Prostate Imaging Reporting Research Articles

MP40-17 CLINICAL AND HIGH-RESOLUTION MICRO-ULTRASOUND RISK FACTORS FOR DETECTING CLINICALLY SIGNIFICANT PROSTATE CANCER IN MEN WITH PI-RADS 3 LESIONS: UPDATE FROM A LARGE SINGLE CENTER EXPERIENCE

You have accessJournal of UrologyCME1 Apr 2023MP40-17 CLINICAL AND HIGH-RESOLUTION MICRO-ULTRASOUND RISK FACTORS FOR DETECTING CLINICALLY SIGNIFICANT PROSTATE CANCER IN MEN WITH PI-RADS 3 LESIONS: UPDATE FROM A LARGE SINGLE CENTER EXPERIENCE Pier Paolo Avolio, Vittorio Fasulo, Davide Maffei, Cesare Saitta, Fabio De Carne, Nicola Frego, Marco Paciotti, Massimo Lazzeri, Rodolfo Hurle, Alberto Saita, Paolo Casale, Nicolò Maria Buffi, and Giovanni Lughezzani Pier Paolo AvolioPier Paolo Avolio More articles by this author , Vittorio FasuloVittorio Fasulo More articles by this author , Davide MaffeiDavide Maffei More articles by this author , Cesare SaittaCesare Saitta More articles by this author , Fabio De CarneFabio De Carne More articles by this author , Nicola FregoNicola Frego More articles by this author , Marco PaciottiMarco Paciotti More articles by this author , Massimo LazzeriMassimo Lazzeri More articles by this author , Rodolfo HurleRodolfo Hurle More articles by this author , Alberto SaitaAlberto Saita More articles by this author , Paolo CasalePaolo Casale More articles by this author , Nicolò Maria BuffiNicolò Maria Buffi More articles by this author , and Giovanni LughezzaniGiovanni Lughezzani More articles by this author View All Author Informationhttps://doi.org/10.1097/JU.0000000000003278.17AboutPDF ToolsAdd to favoritesDownload CitationsTrack CitationsPermissionsReprints ShareFacebookLinked InTwitterEmail Abstract INTRODUCTION AND OBJECTIVE: Multiparametric magnetic resonance imaging (mpMRI) is an invaluable diagnostic tool in prostate biopsies (PBx) decision making. However, most Prostate Imaging–Reporting and Data System (PI-RADS) 3 lesions do not contain clinically significant prostate cancer (CSPCa; grade group ≥2). This study is an update of a previous study aimed to investigate clinical and high-resolution micro-ultrasound (microUS) derived risk factors that predict CSPCa in men with PI-RADS 3 lesions. METHODS: A total of 200 patients who underwent microUS-guided PBx with the ExactVu system for a PI-RADS 3 lesion were prospectively enrolled between October 2017 and September 2022. The Prostate Risk Identification using microUS (PRI-MUS) protocol was used to identify suspicious areas; PBx included targeted and systematic sampling. The primary endpoint was the assessment of microUS diagnostic accuracy in detecting csPCa. Secondary endpoints included determining: the proportion of patients with a PIRADS 3 lesion who may avoid PBx after microUS examination; predictors of csPCa in patients presenting with PI-RADS 3 lesions. RESULTS: Median patient age was 64 (IQR 58–69) years, median total PSA was 6 (IQR 4.5–8.4) ng/mL and median prostate volume was 51.6 (IQR 35–73.7) mL. Overall, 91 (45.5%) patients were in the repeat biopsy setting. Micro-US detected prostate lesions with a PRI-MUS score of 3, 4 and 5 in respectively 47 (35.3%), 63 (47.4%) and 23 (17.3%) patients, while in 67 (33.5%) individuals micro-US did not identify any target. Overall, 44 (22.0%) harbored csPCa. Considering csPCa detection rate, microUS showed optimal sensitivity and negative predictive value (respectively 95.4% and 97.0%), while specificity and positive predictive value were 41.6% and 31.6%, respectively. 65 (32.5%) patients with negative microUS examination could have avoided PBx with 2 (4.5%) missed csPCa. In multivariable logistic regression models (MLRMs), positive microUS, age, and PSA density ≥0.15 emerged as independent predictors of PCa. The accuracy of a model including PRI-MUS score, age, PSA density, family history and previous biopsies was 0.764 (95% CI: 0.673−0.854). CONCLUSIONS: Our update findings confirm that MicroUS could represent a helpful tool capable of discriminating patients harbouring csPCa among subjects with PI-RADS 3 lesion. Further studies are still needed to corroborate our findings and to better establish the role of this promising strategy within the diagnostic work up of PCa patients. Source of Funding: None © 2023 by American Urological Association Education and Research, Inc.FiguresReferencesRelatedDetails Volume 209Issue Supplement 4April 2023Page: e551 Advertisement Copyright & Permissions© 2023 by American Urological Association Education and Research, Inc.MetricsAuthor Information Pier Paolo Avolio More articles by this author Vittorio Fasulo More articles by this author Davide Maffei More articles by this author Cesare Saitta More articles by this author Fabio De Carne More articles by this author Nicola Frego More articles by this author Marco Paciotti More articles by this author Massimo Lazzeri More articles by this author Rodolfo Hurle More articles by this author Alberto Saita More articles by this author Paolo Casale More articles by this author Nicolò Maria Buffi More articles by this author Giovanni Lughezzani More articles by this author Expand All Advertisement PDF downloadLoading ...

V10-08 THE USE OF FOCAL IRREVERSIBLE ELECTROPORATION FOR PROSTATE CANCER

You have accessJournal of UrologyCME1 Apr 2023V10-08 THE USE OF FOCAL IRREVERSIBLE ELECTROPORATION FOR PROSTATE CANCER John Torosyan, Amy Cherry, Hasan Abbas, Shima Tayebi, and Abhinav Sidana John TorosyanJohn Torosyan More articles by this author , Amy CherryAmy Cherry More articles by this author , Hasan AbbasHasan Abbas More articles by this author , Shima TayebiShima Tayebi More articles by this author , and Abhinav SidanaAbhinav Sidana More articles by this author View All Author Informationhttps://doi.org/10.1097/JU.0000000000003328.08AboutPDF ToolsAdd to favoritesDownload CitationsTrack CitationsPermissionsReprints ShareFacebookLinked InTwitterEmail Abstract INTRODUCTION AND OBJECTIVE: Focal therapy of prostate cancer is a treatment strategy that aims to destroy the cancer-containing parts of the prostate while preserving uninvolved prostatic tissue in an attempt to preserve genitourinary function. Irreversible Electroporation (IRE) is a novel ablative modality which utilizes electrical pulses to induce cell apoptosis and can be applied to various malignancies, including prostate cancer. The objective of this video is to discuss the mechanism of action of IRE and describe the components, setup, and operative technique for performing IRE for the focal treatment of prostate cancer. METHODS: IRE is performed under general anesthesia with the patient placed in lithotomy position. Monopolar electrodes are inserted into the prostate under ultrasound guidance and using a brachytherapy grid. The probes are placed 1.5 to 2cm away from one another, and 3-5mm away from the prostatic capsule using cognitive fusion to cover the lesion and 5-10mm margin. After initially estimating voltage configurations, ten test impulses are fired between each probe pair to assess resulting currents. Using test results, final voltages are assigned, and the remaining 80 impulses are fired between each probe pair. RESULTS: This case involves a 74-year-old male with a history of hypertension and hyperlipidemia who presented with an elevated Prostate-Specific Antigen (PSA) of 6.35 and was found to have Gleason 3+4 cancer in the Prostate Imaging Reporting & Data System (PI-RADS) 4 lesion localized in the right mid gland to apex. The patient had a pre-treatment International Prostate Symptom Score (IPSS) of 4-1 and a Sexual Health Inventory for Men (SHIM) of 18 without the use of erectile dysfunction medication. The patient underwent a successful IRE ablation of the lesion along with the margin. The procedure was tolerated well, and the patient was discharged later that day. At his 6-week follow-up, PSA declined to 0.66 and he had an unchanged IPSS/SHIM. CONCLUSIONS: The use of focal therapy in prostate cancer is promising because of its effectiveness paired with minimal procedural side effects. Focal IRE provides a safe and effective way to achieve focal therapy of prostate cancer. Source of Funding: None. © 2023 by American Urological Association Education and Research, Inc.FiguresReferencesRelatedDetails Volume 209Issue Supplement 4April 2023Page: e928 Advertisement Copyright & Permissions© 2023 by American Urological Association Education and Research, Inc.MetricsAuthor Information John Torosyan More articles by this author Amy Cherry More articles by this author Hasan Abbas More articles by this author Shima Tayebi More articles by this author Abhinav Sidana More articles by this author Expand All Advertisement PDF downloadLoading ...

MP55-20 A NOVEL MACHINE LEARNING FRAMEWORK FOR AUTOMATED DETECTION OF PROSTATE CANCER LESIONS CONFIRMED ON MRI-INFORMED TARGET BIOPSY

MP55-20 A NOVEL MACHINE LEARNING FRAMEWORK FOR AUTOMATED DETECTION OF PROSTATE CANCER LESIONS CONFIRMED ON MRI-INFORMED TARGET BIOPSY

MP40-20 CAN WE PREDICT FOR MISSED CLINICALLY SIGNIFICANT PROSTATE CANCERS ON MRI-TARGETED BIOPSY ALONE?

You have accessJournal of UrologyCME1 Apr 2023MP40-20 CAN WE PREDICT FOR MISSED CLINICALLY SIGNIFICANT PROSTATE CANCERS ON MRI-TARGETED BIOPSY ALONE? Woon Chau Tsang, Kaiying Wang, Abner Quek, Ziting Wang, Edmund Chiong, and Qinghui Wu Woon Chau TsangWoon Chau Tsang More articles by this author , Kaiying WangKaiying Wang More articles by this author , Abner QuekAbner Quek More articles by this author , Ziting WangZiting Wang More articles by this author , Edmund ChiongEdmund Chiong More articles by this author , and Qinghui WuQinghui Wu More articles by this author View All Author Informationhttps://doi.org/10.1097/JU.0000000000003278.20AboutPDF ToolsAdd to favoritesDownload CitationsTrack CitationsPermissionsReprints ShareFacebookLinked InTwitterEmail Abstract INTRODUCTION AND OBJECTIVE: MRI-Targeted prostate biopsy (TBx) strategy has been shown to diagnose more clinically significant prostate cancer (csPCa) and less clinically insignificant prostate cancer (ciPCa). Currently, the yield of systematic or saturation biopsy in addition to TBx remains remain unclear. This study aims to evaluate for factors that may predict for csPCa that are missed on TBx alone. METHODS: From 2015 to 2022, we collected prospective single-centre data of consecutive patients who underwent prostate biopsy. We included patients who were biopsy-naïve, had prior negative biopsies, or were on active surveillance for low risk prostate cancer. mpMRI-ultrasound fusion-guided robotic-assisted TBx was performed for every lesion of Prostate Imaging Reporting and Data System (PIRADS) 3 and above, and every patient additionally received saturation biopsy (SBx). Patient data, MRI lesion characteristics, PIRADS score and biopsy results were evaluated. csPCa was defined as ISUP grade group 2 and above. RESULTS: 499 men underwent combined TBx and SBx. The median serum PSA was 7.31ug/L. The overall cancer detection rate was 65.7%, where csPCa rate was 45.1%. The overall cancer and csPCa rates for TBx only vs TBx plus SBx, was 52.9% vs 65.7% (p<0.01), and 39.9% vs 45.1% (p=0.10) respectively. If only TBx was performed, 19.5% of all cancers and 11.5% of csPCa would have been missed. Patients with missed csPCa on TBx only had lower PSA (7.75 vs 10.6, p<0.01), higher prostate volume (59.5 vs 42.9cc, p=0.04), and lower PSA density (0.164 vs 0.271, p<0.01). They also had lower prostate health index (PHI) score (50.6 vs 61.9, p=0.04), although PHI density was similar (1.22 vs 1.56, p=0.09). A smaller index lesion diameter was also predictive of missed csPCa on TBx (8.70 vs 12.2 mm, p<0.01). Patients with PIRADS 3 index lesions were more likely to have missed csPCa on TBx than PIRADS 4 and 5, with a missed csPCa rate of 25.8% vs 11.8% vs 3.45% (p<0.01) respectively. Age, number of lesions on mpMRI, and indication for biopsy were not predictive of missed csPCa. CONCLUSIONS: In our series, TBx alone strategy can miss 11.5% of csPCa. Factors predictive of missed csPCa include initial low PSA level, larger prostate volume, low PSA density, low PHI, small index lesion diameter and lower PIRADS score of the index lesion. A nomogram is created to aid decision making on patient selection to omit systematic biopsy when performing TBx. Source of Funding: None © 2023 by American Urological Association Education and Research, Inc.FiguresReferencesRelatedDetails Volume 209Issue Supplement 4April 2023Page: e553 Advertisement Copyright & Permissions© 2023 by American Urological Association Education and Research, Inc.MetricsAuthor Information Woon Chau Tsang More articles by this author Kaiying Wang More articles by this author Abner Quek More articles by this author Ziting Wang More articles by this author Edmund Chiong More articles by this author Qinghui Wu More articles by this author Expand All Advertisement PDF downloadLoading ...

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

You have accessJournal of UrologyCME1 Apr 2023MP55-18 A NOVEL MACHINE LEARNING FRAMEWORK TO AUTOMATED CHARACTERIZE PROSTATE IMAGING REPORTING AND DATA SYSTEM (PIRADS) ON MRI Giovanni e. Cacciamani, masatomo kaneko, yijing yang, vasileios magoulianitis, jintang xue, jiaxin yang, jinyuan liu, maria sarah L. Lenon, Passant Mohamed, Darryl H. Hwang, karan gill, Manju Aron, Vinay Duddalwar, Suzanne L. Palmer, C.-C. Jay Kuo, Inderbir Gill, Andre Luis Abreu, and Chrysostomos L. Nikias Giovanni e. CacciamaniGiovanni e. Cacciamani More articles by this author , masatomo kaneko masatomo kaneko More articles by this author , yijing yang yijing yang More articles by this author , vasileios magoulianitis vasileios magoulianitis More articles by this author , jintang xue jintang xue More articles by this author , jiaxin yang jiaxin yang More articles by this author , jinyuan liu jinyuan liu More articles by this author , maria sarah L. Lenon maria sarah L. Lenon More articles by this author , Passant MohamedPassant Mohamed More articles by this author , Darryl H. HwangDarryl H. Hwang More articles by this author , karan gill karan gill More articles by this author , Manju AronManju Aron More articles by this author , Vinay DuddalwarVinay Duddalwar More articles by this author , Suzanne L. PalmerSuzanne L. Palmer More articles by this author , C.-C. Jay KuoC.-C. Jay Kuo More articles by this author , Inderbir GillInderbir Gill More articles by this author , Andre Luis AbreuAndre Luis Abreu More articles by this author , and Chrysostomos L. NikiasChrysostomos L. Nikias More articles by this author View All Author Informationhttps://doi.org/10.1097/JU.0000000000003308.18AboutPDF ToolsAdd to favoritesDownload CitationsTrack CitationsPermissionsReprints ShareFacebookLinked InTwitterEmail Abstract INTRODUCTION AND OBJECTIVE: To develop an automated machine learning model to characterize Prostate Imaging Reporting and Data System (PIRADS) lesions using biparametric (bp) magnetic resonance imaging (MRI). METHODS: Consecutive men who underwent 3T prostate MRI (T2-weighted [T2WI], diffusion-weighted images [DWI], and apparent diffusion coefficient [ADC]) followed by prostate biopsy (PBx) were identified from a PBx database (IRB# HS-13-00663). MRI were acquired and interpreted according to PIRADS v2 or v2.1 by experienced radiologists. The PIRADS 3-5 lesions were manually segmented on T2WI, high-b-value (b≥1000) DWI, and ADC. Men with single lesion (PIRADS≥3) were included. A novel Green Learning framework with a lightweight model and explainable feature extraction process was used (Figure 1). A data-driven automatic and unsupervised process, namely IP-HOPII, by cascading layers of local-to-global Principal Component Analysis on the input voxels was applied. A spatial-spectral representation was derived of the region of interest. Then a feature selection module was employed to filter out the noisy spectral dimensions. Finally, the best features were fed to the Extreme Gradient Boosting classifier. The performances of classifying PIRADS were assessed by concordance rate for three-class classification and receiver operating characteristic (ROC) analysis for binary classification. The sensitivity and specificity were determined at the Youden index. RESULTS: Overall, 259 patients (205 for training and 54 for validation) with single lesion were included: PIRADS 3, 4, and 5, were 152 (59%), 70 (27%), and 37 (14%), respectively. The concordance rate between PIRADS and the model was 60% for PZ and 67% for TZ lesions. For the PZ, the area under the ROC curve (AUC) to characterize PIRADS were 0.73 for 3 vs 4-5, and 0.76 for 3-4 vs 5, respectively. The sensitivity and specificity were 75% and 69% to classify PIRADS≥4 lesions, and 78% and 71% for PIRADS 5 lesions. For the TZ, the AUC for the model was 0.69 for PIRADS 3 vs 4-5, and 0.64 for PIRADS 3-4 vs 5, respectively. The sensitivity and specificity were 62% and 73% to classify PIRADS≥4 lesions, and 60% and 59% for PIRADS 5 lesions. CONCLUSIONS: Machine learning model following the Green Learning paradigm can accurately characterize lesions on prostate bpMRI. Source of Funding: None. © 2023 by American Urological Association Education and Research, Inc.FiguresReferencesRelatedDetails Volume 209Issue Supplement 4April 2023Page: e771 Advertisement Copyright & Permissions© 2023 by American Urological Association Education and Research, Inc.MetricsAuthor Information Giovanni e. Cacciamani More articles by this author masatomo kaneko More articles by this author yijing yang More articles by this author vasileios magoulianitis More articles by this author jintang xue More articles by this author jiaxin yang More articles by this author jinyuan liu More articles by this author maria sarah L. Lenon More articles by this author Passant Mohamed More articles by this author Darryl H. Hwang More articles by this author karan gill More articles by this author Manju Aron More articles by this author Vinay Duddalwar More articles by this author Suzanne L. Palmer More articles by this author C.-C. Jay Kuo More articles by this author Inderbir Gill More articles by this author Andre Luis Abreu More articles by this author Chrysostomos L. Nikias More articles by this author Expand All Advertisement PDF downloadLoading ...

MP09-05 AUTOMATED PROSTATE GLAND AND PROSTATE ZONES SEGMENTATION USING A NOVEL MRI-BASED MACHINE LEARNING FRAMEWORK AND CREATION OF SOFTWARE INTERFACE FOR USERS ANNOTATION

You have accessJournal of UrologyCME1 Apr 2023MP09-05 AUTOMATED PROSTATE GLAND AND PROSTATE ZONES SEGMENTATION USING A NOVEL MRI-BASED MACHINE LEARNING FRAMEWORK AND CREATION OF SOFTWARE INTERFACE FOR USERS ANNOTATION Masatomo Kaneko, GIovanni E. Cacciamani, Yijing Yang, Vasileios Magoulianitis, Jintang Xue, Jiaxin Yang, Jinyuan Liu, Maria Sarah L. Lenon, Passant Mohamed, Darryl H. Hwang, Karan Gill, Manju Aron, Vinay Duddalwar, Suzanne L. Palmer, C.-C. Jay Kuo, Andre Luis Abreu, Inderbir Gill, and Chrysostomos L. Nikias Masatomo KanekoMasatomo Kaneko More articles by this author , GIovanni E. CacciamaniGIovanni E. Cacciamani More articles by this author , Yijing YangYijing Yang More articles by this author , Vasileios MagoulianitisVasileios Magoulianitis More articles by this author , Jintang XueJintang Xue More articles by this author , Jiaxin YangJiaxin Yang More articles by this author , Jinyuan LiuJinyuan Liu More articles by this author , Maria Sarah L. LenonMaria Sarah L. Lenon More articles by this author , Passant MohamedPassant Mohamed More articles by this author , Darryl H. HwangDarryl H. Hwang More articles by this author , Karan GillKaran Gill More articles by this author , Manju AronManju Aron More articles by this author , Vinay DuddalwarVinay Duddalwar More articles by this author , Suzanne L. PalmerSuzanne L. Palmer More articles by this author , C.-C. Jay KuoC.-C. Jay Kuo More articles by this author , Andre Luis AbreuAndre Luis Abreu More articles by this author , Inderbir GillInderbir Gill More articles by this author , and Chrysostomos L. NikiasChrysostomos L. Nikias More articles by this author View All Author Informationhttps://doi.org/10.1097/JU.0000000000003224.05AboutPDF ToolsAdd to favoritesDownload CitationsTrack CitationsPermissionsReprints ShareFacebookLinked InTwitterEmail Abstract INTRODUCTION AND OBJECTIVE: To develop an automated machine learning (ML) model to segment the prostate gland, the peripheral zone (PZ), and the transition zone (TZ) using magnetic resonance image (MRI) and to create a web-based software interface for annotation. METHODS: Consecutive men who underwent prostate MRI followed by prostate biopsy (PBx) were identified from our PBx database (IRB# HS-13-00663). The 3T MRI was performed according to Prostate Imaging-Reporting and Data System (PIRADS) v2 or v2.1. The T2-weighted (T2W) images were manually segmented into the whole prostate, PZ, and TZ by experienced radiologist and urologist. A novel two-stage automatic Green Learning (GL) based machine learning model was designed, which is a novel non-deep learning method. The first stage segments the prostate gland and the second stage zooms into the prostate area to delineate TZ and PZ. Both stages share a lightweight feed-forward encoder-decoder GL system. Included accessions were split for 5-fold cross-validation. The volumes were calculated according to the number of pixels/voxels. The model performance for automated prostate segmentation was evaluated by Dice scores and Pearson correlation coefficients. The web-based software interface was designed and implemented for users to interact with the AI annotation model and make necessary adjustments. RESULTS: A total of 119 patients (19992 T2W images) met the inclusion criteria (Figure 1). Using the training dataset of 95 MRIs, a ML model for whole prostate, PZ, and TZ segmentation was constructed. The mean Dice scores for whole prostate, PZ, and TZ were 0.85, 0.62 and 0.81, respectively. The Pearson correlation coefficient for volumes of whole prostate, PZ, and TZ segmentation were 0.92 (p<0.01), 0.62 (p<0.01), and 0.93 (p<0.01), respectively. The web-based software interface takes a mean of 90sec for prostate segmentation with 168 slices. The platform supports DICOM series upload, image preview, image modification, 3-dimensional preview, and annotation mask export, from any device without migrating data. CONCLUSIONS: A lightweight feed-forward encoder-decoder model based on Green Learning can precisely segment the whole prostate, PZ and TZ. This is available on a user-friendly software interface. Source of Funding: None © 2023 by American Urological Association Education and Research, Inc.FiguresReferencesRelatedDetails Volume 209Issue Supplement 4April 2023Page: e105 Advertisement Copyright & Permissions© 2023 by American Urological Association Education and Research, Inc.MetricsAuthor Information Masatomo Kaneko More articles by this author GIovanni E. Cacciamani More articles by this author Yijing Yang More articles by this author Vasileios Magoulianitis More articles by this author Jintang Xue More articles by this author Jiaxin Yang More articles by this author Jinyuan Liu More articles by this author Maria Sarah L. Lenon More articles by this author Passant Mohamed More articles by this author Darryl H. Hwang More articles by this author Karan Gill More articles by this author Manju Aron More articles by this author Vinay Duddalwar More articles by this author Suzanne L. Palmer More articles by this author C.-C. Jay Kuo More articles by this author Andre Luis Abreu More articles by this author Inderbir Gill More articles by this author Chrysostomos L. Nikias More articles by this author Expand All Advertisement PDF downloadLoading ...

The risk of prostate cancer on incidental finding of an avid prostate uptake on 2-deoxy-2-[18F]fluoro-d-glucose positron emission tomography/computed tomography for non-prostate cancer-related pathology: A single centre retrospective study

ObjectiveTo review the risk of prostate cancer (PCa) in men with incidentally reported increased intraprostatic uptake at 2-deoxy-2-[18F]fluoro-d-glucose positron emission tomography/computed tomography (18F-FDG PET/CT) ordered at Department of Urology, The Wesley Hospital, Brisbane, QLD, Australia for non-PCa related pathology. MethodsRetrospective analysis of consecutive men between August 2014 and August 2019 presenting to a single institution for 18F-FDG PET/CT for non-prostate related conditions was conducted. Men were classified as benign, indeterminate, or malignant depending of the results of prostate-specific antigen (PSA), PSA velocity, biopsy histopathology, and three-Tesla (3 T) multiparametric MRI (mpMRI) Prostate Imaging Reporting and Data System score, or gallium-68-prostate-specific membrane antigen (68Ga-PSMA) PET/CT results. ResultsThree percent (273/9122) of men demonstrated 18F-FDG avidity within the prostate. Eighty-five percent (231/273) were further investigated, including with PSA tests (227/231, 98.3%), 3 T mpMRI (68/231, 29.4%), 68Ga-PSMA PET/CT (33/231, 14.3%), and prostate biopsy (57/231, 24.7%). Results were considered benign in 130/231 (56.3%), indeterminate in 31/231 (13.4%), and malignant in 70/231 (30.3%). PCa was identified in 51/57 (89.5%) of the men who proceeded to biopsy, including 26/27 (96.3%) men with Prostate Imaging Reporting and Data System scores 4–5 mpMRI and six men with a positive 68Ga-PSMA PET/CT. The most common Gleason score on biopsy was greater than or equal to 4+5 (14/51, 27.5%). 68Ga-PSMA PET/CT was concordant with the 18F-FDG findings in 26/33 (78.8%). All 13 men with a positive concordant 18F-FDG, 3 T mpMRI, and 68Ga-PSMA PET/CT had PCa on biopsy. There was no statistically significant difference in the 18F-FDG maximum standardized uptake value between the benign or malignant groups (5.7 vs. 6.1; p=0.580). ConclusionIn this study, after an incidental finding of an avid intraprostatic lesion on 18F-FDG PET/CT, 70 of the 231 cases (30.3%; 0.8% of the entire cohort) had results consistent with PCa, most commonly as Gleason score greater than or equal to 4+5 disease. Unless there is limited life expectancy due to competing medical co-morbidity, men with an incidental finding of intraprostatic uptake on 18F-FDG should be further investigated using principles of PCa detection.

Using IsoPSA With Prostate Imaging Reporting and Data System Score May Help Refine Biopsy Decision Making in Patients With Elevated PSA

ObjectiveTo assess how IsoPSA, a structure-based serum assay which has been prospectively validated in detecting clinically significant prostate cancer (csPCa), can help the biopsy decision process when combined with the prostate imaging reporting and data systems (PI-RADS). Materials and MethodsThis was a single-center retrospective review of prospectively collected data on patients receiving IsoPSA testing for elevated PSA (>4.0ng/mL). Patients were included if they had received an IsoPSA test and prostate MRI within 1 year of IsoPSA testing, and subsequently underwent prostate biopsy. Multivariable logistic regression was used to identify predictors of (csPCa, ie, GG ≥ 2) on biopsy. Predictive probabilities for csPCa at biopsy were generated using IsoPSA and various PI-RADS scores. ResultsTwo hundred and 7 patients were included. Twenty-two percent had csPCa. Elevated IsoPSA ratio (defined as ≥6.0) (OR: 5.06, P = .015) and a PI-RADS 4-5 (OR: 6.37, P <.001) were significant predictors of csPCa. The combination of elevated IsoPSA ratio and PI-RADS 4-5 lesion had the highest area under the curve (AUC) (AUC: 0.83, P <.001). The predicted probability of csPCa when a patient had a negative or equivocal MRI (PI-RADS 1-3) and a low IsoPSA ratio (≤6) was <5%. ConclusionThe combination of PI-RADS with IsoPSA ratios may help refine the biopsy decision-making process. In our cohort, a negative or equivocal MRI with a low IsoPSA may provide a low enough predicted probability to omit biopsy in such patients.

Clinical value of minimum apparent diffusion coefficient for prediction of clinically significant prostate cancer in the transition zone

BackgroundThis study investigated the association between apparent diffusion coefficients in Prostate Imaging Reporting and Data System 4/5 lesions and clinically significant prostate cancer in the transition zone.MethodsWe included 102 patients who underwent transperineal cognitive fusion targeted biopsy for Prostate Imaging Reporting and Data System 4/5 lesions in the transition zone between 2016 and 2020. The association between apparent diffusion coefficients and prostate cancers in the transition zone was analyzed.ResultsThe detection rate of prostate cancer was 49% (50/102), including clinically significant prostate cancer in 37.3% (38/102) of patients. The minimum apparent diffusion coefficients in patients with clinically significant prostate cancer were 494.5 ± 133.6 µm2/s, which was significantly lower than 653.8 ± 172.5 µm2/s in patients with benign histology or clinically insignificant prostate cancer. Age, prostate volume, transition zone volume, and mean and minimum apparent diffusion coefficients were associated with clinically significant prostate cancer. Multivariate analysis demonstrated that only the minimum apparent diffusion coefficient value (odds ratio: 0.994; p < 0.001) was an independent predictor of clinically significant prostate cancer. When the cutoff value of the minimum apparent diffusion coefficient was less than 595 µm2/s, indicating the presence of prostate cancer in the transition zone, the detection rate increased to 59.2% (29/49) in this cohort.ConclusionThe minimum apparent diffusion coefficient provided additional value to indicate the presence of clinically significant prostate cancer in the transition zone. It may help consider the need for subsequent biopsies in patients with Prostate Imaging Reporting and Data System 4/5 lesions and an initial negative targeted biopsy.

Accurate diagnosis of prostate cancer by combining Proclarix with magnetic resonance imaging.

To assess of the clinical performance of Proclarix® (a novel Conformité Européenne [CE]-marked biomarker test aiding in the identification of clinically significant prostate cancer [csPCa]) alone or in combination with multiparametric magnetic resonance imaging (mpMRI) to predict csPCa (International Society of Urological Pathology Grade Group ≥2). The study included blood samples from 721 men undergoing mpMRI followed by biopsy at University College London, London, and Vall d'Hebron University Hospital, Barcelona. Samples were tested blindly. The Proclarix-MRI model combining prostate volume, Proclarix and mpMRI results was trained using the UCL cohort (n= 159) and validated in the Vall d'Hebron cohort (n= 562). Its diagnostic performance was established in correlation to biopsy outcome and compared to available clinical parameters and risk calculators. Clinical performance of the Proclarix-MRI model in the validation cohort did not significantly differ from the training cohort and resulted in a sensitivity for csPCa of 90%, 90% negative predictive value and 66% positive predictive value. The Proclarix-MRI score's specificity (68%) was significantly (P< 0.001) better than the MRI-European Randomized study of Screening for Prostate Cancer risk score (51%), Proclarix (27%) or mpMRI (28%) alone. In addition, Proclarix by itself was found to be useful in the MRI Prostate Imaging-Reporting and Data System (PI-RADS) score 3 subgroup by outperforming prostate-specific antigen density in terms of specificity (25% vs 13%, P= 0.004) at 100% sensitivity. When combined with mpMRI and prostate volume, Proclarix reliably predicted csPCa and ruled out men with no or indolent cancer. A large reduction of two thirds of unneeded biopsies was achieved. Proclarix can further be used with high confidence to reliably detect csPCa in men with an indeterminate PI-RADS score 3 mpMRI. Despite these encouraging results, further validation is needed.

Die multiparametrische MRT der Prostata: Anforderungen und Grundlagen der Befundung

Multiparametric MRI (mpMRI) is one of the primary diagnostic tools for detecting clinically relevant prostate cancer. It should be routinely used in addition to urological investigations owing to its higher diagnostic yield than systematic biopsies. However, combining targeted and systematic biopsies achieves the highest diagnostic rate. The Prostate Imaging Reporting and Data System (PI-RADS Version2.1) standardizes the acquisition and interpretation of mpMRI of the prostate. It consists of high-resolution T2- and diffusion-weighted images, the corresponding apparent diffusion coefficient (ADC) maps, and adynamic contrast-enhanced sequence. Reports describe the increasing likelihood of clinically significant prostate cancer with PI-RADS categories 1-5. The MRI sequence determining the PI-RADS category of alesion depends on its location within the prostate: in the transitional zone, the T2-weighted sequence and, in the peripheral zone, the diffusion-weighted sequence are the primary determinants. The diffusion-weighted and contrast-enhanced sequences provide secondary classification for the transitional and peripheral zones, respectively. This review summarizes and illustrates the diagnostic criteria defined in PI-RADS 2.1. In addition, evidence for mpMRI of the prostate, its indication and implementation are described.

Does deep learning software improve the consistency and performance of radiologists with various levels of experience in assessing bi-parametric prostate MRI?

ObjectiveTo investigate whether commercially available deep learning (DL) software improves the Prostate Imaging-Reporting and Data System (PI-RADS) scoring consistency on bi-parametric MRI among radiologists with various levels of experience; to assess whether the DL software improves the performance of the radiologists in identifying clinically significant prostate cancer (csPCa).MethodsWe retrospectively enrolled consecutive men who underwent bi-parametric prostate MRI at a 3 T scanner due to suspicion of PCa. Four radiologists with 2, 3, 5, and > 20 years of experience evaluated the bi-parametric prostate MRI scans with and without the DL software. Whole-mount pathology or MRI/ultrasound fusion-guided biopsy was the reference. The area under the receiver operating curve (AUROC) was calculated for each radiologist with and without the DL software and compared using De Long’s test. In addition, the inter-rater agreement was investigated using kappa statistics.ResultsIn all, 153 men with a mean age of 63.59 ± 7.56 years (range 53–80) were enrolled in the study. In the study sample, 45 men (29.80%) had clinically significant PCa. During the reading with the DL software, the radiologists changed their initial scores in 1/153 (0.65%), 2/153 (1.3%), 0/153 (0%), and 3/153 (1.9%) of the patients, yielding no significant increase in the AUROC (p > 0.05). Fleiss’ kappa scores among the radiologists were 0.39 and 0.40 with and without the DL software (p = 0.56).ConclusionsThe commercially available DL software does not increase the consistency of the bi-parametric PI-RADS scoring or csPCa detection performance of radiologists with varying levels of experience.

Comparison of quantitative parameters and radiomic features as inputs into machine learning models to predict the Gleason score of prostate cancer lesions

IntroductionThe classification of prostate cancer (PCa) lesions using Prostate Imaging Reporting and Data System (PI-RADS) suffers from poor inter-reader agreement. This study compared quantitative parameters or radiomic features from multiparametric magnetic resonance imaging (mpMRI) or positron emission tomography (PET), as inputs into machine learning (ML) to predict the Gleason scores (GS) of detected lesions for improved PCa lesion classification. Methods20 biopsy-confirmed PCa subjects underwent imaging before radical prostatectomy. A pathologist assigned GS from tumour tissue. Two radiologists and one nuclear medicine physician delineated the lesions on the mpMR and PET images, yielding 45 lesion inputs. Seven quantitative parameters were extracted from the lesions, namely T2-weighted (T2w) image intensity, apparent diffusion coefficient (ADC), transfer constant (KTRANS), efflux rate constant (Kep), and extracellular volume ratio (Ve) from mpMR images, and SUVmean and SUVmax from PET images. Eight radiomic features were selected out of 109 radiomic features from T2w, ADC and PET images. Quantitative parameters or radiomic features, with risk factors of age, prostate-specific antigen (PSA), PSA density and volume, of 45 different lesion inputs were input in different combinations into four ML models - Decision Tree (DT), Support Vector Machine (SVM), k-Nearest-Neighbour (kNN), Ensembles model (EM). ResultsSUVmax yielded the highest accuracy in discriminating detected lesions. Among the 4 ML models, kNN yielded the highest accuracies of 0.929 using either quantitative parameters or radiomic features with risk factors as input. ConclusionsML models' performance is dependent on the input combinations and risk factors further improve ML classification accuracy.

Impact of an Expanded Definition of Family History on Outcomes of Active Surveillance for Prostate Cancer.

Despite family history being an established risk factor for prostate cancer, the role of a broader definition of family history inclusive of not just prostate cancer but other genetically related malignancies has not been investigated in the active surveillance population. Here, we evaluate the impact of an expanded definition of family history on active surveillance outcomes. Patients undergoing active surveillance for prostate cancer at Massachusetts General Hospital from 1997-2019 with detailed data available on family cancer history were identified. Primary outcome was biopsy progression-free survival, and secondary outcomes were treatment-free survival, adverse pathological features at prostatectomy, and biochemical recurrence after treatment. Statistical analyses were conducted using the Kaplan-Meier method and Cox regression. Among 855 evaluable patients, 300 (35.1%) patients had any family history of prostate cancer, and 95 (11.1%) had a family history of related malignancies suggestive of a hereditary cancer syndrome. Family history of prostate cancer alone was not associated with biopsy progression, whereas family history suggestive of a hereditary cancer syndrome was associated with a significantly increased risk of biopsy progression (HR 1.43, 95%CI 1.01-2.02), independent of other known clinicopathological risk factors in multivariable analysis. Similarly, family history suggestive of a hereditary cancer syndrome was associated with significantly lower treatment-free survival (HR 1.58, 95%CI 1.14-2.18) in multivariable analysis. No significant association was found between family history and adverse features on surgical pathology or biochemical recurrence. An expanded family history suggestive of a hereditary cancer syndrome is an independent predictor of biopsy progression during active surveillance. Men with such a family history may still be offered active surveillance but should be counseled regarding the higher risk of disease progression.

Developing a predictive model for clinically significant prostate cancer by combining age, PSA density, and mpMRI

PurposeThe study aimed to construct a predictive model for clinically significant prostate cancer (csPCa) and investigate its clinical efficacy to reduce unnecessary prostate biopsies.MethodsA total of 847 patients from institute 1 were included in cohort 1 for model development. Cohort 2 included a total of 208 patients from institute 2 for external validation of the model. The data obtained were used for retrospective analysis. The results of magnetic resonance imaging were obtained using Prostate Imaging Reporting and Data System version 2.1 (PI-RADS v2.1). Univariate and multivariate analyses were performed to determine significant predictors of csPCa. The diagnostic performances were compared using the receiver operating characteristic (ROC) curve and decision curve analyses.ResultsAge, prostate-specific antigen density (PSAD), and PI-RADS v2.1 scores were used as predictors of the model. In the development cohort, the areas under the ROC curve (AUC) for csPCa about age, PSAD, PI-RADS v2.1 scores, and the model were 0.675, 0.823, 0.875, and 0.938, respectively. In the external validation cohort, the AUC values predicted by the four were 0.619, 0.811, 0.863, and 0.914, respectively. Decision curve analysis revealed that the clear net benefit of the model was higher than PI-RADS v2.1 scores and PSAD. The model significantly reduced unnecessary prostate biopsies within the risk threshold of > 10%.ConclusionsIn both internal and external validation, the model constructed by combining age, PSAD, and PI-RADS v2.1 scores exhibited excellent clinical efficacy and can be utilized to reduce unnecessary prostate biopsies.

A risk-organised model for clinically significant prostate cancer early detection.

A risk-organised model for clinically significant prostate cancer early detection.

Role of magnetic resonance imaging for preoperative prediction of early biochemical failure in localized prostate cancer.

The purpose of our study was to assess preoperative clinical biological and Magnetic Resonance Imaging (MRI) predictive factors of early biochemical failure (BF), defined as persistence of significant post-operative plasmatic prostate specific antigen (PSA) level after radical prostatectomy (RP) in patients with localized prostate cancer (PCa). In a retrospective cohort study we included 142 patients from our university hospital with newly diagnosed PCa, who underwent 3T multiparametric MRI prior to RP. Only the MRI target lesions [Prostate Imaging Reporting and Data System (PIRADS) ≥3] with histological correspondence were considered significant. Clinical, biological, MRI and pathological preoperative data were studied. We performed univariate and multivariate logistic regression analysis to identify significant parameters associated with early BF. Early BF occurred in 14% of patients (20/142). Patients with BF had higher PSA level at diagnosis, Gleason score, number of positive biopsies, size of the largest positive biopsy and higher National Comprehensive Cancer Network (NCCN) risk score (P<0.001 for all). According to MRI, they also had higher T stage and a higher size of capsular contact (P<0.001 for all). In contrast, there was no difference concerning neither ADC value, perfusion profile and zonal location of the index lesion. In multivariate analysis, the best combination of predictive factors of early BF was the association of preoperative Gleason score ≥4+3 [odds ratio (OR) =6.8 (1.4-32.5); P=0.002] and T stage ≥3 on preoperative MRI [OR =17.4 (3.2-94.9); P<0.001] with an area under the curve (AUC) of 0.89 [99% confidence interval (CI): 0.77-1], a negative predictive value of 94% and a positive predictive value of 75%. Combination of simple preoperative biomarkers as Gleason score and T stage according to MRI accurately stratify the risk of early BF following RP. These results emphasize the pivotal role of preoperative MRI for the management of localized PCa.

Magnetic resonance imaging radiomic features for recurrent prostate cancer following proton radiation therapy-A pilot study.

The role of multiparametric MRI (mp-MRI) for postproton radiation evaluation is unclear. In this pilot study, we characterize the mp-MRI features using the Prostate Imaging-Reporting and Data System (PI-RADS) for recurrent prostate cancer (PCa) following proton radiation therapy. After obtaining IRB approval, we identified 163 consecutive cases who underwent MRI-fusion prostate biopsy at our institution from November 2017 to May 2020. This study evaluated patients with prostate cancer (PCa) with biochemical recurrence following proton radiation. Patients were excluded if they had grossly metastatic disease, metal fragments, implanted devices, or with surgically removed prostates. The mpMRI studies were reviewed in depth and scored by 2 fellowship-trained radiologists. Following MRI-fusion biopsy of lesions of interest (LOI), slides were read by fellowship-trained pathologists. We found 14 patients with 16 lesions who met the study inclusion criteria. The median age was 69 years (range 57-79) and median time to biochemical recurrence was 7.3 years (range 3-13). On post-treatment imaging, decreases in prostate size and diffusely decreased T2 signal intensity were observed, making the use of apparent diffusion coefficient (ADC) and early enhancement at dynamic contrast enhanced (DCE) imaging often necessary for diagnosis of disease recurrence. We identified a total of 16 lesions with PIRADS scores of 3 or higher. Of these lesions, there were 5 PIRADS 3 lesions (4/5 (80%) without prostate cancer), 7 PIRADS 4-5 lesions (6 (86%) had high risk Pca), and 4 lesions with unassigned PIRADS scores (100% had high risk cancers). Among the MRI variables, diffusion weighted imaging (DWI) heterogeneity had the strongest association with recurrence of PCa (P < 0.001). Results of our pilot study showed that the PIRADS scoring system in the postproton radiation therapy setting has some correlations with prostate cancer recurrence; However, the clinical value of these findings are unclear. While definitive PIRADS categorization of lesions demonstrated expected frequency of cancer consistent with the scoring system, all unassigned lesions also harbored malignancy suggesting a cautious approach to PIRADS scoring system in postproton radiation setting. The findings from this study may be validated using a larger cohort.

Prospective study of prostate cancer detection using multiparametric magnetic resonance imaging ultrasound-guided fusion, standard, and saturation biopsy

Background. Currently, about 80 % of men with low-grade prostate cancer (per ISUP 1 (International Society of Urological Pathology)) have indications for radical treatment. Overdiagnosis of low-grade cancer is associated with the use of systematic biopsy methods (standard transrectal, saturation) under ultrasound control for diagnosis verification. To improve prostate cancer diagnosis, the European Association of Urology (2019) recommended multiparametric magnetic resonance imaging before biopsy, and in case of detection of a suspicious lesion magnetic resonance imaging (MRI)-targeted biopsy. In clinical practice, the most common method of MRI-targeted biopsy is multiparametric MRI ultrasound-guided (mpMRI/US) fusion biopsy. However, some studies show contradictory results in detection of prostate cancer using systematic and MRI-targeted biopsy techniques.Aim. To compare detection of clinically significant prostate cancer (ISUP ≥2) using mpMRI/US fusion, standard, and saturation biopsy.Materials and methods. The study included 96 patients. The following inclusion criteria were applied: prostate-specific antigen &gt;2 ng/mL and/or detection of a suspicious lesion during digital rectal and/or transrectal ultrasound examination, and PI-RADS (Prostate Imaging Reporting and Data System) v.2.1 score ≥3. At the first stage, “unblinded” urologist performed a transperineal mpMRI/US fusion and saturation biopsies. At the second stage, “blinded” urologist performed standard transrectal biopsy. Clinically significant cancer was defined as ISUP ≥2.Results. Median age was 63 years, prostate volume – 47 cm3, prostate-specific antigen – 6.82 ng/mL. MpMRI/US fusion, standard, and saturation biopsies were comparable in regard to the rate of detection of clinically significant (29, 24, 28 %; p = 0.81) and clinically insignificant (25, 26, 35 %; p = 0.43) cancer. Overall prostate cancer detection rates were also similar: 54, 50, 63 %, respectively (p = 0.59). The percentages of positive cores in mpMRI/US fusion, standard, and saturation biopsies were 33, 10 and 13 %, respectively (p &lt;0.01). The maximal core length in mpMRI/US was 6.4 mm, in standard biopsy – 6.35 mm, in saturation biopsy – 5.1 mm (p = 0.7).Conclusion. Detection rates of clinically significant, clinically insignificant prostate cancer and overall detection rate are comparable between systematic biopsy techniques and mpMRI/US fusion biopsy.

Prediction of significant prostate cancer in equivocal MRI lesions: A high-volume international multicenter study.

311 Background: The decision of performing prostate biopsy in men with equivocal findings in prostate magnetic resonance imaging (MRI) is challenging as they have a low but still relevant risk of harboring significant prostate cancer (sPC). Objective: To identify clinical predictors of sPC in men with equivocal findings in prostate MRI. Secondly, we aimed to analyze the hypothetical effect of incorporating prostate-specific antigen density (PSAD) into biopsy decision. Methods: We analysed a retrospective multinational cohort from 10 academic centers comprising 1476 men who underwent combined prostate biopsy (MRI-targeted plus systematic) between 02/2012 – 04/2021 due to an equivocal lesion found in prostate MRI (Prostate Imaging Reporting and Data System 3). Primary outcome was the detection of sPC (ISUP ≥ 2) in combined biopsy. Regression analysis was performed to identify predictors for this outcome. Descriptive statistics were applied to evaluate the hypothetical effect of involving PSAD into biopsy decision. Results: 273/1476 (18.5%) men were diagnosed with sPC by combined biopsy. MRI-targeted biopsy diagnosed less sPC as compared to combined strategy: 183/1476 (12.4%) vs. 273/1476 (18.5%), p&lt;0.01. Regression analysis confirmed age (OR 1.10 [95% CI: 1.05 – 1.15]; p &lt; 0.001), prior negative biopsy (OR 0.46 [0.24 – 0.89]; p = 0.022) and PSAD (p&lt;0.001) as independent predictors for sPC. Applying a PSAD cut-off of 0.15 for biopsy decision, 817/1398 (58.4%) of the biopsy procedures would have been avoided at the cost of missing sPC in 91 (6.5%) men. Limitations were the retrospective design, heterogeneity of the study cohort due to the long inclusion period and a missing central revision of MRI. Conclusions: Age, previous biopsy status and PSAD were found independent predictors of sPC in men with equivocal prostate MRI. Implementation of PSAD into biopsy decision can avoid a large proportion of unnecessary biopsies. Clinical parameters such as PSAD need validation in a prospective setting.