Computer-Aided Diagnosis Improves the Detection of Clinically Significant Prostate Cancer on Multiparametric-MRI: A Multi-Observer Performance Study Involving Inexperienced Readers.
Ontology highlight
ABSTRACT:
SUBMITTER: Giannini V
PROVIDER: S-EPMC8227686 | biostudies-literature |
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:ObjectivesTo quantify the incremental benefit of computer-assisted-detection (CAD) for polyps, for inexperienced readers versus experienced readers of CT colonography.Methods10 inexperienced and 16 experienced radiologists interpreted 102 colonography studies unassisted and with CAD utilised in a concurrent paradigm. They indicated any polyps detected on a study sheet. Readers' interpretations were compared against a ground-truth reference standard: 46 studies were normal and 56 had at least one polyp (132 polyps in total). The primary study outcome was the difference in CAD net benefit (a combination of change in sensitivity and change in specificity with CAD, weighted towards sensitivity) for detection of patients with polyps.ResultsInexperienced readers' per-patient sensitivity rose from 39.1% to 53.2% with CAD and specificity fell from 94.1% to 88.0%, both statistically significant. Experienced readers' sensitivity rose from 57.5% to 62.1% and specificity fell from 91.0% to 88.3%, both non-significant. Net benefit with CAD assistance was significant for inexperienced readers but not for experienced readers: 11.2% (95%CI 3.1% to 18.9%) versus 3.2% (95%CI -1.9% to 8.3%) respectively.ConclusionsConcurrent CAD resulted in a significant net benefit when used by inexperienced readers to identify patients with polyps by CT colonography. The net benefit was nearly four times the magnitude of that observed for experienced readers. Experienced readers did not benefit significantly from concurrent CAD.
| S-EPMC4565691 | biostudies-literature
Project description:ObjectivesTo investigate the added diagnostic value of arterial spin labelling (ASL) and diffusion tensor imaging (DTI) to structural MRI for computer-aided classification of Alzheimer's disease (AD), frontotemporal dementia (FTD), and controls.MethodsThis retrospective study used MRI data from 24 early-onset AD and 33 early-onset FTD patients and 34 controls (CN). Classification was based on voxel-wise feature maps derived from structural MRI, ASL, and DTI. Support vector machines (SVMs) were trained to classify AD versus CN (AD-CN), FTD-CN, AD-FTD, and AD-FTD-CN (multi-class). Classification performance was assessed by the area under the receiver-operating-characteristic curve (AUC) and accuracy. Using SVM significance maps, we analysed contributions of brain regions.ResultsCombining ASL and DTI with structural MRI resulted in higher classification performance for differential diagnosis of AD and FTD (AUC?=?84%; p?=?0.05) than using structural MRI by itself (AUC?=?72%). The performance of ASL and DTI themselves did not improve over structural MRI. The classifications were driven by different brain regions for ASL and DTI than for structural MRI, suggesting complementary information.ConclusionsASL and DTI are promising additions to structural MRI for classification of early-onset AD, early-onset FTD, and controls, and may improve the computer-aided differential diagnosis on a single-subject level.Key points• Multiparametric MRI is promising for computer-aided diagnosis of early-onset AD and FTD. • Diagnosis is driven by different brain regions when using different MRI methods. • Combining structural MRI, ASL, and DTI may improve differential diagnosis of dementia.
| S-EPMC5491625 | biostudies-literature
Project description:OBJECTIVE. The purpose of this study was to compare in a multireader manner the diagnostic accuracies of 3-T multiparametric MRI interpretation and serial prostate-specific antigen (PSA) measurement in predicting the presence of residual clinically significant prostate cancer after focal laser ablation. MATERIALS AND METHODS. Eighteen men had undergone focal laser ablation for low- or intermediate-risk prostate cancer as part of two National Cancer Institute-funded phase 1 clinical trials. Multiparametric MRI was performed immediately after and 6 and 12 months after focal laser ablation. Serial PSA measurements after focal laser ablation were recorded, and MRI-ultrasound fusion biopsy was performed 6 and 12 months after ablation and served as the reference standard. Multiparametric MRI was performed at 3 T with pelvic phased-array coils. T2-weighted, DW, and dynamic contrast-enhanced MR images were retrospectively assessed by two blinded radiologists using a 3-point Likert scale (0-2). Inter-reader agreement was assessed with the Cohen kappa statistic. The diagnostic accuracies of multiparametric MRI and PSA measurement were compared. RESULTS. Residual clinically significant prostate cancer was identified in 11 of 18 (61%) men. Logistic regression analysis of serial PSA measurements yielded a correct classification rate of 61.1% (p > 0.05). Using a multiparametric MRI threshold score of 4 or greater, both radiologists made correct classifications for 16 of 18 men (89%) at 6 months and 15 of 17 men (88%) at 12 months. Interreader agreement was substantial to excellent for T2-weighted imaging, DWI, and dynamic contrast-enhanced MRI and improved uniformly from 6 to 12 months. Logistic regression analysis of the retrospectively reviewed multiparametric MR images yielded AUCs greater than 0.90 for each radiologist 6 and 12 months after focal laser ablation (p < 0.001). CONCLUSION. Multiparametric MRI 6 and 12 months after focal laser ablation significantly outperformed serial PSA measurements for predicting the presence of residual clinically significant prostate cancer.
| S-EPMC7311209 | biostudies-literature
Project description:We consider the current and future role of transrectal ultrasound imaging in the diagnosis of prostate cancer, with a particular focus on the pre-biopsy localization and targeting role that multiparametric MRI (mpMRI) has come to occupy for some men in recent years. We draw a distinction between transrectal ultrasound (TRUS) used only as a means of distributing zonal biopsies with its employment as a means for identifying and targeting sonographically abnormal lesions. The role of AI in lesion identification and targeting will be reviewed. Comparisons of cost and availability, frequency of contraindications and diagnostic accuracy between these two imaging modalities will be drawn.
| S-EPMC7354342 | biostudies-literature
Project description:ObjectivesTo create a radiomics approach based on multiparametric magnetic resonance imaging (mpMRI) features extracted from an auto-fixed volume of interest (VOI) that quantifies the phenotype of clinically significant (CS) peripheral zone (PZ) prostate cancer (PCa).MethodsThis study included 206 patients with 262 prospectively called mpMRI prostate imaging reporting and data system 3-5 PZ lesions. Gleason scores > 6 were defined as CS PCa. Features were extracted with an auto-fixed 12-mm spherical VOI placed around a pin point in each lesion. The value of dynamic contrast-enhanced imaging(DCE), multivariate feature selection and extreme gradient boosting (XGB) vs. univariate feature selection and random forest (RF), expert-based feature pre-selection, and the addition of image filters was investigated using the training (171 lesions) and test (91 lesions) datasets.ResultsThe best model with features from T2-weighted (T2-w) + diffusion-weighted imaging (DWI) + DCE had an area under the curve (AUC) of 0.870 (95% CI 0.980-0.754). Removal of DCE features decreased AUC to 0.816 (95% CI 0.920-0.710), although not significantly (p = 0.119). Multivariate and XGB outperformed univariate and RF (p = 0.028). Expert-based feature pre-selection and image filters had no significant contribution.ConclusionsThe phenotype of CS PZ PCa lesions can be quantified using a radiomics approach based on features extracted from T2-w + DWI using an auto-fixed VOI. Although DCE features improve diagnostic performance, this is not statistically significant. Multivariate feature selection and XGB should be preferred over univariate feature selection and RF. The developed model may be a valuable addition to traditional visual assessment in diagnosing CS PZ PCa.Key points• T2-weighted and diffusion-weighted imaging features are essential components of a radiomics model for clinically significant prostate cancer; addition of dynamic contrast-enhanced imaging does not significantly improve diagnostic performance. • Multivariate feature selection and extreme gradient outperform univariate feature selection and random forest. • The developed radiomics model that extracts multiparametric MRI features with an auto-fixed volume of interest may be a valuable addition to visual assessment in diagnosing clinically significant prostate cancer.
| S-EPMC7033141 | biostudies-literature
Project description:PurposeTo assess the effect of computer-aided detection (CAD) of brain metastasis (BM) on radiologists' diagnostic performance in interpreting three-dimensional brain magnetic resonance (MR) imaging using follow-up imaging and consensus as the reference standard.Materials and methodsThe institutional review board approved this retrospective study. The study cohort consisted of 110 consecutive patients with BM and 30 patients without BM. The training data set included MR images of 80 patients with 450 BM nodules. The test set included MR images of 30 patients with 134 BM nodules and 30 patients without BM. We developed a CAD system for BM detection using template-matching and K-means clustering algorithms for candidate detection and an artificial neural network for false-positive reduction. Four reviewers (two neuroradiologists and two radiology residents) interpreted the test set images before and after the use of CAD in a sequential manner. The sensitivity, false positive (FP) per case, and reading time were analyzed. A jackknife free-response receiver operating characteristic (JAFROC) method was used to determine the improvement in the diagnostic accuracy.ResultsThe sensitivity of CAD was 87.3% with an FP per case of 302.4. CAD significantly improved the diagnostic performance of the four reviewers with a figure-of-merit (FOM) of 0.874 (without CAD) vs. 0.898 (with CAD) according to JAFROC analysis (p < 0.01). Statistically significant improvement was noted only for less-experienced reviewers (FOM without vs. with CAD, 0.834 vs. 0.877, p < 0.01). The additional time required to review the CAD results was approximately 72 sec (40% of the total review time).ConclusionCAD as a second reader helps radiologists improve their diagnostic performance in the detection of BM on MR imaging, particularly for less-experienced reviewers.
| S-EPMC5464563 | biostudies-literature
Project description:The risk of misclassifying clinically significant prostate cancer (csPCa) by multiparametric magnetic resonance imaging is consistent, also using the updated PIRADS score and although different definitions of csPCa, patients with Gleason Grade group (GG) ≥ 3 have a significantly worse prognosis. This study aims to develop a machine learning model predicting csPCa (i.e., any GG ≥ 3 lesion at target biopsy) by mpMRI radiomic features and analyzing similarities between GG groups. One hundred and two patients with 117 PIRADS ≥ 3 lesions at mpMRI underwent target+systematic biopsy, providing histologic diagnosis of PCa, 61 GG < 3 and 56 GG ≥ 3. Features were generated locally from an apparent diffusion coefficient and selected, using the LASSO method and Wilcoxon rank-sum test (p < 0.001), to achieve only four features. After data augmentation, the features were exploited to train a support vector machine classifier, subsequently validated on a test set. To assess the results, Kruskal-Wallis and Wilcoxon rank-sum tests (p < 0.001) and receiver operating characteristic (ROC)-related metrics were used. GG1 and GG2 were equivalent (p = 0.26), whilst clear separations between either GG[1,2] and GG ≥ 3 exist (p < 10-6). On the test set, the area under the curve = 0.88 (95% CI, 0.68-0.94), with positive and negative predictive values being 84%. The features retain a histological interpretation. Our model hints at GG2 being much more similar to GG1 than GG ≥ 3.
| S-EPMC9776977 | biostudies-literature
Project description:IntroductionThe Prostate Imaging Reporting and Data System (PIRADS) has shown promise in improving the detection of Gleason grade group (GG) 2-5 prostate cancer (PCa) and reducing the detection of indolent GG1 PCa. However, data on the performance of PIRADS in Black and Hispanic men is sparse. We evaluated the accuracy of PIRADS scores in detecting GG2-5 PCa in White, Black, and Hispanic men.MethodsWe performed a multicenter retrospective review of biopsy-naïve Black (n = 108), White (n = 108), and Hispanic (n = 64) men who underwent prostate biopsy (PB) following multiparametric MRI. Sensitivity and specificity of PIRADS for GG2-5 PCa were calculated. Race-stratified binary logistic regression models for GG2-5 PCa using standard clinical variables and PIRADS were used to calculate area under the receiver operating characteristics curves (AUC).ResultsRates of GG2-5 PCa were statistically similar between Blacks, Whites, and Hispanics (52.8% vs 42.6% vs 37.5% respectively, p = 0.12). Sensitivity was lower in Hispanic men compared to White men (87.5% vs 97.8% respectively, p = 0.01). Specificity was similar in Black versus White men (21.6% vs 27.4%, p = 0.32) and White versus Hispanic men (27.4% vs 17.5%, p = 0.14). The AUCs of the PIRADS added to standard clinical data (age, PSA and suspicious prostate exam) were similar when comparing Black versus White men (0.75 vs 0.73, p = 0.79) and White versus Hispanic men (0.73 vs 0.59, p = 0.11). The AUCs for the Base model and PIRADS model alone were statistically similar when comparing Black versus White men and White versus Hispanic men.ConclusionsThe accuracy of the PIRADS and clinical data for detecting GG2-5 PCa seems statistically similar across race. However, there is concern that PIRADS 2.0 has lower sensitivity in Hispanic men compared to White men. Prospective validation studies are needed.
| S-EPMC9295380 | biostudies-literature
Project description:Texture features based on the spatial relationship of pixels, known as the gray-level co-occurrence matrix (GLCM), may play an important role in providing the accurate classification of suspected prostate cancer. The purpose of this study was to use quantitative imaging parameters of pre-biopsy multiparametric magnetic resonance imaging (mpMRI) for the prediction of clinically significant prostate cancer. This was a prospective study, recruiting 200 men suspected of having prostate cancer. Participants were imaged using a protocol-based 3T MRI in the pre-biopsy setting. Radiomics parameters were extracted from the T2WI and ADC texture features of the gray-level co-occurrence matrix were delineated from the region of interest. Radical prostatectomy histopathology was used as a reference standard. A Kruskal-Wallis test was applied first to identify the significant radiomic features between the three groups of Gleason scores (i.e., G1, G2 and G3). Subsequently, the Holm-Bonferroni method was applied to correct and control the probability of false rejections. We compared the probability of correctly predicting significant prostate cancer between the explanatory GLCM radiomic features, PIRADS and PSAD, using the area under the receiver operation characteristic curves. We identified the significant difference in radiomic features between the three groups of Gleason scores. In total, 12 features out of 22 radiomics features correlated with the Gleason groups. Our model demonstrated excellent discriminative ability (C-statistic = 0.901, 95%CI 0.859-0.943). When comparing the probability of correctly predicting significant prostate cancer between explanatory GLCM radiomic features (Sum Variance T2WI, Sum Entropy T2WI, Difference Variance T2WI, Entropy ADC and Difference Variance ADC), PSAD and PIRADS via area under the ROC curve, radiomic features were 35.0% and 34.4% more successful than PIRADS and PSAD, respectively, in correctly predicting significant prostate cancer in our patients (p < 0.001). The Sum Entropy T2WI score had the greatest impact followed by the Sum Variance T2WI. Quantitative GLCM texture analyses of pre-biopsy MRI has the potential to be used as a non-invasive imaging technique to predict clinically significant cancer in men suspected of having prostate cancer.
| S-EPMC8699138 | biostudies-literature
Project description:BackgroundThere are some limitations in the commonly used methods for the detection of prostate cancer. There is a lack of nomograms based on multiparametric magnetic resonance imaging (mpMRI) and 68Ga-prostate-specific membrane antigen (PSMA) positron emission tomography-computed tomography (PET-CT) for the prediction of prostate cancer. The study seeks to compare the performance of mpMRI and 68Ga-PSMA PET-CT, and design a novel predictive model capable of predicting clinically significant prostate cancer (csPCa) before biopsy based on a combination of 68Ga-PSMA PET-CT, mpMRI, and patient clinical parameters.MethodsFrom September 2020 to June 2021, we prospectively enrolled 112 consecutive patients with no prior history of prostate cancer who underwent both 68Ga-PSMA PET-CT and mpMRI prior to biopsy at our clinical center. Univariate and multivariate regression analyses were used to identify predictors of csPCa, with a predictive model and its nomogram incorporating 68Ga-PSMA PET-CT, mpMRI, and the clinical predictors then being generated. The constructed model was evaluated using receiver operating characteristic (ROC) curve, calibration curve, and decision curve analysis, and further validated with the internal and external cohorts.ResultsThe model incorporated prostate-specific antigen density (PSAd), Prostate Imaging Reporting and Data System (PI-RADS) category, and maximum standardized uptake value (SUVmax), and it exhibited excellent predictive efficacy when applying to evaluate both training and validation cohorts [area under the curve (AUC): 0.936 and 0.940, respectively]. Compared with SUVmax alone, the model demonstrated excellent diagnostic performance with improved specificity (0.910, 95% CI: 0.824-0.963) and positive predictive values (0.811, 95% CI: 0.648-0.920). Calibration curve and decision curve analysis further confirmed that the model exhibited a high degree of clinical net benefit and low error rate.ConclusionsThe constructed model in this study was capable of accurately predicting csPCa prior to biopsy with excellent discriminative ability. As such, this model has the potential to be an effective non-invasive approach for the diagnosis of csPCa.
| S-EPMC10406546 | biostudies-literature