Impact of prebiopsy magnetic resonance imaging of the prostate on cancer detection and treatment patterns

Three-dimensional convolutional neural network model to identify clinically significant prostate cancer in transrectal ultrasound videos: a prospective, multi-institutional, diagnostic study

Background

Identifying patients with clinically significant prostate cancer (csPCa) before biopsy helps reduce unnecessary biopsies and improve patient prognosis. The diagnostic performance of traditional transrectal ultrasound (TRUS) for csPCa is relatively limited. This study was aimed to develop a high-performance convolutional neural network (CNN) model (P-Net) based on a TRUS video of the entire prostate and investigate its efficacy in identifying csPCa.

Methods

Between January 2021 and December 2022, this study prospectively evaluated 832 patients from four centres who underwent prostate biopsy and/or radical prostatectomy. All patients had a standardised TRUS video of the whole prostate. A two-dimensional CNN (2D P-Net) and three-dimensional CNN (3D P-Net) were constructed using the training cohort (559 patients) and tested on the internal validation cohort (140 patients) as well as on the external validation cohort (133 patients). The performance of 2D P-Net and 3D P-Net in predicting csPCa was assessed in terms of the area under the receiver operating characteristic curve (AUC), biopsy rate, and unnecessary biopsy rate, and compared with the TRUS 5-point Likert score system as well as multiparametric magnetic resonance imaging (mp-MRI) prostate imaging reporting and data system (PI-RADS) v2.1. Decision curve analyses (DCAs) were used to determine the net benefits associated with their use. The study is registered at https://www.chictr.org.cn with the unique identifier ChiCTR2200064545.

Findings

The diagnostic performance of 3D P-Net (AUC: 0.85-0.89) was superior to TRUS 5-point Likert score system (AUC: 0.71-0.78, P = 0.003-0.040), and similar to mp-MRI PI-RADS v2.1 score system interpreted by experienced radiologists (AUC: 0.83-0.86, P = 0.460-0.732) and 2D P-Net (AUC: 0.79-0.86, P = 0.066-0.678) in the internal and external validation cohorts. The biopsy rate decreased from 40.3% (TRUS 5-point Likert score system) and 47.6% (mp-MRI PI-RADS v2.1 score system) to 35.5% (2D P-Net) and 34.0% (3D P-Net). The unnecessary biopsy rate decreased from 38.1% (TRUS 5-point Likert score system) and 35.2% (mp-MRI PI-RADS v2.1 score system) to 32.0% (2D P-Net) and 25.8% (3D P-Net). 3D P-Net yielded the highest net benefit according to the DCAs.

Interpretation

3D P-Net based on a prostate grayscale TRUS video achieved satisfactory performance in identifying csPCa and potentially reducing unnecessary biopsies. More studies to determine how AI models better integrate into routine practice and randomized controlled trials to show the values of these models in real clinical applications are warranted.

Funding

The National Natural Science Foundation of China (Grants 82202174 and 82202153), the Science and Technology Commission of Shanghai Municipality (Grants 18441905500 and 19DZ2251100), Shanghai Municipal Health Commission (Grants 2019LJ21 and SHSLCZDZK03502), Shanghai Science and Technology Innovation Action Plan (21Y11911200), and Fundamental Research Funds for the Central Universities (ZD-11-202151), Scientific Research and Development Fund of Zhongshan Hospital of Fudan University (Grant 2022ZSQD07).

Protocol of a multicentre randomised controlled trial assessing transperineal prostate biopsy to reduce infectiouscomplications

INTRODUCTION

Approximately one million prostate biopsies are performed annually in the USA, and most are performed using a transrectal approach under local anaesthesia. The risk of postbiopsy infection is increasing due to increasing antibiotic resistance of rectal flora. Single-centre studies suggest that a clean, percutaneous transperineal approach to prostate biopsy may have a lower risk of infection. To date, there is no high-level evidence comparing transperineal versus transrectal prostate biopsy. We hypothesise that transperineal versus transrectal prostate biopsy under local anaesthesia has a significantly lower risk of infection, similar pain/discomfort levels and comparable detection of non-low-grade prostate cancer.

METHODS AND ANALYSIS

We will perform a multicentre, prospective randomised clinical trial to compare transperineal versus transrectal prostate biopsy for elevated prostate-specific antigen in the first biopsy, prior negative biopsy and active surveillance biopsy setting. Prostate MRI will be performed prior to biopsy, and targeted biopsy will be conducted for suspicious MRI lesions in addition to systematic biopsy (12 cores). Approximately 1700 men will be recruited and randomised in a 1:1 ratio to transperineal versus transrectal biopsy. A streamlined design to collect data and to determine trial eligibility along with the two-stage consent process will be used to facilitate subject recruitment and retention. The primary outcome is postbiopsy infection, and secondary outcomes include other adverse events (bleeding, urinary retention), pain/discomfort/anxiety and critically, detection of non-low-grade (grade group ≥2) prostate cancer.

ETHICS AND DISSEMINATION

The Institutional Review Board of the Biomedical Research Alliance of New York approved the research protocol (protocol number #18-02-365, approved 20 April 2020). The results of the trial will be presented at scientific conferences and published in peer-reviewed medical journals.

TRIAL REGISTRATION NUMBER

NCT04815876.

Cancer-specific outcomes for prostate cancer patients who had prebiopsy prostate MRI

PURPOSE

We characterized population-level cancer-specific outcomes for prostate cancer patients based on use of prebiopsy prostate MRI.

METHODS

Using SEER-Medicare claims, we identified men diagnosed with localized prostate cancer from 2010-2015 and prostate-specific antigen (PSA) < 20 ng/mL. Primary exposure was prebiopsy prostate MRI prior to diagnosis (i.e., CPT 72197 linked to urology-specific diagnosis). Outcomes included diagnosis of Grade Group 2+ disease on biopsy and proportion treated with prostatectomy. We assessed those treated with prostatectomy and evaluated association with prebiopsy MRI and grade concordance between biopsy and prostatectomy. We estimated adjusted odds ratios with multivariable regression after accounting for other factors (e.g., age, year, PSA, race/ethnicity).

RESULTS

We identified 48,574 patients, where 915 (1.9%) underwent prebiopsy MRI. Patients with prebiopsy MRI had more GG>2 cancer on biopsy (70.0% MRI vs. 62.8% no MRI) but lost significance after adjustment (OR 1.12, 95% CI 0.96-1.30). Patients with prebiopsy MRI were more likely to have prostatectomy (39.2% vs. 28.5%, adjusted OR 1.51, 95%CI 1.31-1.76). Downgrading from biopsy GG 3-5 to final GG 1-2 was less common after prebiopsy MRI (21.3% vs. 28.2% no MRI, P = 0.05) but not significant after adjustment (OR 0.74, 95% CI 0.51 - 1.08). Among 14,027 men with prostatectomy, accurate risk classification was not more likely with a prebiopsy MRI (48.0% no MRI vs. 49.6% prebiopsy MRI, P = 0.56).

CONCLUSION

During initial adoption, men with prebiopsy prostate MRI had marginally increased detection of significant cancer on biopsy and were more likely to be treated with prostatectomy. For those treated with prostatectomy, use of prebiopsy MRI was not associated with a greater likelihood of accurate risk classification or grade concordance between biopsy and final pathology results.

Who can safely evade a magnetic resonance imaging fusion-targeted biopsy (MRIFTB) for prostate imaging reporting and data system (PI-RADS) 3 lesion?

OBJECTIVE

To identify patients who can safely evade the magnetic resonance imaging fusion-targeted biopsy (MRIFTB) for prostate imaging reporting and data system (PI-RADS) 3 lesion.

MATERIALS AND METHODS

Overall, 755 men with PI-RADS 3-5 lesions who underwent MRIFTB were retrospectively analyzed. Univariate and multivariate analyses were performed to determine significant predictors for clinically significant prostate cancer (CSPCa), defined as Gleason grade group ≥ II. Detection rates and negative predictive values of CSPCa were estimated according to various clinical settings.

RESULTS

Median age, prostate-specific antigen (PSA), and PSA density of patients were 66.0 years, 7.39 ng/mL, and 0.19 ng/mL, respectively. Overall detection rates of CSPCa according to PI-RADS 3 (n = 347), 4 (n = 260), and 5 (n = 148) lesions were 15.0%, 30.4%, and 80.4%, respectively. The negative predictive value (NPV) of PI-RADS 3 lesion on MRI was 15.0%. On multivariate analysis, age [≥ 65 years, odds ratio (OR) = 0.427], PSA density (≥ 0.20 ng/mL², OR = 0.234), prior negative biopsy history (OR = 2.231), and PI-RADS score (4, OR = 0.427; 5, OR = 0.071) were independent predictors for the absence of CSPCa by MRIFTB. When assessed according to various conditions, NPVs of PI-RADS 3 lesions were relatively high in subgroups with low PSA density (< 0.20 ng/mL²) regardless of age or prior biopsy history (NPV range 91.1-91.9%). Contrarily, NPVs in subgroups with high PSA density were relatively low and varied according to age or prior biopsy history groups (NPV range 50.0-86.8%).

CONCLUSIONS

Men with the PI-RADS 3 lesion and low PSA density might safely evade the MRIFTB, regardless of age or prior biopsy history.