Evaluation of the accuracy of multiparametric MRI for predicting prostate cancer pathology and tumour staging in the real world: an multicentre study

Discrepancy in the Location of Prostate Cancer Indicated on Biparametric Magnetic Resonance Imaging and Pathologically Diagnosed Using Surgical Specimens

Accurate diagnosis of the localization of prostate cancer (PCa) on magnetic resonance imaging (MRI) remains a challenge. We aimed to assess discrepancy between the location of PCa pathologically diagnosed using surgical specimens and lesions indicated as possible PCa by the Prostate Imaging Reporting and Data System on MRI. The primary endpoint was the concordance rate between the site of probable clinically significant PCa (csPCa) identified using biparametric MRI (bpMRI) and location of PCa in the surgical specimen obtained using robot-assisted total prostatectomy. Among 85 lesions identified in 30 patients; 42 (49.4%) were identified as possible PCa on MRI. The 85 PCa lesions were divided into positive and negative groups based on the bpMRI results. None of the patients had missed csPCa. Although the diagnostic accuracy of bpMRI was relatively high for PCas located in the middle of the prostate (p = 0.029), it was relatively low for PCa located at the base of the prostate, all of which were csPCas. Although current modalities can accurately diagnose PCa, the possibility that PCa is present with multiple lesions in the prostate should be considered, even if MRI does not detect PCa.

Targeted multiparametric magnetic resonance imaging/transrectal ultrasound-guided (mpMRI/TRUS) fusion prostate biopsy versus systematic random prostate biopsy: A comparative real-life study

BACKGROUND

Patients with suspected prostate cancer usually undergo transrectal ultrasound-guided (TRUS) systematic biopsy, which can miss relevant prostate cancers and lead to overtreatment.

AIMS

The aim of this study was to evaluate the detection rate for prostate cancer in MR-guided targeted biopsy (TB) and systematic biopsy (SB) in comparison with mpMRI of the prostate.

METHODS AND RESULTS

Three hundred and eight men who underwent mpMRI due to elevated PSA values between 2015 and 2020 were studied at university hospital Aachen, Germany. MRI-images were divided into cohorts with suspicious findings (PI-RADS ≥ 3) and negative findings (PI-RADS < 3). In patients with PI-RADS ≥ 3 TB combined with SB was performed. A part of this group underwent RP subsequently. In patients with PI-RADS < 3 and clinical suspicion SB was performed. In the PI-RADS ≥ 3 group (n = 197), TB combined with SB was performed in 194 cases. Three cases were lost to follow-up. Biopsy yielded 143 positive biopsies and 51 cases without carcinoma. TB detected 71% (102/143) and SB 98% (140/143) of the overall 143 carcinoma. Overall, 102 carcinomas were detected by TB, hereof 66% (67/102) clinically significant (Gleason ≥ 3+4) and 34% (35/102) clinically insignificant carcinoma (Gleason 3+3). SB detected 140 carcinomas, hereof 64% (90/140) csPCA and 36% (50/140) nsPCA. Forty-one of the overall 143 detected carcinoma were only found by SB, hereof 46% (19/41) csPCA and 54% (22/41) nsPCA. Tumor locations overlapped in 44% (63/143) between TB and SB. In 25% (36/143), SB detected additional tumor foci outside the target lesions. 70/143 patients subsequently underwent RP. The detection of tumor foci was congruent between mpMRI and prostatectomy specimen in 79% (55/70) of cases. Tumor foci were mpMRI occult in 21% (15/70) of cases. In the group with negative mpMRI (n = 111), biopsy was performed in 81 cases. Gleason ≥ 3+4 carcinoma was detected in 7% and Gleason 3+3 in 24% cases.

CONCLUSION

There was a notable number of cases in which SB detected tumor foci that were mpMRI occult and could have been missed by TB alone. Therefore, additional systematic random biopsy is still required. A supplemental random biopsy should be considered depending on the overall clinical suspicion in negative mpMRI.

Oncological outcomes after attempted nerve-sparing radical prostatectomy (NSRP) in patients with high-risk prostate cancer are comparable to standard non-NSRP: a longitudinal long-term propensity-matched single-centre study

OBJECTIVE

To assess the long-term safety of nerve-sparing radical prostatectomy (NSRP) in men with high-risk prostate cancer (PCa) by comparing survival outcomes, disease recurrence, the need for additional therapy, and perioperative outcomes of patients undergoing NSRP to those having non-NSRP.

PATIENTS AND METHODS

We included consecutive patients at a single, academic centre who underwent open RP for high-risk PCa, defined as preoperative prostate-specific antigen level of > 20 ng/mL and/or postoperative International Society of Urological Pathology Grade Group 4 or 5 (i.e., Gleason score ≥ 8) and/or ≥pT3 and/or pN1 assessing the RP and lymph node specimen. We calculated a propensity score and used inverse probability of treatment weighting to match baseline characteristics of patients with high-risk PCa who underwent NSRP vs non-NSRP. We analysed oncological outcome as time-to-event and calculated hazard ratios (HRs).

RESULTS

A total of 726 patients were included in this analysis of which 84% (n = 609) underwent NSRP. There was no evidence for the positive surgical margin rate being different between the NSRP and non-NSRP groups (47% vs 49%, P = 0.64). Likewise, there was no evidence for the need for postoperative radiotherapy being different in men who underwent NSRP from those who underwent non-NSRP (HR 0.78, 95% confidence interval [CI] 0.53-1.15). NSRP did not impact the risk of any recurrence (HR 0.99, 95% CI 0.73-1.34, P = 0.09) and there was no evidence for survival being different in men who underwent NSRP to those who underwent non-NSRP (HR 0.65, 95% CI 0.39-1.08). There was also no evidence for the cancer-specific survival (HR 0.56, 95% CI 0.29-1.11) or progression-free survival (HR 0.99, 95% CI 0.73-1.34) being different between the groups.

CONCLUSION

In patients with high-risk PCa, NSRP can be attempted without compromising long-term oncological outcomes provided a comprehensive assessment of objective (e.g., T Stage) and subjective (e.g., intraoperative appraisal of tissue planes) criteria are conducted.

Functional Impact of Neuro-Vascular Bundle Preservation in High Risk Prostate Cancer without Compromising Oncological Outcomes: A Propensity-Modelled Analysis

Nerve sparing (NS) is a surgical technique to optimize functional outcomes of radical prostatectomy (RP). However, it is not recommended in high risk (HR) cases because of the risk of a positive surgical margin that may increase the risk of cancer recurrence. In the last two decades there has been a change of perspective to the effect that in well-selected cases NS could be an oncologically safe option with better functional outcomes. Therefore, we aim to compare the functional outcomes and oncological safety of NS during RP in men with HR disease. A total of 1340 patients were included in this analysis, of which 12% (n = 158) underwent non-NSRP and 39% (n = 516) and 50% (n = 666) uni- and bilateral NSRP, respectively. We calculated a propensity score and used inverse probability of treatment weighting (IPTW) to balance the baseline characteristics of Pca patients undergoing non-NSRP and those having uni- and bilateral NSRP, respectively. NS improved functional outcomes; after IPTW, only 3% of patients having non-NSRP reached complete erectile function recovery (without erectile aid) at 24 months, whereas 22% reached erectile function recovery (with erectile aid), while 87% were continent. Unilateral NS increased the probability of functional recovery in all outcomes (OR 1.1 or 1.2, respectively), bilateral NS slightly more so (OR 1.1 to 1.4). NSRP did not impact the risk of any recurrence (HR 0.99, 95%CI 0.73-1.34, p = 0.09), and there was no difference in survival for men who underwent NSRP (HR 0.65, 95%CI 0.39-1.08). There was no difference in cancer-specific survival (0.56, 95%CI 0.29-1.11). Our study found that NSRP significantly improved functional outcomes and can be safely performed in carefully selected patients with HR-PCa without compromising long term oncological outcomes.

Multiparametric MRI is not sufficient for prostate cancer staging: A single institutional experience validated by a multi-institutional regional collaborative

OBJECTIVE

Multiparametric magnetic resonance imaging (mpMRI) has been increasingly utilized in prostate cancer (CaP) diagnosis and staging. While Level 1 data supports MRI utility in CaP diagnosis, there is less data on staging utility. We sought to evaluate the real-world accuracy of mpMRI in staging localized CaP.

MATERIALS AND METHODS

Men who underwent radical prostatectomy (RP) for CaP in 2021 at our institution were identified. Sensitivity, specificity, positive predictive value and negative predictive value of mpMRI in predicting pT2N0 organ confined disease , extracapsular extension , seminal vesicle invasion , lymph node involvement, and bladder neck invasion were evaluated. Associations between MRI accuracy and AUA risk stratification (AUA RS), MRI institution (MRI-I), MRI strength (1.5 vs. 3T) (MRI-S), and MRI timing (MRI-T) were assessed. These analyses were repeated using Pennsylvania Urologic Regional Collaborative (PURC) data.

RESULTS

Institutional and community mpMRI CaP staging data demonstrated poor sensitivity (2.9%-49.2%% vs. 16.8%-24.4%), positive predictive value (40%-100% vs. 35.8%-68.2%), and negative predictive value (56.3%-94.3% vs. 68.4%-96.2%) in predicting surgical pathologic features - in contrast, specificity (89.1%-100% vs. 93.9%-98.6%) was adequate. mpMRI accuracy for extracapsular extension, seminal vesicle invasion, and lymph node involvement was significantly (p < 0.001) associated with AUA RS. There was no association between mpMRI accuracy and MRI-I, MRI-S, and MRI-T.

CONCLUSION

Despite enthusiasm for its use, in a real-world setting, mpMRI appears to be a poor staging study for localized CaP and is unreliable as the sole means of staging patients prior to prostatectomy. mpMRI should be used cautiously as a staging tool for CaP, and should be interpreted considering individual patient risk strata.

Generative Adversarial Networks Can Create High Quality Artificial Prostate Cancer Magnetic Resonance Images

The recent integration of open-source data with machine learning models, especially in the medical field, has opened new doors to studying disease progression and/or regression. However, the ability to use medical data for machine learning approaches is limited by the specificity of data for a particular medical condition. In this context, the most recent technologies, like generative adversarial networks (GANs), are being looked upon as a potential way to generate high-quality synthetic data that preserve the clinical variability of a condition. However, despite some success, GAN model usage remains largely minimal when depicting the heterogeneity of a disease such as prostate cancer. Previous studies from our group members have focused on automating the quantitative multi-parametric magnetic resonance imaging (mpMRI) using habitat risk scoring (HRS) maps on the prostate cancer patients in the BLaStM trial. In the current study, we aimed to use the images from the BLaStM trial and other sources to train the GAN models, generate synthetic images, and validate their quality. In this context, we used T2-weighted prostate MRI images as training data for Single Natural Image GANs (SinGANs) to make a generative model. A deep learning semantic segmentation pipeline trained the model to segment the prostate boundary on 2D MRI slices. Synthetic images with a high-level segmentation boundary of the prostate were filtered and used in the quality control assessment by participating scientists with varying degrees of experience (more than ten years, one year, or no experience) to work with MRI images. Results showed that the most experienced participating group correctly identified conventional vs. synthetic images with 67% accuracy, the group with one year of experience correctly identified the images with 58% accuracy, and the group with no prior experience reached 50% accuracy. Nearly half (47%) of the synthetic images were mistakenly evaluated as conventional. Interestingly, in a blinded quality assessment, a board-certified radiologist did not significantly differentiate between conventional and synthetic images in the context of the mean quality of synthetic and conventional images. Furthermore, to validate the usability of the generated synthetic images from prostate cancer MRIs, we subjected these to anomaly detection along with the original images. Importantly, the success rate of anomaly detection for quality control-approved synthetic data in phase one corresponded to that of the conventional images. In sum, this study shows promise that high-quality synthetic images from MRIs can be generated using GANs. Such an AI model may contribute significantly to various clinical applications which involve supervised machine-learning approaches.

Diagnostic Performance Evaluation of Multiparametric Magnetic Resonance Imaging in the Detection of Prostate Cancer with Supervised Machine Learning Methods

Prostate cancer is the second leading cause of cancer-related death in men. Its early and correct diagnosis is of particular importance to controlling and preventing the disease from spreading to other tissues. Artificial intelligence and machine learning have effectively detected and graded several cancers, in particular prostate cancer. The purpose of this review is to show the diagnostic performance (accuracy and area under the curve) of supervised machine learning algorithms in detecting prostate cancer using multiparametric MRI. A comparison was made between the performances of different supervised machine-learning methods. This review study was performed on the recent literature sourced from scientific citation websites such as Google Scholar, PubMed, Scopus, and Web of Science up to the end of January 2023. The findings of this review reveal that supervised machine learning techniques have good performance with high accuracy and area under the curve for prostate cancer diagnosis and prediction using multiparametric MR imaging. Among supervised machine learning methods, deep learning, random forest, and logistic regression algorithms appear to have the best performance.

Investigating PSMA-PET/CT to resolve prostate MRI PIRADS4-5 and negative biopsy discordance

BACKGROUND

To determine the utility of diagnostic 18F-DCPyL PSMA-PET/CT to aid management of men with highly suspicious multiparametric MRI prostate (PIRAD 4-5 lesions) and discrepant negative prostate biopsy.

METHODS

A multicentre prospective consecutive case series was conducted (2018-2021), recruiting men with prior mpMRI prostate PIRADS 4-5 lesions and negative prostate biopsy. All men had 18F-DCPyL PSMA-PET/CT with subsequent management based on the concordance between MRI and PET: (1) Concordant lesions were biopsied using in-bore MRI targeting; (2) PSMA-PET/CT avidity without MRI correlate were biopsied using cognitive/software targeting with ultrasound guidance and (3) Patients with negative PET/CT were returned to standard of care follow-up.

RESULTS

29 patients were recruited with 48% (n = 14) having concordant MRI/PET abnormalities. MRI targeted biopsy found prostate cancer in six patients, with grade groups GG3 (n = 1), GG2 (n = 1), GG1 (n = 4) found. Of the 20 men who PSMA-PET/CT avidity and biopsy, analysis showed higher SUVmax (20.1 vs 6.8, p = 0.036) predicted prostate cancer. Of patients who had PSMA-PET avidity without MRI correlate, and those with no PSMA-PET avidity, only one patient was subsequently found to have prostate cancer (GG1). The study is limited by small size and short follow-up of 17 months (IQR 12.5-29.9).

CONCLUSIONS

PSMA-PET/CT is useful in this group of men but requires further investigation. Avidity (higher SUVmax) that correlates to the mpMRI prostate lesion should be considered for targeted biopsy.

More than Meets the Eye: Using Textural Analysis and Artificial Intelligence as Decision Support Tools in Prostate Cancer Diagnosis—A Systematic Review

(1) Introduction: Multiparametric magnetic resonance imaging (mpMRI) is the main imagistic tool employed to assess patients suspected of harboring prostate cancer (PCa), setting the indication for targeted prostate biopsy. However, both mpMRI and targeted prostate biopsy are operator dependent. The past decade has been marked by the emerging domain of radiomics and artificial intelligence (AI), with extended application in medical diagnosis and treatment processes. (2) Aim: To present the current state of the art regarding decision support tools based on texture analysis and AI for the prediction of aggressiveness and biopsy assistance. (3) Materials and Methods: We performed literature research using PubMed MeSH, Scopus and WoS (Web of Science) databases and screened the retrieved papers using PRISMA principles. Articles that addressed PCa diagnosis and staging assisted by texture analysis and AI algorithms were included. (4) Results: 359 papers were retrieved using the keywords “prostate cancer”, “MRI”, “radiomics”, “textural analysis”, “artificial intelligence”, “computer assisted diagnosis”, out of which 35 were included in the final review. In total, 24 articles were presenting PCa diagnosis and prediction of aggressiveness, 7 addressed extracapsular extension assessment and 4 tackled computer-assisted targeted prostate biopsies. (5) Conclusions: The fusion of radiomics and AI has the potential of becoming an everyday tool in the process of diagnosis and staging of the prostate malignancies.

Prostate cancer in PI-RADS scores 1 and 2 version 2.1: a comparison to previous PI-RADS versions

PURPOSE

To evaluate the validity of PI-RADS categories 1 and 2 version 2.1 (V2.1) as predictors of the absence of carcinoma and to reevaluate lesions that were analysed as suspicious prior to PI-RADS or according to PI-RADS versions 1 and 2 and classified as PI-RADS 1 or 2 in V2.1.

METHODS

Retrospective evaluation of 1170 multiparametric MRIs performed at one academic teaching hospital (2012-2019). Study cohort comprised 188 men that achieved PI-RADS scores 1 or 2 (V2.1) and underwent systematic and targeted biopsy, split into one group with suspect findings in the original reports that were created prior to PI-RADS or with version 1 and 2, and another group with unremarkable reports. Differences in presence of prostate cancer and PSA density were assessed by Chi-square and Fisher's exact test, and the negative predictive value (NPV) for both groups was conducted.

RESULTS

The NPV for clinically significant carcinoma (csCa) was 89.1% for 55 men with suspect findings in the original report and 93.2% for 133 men with negative MRI. There was no difference between the groups regarding the detection of csCa (p = 0.103). PSA density was significantly higher in the group with suspect original reports (p = 0.015).

CONCLUSION

A PI-RADS score 1 or 2 appears less likely to miss existing prostate cancer, although a small amount of csCa can be overlooked. In case of clinical suspicion or elevated PSA density and PI-RADS score 1 or 2, an individual decision has to be taken if biopsy is necessary or if monitoring is sufficient.

Detection of hypermethylated BCAT1 and IKZF1 DNA in blood and tissues of colorectal, breast and prostate cancer patients

BACKGROUND: Detection of circulating cell-free DNA (ccfDNA) methylated in BCAT1 and IKZF1 is a sensitive for detection of colorectal cancer (CRC), but it is not known if these biomarkers are present in other common adenocarcinomas. OBJECTIVE: Compare methylation levels of BCAT1 and IKZF1 in tissue and plasma from breast, prostate, and colorectal cancer patients. METHODS: Blood was collected from 290 CRC, 32 breast and 101 prostate cancer patients, and 606 cancer-free controls. Tumor and matched normal tissues were collected at surgery: 26 breast, 9 prostate and 15 CRC. DNA methylation in BCAT1 and IKZF1 was measured in blood and tissues. RESULTS: Either biomarker was detected in blood from 175/290 (60.3%) of CRC patients. The detection rate was higher than that measured in controls (48/606 (8.1%), OR = 18.2, 95%CI: 11.1–29.0). The test positivity rates in breast and prostate cancer patients were 9.4% (3/32) and 6.9% (7/101), respectively, and not significantly different to that measured in gender-matched controls (8.0% (33/382) females (OR = 0.84, 95%CI: 0.23–3.1) and 7.6% (26/318) males (OR = 0.86, 95%CI: 0.65–2.1). In tumor and non-neoplastic tissues, 93.5% (14/15) of CRC tumors were methylated in BCAT1 and/or IKZF1 (p< 0.004). Only 11.5% (3/26) and 44.4% (4/9) (p= 0.083) of breast and prostate tumors were hypermethylated in these two genes. CONCLUSIONS: Detection of circulating DNA methylated in BCAT1 and IKZF1 is sensitive and specific for CRC but not breast or prostate cancer.

The impact of health‐policy‐driven subsidisation of prostate magnetic resonance imaging on transperineal prostate biopsy practice and outcomes

Background

From 1 July 2018, the Australian Medicare Benefits Schedule (MBS) introduced rebates for multi‐parametric magnetic resonance imaging (mpMRI) for the workup for prostate cancer (PCa). We aimed to determine if subsidisation of mpMRI prior to transperineal biopsy altered our institution's prostate biopsy practice patterns and outcomes.

Methods

All patients who underwent transperineal prostate biopsy at an Australian tertiary institution from 1 January 2017 to 1 January 2020 were identified. Patients with known PCa were excluded. Patients were stratified into two groups: a pre‐subsidisation cohort comprising patients biopsied prior to the introduction of mpMRI subsidisation on 1 July 2018 and a post‐subsidisation cohort comprising patients biopsied after 1 July 2018. Histopathological results were compared with further stratification based on mpMRI results. Clinically significant cancer was defined as ISUP Grade Group ≥ 2.

Results

Six hundred and fifty men fulfilled the inclusion criteria. Three hundred and sixty‐one patients were in the pre‐subsidisation cohort and 289 in the post‐subsidisation cohort. Of the patients in the pre‐subsidisation group, 36.3% underwent a pre‐biopsy mpMRI compared with 77.5% in the post‐subsidisation group. Of the patients in the pre‐subsidisation group, 59.6% had positive biopsies (p = 0.024) compared with 68.2% in the post‐subsidisation group. The rate of clinically significant PCa was lower in the pre‐subsidisation group (39.1%) compared with the post‐subsidisation (49.5%, p = 0.008). The negative predictive value of mpMRI for clinically significant PCa was 86.5%.

Conclusion

Our institution experienced a reduction of negative prostate biopsies and an increase in clinically significant PCa within transperineal biopsy specimens after the Australian healthcare system introduced financial subsidisation of mpMRI.

Use of high-resolution micro-ultrasound to predict extraprostatic extension of prostate cancer prior to surgery: a prospective single-institutional study

PURPOSE

We aim to evaluate the accuracy of micro-ultrasound (microUS) in predicting extraprostatic extension (EPE) of Prostate Cancer (PCa) prior to surgery.

METHODS

Patients with biopsy-proven PCa scheduled for robot-assisted radical prostatectomy (RARP) were prospectively recruited. The following MRI-derived microUS features were evaluated: capsular bulging, visible breach of the prostate capsule (visible extracapsular extension; ECE), presence of hypoechoic halo, and obliteration of the vesicle-prostatic angle. The ability of each feature to predict EPE was determined.

RESULTS

Overall, data from 140 patients were examined. All predictors were associated with non-organ-confined disease (p < 0.001). Final pathology showed that 79 patients (56.4%) had a pT2 disease and 61 (43.3%) ≥ pT3. Rate of non-organ-confined disease increased from 44% in those individuals with only 1 predictor (OR 7.71) to 92.3% in those where 4 predictors (OR 72.00) were simultaneously observed. The multivariate logistic regression model including clinical parameters showed an area under the curve (AUC) of 82.3% as compared to an AUC of 87.6% for the model including both clinical and microUS parameters. Presence of ECE at microUS predicted EPE with a sensitivity of 72.1% and a specificity of 88%, a negative predictive value of 80.5% and positive predictive value of 83.0%, with an AUC of 80.4%.

CONCLUSIONS

MicroUS can accurately predict EPE at the final pathology report in patients scheduled for RARP.

The use of 29 MHz transrectal micro-ultrasound to stratify the prostate cancer risk in patients with PI-RADS III lesions at multiparametric MRI: A single institutional analysis

INTRODUCTION

Magnetic Resonance Imaging (MRI) has emerged as the most accurate diagnostic tool, showing a high sensitivity in the diagnosis of clinically significant prostate cancer (csCaP). However only a minority of patients with a PI-RADS 3 lesion at multiparametric magnetic resonance imaging (MRI) are diagnosed with csCaP. The aim of the current study was to assess whether high resolution micro-ultrasound (microUS) could help in sub-stratifying the risk of csCaP in this specific population.

MATERIAL AND METHODS

We retrospectively analyzed the records of 111 consecutive patients scheduled for a prostate biopsy with at least 1 PI-RADS 3 lesions at MRI. We excluded patients with a PIRADS >3 lesion, even if they had a coexisting PIRADS 3 lesions. MicroUS was performed in all patients before prostate biopsy by an operator blind to MRI results. The Prostate Risk Identification using MicroUS (PRI-MUS) protocol was used to assess the risk of CaP and csCaP. All patients received both targeted and systematic biopsies. The primary endpoint was to determine the diagnostic accuracy of microUS in detection of csCaP in patients with a PI-RADS 3 lesion at MRI. Specifically, sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV) of microUS were determined. Multivariable logistic regression models (MLRMs) were fitted to identify predictors of CaP. The diagnostic accuracy was reported as area under the receiver operator characteristic (ROC) curve.

RESULTS

Overall, 43 patients (38.7%) harboured CaP and 22 (20%) csCaP. MicroUS showed a high sensitivity and negative predictive value (100%), while its specificity and positive predictive value were 33.7% and 27.2%, respectively. Among patients without lesions at microUS, 25 (83.3%) did not harbour CaP, while 5 (16.7%) patients were diagnosed with a Gleason score 6 CaP, with no patients harbouring csCaP. Using microUS, the csCaP detection would have remained 100%, while reducing the detection of insignificant CaP of a 23.8% extent (n = 5). In MLRMs, lesion identified at microUS and continuously-coded PSAd were independent predictors of CaP. The accuracy of a model including PRI-MUS score, digital rectal examination (DRE), PSA density, age and family history was 0.744 (95% CI: 0.645 - 0.843).

CONCLUSION

In our single-institutional retrospective study, microUS was potentially capable to stratify the presence of CaP in patients with an equivocal MRI. Further prospective studies on larger populations are needed to validate our results.

Artificial intelligence is a promising prospect for the detection of prostate cancer extracapsular extension with mpMRI: a two-center comparative study

PURPOSE

A balance between preserving urinary continence as well as sexual potency and achieving negative surgical margins is of clinical relevance while implementary difficulty. Accurate detection of extracapsular extension (ECE) of prostate cancer (PCa) is thus crucial for determining appropriate treatment options. We aimed to develop and validate an artificial intelligence (AI)-based tool for detecting ECE of PCa using multiparametric magnetic resonance imaging (mpMRI).

METHODS

Eight hundred and forty nine consecutive PCa patients who underwent mpMRI and prostatectomy without previous radio- or hormonal therapy from two medical centers were retrospectively included. The AI tool was built on a ResNeXt network embedded with a spatial attention map of experts' prior knowledge (PAGNet) from 596 training patients. Model validation was performed in 150 internal and 103 external patients. Performance comparison was made between AI, two experts using a criteria-based ECE grading system, and expert-AI interaction.

RESULTS

An index PAGNet model using a single-slice image yielded the highest areas under the receiver operating characteristic curve (AUC) of 0.857 (95% confidence interval [CI], 0.827-0.884), 0.807 (95% CI, 0.735-0.867), and 0.728 (95% CI, 0.631-0.811) in training, internal, and external validation data, respectively. The performance of two experts (AUC, 0.632 to 0.741 vs 0.715 to 0.857) was lower (paired comparison, all p values < 0.05) than that of AI assessment. When experts' interpretations were adjusted by AI assessments, the performance of two experts was improved.

CONCLUSION

Our AI tool, showing improved accuracy, offers a promising alternative to human experts for ECE staging using mpMRI.

The diagnostic accuracy of multiparametric MRI for detection and localization of prostate cancer depends on the affected region

Objectives

To determine the diagnostic accuracy of 3T multiparametric magnetic resonance imaging (mpMRI) for detecting and locating prostate cancer (PCa) on Dickinson's 27‐sector map, using histopathology specimens from radical prostatectomy (RP) as the reference standard.

Patients and methods

The authors studied a continuous series of 140 patients who underwent RP over three consecutive years. Prior to RP, all patients had mpMRI for detection and localization of PCa and further assessment by biopsy. To minimize the potential of disease progression, 25 patients were excluded because the interval between mpMRI and RP exceeded 6 months, which left 115 patients eligible for analysis. The mpMRI findings were reported using the Prostate Imaging‐Reporting and Data System (PI‐RADS) v2, considering PI‐RADS ≥ 3 to indicate PCa. The histopathology findings from RP specimens were graded using the Gleason scoring system, considering Gleason ≥ 6 to indicate PCa. The location of the tumors was mapped on Dickinson's 27‐sector map for both mpMRI and histopathology and compared by rigid sector‐by‐sector matching.

Results

The cohort of 115 patients eligible for analysis was aged 66.5 ± 6.0 years at RP. Of the 3105 sectors analyzed, there were 412 true positives (13%), 28 false positives (1%), 68 false negatives (2%), and 2597 true negatives (84%). Across the 27 sectors of the prostate, mpMRI sensitivity ranged from 50% to 100% and specificity from 96% to 100%, while PPV ranged from 50% to 100%, and NPV from 91% to 100%. For the anterior prostate, mpMRI had a sensitivity of 80% (CI, 71%‐86%), specificity of 99% (CI, 99%‐100%), PPV of 91% (CI, 83%‐95%), and NPV of 99% (CI, 98%‐99%). For the posterior prostate, mpMRI had a sensitivity of 88% (CI, 84%‐91%), specificity of 98% (CI, 97%‐99%), PPV of 94% (CI, 92%‐96%), and NPV of 96% (CI, 94%‐97%). Overall, mpMRI had a sensitivity of 86%, specificity of 99%, PPV of 94%, and NPV of 97%.

Conclusions

The accuracy of mpMRI in detecting and locating prostate tumors depends on the affected region, but its high NPV across all sectors suggests that negative findings may not need corroboration by other techniques.

Multiparametric MRI with in-bore targeted biopsy in the diagnostic pathway of prostate cancer: Data from a single institution experience

BACKGROUND

Accuracy of multiparametric MRI (mpMRI) for the detection of significant prostate cancer (CaP) varies in the literature as only few studies use radical prostatectomy specimens as their gold standard. On another hand, MRI-targeted prostate biopsy is emerging as an alternative to the traditional randomized biopsy, with a higher detection rate of high-grade cancers. However, data on MRI guided in bore biopsy is lacking.

MATERIAL AND METHODS

We reviewed every patient that had his mpMRI, MRI guided in bore biopsy and radical prostatectomy performed in our hospital between November 2015 and December 2020. The diagnostic performances of both mpMRI and MRI targeted biopsy in sampling PIRADS index lesions were studied, using radical prostatectomy specimens as the gold standard. Sensitivity, specificity, positive predictive value and negative predictive value of mpMRI for detecting T3 stage, extra-capsular extension, seminal vesicles involvement and lymph node disease were also evaluated.

RESULTS

Sixty-two met our inclusion criteria. For PIRADS≥3 lesions, sensitivity and positive predictive value for detecting clinically significant CaP were of 83.5% and 94.7%. A total of 32.2% prostate cancers on targeted biopsy were upgraded on final pathology, with an upgrading to ISUP≥2 in 3.2% and to ISUP≥3 in 14.5%. A total of 20.9% of cancers were downgraded but without any downgrading to ISUP 1. When final pathology is taken as a gold standard, sensitivity of mpMRI was 31.8% for T3 staging prediction, 30.0% for extra-capsular extension, 28.7% for seminal vesicles involvement and 66.7% for lymph node disease prediction. Specificity was 89.3%, 93.1%, 95.3%, and 92.7%, respectively.

CONCLUSION

mpMRI has an acceptable accuracy for the prediction of significant CaP and index lesion detection but is unreliable for CaP staging. Comparison between pathology and biopsy results revealed that the in-bore biopsy technique has an upgrading and downgrading rate comparable in the literature to fusion biopsy, but higher than the combined biopsy approach.

Predictive clinical features for negative histopathology of MRI/Ultrasound-fusion-guided prostate biopsy in patients with high likelihood of cancer at prostate MRI: Analysis from a urologic outpatient clinic1

OBJECTIVE

The aim of this study was to evaluate clinical features associated with benign histopathology of Prostate Imaging Reporting and Data System (PI-RADS) category 4 and 5 lesions.

MATERIALS AND METHODS

Between March 2015 and November 2020, 1161 patients underwent mpMRI/Ultrasound-fusion-guided prostate biopsy (FBx) and concurrent 12-core systematic prostate biopsy (SBx) at the Department of Urology of the Ludwig-Maximilians-University of Munich, Germany. 848/ 1161 (73%) patients presented with either PI-RADS 4 or 5 index lesion and were retrospectively evaluated. Multivariate analysis was performed to evaluate clinical parameters associated with a negative outcome of PI-RADS 4 or 5 category lesions after FBx. Area under the receiver operating characteristics (ROC) curve (AUC) was conducted using ROC-analysis.

RESULTS

676/848 (79.7%) patients with either PI-RADS 4 or 5 index lesion were diagnosed with prostate cancer (PCa) by FBx and 172/848 (20.3%) patients had a negative biopsy (including the concurrent systematic prostate biopsy), respectively. Prostate volume (P-Vol) (OR 0.99, 95% CI = 0.98-1.00, p = 0.038), pre-biopsy-status (OR 0.48, 95% CI = 0.29-0.79, p = 0.004) and localization of the lesion in the transitional zone (OR 0.28, 95% CI = 0.13-0.60, p = 0.001) were independent risk factors for a negative outcome of FBx. Age (OR 1.09, 95% CI = 1.05-1.13, p < 0.001) and PSA density (PSAD) (OR 75.92, 95% CI = 1.03-5584.61, p = 0.048) increased the risk for PCa diagnosis after FBx. The multivariate logistic regression model combining all clinical characteristics achieved an AUC of 0.802 (95% CI = 0.765-0.835; p < 0.001) with a sensitivity and specificity of 66% and 85%.

CONCLUSION

Lesions with high or highly likelihood of PCa on multiparametric magnetic resonance imaging (mpMRI) but subsequent negative prostate biopsy occur in a small amount of patients. Localization of the lesion in the transitional zone, prostate volume and prebiopsy were shown to be predictors for benign histopathology of category 4 or 5 lesions on mpMRI. Integration of these features into daily clinical routine could be used for risk-stratification of these patients after negative biopsy of PI-RADS 4 or 5 index lesions.

The role of multiparametric resonance and biopsy in prostate cancer detection: comparison with definitive histological report after laparoscopic/robotic radical prostatectomy

Purpose

Magnetic Resonance Imaging (MRI) targeted biopsy increases overall detection rates and decreases the risk of clinically insignificant PCa detection. The aim of this retrospective study is to compare concordance rates regarding side of lesion and Gleason Score at fusion targeted/systematic biopsy and MRI with the definitive histologic report of prostatectomy specimen.

Methods

115 patients underwent multiparametric (mp) MRI and successively fusion targeted/systematic biopsy. 107 patients, with a positive biopsy for PCa, further underwent laparoscopic/robotic radical prostatectomy. We compared surgical histologic report with biopsy histologic report for side of lesion and Gleason Score. We further compared PIRADS score at mpMRI with Gleason Score of both histologic reports.

Results

Concordance rate for mpMRI lesion side was 74% compared to biopsy and 52.3% compared to surgical histologic report (p < 0.0001). Fusion targeted/systematic biopsy reported a concordance rate with surgical histologic report of 67.3% for side of the lesion, while Gleason Score was concordant for 73.6% for clinically significant cancer (Gleason Score ≥ 7) (p < 0.0001). PIRADS score ≥ 3 was further associated with clinically significant cancer at surgical histologic report in 92.4% of cases (p = 0.359).

Conclusion

Multiparametric MRI of the prostate reaches a good and improvable accuracy in the detection of suspicious PCa before biopsy. A combined approach of fusion targeted and systematic biopsy could further increase the overall accuracy in PCa diagnosis, especially in biopsy-naïve patients, reaching concordance rates with definitive histologic report up to 52.3% and 85.5%.

Funding of prostate magnetic resonance imaging leads to fewer biopsies and potential savings to health systems in the management of prostate cancer

OBJECTIVES

To assess the impact of the introduction of multiparametric magnetic resonance imaging of the prostate (mpMRIp) on the number of prostate biopsies performed in Australia.

METHODS

Australian Medicare published statistics from 1 July 2007 to 30 June 2019 were obtained from publically available databases for prostate-specific antigen (PSA) testing, prostate biopsy, and mpMRIp. Analysis was divided into three time periods broadly based on availability of mpMRI to the Australian public: 2007-2012 (no mpMRIp), 2012-2018 (mpMRIp available, privately funded), and 2018-2019 (mpMRIp available with Medicare funding). Introduction of mpMRIp was hypothesised to reduce the number of prostate biopsies performed. PSA testing numbers were used as a control. The economics model, proposed by the Medical Services Advisory Committee (MSAC), was analysed for cost savings.

RESULTS

Accounting for variations in PSA testing, the introduction of mpMRIp from 2012 coincided with a reduction in the number of prostate biopsies by an average of 354.7/month (95% CI 175, 534.4; P < 0.001). Whilst the number of mpMRIp performed for the initial 12 months was underestimated by the MSAC at 38 470 vs 20 149 (+$8.3 million Australian dollars), we estimate the annual savings from reduced number biopsies and biopsy-associated complications to be $13.2 ± 9.6 million.

CONCLUSION

Availability of mpMRIp in Australia has correlated with a significant reduction in prostate biopsy rates, with an estimated annual saving of $13.2 ± 9.6 million. Government funding of this diagnostic service has the potential to improve health equity and save on health expenditure.