Predicting the Need for Biopsy to Detect Clinically Significant Prostate Cancer in Patients with a Magnetic Resonance Imaging-detected Prostate Imaging Reporting and Data System/Likert ≥3 Lesion: Development and Multinational External Validation of the Imperial Rapid Access to Prostate Imaging and Diagnosis Risk Score.

BACKGROUND: Although multiparametric magnetic resonance imaging (MRI) has high sensitivity, its lower specificity leads to a high prevalence of false-positive lesions requiring biopsy. OBJECTIVE: To develop and externally validate a scoring system for MRI-detected Prostate Imaging Reporting and Data System (PIRADS)/Likert ≥3 lesions containing clinically significant prostate cancer (csPCa). DESIGN, SETTING, AND PARTICIPANTS: The multicentre Rapid Access to Prostate Imaging and Diagnosis (RAPID) pathway included 1189 patients referred to urology due to elevated age-specific prostate-specific antigen (PSA) and/or abnormal digital rectal examination (DRE); April 27, 2017 to October 25, 2019. INTERVENTION: Visual-registration or image-fusion targeted and systematic transperineal biopsies for an MRI score of ≥4 or 3 + PSA density ≥0.12 ng/ml/ml. OUTCOME MEASUREMENTS AND STATISTICAL ANALYSIS: Fourteen variables were used in multivariable logistic regression for Gleason ≥3 + 4 (primary) and Gleason ≥4 + 3, and PROMIS definition 1 (any ≥4 + 3 or ≥6 mm any grade; secondary). Nomograms were created and a decision curve analysis (DCA) was performed. Models with varying complexity were externally validated in 2374 patients from six international cohorts. RESULTS AND LIMITATIONS: The five-item Imperial RAPID risk score used age, PSA density, prior negative biopsy, prostate volume, and highest MRI score (corrected c-index for Gleason ≥3 + 4 of 0.82 and 0.80-0.86 externally). Incorporating family history, DRE, and Black ethnicity within the eight-item Imperial RAPID risk score provided similar outcomes. The DCA showed similar superiority of all models, with net benefit differences increasing in higher threshold probabilities. At 20%, 30%, and 40% of predicted Gleason ≥3 + 4 prostate cancer, the RAPID risk score was able to reduce, respectively, 11%, 21%, and 31% of biopsies against 1.8%, 6.2%, and 14% of missed csPCa (or 9.6%, 17%, and 26% of foregone biopsies, respectively). CONCLUSIONS: The Imperial RAPID risk score provides a standardised tool for the prediction of csPCa in patients with an MRI-detected PIRADS/Likert ≥3 lesion and can support the decision for prostate biopsy. PATIENT SUMMARY: In this multinational study, we developed a scoring system incorporating clinical and magnetic resonance imaging characteristics to predict which patients have prostate cancer requiring treatment and which patients can safely forego an invasive prostate biopsy. This model was validated in several other countries.

Individualised non-contrast MRI-based risk estimation and shared decision-making in men with a suspicion of prostate cancer: protocol for multicentre randomised controlled trial (multi-IMPROD V.2.0).

INTRODUCTION: European Association of Urology and UK National Institute for Health and Care Excellence guidelines recommend that all men with suspicions of prostate cancer should undergo prebiopsy contrast enhanced, that is, multiparametric prostate MRI. Subsequent prostate biopsies should also be performed if MRI is positive, that is, Prostate Imaging-Reporting and Data System (PI-RADS) scores 3-5. However, several retrospective post hoc analyses have shown that this approach still leads to many unnecessary biopsy procedures. For example, 88%-96% of men with PI-RADS, three findings are still diagnosed with clinically non-significant prostate cancer or no cancer at all. METHODS AND ANALYSIS: This is a prospective, randomised, controlled, multicentre trial, being conducted in Finland, to demonstrate non-inferiority in clinically significant cancer detection rates among men undergoing prostate biopsies post-MRI and men undergoing prostate biopsies post-MRI only after a shared decision based on individualised risk estimation. Men without previous diagnosis of prostate cancer and with abnormal digital rectal examination findings and/or prostate-specific antigen between 2.5 ug/L and 20.0 ug/L are included. We aim to recruit 830 men who are randomised at a 1:1 ratio into control (all undergo biopsies after MRI) and intervention arms (the decision to perform biopsies is based on risk estimation and shared decision-making). The primary outcome of the study is the proportion of men with clinically significant prostate cancer (Gleason 4+3 prostate cancer or higher). We will also compare the overall biopsy rate, benign biopsy rate and the detection of non-significant prostate cancer between the two study groups. ETHICS AND DISSEMINATION: The study (protocol V.2.0, 4 January 2021) was approved by the Ethics Committee of the Hospital District of Southwest Finland (IORG number: 0001744, IBR number: 00002216; trial number: 99/1801/2019). Participants are required to provide written informed consent. Full reports of this study will be submitted to peer-reviewed journals, mainly urology and radiology. TRIAL REGISTRATION NUMBER: NCT04287088; the study is registered at ClinicalTrials.gov.

Detection of Prostate Cancer Using Biparametric Prostate MRI, Radiomics, and Kallikreins: A Retrospective Multicenter Study of Men With a Clinical Suspicion of Prostate Cancer.

BACKGROUND: Accurate detection of clinically significant prostate cancer (csPCa), Gleason Grade Group ≥ 2, remains a challenge. Prostate MRI radiomics and blood kallikreins have been proposed as tools to improve the performance of biparametric MRI (bpMRI). PURPOSE: To develop and validate radiomics and kallikrein models for the detection of csPCa. STUDY TYPE: Retrospective. POPULATION: A total of 543 men with a clinical suspicion of csPCa, 411 (76%, 411/543) had kallikreins available and 360 (88%, 360/411) did not take 5-alpha-reductase inhibitors. Two data splits into training, validation (split 1: single center, n = 72; split 2: random 50% of pooled datasets from all four centers), and testing (split 1: 4 centers, n = 288; split 2: remaining 50%) were evaluated. FIELD STRENGTH/SEQUENCE: A 3 T/1.5 T, TSE T2-weighted imaging, 3x SE DWI. ASSESSMENT: In total, 20,363 radiomic features calculated from manually delineated whole gland (WG) and bpMRI suspicion lesion masks were evaluated in addition to clinical parameters, prostate-specific antigen, four kallikreins, MRI-based qualitative (PI-RADSv2.1/IMPROD bpMRI Likert) scores. STATISTICAL TESTS: For the detection of csPCa, area under receiver operating curve (AUC) was calculated using the DeLong's method. A multivariate analysis was conducted to determine the predictive power of combining variables. The values of P-value < 0.05 were considered significant. RESULTS: The highest prediction performance was achieved by IMPROD bpMRI Likert and PI-RADSv2.1 score with AUC = 0.85 and 0.85 in split 1, 0.85 and 0.83 in split 2, respectively. bpMRI WG and/or kallikreins demonstrated AUCs ranging from 0.62 to 0.73 in split 1 and from 0.68 to 0.76 in split 2. AUC of bpMRI lesion-derived radiomics model was not statistically different to IMPROD bpMRI Likert score (split 1: AUC = 0.83, P-value = 0.306; split 2: AUC = 0.83, P-value = 0.488). DATA CONCLUSION: The use of radiomics and kallikreins failed to outperform PI-RADSv2.1/IMPROD bpMRI Likert and their combination did not lead to further performance gains. LEVEL OF EVIDENCE: 1 TECHNICAL EFFICACY: Stage 2.

Added value of systematic biopsy in men with a clinical suspicion of prostate cancer undergoing biparametric MRI-targeted biopsy: multi-institutional external validation study.

PURPOSE: We aimed to develop and externally validate a nomogram based on MRI volumetric parameters and clinical information for deciding when SBx should be performed in addition to TBx in man with suspicious prostate MRI. MATERIALS AND METHODS: Retrospective analyses of single (IMPROD, NCT01864135) and multi-institution (MULTI-IMPROD, NCT02241122) clinical trials. All men underwent a unique rapid biparametric magnetic resonance imaging (IMPROD bpMRI) consisting of T2-weighted imaging and three separate DWI acquisitions. Men with IMPROD bpMRI Likert scores of 3-5 were included. Logistic regression models were developed using IMPROD trial (n = 122) and validated using MULTI-IMPROD trial (n = 262) data. The model's performance was evaluated in the terms of PCa detection with Gleason Grade Group 1 (clinically insignificant prostate cancer, iPCa) and > 1 (clinically significant prostate cancer, csPCa). Net benefits and decision curve analyses (DCA) were compared. Combined biopsies were used for reference. RESULTS: The developed nomogram included age, PSA, prostate volume, MRI suspicion score (IMPROD bpMRI Likert or PIRADsv2.1 score), MRI-suspicion lesion volume percentage, and lesion location. All these variables were significant predictors of csPCa in SBx in multivariable analysis. In the validation cohort (n = 262) using different nomogram cutoffs, 19-43% of men would have avoided SBx while missing 1-4% of csPCa and avoiding detection of 9-20% of iPCa. Similar performance was found for nomograms using IMPROD bpMRI Likert score or v2.1. CONCLUSIONS: The developed nomogram demonstrated potential to select men with a clinical suspicion of PCa who would benefit from performing SBx in addition to TBx. Public access to the nomogram is provided at: https://petiv.utu.fi/multiimprod/ .

Symptoms and diagnostic delays in bladder cancer with high risk of recurrence: results from a prospective FinnBladder 9 trial.

PURPOSE: To investigate the symptoms and delays in the clinical pathway of bladder cancer (BC). METHODS: This is a substudy of a prospective, randomized, multicenter phase III study (FinnBladder 9, NCT01675219) where the efficacy of photodynamic diagnosis and 6 weekly optimized mitomycin C instillations are studied in pTa bladder cancer with high risk for recurrence. The data of presenting symptoms and critical time points were prospectively collected, and the effect of factors on delays was analyzed. RESULTS: At the time of analysis, 245 patients were randomized. Analysis included 131 patients with primary bladder cancer and their complete data. Sixty-nine percent had smoking history and 67% presented with macroscopic hematuria. Median patient delay (from symptoms to health-care contact) was 7 days. The median general practice delay (from health-care contact to urology referral) was 8 days. Median time from urology referral to cystoscopy was 23 days and from cystoscopy to TUR-BT 21 days. Total time used in the clinical pathway (from symptom to TUR-BT) was 78 days. Current and former smokers had non-significantly shorter patient-related and general practice delays compared to never smokers. TUR-BT delay was significantly shorter in patients with malignant cytology (16 days) compared to patients with benign cytology (21 days, p = 0.03). CONCLUSIONS: Patient-derived delay was short and most of the delay occurred in the referral centers. The majority had macroscopic hematuria as the initial symptom. Surprisingly, current and past smokers were more prone to contact the health-care system compared to never smokers.

Prostate Cancer Risk Stratification in Men With a Clinical Suspicion of Prostate Cancer Using a Unique Biparametric MRI and Expression of 11 Genes in Apparently Benign Tissue: Evaluation Using Machine-Learning Techniques.

BACKGROUND: Accurate risk stratification of men with a clinical suspicion of prostate cancer (cSPCa) remains challenging despite the increasing use of MRI. PURPOSE: To evaluate the diagnostic accuracy of a unique biparametric MRI protocol (IMPROD bpMRI) combined with clinical and molecular markers in men with cSPCa. STUDY TYPE: Prospective single-institutional clinical trial (NCT01864135). SUBJECTS: Eighty men with cSPCa. FIELD STRENGTH/SEQUENCE: 3T, surface array coils. Two T2 -weighted and three diffusion-weighted imaging (DWI) acquisitions: 1) b-values 0, 100, 200, 300, 500 s/mm2 ; 2) b-values 0,1500 s/mm2 ; 3) b-values 0, 2000 s/mm2 . ASSESSMENT: IMPROD bpMRI examinations were qualitatively (IMPROD bpMRI Likert score) and quantitatively (DWI-based Gleason grade score) prospectively reported. Men with IMPROD bpMRI Likert 3-5 had two targeted biopsies followed by 12-core systematic biopsies (SB); those with IMPROD bpMRI Likert 1-2 had only SB. Additionally, 2-core from normal-appearing prostate areas were obtained for the mRNA expression of ACSM1, AMACR, CACNA1D, DLX1, PCA3, PLA2G7, RHOU, SPINK1, SPON2, TMPRSS2-ERG, and TDRD1 measured by quantitative reverse-transcription polymerase chain reaction. STATISTICAL TESTS: Univariate and multivariate analysis using regularized least-squares, feature selection and tournament leave-pair-out cross-validation (TLPOCV), as well as 10 random splits of the data in training-testing sets, were used to evaluate the mRNA, clinical and IMPROD bpMRI parameters in detecting clinically significant prostate cancer (SPCa) defined as Gleason score ≥ 3 + 4. The evaluation metric was the area under the curve (AUC). RESULTS: IMPROD bpMRI Likert demonstrated the highest TLPOCV AUC of 0.92. The tested clinical variables had AUC 0.56-0.73, while the mRNA and additional IMPROD bpMRI parameters had AUC 0.50-0.67 and 0.65-0.89 respectively. The combination of clinical and mRNA biomarkers produced TLPOCV AUC of 0.87, the highest TLPOCV performance without including IMPROD bpMRI Likert. DATA CONCLUSION: The qualitative IMPROD bpMRI Likert score demonstrated the highest accuracy for SPCa detection compared with the tested clinical variables and mRNA biomarkers. LEVEL OF EVIDENCE: 1 Technical Efficacy Stage: 2 J. Magn. Reson. Imaging 2020;51:1540-1553.

Radiomics and machine learning of multisequence multiparametric prostate MRI: Towards improved non-invasive prostate cancer characterization.

PURPOSE: To develop and validate a classifier system for prediction of prostate cancer (PCa) Gleason score (GS) using radiomics and texture features of T2-weighted imaging (T2w), diffusion weighted imaging (DWI) acquired using high b values, and T2-mapping (T2). METHODS: T2w, DWI (12 b values, 0-2000 s/mm2), and T2 data sets of 62 patients with histologically confirmed PCa were acquired at 3T using surface array coils. The DWI data sets were post-processed using monoexponential and kurtosis models, while T2w was standardized to a common scale. Local statistics and 8 different radiomics/texture descriptors were utilized at different configurations to extract a total of 7105 unique per-tumor features. Regularized logistic regression with implicit feature selection and leave pair out cross validation was used to discriminate tumors with 3+3 vs >3+3 GS. RESULTS: In total, 100 PCa lesions were analysed, of those 20 and 80 had GS of 3+3 and >3+3, respectively. The best model performance was obtained by selecting the top 1% features of T2w, ADCm and K with ROC AUC of 0.88 (95% CI of 0.82-0.95). Features from T2 mapping provided little added value. The most useful texture features were based on the gray-level co-occurrence matrix, Gabor transform, and Zernike moments. CONCLUSION: Texture feature analysis of DWI, post-processed using monoexponential and kurtosis models, and T2w demonstrated good classification performance for GS of PCa. In multisequence setting, the optimal radiomics based texture extraction methods and parameters differed between different image types.

IMPROD biparametric MRI in men with a clinical suspicion of prostate cancer (IMPROD Trial): Sensitivity for prostate cancer detection in correlation with whole-mount prostatectomy sections and implications for focal therapy.

BACKGROUND: Prostate MRI is increasingly being used in men with a clinical suspicion of prostate cancer (PCa). However, development and validation of methods for focal therapy planning are still lagging. PURPOSE: To evaluate the diagnostic accuracy on lesion, region-of-interest (ROI), and voxel level of IMPROD biparametric prostate MRI (bpMRI) for PCa detection in men with a clinical suspicion of PCa who subsequently underwent radical prostatectomy. STUDY TYPE: Prospective single-institution clinical trial (NCT01864135). POPULATION: Sixty-four men who underwent radical prostatectomy after IMPROD bpMRI performed in prebiopsy settings. FIELD STRENGTH/SEQUENCE: IMPROD bpMRI consisted of T2 -weighted imaging (T2 w) and three separate diffusion-weighted imaging acquisitions with an average acquisition time of 15 minutes. ASSESSMENT: The diagnostic accuracy of prospectively reported manual cancer delineations and regions increased with 3D dilation were evaluated on the voxel level (volume of 1.17 mm3 , 1 mm3 , 125 mm3 ) as well as the 36 ROI level. Only PCa lesions with a diameter ≥ 5 mm or any Gleason Grade 4 were analyzed. All data and protocols are freely available at: http://petiv.utu.fi/improd STATISTICAL TESTS: Sensitivity, specificity, accuracy. RESULTS: In total, 99 PCa lesions were identified. Forty (40%, 40/99) had a Gleason score (GS) of >3 + 4. Twenty-eight PCa lesions (28%, 28/99) were missed by IMPROD bpMRI, three (7.5%, 3/40) with GS >3 + 4. 3D dilation of manual cancer delineations in all directions by ~10-12 mm (corresponding to the Hausdorff distance) was needed to achieve sensitivity approaching 100% on a voxel level. DATA CONCLUSION: IMPROD bpMRI had a high sensitivity on lesion level for PCa with GS >3 + 4. Increasing 3D lesion delineations by ~10-12 mm (corresponding to the Hausdorff distance) was needed to achieve high sensitivity on the voxel level. Such information may help in planning ablation therapies. LEVEL OF EVIDENCE: 1 Technical Efficacy: Stage 2 J. Magn. Reson. Imaging 2019;50:1641-1650.

Tournament leave-pair-out cross-validation for receiver operating characteristic analysis.

Receiver operating characteristic analysis is widely used for evaluating diagnostic systems. Recent studies have shown that estimating an area under receiver operating characteristic curve with standard cross-validation methods suffers from a large bias. The leave-pair-out cross-validation has been shown to correct this bias. However, while leave-pair-out produces an almost unbiased estimate of area under receiver operating characteristic curve, it does not provide a ranking of the data needed for plotting and analyzing the receiver operating characteristic curve. In this study, we propose a new method called tournament leave-pair-out cross-validation. This method extends leave-pair-out by creating a tournament from pair comparisons to produce a ranking for the data. Tournament leave-pair-out preserves the advantage of leave-pair-out for estimating area under receiver operating characteristic curve, while it also allows performing receiver operating characteristic analyses. We have shown using both synthetic and real-world data that tournament leave-pair-out is as reliable as leave-pair-out for area under receiver operating characteristic curve estimation and confirmed the bias in leave-one-out cross-validation on low-dimensional data. As a case study on receiver operating characteristic analysis, we also evaluate how reliably sensitivity and specificity can be estimated from tournament leave-pair-out receiver operating characteristic curves.

Assessment of metal ion concentration in water with structured feature selection.

We propose a cost-effective system for the determination of metal ion concentration in water, addressing a central issue in water resources management. The system combines novel luminometric label array technology with a machine learning algorithm that selects a minimal number of array reagents (modulators) and liquid sample dilutions, such that enable accurate quantification. The algorithm is able to identify the optimal modulators and sample dilutions leading to cost reductions since less manual labour and resources are needed. Inferring the ion detector involves a unique type of a structured feature selection problem, which we formalize in this paper. We propose a novel Cartesian greedy forward feature selection algorithm for solving the problem. The novel algorithm was evaluated in the concentration assessment of five metal ions and the performance was compared to two known feature selection approaches. The results demonstrate that the proposed system can assist in lowering the costs with minimal loss in accuracy.

Luminometric Label Array for Quantification and Identification of Metal Ions.

Quantification and identification of metal ions has gained interest in drinking water and environmental analyses. We have developed a novel label array method for the quantification and identification of metal ions in drinking water. This simple ready-to-go method is based on the nonspecific interactions of multiple unstable lanthanide chelates and nonantenna ligands with sample leading to a luminescence signal profile, unique to the sample components. The limit of detection at ppb concentration level and average coefficient of variation of 10% were achieved with the developed label array. The identification of 15 different metal ions including different oxidation states Cr(3+)/Cr(6+), Cu(+)/Cu(2+), Fe(2+)/Fe(3+), and Pb(2+)/Pb(4+) was demonstrated. Moreover, a binary mixture of Cu(2+) and Fe(3+) and ternary mixture of Cd(2+), Ni(2+), and Pb(2+) were measured and individual ions were distinguished.