Performance of a Region of Interest-based Algorithm in Diagnosing International Society of Urological Pathology Grade Group ≥2 Prostate Cancer on the MRI-FIRST Database-CAD-FIRST Study.

BACKGROUND AND OBJECTIVE: Prostate multiparametric magnetic resonance imaging (MRI) shows high sensitivity for International Society of Urological Pathology grade group (GG) ≥2 cancers. Many artificial intelligence algorithms have shown promising results in diagnosing clinically significant prostate cancer on MRI. To assess a region-of-interest-based machine-learning algorithm aimed at characterising GG ≥2 prostate cancer on multiparametric MRI. METHODS: The lesions targeted at biopsy in the MRI-FIRST dataset were retrospectively delineated and assessed using a previously developed algorithm. The Prostate Imaging-Reporting and Data System version 2 (PI-RADSv2) score assigned prospectively before biopsy and the algorithm score calculated retrospectively in the regions of interest were compared for diagnosing GG ≥2 cancer, using the areas under the curve (AUCs), and sensitivities and specificities calculated with predefined thresholds (PIRADSv2 scores ≥3 and ≥4; algorithm scores yielding 90% sensitivity in the training database). Ten predefined biopsy strategies were assessed retrospectively. KEY FINDINGS AND LIMITATIONS: After excluding 19 patients, we analysed 232 patients imaged on 16 different scanners; 85 had GG ≥2 cancer at biopsy. At patient level, AUCs of the algorithm and PI-RADSv2 were 77% (95% confidence interval [CI]: 70-82) and 80% (CI: 74-85; p = 0.36), respectively. The algorithm's sensitivity and specificity were 86% (CI: 76-93) and 65% (CI: 54-73), respectively. PI-RADSv2 sensitivities and specificities were 95% (CI: 89-100) and 38% (CI: 26-47), and 89% (CI: 79-96) and 47% (CI: 35-57) for thresholds of ≥3 and ≥4, respectively. Using the PI-RADSv2 score to trigger a biopsy would have avoided 26-34% of biopsies while missing 5-11% of GG ≥2 cancers. Combining prostate-specific antigen density, the PI-RADSv2 and algorithm's scores would have avoided 44-47% of biopsies while missing 6-9% of GG ≥2 cancers. Limitations include the retrospective nature of the study and a lack of PI-RADS version 2.1 assessment. CONCLUSIONS AND CLINICAL IMPLICATIONS: The algorithm provided robust results in the multicentre multiscanner MRI-FIRST database and could help select patients for biopsy. PATIENT SUMMARY: An artificial intelligence-based algorithm aimed at diagnosing aggressive cancers on prostate magnetic resonance imaging showed results similar to expert human assessment in a prospectively acquired multicentre test database.

Zone-specific computer-aided diagnosis system aimed at characterizing ISUP ≥ 2 prostate cancers on multiparametric magnetic resonance images: evaluation in a cohort of patients on active surveillance.

PURPOSE: To assess a region-of-interest-based computer-assisted diagnosis system (CAD) in characterizing aggressive prostate cancer on magnetic resonance imaging (MRI) from patients under active surveillance (AS). METHODS: A prospective biopsy database was retrospectively searched for patients under AS who underwent MRI and subsequent biopsy at our institution. MRI lesions targeted at baseline biopsy were retrospectively delineated to calculate the CAD score that was compared to the Prostate Imaging-Reporting and Data System (PI-RADS) version 2 score assigned at baseline biopsy. RESULTS: 186 patients were selected. At baseline biopsy, 51 and 15 patients had International Society of Urological Pathology (ISUP) grade ≥ 2 and ≥ 3 cancer respectively. The CAD score had significantly higher specificity for ISUP ≥ 2 cancers (60% [95% confidence interval (CI): 51-68]) than the PI-RADS score (≥ 3 dichotomization: 24% [CI: 17-33], p = 0.0003; ≥ 4 dichotomization: 32% [CI: 24-40], p = 0.0003). It had significantly lower sensitivity than the PI-RADS ≥ 3 dichotomization (85% [CI: 74-92] versus 98% [CI: 91-100], p = 0.015) but not than the PI-RADS ≥ 4 dichotomization (94% [CI:85-98], p = 0.104). Combining CAD findings and PSA density could have avoided 47/184 (26%) baseline biopsies, while missing 3/51 (6%) ISUP 2 and no ISUP ≥ 3 cancers. Patients with baseline negative CAD findings and PSAd < 0.15 ng/mL2 who stayed on AS after baseline biopsy had a 9% (4/44) risk of being diagnosed with ISUP ≥ 2 cancer during a median follow-up of 41 months, as opposed to 24% (18/74) for the others. CONCLUSION: The CAD could help define AS patients with low risk of aggressive cancer at baseline assessment and during subsequent follow-up.

Characterization of high-grade prostate cancer at multiparametric MRI using a radiomic-based computer-aided diagnosis system as standalone and second reader.

PURPOSE: The purpose of this study was to develop and test across various scanners a zone-specific region-of-interest (ROI)-based computer-aided diagnosis system (CAD) aimed at characterizing, on MRI, International Society of Urological Pathology (ISUP) grade≥2 prostate cancers. MATERIALS AND METHODS: ROI-based quantitative models were selected in multi-vendor training (265 pre-prostatectomy MRIs) and pre-test (112 pre-biopsy MRIs) datasets. The best peripheral and transition zone models were combined and retrospectively assessed in internal (158 pre-biopsy MRIs) and external (104 pre-biopsy MRIs) test datasets. Two radiologists (R1/R2) retrospectively delineated the lesions targeted at biopsy in test datasets. The CAD area under the receiver operating characteristic curve (AUC) for characterizing ISUP≥2 cancers was compared to that of the Prostate Imaging-Reporting and Data System version2 (PI-RADSv2) score prospectively assigned to targeted lesions. RESULTS: The best models used the 25th apparent diffusion coefficient (ADC) percentile in transition zone and the 2nd ADC percentile and normalized wash-in rate in peripheral zone. The PI-RADSv2 AUCs were 82% (95% confidence interval [CI]: 74-87) and 86% (95% CI: 81-91) in the internal and external test datasets respectively. They were not different from the CAD AUCs obtained with R1 and R2 delineations, in the internal (82% [95% CI: 76-89], P = 0.95 and 85% [95% CI: 78-91], P = 0.55) and external (82% [95% CI: 74-91], P = 0.41 and 86% [95% CI:78-95], P = 0.98) test datasets. The CAD yielded sensitivities of 86-89% and 90-91%, and specificities of 64-65% and 69-75% in the internal and external test datasets respectively. CONCLUSION: The CAD performance for characterizing ISUP grade≥2 prostate cancers on MRI is not different from that of PI-RADSv2 score across two test datasets.

Prostatic arterial embolization versus holmium laser enucleation of the prostate: 1-year outcomes.

PURPOSE: Holmium Laser Enucleation of the Prostate (HoLEP) and Prostatic Artery Embolization (PAE) are novel techniques for the treatment of benign prostatic hyperplasia lower urinary tract symptoms (BPH-LUTS). The objective of this study was to describe and compare the functional results and complications of these two techniques at one year follow-up. MATERIALS AND METHODS: We performed a retrospective, monocentric study of all patients consecutively treated in our center with HoLEP or PAE for symptomatic or complicated BPH between January 2016 and December 2019. Data regarding patient and perioperative characteristics, follow-up biological results, functional questionnaires and uroflowmetry were collected from medical records. RESULTS: A total of 490 and 57 patients were treated with HoLEP and PAE, respectively. The demographic and clinical characteristics of the two groups were similar. The operative time was significantly higher for PAE (p < 0.001) and hospitalization time longer after HoLEP (p = 0.0006). The urinary catheterization time was longer after PAE (p < 0.001). The prostatic volume treated was higher with HoLEP than with PAE (56% versus 26%, p < 0.001). The mean difference in IPSS from baseline to 12 months was significantly higher after HoLEP than after PAE: - 17.58 versus - 8 (p < 0.001). The mean difference in QoL-IPSS from baseline to 12 months was significantly higher after HoLEP: - 4.09 versus - 2.27 (p < 0.001). The rate of postoperative adverse events in the first three months was similar between the two groups:35% after HoLEP and 33% after PAE (p = 0.88). CONCLUSIONS: HoLEP and PAE both significantly improved BPH-LUTS, with HoLEP having an advantage over PAE.

Combined model-based and deep learning-based automated 3D zonal segmentation of the prostate on T2-weighted MR images: clinical evaluation.

OBJECTIVE: To train and to test for prostate zonal segmentation an existing algorithm already trained for whole-gland segmentation. METHODS: The algorithm, combining model-based and deep learning-based approaches, was trained for zonal segmentation using the NCI-ISBI-2013 dataset and 70 T2-weighted datasets acquired at an academic centre. Test datasets were randomly selected among examinations performed at this centre on one of two scanners (General Electric, 1.5 T; Philips, 3 T) not used for training. Automated segmentations were corrected by two independent radiologists. When segmentation was initiated outside the prostate, images were cropped and segmentation repeated. Factors influencing the algorithm's mean Dice similarity coefficient (DSC) and its precision were assessed using beta regression. RESULTS: Eighty-two test datasets were selected; one was excluded. In 13/81 datasets, segmentation started outside the prostate, but zonal segmentation was possible after image cropping. Depending on the radiologist chosen as reference, algorithm's median DSCs were 96.4/97.4%, 91.8/93.0% and 79.9/89.6% for whole-gland, central gland and anterior fibromuscular stroma (AFMS) segmentations, respectively. DSCs comparing radiologists' delineations were 95.8%, 93.6% and 81.7%, respectively. For all segmentation tasks, the scanner used for imaging significantly influenced the mean DSC and its precision, and the mean DSC was significantly lower in cases with initial segmentation outside the prostate. For central gland segmentation, the mean DSC was also significantly lower in larger prostates. The radiologist chosen as reference had no significant impact, except for AFMS segmentation. CONCLUSIONS: The algorithm performance fell within the range of inter-reader variability but remained significantly impacted by the scanner used for imaging. KEY POINTS: • Median Dice similarity coefficients obtained by the algorithm fell within human inter-reader variability for the three segmentation tasks (whole gland, central gland, anterior fibromuscular stroma). • The scanner used for imaging significantly impacted the performance of the automated segmentation for the three segmentation tasks. • The performance of the automated segmentation of the anterior fibromuscular stroma was highly variable across patients and showed also high variability across the two radiologists.

International Multi-Site Initiative to Develop an MRI-Inclusive Nomogram for Side-Specific Prediction of Extraprostatic Extension of Prostate Cancer.

BACKGROUND: To develop an international, multi-site nomogram for side-specific prediction of extraprostatic extension (EPE) of prostate cancer based on clinical, biopsy, and magnetic resonance imaging- (MRI) derived data. METHODS: Ten institutions from the USA and Europe contributed clinical and side-specific biopsy and MRI variables of consecutive patients who underwent prostatectomy. A logistic regression model was used to develop a nomogram for predicting side-specific EPE on prostatectomy specimens. The performance of the statistical model was evaluated by bootstrap resampling and cross validation and compared with the performance of benchmark models that do not incorporate MRI findings. RESULTS: Data from 840 patients were analyzed; pathologic EPE was found in 320/840 (31.8%). The nomogram model included patient age, prostate-specific antigen density, side-specific biopsy data (i.e., Gleason grade group, percent positive cores, tumor extent), and side-specific MRI features (i.e., presence of a PI-RADSv2 4 or 5 lesion, level of suspicion for EPE, length of capsular contact). The area under the receiver operating characteristic curve of the new, MRI-inclusive model (0.828, 95% confidence limits: 0.805, 0.852) was significantly higher than that of any of the benchmark models (p < 0.001 for all). CONCLUSIONS: In an international, multi-site study, we developed an MRI-inclusive nomogram for the side-specific prediction of EPE of prostate cancer that demonstrated significantly greater accuracy than clinical benchmark models.

The current role of prostate multiparametric magnetic resonance imaging.

Prostate multi-parametric magnetic resonance imaging (mpMRI) has shown excellent sensitivity for Gleason ≥7 cancers, especially when their volume is ≥0.5 mL. As a result, performing an mpMRI before prostate biopsy could improve the detection of clinically significant prostate cancer (csPCa) by adding targeted biopsies to systematic biopsies. Currently, there is a consensus that targeted biopsies improve the detection of csPCa in the repeat biopsy setting and at confirmatory biopsy in patients considering active surveillance. Several prospective multicentric controlled trials recently showed that targeted biopsy also improved csPCa detection in biopsy-naïve patients. The role of mpMRI and targeted biopsy during the follow-up of active surveillance remains unclear. Whether systematic biopsy could be omitted in case of negative mpMRI is also a matter of controversy. mpMRI did show excellent negative predictive values (NPV) in the literature, however, since NPV depends on the prevalence of the disease, negative mpMRI findings should be interpreted in the light of a priori risk for csPCa of the patient. Nomograms combining mpMRI findings and classical risk predictors (age, prostate-specific antigen density, digital rectal examination, etc.) will probably be developed in the future to decide whether a prostate biopsy should be obtained. mpMRI has a good specificity for detecting T3 stage cancers, but its sensitivity is low. It should therefore not be used routinely for staging purposes in low-risk patients. Nomograms combining mpMRI findings and other clinical and biochemical data will also probably be used in the future to better assess the risk of T3 stage disease.

Characterization of Prostate Cancer with Gleason Score of at Least 7 by Using Quantitative Multiparametric MR Imaging: Validation of a Computer-aided Diagnosis System in Patients Referred for Prostate Biopsy.

Purpose To determine the performance of a computer-aided diagnosis (CAD) system trained at characterizing cancers in the peripheral zone (PZ) with a Gleason score of at least 7 in patients referred for multiparametric magnetic resonance (MR) imaging before prostate biopsy. Materials and Methods Two institutional review board-approved prospective databases of patients who underwent multiparametric MR imaging before prostatectomy (database 1) or systematic and targeted biopsy (database 2) were retrospectively used. All patients gave informed consent for inclusion in the databases. A CAD combining the 10th percentile of the apparent diffusion coefficient and the time to peak of enhancement was trained to detect cancers in the PZ with a Gleason score of at least 7 in 106 patients from database 1. The CAD was tested in 129 different patients from database 2. All targeted lesions were prospectively scored at biopsy by using a five-level Likert score. The CAD scores were retrospectively calculated. Biopsy results were used as the reference standard. Areas under the receiver operating characteristic curves (AUCs) were computed for CAD and Likert scores by using binormal smoothing for per-lesion and per-lobe analyses, and a density function for per-patient analysis. Results The CAD outperformed the Likert score in the overall population and all subgroups, except in the transition zone. The difference was statistically significant for the overall population (AUC, 0.95 [95% confidence interval {CI}: 0.90, 0.98] vs 0.88 [95% CI: 0.68, 0.96]; P = .02) at per-patient analysis, and for less-experienced radiologists (<1 year) at per-lesion (AUC, 0.90 [95% CI: 0.81, 0.95] vs 0.83 [95% CI: 0.73, 0.90]; P = .04) and per-lobe (AUC, 0.92 [95% CI: 0.80, 0.96] vs 0.84 [95% CI: 0.72, 0.91]; P = .04) analysis. Conclusion The CAD outperformed the Likert score prospectively assigned at biopsy in characterizing cancers with a Gleason score of at least 7. © RSNA, 2018 Online supplemental material is available for this article.

What Is the Negative Predictive Value of Multiparametric Magnetic Resonance Imaging in Excluding Prostate Cancer at Biopsy? A Systematic Review and Meta-analysis from the European Association of Urology Prostate Cancer Guidelines Panel.

CONTEXT: It remains unclear whether patients with a suspicion of prostate cancer (PCa) and negative multiparametric magnetic resonance imaging (mpMRI) can safely obviate prostate biopsy. OBJECTIVE: To systematically review the literature assessing the negative predictive value (NPV) of mpMRI in patients with a suspicion of PCa. EVIDENCE ACQUISITION: The Embase, Medline, and Cochrane databases were searched up to February 2016. Studies reporting prebiopsy mpMRI results using transrectal or transperineal biopsy as a reference standard were included. We further selected for meta-analysis studies with at least 10-core biopsies as the reference standard, mpMRI comprising at least T2-weighted and diffusion-weighted imaging, positive mpMRI defined as a Prostate Imaging Reporting Data System/Likert score of ≥3/5 or ≥4/5, and results reported at patient level for the detection of overall PCa or clinically significant PCa (csPCa) defined as Gleason ≥7 cancer. EVIDENCE SYNTHESIS: A total of 48 studies (9613 patients) were eligible for inclusion. At patient level, the median prevalence was 50.4% (interquartile range [IQR], 36.4-57.7%) for overall cancer and 32.9% (IQR, 28.1-37.2%) for csPCa. The median mpMRI NPV was 82.4% (IQR, 69.0-92.4%) for overall cancer and 88.1% (IQR, 85.7-92.3) for csPCa. NPV significantly decreased when cancer prevalence increased, for overall cancer (r=-0.64, p<0.0001) and csPCa (r=-0.75, p=0.032). Eight studies fulfilled the inclusion criteria for meta-analysis. Seven reported results for overall PCa. When the overall PCa prevalence increased from 30% to 60%, the combined NPV estimates decreased from 88% (95% confidence interval [95% CI], 77-99%) to 67% (95% CI, 56-79%) for a cut-off score of 3/5. Only one study selected for meta-analysis reported results for Gleason ≥7 cancers, with a positive biopsy rate of 29.3%. The corresponding NPV for a cut-off score of ≥3/5 was 87.9%. CONCLUSIONS: The NPV of mpMRI varied greatly depending on study design, cancer prevalence, and definitions of positive mpMRI and csPCa. As cancer prevalence was highly variable among series, risk stratification of patients should be the initial step before considering prebiopsy mpMRI and defining those in whom biopsy may be omitted when the mpMRI is negative. PATIENT SUMMARY: This systematic review examined if multiparametric magnetic resonance imaging (MRI) scan can be used to reliably predict the absence of prostate cancer in patients suspected of having prostate cancer, thereby avoiding a prostate biopsy. The results suggest that whilst it is a promising tool, it is not accurate enough to replace prostate biopsy in such patients, mainly because its accuracy is variable and influenced by the prostate cancer risk. However, its performance can be enhanced if there were more accurate ways of determining the risk of having prostate cancer. When such tools are available, it should be possible to use an MRI scan to avoid biopsy in patients at a low risk of prostate cancer.

EAU-ESTRO-SIOG Guidelines on Prostate Cancer. Part 1: Screening, Diagnosis, and Local Treatment with Curative Intent.

OBJECTIVE: To present a summary of the 2016 version of the European Association of Urology (EAU) - European Society for Radiotherapy & Oncology (ESTRO) - International Society of Geriatric Oncology (SIOG) Guidelines on screening, diagnosis, and local treatment with curative intent of clinically localised prostate cancer (PCa). EVIDENCE ACQUISITION: The working panel performed a literature review of the new data (2013-2015). The guidelines were updated and the levels of evidence and/or grades of recommendation were added based on a systematic review of the evidence. EVIDENCE SYNTHESIS: BRCA2 mutations have been added as risk factors for early and aggressive disease. In addition to the Gleason score, the five-tier 2014 International Society of Urological Pathology grading system should now be provided. Systematic screening is still not recommended. Instead, an individual risk-adapted strategy following a detailed discussion and taking into account the patient's wishes and life expectancy must be considered. An early prostate-specific antigen test, the use of a risk calculator, or one of the promising biomarker tools are being investigated and might be able to limit the overdetection of insignificant PCa. Breaking the link between diagnosis and treatment may lower the overtreatment risk. Multiparametric magnetic resonance imaging using standardised reporting cannot replace systematic biopsy, but robustly nested within the diagnostic work-up, it has a key role in local staging. Active surveillance always needs to be discussed with very low-risk patients. The place of surgery in high-risk disease and the role of lymph node dissection have been clarified, as well as the management of node-positive patients. Radiation therapy using dose-escalated intensity-modulated technology is a key treatment modality with recent improvement in the outcome based on increased doses as well as combination with hormonal treatment. Moderate hypofractionation is safe and effective, but longer-term data are still lacking. Brachytherapy represents an effective way to increase the delivered dose. Focal therapy remains experimental while cryosurgery and HIFU are still lacking long-term convincing results. CONCLUSIONS: The knowledge in the field of diagnosis, staging, and treatment of localised PCa is evolving rapidly. The 2016 EAU-ESTRO-SIOG Guidelines on PCa summarise the most recent findings and advice for the use in clinical practice. These are the first PCa guidelines endorsed by the European Society for Radiotherapy and Oncology and the International Society of Geriatric Oncology and reflect the multidisciplinary nature of PCa management. A full version is available from the EAU office and online (http://uroweb.org/guideline/prostate-cancer/). PATIENT SUMMARY: The 2016 EAU-STRO-IOG Prostate Cancer (PCa) Guidelines present updated information on the diagnosis, and treatment of clinically localised prostate cancer. In Northern and Western Europe, the number of men diagnosed with PCa has been on the rise. This may be due to an increase in opportunistic screening, but other factors may also be involved (eg, diet, sexual behaviour, low exposure to ultraviolet radiation). We propose that men who are potential candidates for screening should be engaged in a discussion with their clinician (also involving their families and caregivers) so that an informed decision may be made as part of an individualised risk-adapted approach.

Accuracy of Elastic Fusion of Prostate Magnetic Resonance and Transrectal Ultrasound Images under Routine Conditions: A Prospective Multi-Operator Study.

PURPOSE: To evaluate in unselected patients imaged under routine conditions the co-registration accuracy of elastic fusion between magnetic resonance (MR) and ultrasound (US) images obtained by the Koelis Urostation™. MATERIALS AND METHODS: We prospectively included 15 consecutive patients referred for placement of intraprostatic fiducials before radiotherapy and who gave written informed consent by signing the Institutional Review Board-approved forms. Three fiducials were placed in the prostate under US guidance in standardized positions (right apex, left mid-gland, right base) using the Koelis Urostation™. Patients then underwent prostate MR imaging. Four operators outlined the prostate on MR and US images and an elastic fusion was retrospectively performed. Fiducials were used to measure the overall target registration error (TRE3D), the error along the antero-posterior (TREAP), right-left (TRERL) and head-feet (TREHF) directions, and within the plane orthogonal to the virtual biopsy track (TRE2D). RESULTS: Median TRE3D and TRE2D were 3.8-5.6 mm, and 2.5-3.6 mm, respectively. TRE3D was significantly influenced by the operator (p = 0.013), fiducial location (p = 0.001) and 3D axis orientation (p<0.0001). The worst results were obtained by the least experienced operator. TRE3D was smaller in mid-gland and base than in apex (average difference: -1.21 mm (95% confidence interval (95%CI): -2.03; -0.4) and -1.56 mm (95%CI: -2.44; -0.69) respectively). TREAP and TREHF were larger than TRERL (average difference: +1.29 mm (95%CI: +0.87; +1.71) and +0.59 mm (95%CI: +0.1; +0.95) respectively). CONCLUSIONS: Registration error values were reasonable for clinical practice. The co-registration accuracy was significantly influenced by the operator's experience, and significantly poorer in the antero-posterior direction and at the apex.