MRI-based nomogram for the prediction of prostate cancer diagnosis: A multi-centre validated patient–physician decision tool

Objective: To update and externally validate a magnetic resonance imaging (MRI)-based nomogram for predicting prostate biopsy outcomes with a multi-centre cohort. Materials and methods: Prospective data from five UK-based centres were analysed. All men were biopsy naïve. Those with missing data, no MRI, or prostate-specific antigen (PSA) > 30 ng/mL were excluded. Logistic regression analysis was used to confirm predictors of prostate cancer outcomes including MRI-PIRADS (Prostate Imaging Reporting and Data System) score, PSA density, and age. Clinically significant disease was defined as International Society of Urological Pathology (ISUP) Grade Group ⩾ 2 (Gleason grade ⩾ 7). Biopsy strategy included transrectal and transperineal approaches. Nomograms were produced using logistic regression analysis results. Results: A total of 506 men were included in the analysis with median age 66 (interquartile range (IQR) = 60–69). Median PSA was 6.6 ng/mL (IQR = 4.72–9.26). PIRADS ⩾ 3 was reported in 387 (76.4%). Grade Group ⩾ 2 detection was 227 (44.9%) and 318 (62.8%) for any cancer. Performance of the MRI-based nomogram was an area under curve (AUC) of 0.84 (95% confidence interval (CI) = 0.81–0.88) for Grade Group ⩾ 2% and 0.85 (95% CI = 0.82–0.88) for any prostate cancer. Conclusion: We present external validation of a novel MRI-based nomogram in a multi-centre UK-based cohort, showing good discrimination in identifying men at high risk of having clinically significant disease. These findings support this risk calculator use in the prostate biopsy decision-making process. Level of evidence: 2c

Download Full-text

Evaluation of the Ginsburg Scheme: Where Is Significant Prostate Cancer Missed?

Cancers ◽

10.3390/cancers13102502 ◽

2021 ◽

Vol 13 (10) ◽

pp. 2502

Author(s):

August Sigle ◽

Cordula A. Jilg ◽

Timur H. Kuru ◽

Nadine Binder ◽

Jakob Michaelis ◽

...

Keyword(s):

Prostate Cancer ◽

Logistic Regression ◽

Regression Analysis ◽

Cancer Detection ◽

Logistic Regression Analysis ◽

Anterior Region ◽

Targeted Biopsy ◽

Detection Rates ◽

Clinically Significant ◽

Systematic Biopsy

Background: Systematic biopsy (SB) according to the Ginsburg scheme (GBS) is widely used to complement MRI-targeted biopsy (MR-TB) for optimizing the diagnosis of clinically significant prostate cancer (sPCa). Knowledge of the GBS’s blind sectors where sPCa is missed is crucial to improve biopsy strategies. Methods: We analyzed cancer detection rates in 1084 patients that underwent MR-TB and SB. Cancerous lesions that were missed or underestimated by GBS were re-localized onto a prostate map encompassing Ginsburg sectors and blind-sectors (anterior, central, basodorsal and basoventral). Logistic regression analysis (LRA) and prostatic configuration analysis were applied to identify predictors for missing sPCa with the GBS. Results: GBS missed sPCa in 39 patients (39/1084, 3.6%). In 27 cases (27/39, 69.2%), sPCa was missed within a blind sector, with 17/39 lesions localized in the anterior region (43.6%). Neither LRA nor prostatic configuration analysis identified predictors for missing sPCa with the GBS. Conclusions: This is the first study to analyze the distribution of sPCa missed by the GBS. GBS misses sPCa in few men only, with the majority localized in the anterior region. Adding blind sectors to GBS defined a new sector map of the prostate suited for reporting histopathological biopsy results.

Download Full-text

A nomogram to predict the upgrading rate of ISUP grades of RP in patients undergoing transrectal prostate biopsy and transperineal prostate biopsy

10.21203/rs.3.rs-360077/v1 ◽

2021 ◽

Author(s):

Zhilei Zhang ◽

Fei Qin ◽

Guofeng Ma ◽

Hang Yuan ◽

Yongbo Yu ◽

...

Keyword(s):

Prostate Cancer ◽

Logistic Regression ◽

Regression Analysis ◽

Radical Prostatectomy ◽

Logistic Regression Analysis ◽

Prostate Biopsy ◽

Curve Analysis ◽

Decision Curve Analysis ◽

Biopsy Tissue ◽

Systematic Biopsy

Abstract Backgroud: This study was aimed to develop and internally validate a nomogram for risk of upgrade of ISUP (International Society of Urology Pathology) grade group from biopsy tissue to RP (radical prostatectomy) final histology.Methods: 166 patients with prostate cancer were retrospectively analyzed and divided into two groups based on ISUP upgrade status from needle biopsy to radical prostatectomy specimen, these being the 'ISUP upgrade' group and the 'no ISUP upgrade' group. Logistic regression analysis was used to predict the significant independent factors for ISUP upgrade. A nonogram was then developed based on these independent factors, which would predict risk of ISUP upgrade. The C-index, calibration plot, and decision curve analysis were used to assess the discrimination, calibration, and clinical usefulness of the predicting model. Internal validation was evaluated by using the bootstrapping validation. Results: There were 47 patients in the ISUP upgrade group and 119 patients in the no ISUP upgrade group respectively. Patients in the ISUP upgrade group tended to be of younger age, smaller PV (prostate volume), lower GS (Gleason score) of PB (prostate biopsy) tissue than the no ISUP upgrade group (p=0.043, p=0.041, p < 0.001, p =0.04, respectively). Multivariate logistic regression analysis showed that GS ≤6 (OR=14.236, P=0.001), prostate biopsy approach (TB-SB (transperineal prostate systematic biopsy) VS TR-SB (transrectal prostate systematic biopsy), OR=0.361, P=0.03) and number of positive cores < 10 (OR=0.396, P=0.04) were the independent risk factors for ISUP upgrade. A prediction nomogram model of ISUP upgrade was built based on these significant factors above, the area under the receiver operating characteristic (AUC) curve of which was 0.802. The C-index for the prediction nomogram was 0.798 (95%CI: 0.655–0.941) and the nomogram showed good calibration. High C-index value of 0.772 could still be reached in the interval validation. Decision curve analysis also demonstrated that the threshold value of RP-ISUP upgrade risk was 3% to 67%. Conclusion: A novel nomogram incorporating PSA, GS of PCa, ways of prostate biopsy and number of positive cores was built with a relatively good accuracy to assist clinicians to evaluate the risk of ISUP upgrade in the RP specimen, especially for the low-risk prostate cancer diagnosed by TR-SB.

Download Full-text

The presence of chronic inflammation in positive prostate biopsy is associated with upgrading in radical prostatectomy

Archivio Italiano di Urologia e Andrologia ◽

10.4081/aiua.2021.3.280 ◽

2021 ◽

Vol 93 (3) ◽

pp. 280-284

Author(s):

Ekrem Guner ◽

Yavuz Onur Danacioglu ◽

Yusuf Arikan ◽

Kamil Gokhan Seker ◽

Salih Polat ◽

...

Keyword(s):

Prostate Cancer ◽

Logistic Regression ◽

Regression Analysis ◽

Radical Prostatectomy ◽

Chronic Inflammation ◽

Logistic Regression Analysis ◽

Prostate Biopsy ◽

Chronic Prostatitis ◽

Significant Difference ◽

The Impact

Objective: This study aimed to determine the predictive effect of the presence of chronic prostatitis associated with prostate cancer (PCa) in prostate biopsy on Gleason score upgrade (GSU) in radical prostatectomy (RP) specimens. Materials and methods: The data of 295 patients who underwent open or robotic RP with a diagnosis of localized PCa following biopsy were retrospectively analyzed. Patients were divided into two groups with and without GSU following RP. Predictive factors affecting GSU on biopsy were determined. The impact of chronic prostatitis associated with prostate cancer on GSU was examined via logistic regression analysis. Results: Out of 224 patients with Gleason 3+3 scores on biopsy, 145 (64.7%) had Gleason upgrade, and 79 (35.2%) had no upgrade. Whilst comparing the two groups with and without Gleason upgrade in terms of patient age, prostate-specific antigen (PSA) value, PSA density (PSAD), prostate volume (PV), neutrophil/lymphocyte (N/L) ratio, number of positive cores, percentage of positive cores, and Prostate Imaging Reporting and Data System version 2 score, no statistically significant difference was detected. The presence of chronic prostatitis associated with PCa was higher in the patient cohort with GSU in contrast to the other group (p < 0.001). According to the univariate logistic regression analysis, the presence of chronic prostatitis was identified to be an independent marker for GSU. Conclusions: Pathologists and urologists should be careful regarding the possibility of a more aggressive tumor in the presence of chronic inflammation associated with PCa because inflammation within PCa was revealed to be linked with GSU after RP.

Download Full-text

Prediction of prostate cancer by deep learning with multilayer artificial neural network

Canadian Urological Association Journal ◽

10.5489/cuaj.5526 ◽

2018 ◽

Vol 13 (5) ◽

Cited By ~ 3

Author(s):

Takumi Takeuchi ◽

Mami Hattori-Kato ◽

Yumiko Okuno ◽

Satoshi Iwai ◽

Koji Mikami

Keyword(s):

Neural Network ◽

Prostate Cancer ◽

Artificial Neural Network ◽

Logistic Regression ◽

Regression Analysis ◽

Deep Learning ◽

Logistic Regression Analysis ◽

Prostate Biopsy ◽

Stepwise Logistic Regression ◽

Artificial Neural

Introduction: To predict the rate of prostate cancer detection on prostate biopsy more accurately, the performance of deep learning using a multilayer artificial neural network was investigated. Methods: A total of 334 patients who underwent multiparametric magnetic resonance imaging before ultrasonography guided transrectal 12-core prostate biopsy were enrolled in the analysis. Twenty-two non-selected variables, as well as selected ones by least absolute shrinkage and selection operator (Lasso) regression analysis and by stepwise logistic regression analysis, were input into the constructed multilayer artificial neural network (ANN) programs; 232 patients were used as training cases of ANN programs and the remaining 102 patients were for the test to output the probability of prostate cancer existence, accuracy of prostate cancer prediction, and area under the receiver operating characteristic (ROC) curve with the learned model. Results: With any prostate cancer objective variable, Lasso and stepwise regression analyses selected 12 and nine explanatory variables, respectively, from 22. Using trained ANNs with multiple hidden layers, the accuracy of predicting any prostate cancer in test samples was about 5–10% higher compared to that with logistic regression analysis (LR). The area under the curves (AUC) with multilayer ANN were significantly larger on inputting variables that were selected by the stepwise LR compared with the AUC with LR. The ANN had a higher net benefit than LR between prostate cancer probability cutoff values of 0.38 and 0.6. Conclusions: ANN accurately predicted prostate cancer without biopsy marginally better than LR. However, for clinical application, ANN performance may still need improvement.

Download Full-text

Prediction of prostate cancer by deep learning with multilayer artificial neural network

10.1101/291609 ◽

2018 ◽

Cited By ~ 3

Author(s):

Takumi Takeuchi ◽

Mami Hattori-Kato ◽

Yumiko Okuno ◽

Satoshi Iwai ◽

Koji Mikami

Keyword(s):

Neural Network ◽

Prostate Cancer ◽

Artificial Neural Network ◽

Logistic Regression ◽

Regression Analysis ◽

Deep Learning ◽

Logistic Regression Analysis ◽

Prostate Biopsy ◽

Stepwise Logistic Regression ◽

Artificial Neural

AbstractObjectivesTo predict the rate of prostate cancer detection on prostate biopsy more accurately, the performance of deep learning utilizing a multilayer artificial neural network was investigated.Materials and methodsA total of 334 patients who underwent multiparametric magnetic resonance imaging before ultrasonography-guided transrectal 12-core prostate biopsy were enrolled in the analysis. Twenty-two non-selected variables as well as selected ones by least absolute shrinkage and selection operator (Lasso) regression analysis and by stepwise logistic regression analysis were input into the constructed multilayer artificial neural network (ANN) programs. 232 patients were used as training cases of ANN programs, and the remaining 102 patients were for the test to output the probability of prostate cancer existence, accuracy of prostate cancer prediction, and area under the receiver operating characteristic (ROC) curve with the learned model.ResultsWith any prostate cancer objective variable, Lasso and stepwise regression analyses selected 12 and 9 explanatory variables from 22, respectively. In common between them, age at biopsy, findings on digital rectal examination, findings in the peripheral zone on MRI diffusion-weighted imaging, and body mass index were positively influential variables, while numbers of previous prostatic biopsy and prostate volume were negatively influential. Using trained ANNs with multiple hidden layers, the accuracy of predicting any prostate cancer in test samples was about 5-10% higher compared with that with logistic regression analysis (LR). The AUCs with multilayer ANN were significantly larger on inputting variables that were selected by the stepwise logistic regression compared with the AUC with LR. The ANN had a higher net-benefit than LR between prostate cancer probability cut-off values of 0.38 and 0.6.ConclusionANN accurately predicted prostate cancer without biopsy marginally better than LR. However, for clinical application, ANN performance may still need improvement.

Download Full-text

Can free PSA be used as a biomarker in biochemical recurrence after surgery to predict castrate resistant prostate cancer?

Journal of Clinical Oncology ◽

10.1200/jco.2018.36.6_suppl.177 ◽

2018 ◽

Vol 36 (6_suppl) ◽

pp. 177-177

Author(s):

Hanan Goldberg ◽

Ally Hoffman ◽

Teck Sing Woon ◽

Zachary William Abraham Klaassen ◽

Thenappan Chandrasekar ◽

...

Keyword(s):

Prostate Cancer ◽

Logistic Regression ◽

Regression Analysis ◽

Median Survival ◽

Logistic Regression Analysis ◽

Biochemical Recurrence ◽

Multivariable Logistic Regression Analysis ◽

Group 2 ◽

Castrate Resistant ◽

Group 1

177 Background: PSA produced from prostate cancer (PC) cells escapes proteolytic processing, resulting in a more complexed PSA and a lower %fPSA. Higher %fpsa correlates with lower PC risk. However, the role of fPSA in biochemical recurrence (BCR) after radical prostatectomy (RP) is unknown. Methods: All patients who had BCR after RP and at least one fPSA test, were included. Patients were stratified according to the %fPSA cut-off of 0.15. Multivariable logistic regression analysis was performed to predict covariates associated with a higher %fPSA. Results: A total of 81 men with BCR were found (Table 1). Interestingly, 20% (group 1) vs. 60% (groups 2) become castrate resistant (CRPC), p<0.0001 and the time to reach CRPC state was much shorter in group 2 (33.5 months) vs. group 1 (57.9 months), p=0.05. Additionally, 60% of group 2 patients vs. 32.5% of group 1 patients developed metastasis, p=0.014. Lastly, median survival of 193 months for group 2 patients with no median survival for group 1, Log Rank test p=0.023. Multivariable logistic regression analysis demonstrated that secondary Gleason score of 5 (compared to 3) and %fPSA>0.15 predicted CRPC status (OR 11.63, CI 95% 1.38-97.4, p=0.024, OR 7.99, CI 95% 2-31.95, p=0.003, respectively). Conclusions: %fPSA>0.15 in the setting of BCR confers a more aggressive disease, manifesting in a faster development of CRPC, metastasis and death. Our findings suggest a reversal in the significance of % fPSA values in BCR patients, and should be validated in larger cohorts. [Table: see text]

Download Full-text

541 Investigation of Suspected Prostate Cancer In UK; Evaluation of Local Practice and Feasibility of Moving Towards MRI As First Line Investigation – Re-Audit Following Change of Radiology Staffing

British Journal of Surgery ◽

10.1093/bjs/znab134.449 ◽

2021 ◽

Vol 108 (Supplement_2) ◽

Author(s):

S Lee ◽

A Luk ◽

Y Kailash ◽

B Chaplin

Keyword(s):

Prostate Cancer ◽

Negative Predictive Value ◽

Predictive Value ◽

Gleason Grade ◽

First Line ◽

Grade Group ◽

Prostate Mri ◽

Radiology Service ◽

Group 2 ◽

Significant Disease

Abstract Introduction NICE recommends MRI as first-line investigation for suspected clinically localised prostate cancer (PCa); previous local audit findings suggest this to be safe and feasible to implement. Recent retirement of radiology staffing however had resulted in MRIs being reported by teleconsultation radiology service. There were concerns on whether this may lead to more missed significant PCa. We performed a re-audit on our prostate MRI and biopsy to assess if this is indeed the case. Method All patients with suspected PCa who have had prostate MRI and biopsy simultaneously from April-August 2019 were retrospectively analysed. Results 222 men were included. 36% of patients with negative MRI had positive biopsies; within this group 25% had significant disease (Gleason grade group ≥2). Compared with our previous audit, specificity for significant PCa has increased (from 34% to 46%), but with a reduced negative predictive value (from 97% to 91%). Conclusions If we are to implement MRI as first-line triage for potential subsequent biopsy, it would result in more men not going for a biopsy (from 18% to 25%), a reduction in diagnosis of non-significant PCa (from 21% to 36%), but at an expense of increase in missed significant PCa (from 3% to 9%).

Download Full-text

Multivariable Logistic Regression Equation to Predict Prostate Cancer

10.21203/rs.3.rs-923836/v1 ◽

2021 ◽

Author(s):

Lu Ma ◽

Dong Cheng ◽

Qinghua Li ◽

Jingbo Zhu ◽

Yu Wang ◽

...

Keyword(s):

Prostate Cancer ◽

Logistic Regression ◽

Regression Analysis ◽

Prediction Model ◽

Prostate Specific Antigen ◽

Sensitivity And Specificity ◽

Logistic Regression Analysis ◽

Roc Curve ◽

Specific Antigen ◽

Clinical Feature

Abstract Objective: To explore the predictive value of white blood cell (WBC), monocyte (M), neutrophil-to-lymphocyte ratio (NLR), fibrinogen (FIB), free prostate-specific antigen (fPSA) and free prostate-specific antigen/prostate-specific antigen (f/tPSA) in prostate cancer (PCa).Materials and methods: Retrospective analysis of 200 cases of prostate biopsy and collection of patients' systemic inflammation indicators, biochemical indicators, PSA and fPSA. First, the dimensionality of the clinical feature parameters is reduced by the Lass0 algorithm. Then, the logistic regression prediction model was constructed using the reduced parameters. The cut-off value, sensitivity and specificity of PCa are predicted by the ROC curve analysis and calculation model. Finally, based on Logistic regression analysis, a Nomogram for predicting PCa is obtained.Results: The six clinical indicators of WBC, M, NLR, FIB, fPSA, and f/tPSA were obtained after dimensionality reduction by Lass0 algorithm to improve the accuracy of model prediction. According to the regression coefficient value of each influencing factor, a logistic regression prediction model of PCa was established: logit P=-0.018-0.010×WBC+2.759×M-0.095×NLR-0.160×FIB-0.306×fPSA-2.910×f/tPSA. The area under the ROC curve is 0.816. When the logit P intercept value is -0.784, the sensitivity and specificity are 72.5% and 77.8%, respectively.Conclusion: The establishment of a predictive model through Logistic regression analysis can provide more adequate indications for the diagnosis of PCa. When the logit P cut-off value of the model is greater than -0.784, the model will be predicted to be PCa.

Download Full-text

Patient-level detection of grade group ≥2 prostate cancer using quantitative diffusion MRI

10.1101/2021.05.24.21256461 ◽

2021 ◽

Author(s):

Allison Y Zhong ◽

Leonardino A Digma ◽

Troy Hussain ◽

Christine H Feng ◽

Christopher C Conlin ◽

...

Keyword(s):

Prostate Cancer ◽

Characteristic Curve ◽

Grade Group ◽

Bootstrap Confidence Intervals ◽

Patient Level ◽

Apparent Diffusion ◽

Spectrum Imaging ◽

Group 2 ◽

Clinically Significant ◽

Group 1

Purpose: Multiparametric MRI (mpMRI) improves detection of clinically significant prostate cancer (csPCa), but the qualitative PI-RADS system and quantitative apparent diffusion coefficient (ADC) yield inconsistent results. An advanced Restrictrion Spectrum Imaging (RSI) model may yield a better quantitative marker for csPCa, the RSI restriction score (RSIrs). We evaluated RSIrs for patient-level detection of csPCa. Materials and Methods: Retrospective analysis of men who underwent mpMRI with RSI and prostate biopsy for suspected prostate cancer from 2017-2019. Maximum RSIrs within the prostate was assessed by area under the receiver operating characteristic curve (AUC) for discriminating csPCa (grade group ≥2) from benign or grade group 1 biopsies. Performance of RSIrs was compared to minimum ADC and PI-RADS v2-2.1via bootstrap confidence intervals and bootstrap difference (two-tailed α=0.05). We also tested whether the combination of PI-RADS and RSIrs (PI-RADS+RSIrs) was superior to PI-RADS, alone. Results: 151 patients met criteria for inclusion. AUC values for ADC, RSIrs, and PI-RADS were 0.50 [95% confidence interval: 0.41, 0.60], 0.76 [0.68, 0.84], and 0.78 [0.71, 0.85], respectively. RSIrs (p=0.0002) and PI-RADS (p<0.0001) were superior to ADC for patient-level detection of csPCa. The performance of RSIrs was comparable to that of PI-RADS (p=0.6). AUC for PI-RADS+RSIrs was 0.84 [0.77, 0.90], superior to PI-RADS or RSIrs, alone (p=0.008, p=0.009). Conclusions: RSIrs was superior to conventional ADC and comparable to (routine, clinical) PI-RADS for patient-level detection of csPCa. The combination of PI-RADS and RSIrs was superior to either alone. RSIrs is a promising quantitative marker worthy of prospective study in the setting of csPCa detection.

Download Full-text