An integrated nomogram combining deep learning, Prostate Imaging-Reporting and Data System (PI-RADS) scoring, and clinical variables for identification of clinically significant prostate cancer on biparametric MRI: a retrospective multicentre study.
Ontology highlight
ABSTRACT:
SUBMITTER: Hiremath A
PROVIDER: S-EPMC8261599 | biostudies-literature | 2021 Jul
REPOSITORIES: biostudies-literature
Publications
An integrated nomogram combining deep learning, Prostate Imaging-Reporting and Data System (PI-RADS) scoring, and clinical variables for identification of clinically significant prostate cancer on biparametric MRI: a retrospective multicentre study.
Hiremath Amogh A Shiradkar Rakesh R Fu Pingfu P Mahran Amr A Rastinehad Ardeshir R AR Tewari Ashutosh A Tirumani Sree Harsha SH Purysko Andrei A Ponsky Lee L Madabhushi Anant A
The Lancet. Digital health 20210701 7
<h4>Background</h4>Biparametric MRI (comprising T2-weighted MRI and apparent diffusion coefficient maps) is increasingly being used to characterise prostate cancer. Although previous studies have combined Prostate Imaging-Reporting & Data System (PI-RADS)-based MRI findings with routinely available clinical variables and with deep learning-based imaging predictors, respectively, for prostate cancer risk stratification, none have combined all three. We aimed to construct an integrated nomogram (r ...[more]
Similar Datasets
Project description:This study aimed to construct nomograms for predicting the likelihood of clinically significant prostate cancer (csPCa) in patients with lesions rated as Prostate Imaging Reporting and Data System (PI-RADS) 3 on biparametric magnetic resonance imaging (bpMRI). We retrospectively analyzed a cohort of 457 patients from the Peking Union Medical College Hospital (January 2017-July 2021) to develop the model and externally validated it with a cohort of 238 patients from the Second Hospital of Tianjin Medical University (September 2017-September 2021). Univariate and multivariate logistic regression analyses identified significant predictors of csPCa, defined by tumor volumes ≥ 0.5 cm3, Gleason score ≥ 7, or presence of extracapsular extension. Diagnostic performance for the peripheral zone (PZ) and transitional zone (TZ) was compared using the receiver operating characteristic (ROC) curve and decision curve analysis (DCA). Through univariate and multivariate logistic regression analyses, we identified age, prostate-specific antigen (PSA), and prostate volume (PV) as predictors of csPCa for the PZ, and age, serum-free to total PSA ratio (f/t PSA), and PSA density (PSAD) for the TZ. The nomograms demonstrated robust discriminative ability, with an area under the ROC curve (AUC) of 0.819 for PZ and 0.804 for TZ. The external validation corroborated the model's high predictive accuracy (AUC of 0.831 for PZ and 0.773 for TZ). Calibration curves indicated excellent agreement between predicted and observed outcomes, and DCA underscored the nomogram's clinical utility for both PZ and TZ. Overall, the nomograms offer high predictive accuracy for csPCa at initial biopsy, potentially reducing unnecessary biopsies in clinical settings.
| S-EPMC10839314 | biostudies-literature
Project description:PurposeTo develop and validate a PI-RADS-based nomogram for predicting the probability of clinically significant prostate cancer (csPCa) at initial prostate biopsy.Patients and MethodsFrom February 2015 to October 2018, 573 consecutive patients made up the development cohort (DC), and another 253 patients were included as an independent validation cohort (VC). Univariate and multivariate analysis were used for determining the dependent clinical risk factors for csPCa. Prediction model1 was constructed by integrating independent clinical risk factors. T?hen added the PI-RADS score to model1 to develop the prediction model2 and present it in the form of a nomogram. The performance of the nomogram was assessed by receiver operating characteristic curve, net reclassification improvement analysis, calibration curve, and decision curve.ResultsAll clinical candidate factors were significantly different between csPCa and non-csPCa in both the DC and VC. Age, PSA density (PSAD), and free-to-total PSA ratio (f/t) were ultimately determined as dependent clinical risk factors for csPCa and integrated into prediction model1. Then, prediction model2 was developed and presented in a nomogram. In the DC, the nomogram (AUC=0.894) was superior to model1, PI-RADS score, or other clinical factors alone in detecting csPCa. Similar result (AUC=0.891) was obtained in the VC. NRI analysis showed that the nomogram improved the classification of patients significantly compared with model1. Furthermore, the nomogram showed favorable calibration and great clinical usefulness.ConclusionThis study developed and validated a nomogram that integrates PI-RADS score with other independent clinical risk factors to facilitate prebiopsy individualized prediction in high-risk patients with csPCa.
| S-EPMC7245434 | biostudies-literature
Project description:PurposeTo compare the performance of radiomics to that of the Prostate Imaging Reporting and Data System (PI-RADS) v2.1 scoring system in the detection of clinically significant prostate cancer (csPCa) based on biparametric magnetic resonance imaging (bpMRI) vs. multiparametric MRI (mpMRI).MethodsA total of 204 patients with pathological results were enrolled between January 2018 and December 2019, with 142 patients in the training cohort and 62 patients in the testing cohort. The radiomics model was compared with the PI-RADS v2.1 for the diagnosis of csPCa based on bpMRI and mpMRI by using receiver operating characteristic (ROC) curve analysis.ResultsThe radiomics model based on bpMRI and mpMRI signatures showed high predictive efficiency but with no significant differences (AUC = 0.975 vs 0.981, p=0.687 in the training cohort, and 0.953 vs 0.968, p=0.287 in the testing cohort, respectively). In addition, the radiomics model outperformed the PI-RADS v2.1 in the diagnosis of csPCa regardless of whether bpMRI (AUC = 0.975 vs. 0.871, p= 0.030 for the training cohort and AUC = 0.953 vs. 0.853, P = 0.024 for the testing cohort) or mpMRI (AUC = 0.981 vs. 0.880, p= 0.030 for the training cohort and AUC = 0.968 vs. 0.863, P = 0.016 for the testing cohort) was incorporated.ConclusionsOur study suggests the performance of bpMRI- and mpMRI-based radiomics models show no significant difference, which indicates that omitting DCE imaging in radiomics can simplify the process of analysis. Adding radiomics to PI-RADS v2.1 may improve the performance to predict csPCa.
| S-EPMC8810653 | biostudies-literature
Project description:PurposeTo develop and validate a radiomics nomogram for the prediction of clinically significant prostate cancer (CsPCa) in Prostate Imaging-Reporting and Data System (PI-RADS) category 3 lesions.MethodsWe retrospectively enrolled 306 patients within PI-RADS 3 lesion from January 2015 to July 2020 in institution 1; the enrolled patients were randomly divided into the training group (n = 199) and test group (n = 107). Radiomics features were extracted from T2-weighted imaging (T2WI), apparent diffusion coefficient (ADC) imaging, and dynamic contrast-enhanced (DCE) imaging. Synthetic minority oversampling technique (SMOTE) was used to address the class imbalance. The ANOVA and least absolute shrinkage and selection operator (LASSO) regression model were used for feature selection and radiomics signature building. Then, a radiomics score (Rad-score) was acquired. Combined with serum prostate-specific antigen density (PSAD) level, a multivariate logistic regression analysis was used to construct a radiomics nomogram. Receiver operating characteristic (ROC) curve analysis was used to evaluate radiomics signature and nomogram. The radiomics nomogram calibration and clinical usefulness were estimated through calibration curve and decision curve analysis (DCA). External validation was assessed, and the independent validation cohort contained 65 patients within PI-RADS 3 lesion from January 2020 to July 2021 in institution 2.ResultsA total of 75 (24.5%) and 16 (24.6%) patients had CsPCa in institution 1 and 2, respectively. The radiomics signature with SMOTE augmentation method had a higher area under the ROC curve (AUC) [0.840 (95% CI, 0.776-0.904)] than that without SMOTE method [0.730 (95% CI, 0.624-0.836), p = 0.08] in the test group and significantly increased in the external validation group [0.834 (95% CI, 0.709-0.959) vs. 0.718 (95% CI, 0.562-0.874), p = 0.017]. The radiomics nomogram showed good discrimination and calibration, with an AUC of 0.939 (95% CI, 0.913-0.965), 0.884 (95% CI, 0.831-0.937), and 0.907 (95% CI, 0.814-1) in the training, test, and external validation groups, respectively. The DCA demonstrated the clinical usefulness of radiomics nomogram.ConclusionThe radiomics nomogram that incorporates the MRI-based radiomics signature and PSAD can be conveniently used to individually predict CsPCa in patients within PI-RADS 3 lesion.
| S-EPMC8825569 | biostudies-literature
Project description:ObjectiveTo compare the performance of Likert and Prostate Imaging-Reporting and Data System (PI-RADS) multiparametric (mp) MRI scoring systems for detecting clinically significant prostate cancer (csPCa).Methods199 biopsy-naïve males undergoing prostate mpMRI were prospectively scored with Likert and PI-RADS systems by four experienced radiologists. A binary cut-off (threshold score ≥3) was used to analyze histological results by three groups: negative, insignificant disease (Gleason 3 + 3; iPCa), and csPCa (Gleason ≥3 +4). Lesion-level results and prostate zonal location were also compared.Results129/199 (64.8%) males underwent biopsy, 96 with Likert or PI-RADS score ≥3, and 21 with negative MRI. A further 12 patients were biopsied during follow-up (mean 507 days). Prostate cancer was diagnosed in 87/199 (43.7%) patients, 65 with (33.6%) csPCa. 30/92 (32.6%) patients with negative MRI were biopsied, with an NPV of 83.3% for cancer and 86.7% for csPCa. Likert and PI-RADS score differences were observed in 92 patients (46.2%), but only for 16 patients (8%) at threshold score ≥3. Likert scoring had higher specificity than PI-RADS (0.77 vs 0.66), higher area under the curve (0.92 vs 0.87, p = 0.002) and higher PPV (0.66 vs 0.58); NPV and sensitivity were the same. Likert had more five score results (58%) compared to PI-RADS (36%), but with similar csCPa detection (81.0 and 80.6% respectively). Likert demonstrated lower proportion of false positive in the predominately AFMS-involving lesions.ConclusionLikert and PI-RADS systems both demonstrate high cancer detection rates. Likert scoring had a higher AUC with moderately higher specificity and lower positive call rate and could potentially help to reduce the number of unnecessary biopsies performed.Advances in knowledgeThis paper illustrates that the Likert scoring system has potential to help urologists reduce the number of prostate biopsies performed.
| S-EPMC7446003 | biostudies-literature
Project description:BackgroundThis study attempted to develop a nomogram for predicting clinically significant prostate cancer (cs-PCa) in the transition zone (TZ) with the Prostate Imaging Reporting and Data System version 2.1 (PI-RADS v2.1) score based on biparametric magnetic resonance imaging (bp-MRI) and clinical indicators.MethodsWe retrospectively reviewed 383 patients with suspicious prostate lesions in the TZ as a training cohort and 128 patients as the validation cohort from January 2015 to March 2020. Multivariable logistic regression analysis was performed to determine independent predictors for building a nomogram, and the performance of the nomogram was assessed by the area under the receiver operating characteristic curve (AUC), the calibration curve and decision curve.ResultsThe PI-RADS v2.1 score and prostate-specific antigen density (PSAD) were independent predictors of TZ cs-PCa. The prediction model had a significantly higher AUC (0.936) than the individual predictors (0.914 for PI-RADS v2.1 score, P=0.045, 0.842 for PSAD, P<0.001). The nomogram showed good discrimination (AUC of 0.936 in the training cohort and 0.963 in the validation cohort) and favorable calibration. When the PI-RADS v2.1 score was combined with PSAD, the diagnostic sensitivity and specificity were 80.7% and 93.8%, respectively, which were better than those of the PI-RADS v2.1 score (sensitivity, 74.2%; specificity, 92.5%) and PSAD (sensitivity, 66.1%; specificity, 88.2%).ConclusionsThe newly constructed nomogram exhibits satisfactory predictive accuracy and consistency for TZ cs-PCa. PI-RADS v2.1 based on bp-MRI is a strong predictor in the detection of TZ cs-PCa. Adding PSAD to PI-RADS v2.1 could improve its diagnostic performance, thereby avoiding unnecessary biopsies.
| S-EPMC8261422 | biostudies-literature
Project description:BackgroundBiparametric MRI (bpMRI) is a faster, contrast-free, and less expensive MRI protocol that facilitates the detection of prostate cancer. The aim of this study is to determine whether a biparametric MRI PI-RADS v2.1 score-based model could reduce unnecessary biopsies in patients with suspected prostate cancer (PCa).MethodsThe patients who underwent MRI-guided biopsies and systematic biopsies between January 2020 and January 2022 were retrospectively analyzed. The development cohort used to derive the prediction model consisted of 275 patients. Two validation cohorts included 201 patients and 181 patients from 2 independent institutions. Predictive models based on the bpMRI PI-RADS v2.1 score (bpMRI score) and clinical parameters were used to detect clinically significant prostate cancer (csPCa) and compared by analyzing the area under the curve (AUC) and decision curves. Spearman correlation analysis was utilized to determine the relationship between International Society of Urological Pathology (ISUP) grade and clinical parameters/bpMRI score.ResultsLogistic regression models were constructed using data from the development cohort to generate nomograms. By applying the models to the all cohorts, the AUC for csPCa was significantly higher for the bpMRI PI-RADS v2.1 score-based model than for the clinical model in both cohorts (p < 0.001). Considering the test trade-offs, urologists would agree to perform 10 fewer bpMRIs to avoid one unnecessary biopsy, with a risk threshold of 10-20% in practice. Correlation analysis showed a strong correlation between the bpMRI score and ISUP grade.ConclusionA predictive model based on the bpMRI score and clinical parameters significantly improved csPCa risk stratification, and the bpMRI score can be used to determine the aggressiveness of PCa prior to biopsy.
| S-EPMC10426075 | biostudies-literature
Project description:PurposeIn this study, we aimed to validate and compare three scoring systems based on biparametric magnetic resonance imaging (bpMRI) for the detection of clinically significant prostate cancer (csPCa) in biopsy-naïve patients.MethodIn this study, we included patients who underwent MRI examinations between January 2018 and December 2022, with MRI-targeted fusion biopsy (MRGB) as the reference standard. The MRI findings were categorized using three bpMRI-based scorings, in all of them the diffusion-weighted imaging (DWI) was the dominant sequence for peripheral zone (PZ) and T2-weighed imaging (T2WI) was the dominant sequence for transition zone (TZ). We also used the Prostate Imaging Reporting and Data System version (PI-RADS) v2.1 to evaluate each lesion. For each scoring, we calculated the sensitivity, specificity, negative predictive value (NPV), positive predictive value (PPV), and area under the receiver operating characteristic (ROC) curves (AUC).ResultsThe calculated AUC for three bpMRI-based scorings were 83.2% (95% CI 78.8%-87.6%), 85.0% (95% CI 80.8%-89.3%), 82.9% (95% CI 78.4%-87.5%), and 86.0% (95% CI 81.8%-90.1%), respectively. Scoring 2 exhibited significantly superior performance than scoring 1 (P = 0.01) and scoring 3 (P < 0.001). Moreover, the accuracy of scoring 2 was not decreased significantly as compared to PI-RADS v2.1 (P = 0.05). There was no significant difference between 3 bpMRI-based scorings and with PI-RADS in TZ. However, although scoring 2 yielded the highest AUC, it was still notably inferior to PI-RADS (P = 0.02).ConclusionAll three bpMRI-based scorings demonstrated favorite diagnostic accuracy, and scoring 2 performed significantly better than the other two bpMRI-based scorings. Notably, scoring 2 was not significantly inferior to the full-sequence PI-RADS v2.1 in terms of sensitivity and specificity.
| S-EPMC11681326 | biostudies-literature
Project description:PurposeThis study aimed to develop and validate a model based on biparametric magnetic resonance imaging (bpMRI) for the detection of clinically significant prostate cancer (csPCa) in biopsy-naïve patients.MethodThis retrospective study included 324 patients who underwent bpMRI and MRI targeted fusion biopsy (MRGB) and/or systematic biopsy, of them 217 were randomly assigned to the training group and 107 were assigned to the validation group. We assessed the diagnostic performance of three bpMRI-based scorings in terms of sensitivity and specificity. Subsequently, 3 models (Model 1, Model 2, and Model 3) combining bpMRI scorings with clinical variables were constructed and compared with each other using the area under the receiver operating characteristic (ROC) curves (AUC). The statistical significance of differences among these models was evaluated using DeLong's test.ResultsIn the training group, 68 of 217 patients had pathologically proven csPCa. The sensitivity and specificity for Scoring 1 were 64.7% (95% CI 52.2%-75.9%) and 80.5% (95% CI 73.3%-86.6%); for Scoring 2 were 86.8% (95% CI 76.4%-93.8%) and 73.2% (95% CI 65.3%-80.1%); and for Scoring 3 were 61.8% (95% CI 49.2%-73.3%) and 80.5% (95% CI 73.3%-86.6%), respectively. Multivariable regression analysis revealed that scorings based on bpMRI, age, and prostate-specific antigen density (PSAD) were independent predictors of csPCa. The AUCs for the 3 models were 0.88 (95% CI 0.83-0.93), 0.90 (95% CI 0.85-0.94), and 0.88 (95% CI 0.83-0.93), respectively. Model 2 showed significantly higher performance than Model 1 (P = 0.03) and Model 3 (P < 0.01).ConclusionAll three scorings had favorite diagnostic accuracy. While in conjunction with age and PSAD the prediction power was significantly improved, and the Model 2 that based on Scoring 2 yielded the highest performance.
| S-EPMC10478308 | biostudies-literature
Project description:PurposesThe presence of clinically significant prostate cancer (csPCa) is equivocal for patients with prostate imaging reporting and data system (PI-RADS) category 3. We aim to develop deep learning models for re-stratify risks in PI-RADS category 3 patients.MethodsThis retrospective study included a bi-parametric MRI of 1567 consecutive male patients from six centers (Centers 1-6) between Jan 2015 and Dec 2020. Deep learning models with double channel attention modules based on MRI (AttenNet) for predicting PCa and csPCa were constructed separately. Each model was first pretrained using 1144 PI-RADS 1-2 and 4-5 images and then retrained using 238 PI-RADS 3 images from three training centers (centers 1-3), and tested using 185 PI-RADS 3 images from the other three testing centers (centers 4-6).ResultsOur AttenNet models achieved excellent prediction performances in testing cohort of center 4-6 with the area under the receiver operating characteristic curves (AUC) of 0.795 (95% CI: [0.700, 0.891]), 0.963 (95% CI: [0.915, 1]) and 0.922 (95% CI: [0.810, 1]) in predicting PCa, and the corresponding AUCs were 0.827 (95% CI: [0.703, 0.952]) and 0.926 (95% CI: [0.846, 1]) in predicting csPCa in testing cohort of center 4 and center 5. In particular, 71.1% to 92.2% of non-csPCa patients were identified by our model in three testing cohorts, who can spare from invasive biopsy or RP procedure.ConclusionsOur model offers a noninvasive screening clinical tool to re-stratify risks in PI-RADS 3 patients, thereby reducing unnecessary invasive biopsies and improving the effectiveness of biopsies.Critical relevance statementThe deep learning model with MRI can help to screen out csPCa in PI-RADS category 3.Key pointsAttenNet models included channel attention and soft attention modules. 71.1-92.2% of non-csPCa patients were identified by the AttenNet model. The AttenNet models can be a screen clinical tool to re-stratify risks in PI-RADS 3 patients.
| S-EPMC11780012 | biostudies-literature