reporting and data system (PI-RADS) score < 3 were excluded). All underwent six cores TB (median), from an average of two lesions on mpMRI and also eight cores SB (median) from normal mpMRI areas of the prostate after informed consent.

Results:

The combined (SB + TB) biopsy cancer detection rate was 67%, 51% having Cs disease. For Cs cancer, 35 patients were detected by both techniques. TB missed four Cs cancer (95% confidence interval (CI), p < 0.0001). Fewer men in the TB group than in the SB group were found to have clinically insignificant (Ci) cancer (95% CI, p < 0.0001). No Cs cancer diagnosis was missed on TB from PI-RADS 5 lesion. Overall, 4% Cs cancers were missed on TB and avoided over diagnosis of 9% Ci cancer.

Conclusions:

Cognitive TB didn’t miss any Cs cancer from PI-RADS 5 lesion found on mpMRI. Only doing Cognitive TB on PI-RADS 5 lesion would save time, reduce workload and will be cost effective both for Urology and Pathology. PI-RADS 3 and 4 lesions on mpMRI will benefit from adding systematic samples.

Level of evidence:

4 Oxford Centre for Evidence-Based Medicine (CEBM).

Can epigenetic and inflammatory biomarkers identify clinically aggressive prostate cancer?

Prostate cancer (PCa) is a highly prevalent malignancy and constitutes a major cause of cancer-related morbidity and mortality. It emerges through the acquisition of genetic and epigenetic alterations. Epigenetic modifications include DNA methylation, histone modifications and microRNA deregulation. These generate heritable transformations in the expression of genes but do not change the DNA sequence. Alterations in DNA methylation (hypo and hypermethylation) are the most characterized in PCa. They lead to genomic instability and inadequate gene expression. Major and minor-specific modifications in chromatin recasting are involved in PCa, with signs suggesting a dysfunction of enzymes modified by histones. MicroRNA deregulation also contributes to the initiation of PCa, including involvement in androgen receptor signalization and apoptosis. The influence of inflammation on prostate tumor carcinogenesis is currently much better known. Recent discoveries about microbial species resident in the urinary tract suggest that these are the initiators of chronic inflammation, promoting prostate inflammatory atrophy and eventually leading to PCa. Complete characterization of the relationship between the urinary microbiome and prostatic chronic inflammation will be crucial to develop plans for the prevention of PCa. The prevalent nature of epigenetic and inflammatory alterations may provide potential biomarkers for PCa diagnosis, treatment decisions, evaluation of prognosis and posttreatment surveillance.

Diagnostic Performance of Mass Enhancement on Dynamic Contrast-Enhanced MRI for Predicting Clinically Significant Peripheral Zone Prostate Cancer

OBJECTIVE. Current criteria for positive findings on dynamic contrast-enhanced MRI (DCE-MRI) are unclear. We compared the diagnostic performance of mass enhancement on DCE-MRI versus conventional DCE-MRI criteria for identifying clinically significant prostate cancer (csPCa) in the peripheral zone (PZ). MATERIALS AND METHODS. A total of 173 consecutive patients with MRI- and surgically proven prostate cancer (PCa) were evaluated. Two readers independently interpreted DCE-MRI examinations of the PZ. Criteria denoting a positive DCE-MRI examination included conventional criteria from the Prostate Imaging Reporting and Data System version 2 (PI-RADSv2) and mass enhancement. The diagnostic performance of and interreader agreement for the two types of enhancement criteria in identifying csPCa in the PZ that met Epstein criteria were investigated. RESULTS. The proportion of csPCa in the PZ was 69.3% (120/173). For both readers, the specificity and positive predictive value of mass enhancement were increased compared with conventional enhancement criteria (specificity, 75.5% vs 5.7% [for reader 1] and 84.9% vs 30.2% [for reader 2], respectively; positive predictive value, 87.1% vs 70.6% [for reader 1] and 91.5% vs 75.3% [for reader 2], respectively). The AUC value of mass enhancement was higher than that of conventional criteria (for reader 1, 0.744 [95% CI, 0.672-0.807] vs 0.528 [95% CI, 0.451-0.605] [p < 0.001], respectively; for reader 2, 0.783 [95% CI, 0.714-0.842] vs 0.602 [95% CI, 0.497-0.700] [p < 0.001], respectively). The weighted kappa value for agreement between the two readers was 0.206 for conventional criteria and 0.613 for mass enhancement. CONCLUSION. PZ lesions with mass enhancement on DCE-MRI are more likely to be csPCa. This enhancement pattern may need to be considered as one of the criteria in PI-RADS.

Rapid perceptual processing in two- and three-dimensional prostate images

Radiologists can identify whether a radiograph is abnormal or normal at above chance levels in breast and lung images presented for half a second or less. This early perceptual processing has only been demonstrated in static two-dimensional images (e.g., mammograms). Can radiologists rapidly extract the "gestalt" from more complex imaging modalities? For example, prostate multiparametric magnetic resonance imaging (mpMRI) displays a series of images as a virtual stack and comprises multiple imaging sequences: anatomical information from the T2-weighted (T2W) sequence, functional information from diffusion-weighted imaging, and apparent diffusion coefficient sequences. We first tested rapid perceptual processing in static T2W images then among the two functional sequences. Finally, we examined whether this rapid radiological perception could be observed using T2W multislice imaging. Readers with experience in prostate mpMRI could detect and localize lesions in all sequences after viewing a 500-ms static image. Experienced prostate readers could also detect and localize lesions when viewing multislice image stacks presented as brief movies, with image slices presented at either 48, 96, or 144 ms. The ability to quickly extract the perceptual gestalt may be a general property of expert perception, even in complex imaging modalities.

Is targeted biopsy really needed when performing systematic prostate biopsy to raise the detection rate for prostate cancer in patients with prostate-specific antigen ≤10 ng/mL?

Targeted biopsy with multiparametric magnetic resonance imaging and hypoechoic lesions on transrectal ultrasound has been implemented to increase prostate cancer detection rate.We compared the detection abilities of systematic prostate biopsy, hypoechoic lesion-targeted biopsy (HL-TBx), and cognitive magnetic resonance imaging-targeted biopsy (MRI-TBx) in patients with suspected prostate cancer. Between September 2014 and August 2016, 193 patients with a prostate-specific antigen level of 3 to 10 ng/mL underwent HL-TBx or MRI-TBx. In patients who refused magnetic resonance imaging examination before prostate biopsy, HL-TBx was performed. We compared cancer detection rates and pathologic outcomes between systematic prostate biopsy and HL-TBx or MRI-TBx.The cancer detection rates for HL-TBx and MRI-TBx were 40.8% and 43.8%, respectively, without a significant difference (P = .683). Of the 81 patients diagnosed with prostate cancer, most patients (77 patients, 95.1%) were diagnosed with prostate cancer by systematic prostate biopsy. The detection ability for prostate cancer was significantly better for systematic prostate biopsy than for HL-TBx or MRI-TBx (P < .001).The detection abilities for clinically significant prostate cancer similar between HL-TBx and systematic prostate biopsy. Systematic prostate biopsy alone should be recommended for detection prostate cancer in patients with a prostate-specific antigen ≤10 ng/mL.

A polymeric paste-drug formulation for intratumoral treatment of prostate cancer

OBJECTIVE

Focal therapy has emerged as a treatment option for low- to intermediate-risk localized prostate cancer (PCa) patients, to balance the risks for urinary and sexual morbidity of radical treatment with the psychological burden of active surveillance. In this context, we developed ST-4PC, an injectable, polymeric paste formulation containing docetaxel (dtx) and bicalutamide (bic) for image-guided focal therapy of PCa. The objective of this work was to evaluate the in vitro characteristics and in vivo toxicity and efficacy of ST-4PC.

MATERIAL AND METHODS

In vitro drug release was evaluated using high-performance liquid chromatography. In vivo toxicity of blank- and drug-loaded ST-4PC was assessed in mice and rats. Tumor growth inhibition was evaluated in LNCaP subcutaneous (s.c.) and LNCaP-luc orthotopic xenograft models. Using the s.c. model, mice were monitored weekly for weight loss, tumor volume (TV) and serum PSA. For the orthotopic model, mice were additionally monitored for bioluminescence as measure of tumor growth.

RESULTS

ST-4PC demonstrated a sustained and steady release of incorporated drugs with 50% dtx and 20% bic being released after 14 days. While no systemic toxicity was observed, dose-dependent local side effects from dtx developed in the s.c. but not in the orthotopic model, illustrating the limitations of s.c. models for evaluating local cytotoxic therapy. In the s.c. model, 0.1%/4% and 0.25%/4% dtx/bic ST-4PC paste significantly reduced PSA progression, but did not have a significant inhibitory effect on TV. ST-4PC loaded with 1%/4% dtx/bic significantly reduced TV, serum PSA, and bioluminescence in the orthotopic xenograft model. Compared with drugs dissolved in DMSO, ST-4PC significantly delayed tumor growth.

CONCLUSION

Image-guided focal therapy using ST-4PC demonstrated promising inhibition of PSA progression and orthotopic tumor growth in vivo without significant toxicity, and warrants further clinical evaluation.

Joint Prostate Cancer Detection and Gleason Score Prediction in mp-MRI via FocalNet

Multi-parametric MRI (mp-MRI) is considered the best non-invasive imaging modality for diagnosing prostate cancer (PCa). However, mp-MRI for PCa diagnosis is currently limited by the qualitative or semi-quantitative interpretation criteria, leading to inter-reader variability and a suboptimal ability to assess lesion aggressiveness. Convolutional neural networks (CNNs) are a powerful method to automatically learn the discriminative features for various tasks, including cancer detection. We propose a novel multi-class CNN, FocalNet, to jointly detect PCa lesions and predict their aggressiveness using Gleason score (GS). FocalNet characterizes lesion aggressiveness and fully utilizes distinctive knowledge from mp-MRI. We collected a prostate mp-MRI dataset from 417 patients who underwent 3T mp-MRI exams prior to robotic-assisted laparoscopic prostatectomy. FocalNet was trained and evaluated in this large study cohort with fivefold cross validation. In the free-response receiver operating characteristics (FROC) analysis for lesion detection, FocalNet achieved 89.7% and 87.9% sensitivity for index lesions and clinically significant lesions at one false positive per patient, respectively. For the GS classification, evaluated by the receiver operating characteristics (ROC) analysis, FocalNet received the area under the curve of 0.81 and 0.79 for the classifications of clinically significant PCa (GS ≥ 3 + 4) and PCa with GS ≥ 4 + 3, respectively. With the comparison to the prospective performance of radiologists using the current diagnostic guideline, FocalNet demonstrated comparable detection sensitivity for index lesions and clinically significant lesions, only 3.4% and 1.5% lower than highly experienced radiologists without statistical significance.