Dataset Information

Repeatability of Multiparametric Prostate MRI Radiomics Features.

ABSTRACT: In this study we assessed the repeatability of radiomics features on small prostate tumors using test-retest Multiparametric Magnetic Resonance Imaging (mpMRI). The premise of radiomics is that quantitative image-based features can serve as biomarkers for detecting and characterizing disease. For such biomarkers to be useful, repeatability is a basic requirement, meaning its value must remain stable between two scans, if the conditions remain stable. We investigated repeatability of radiomics features under various preprocessing and extraction configurations including various image normalization schemes, different image pre-filtering, and different bin widths for image discretization. Although we found many radiomics features and preprocessing combinations with high repeatability (Intraclass Correlation Coefficient > 0.85), our results indicate that overall the repeatability is highly sensitive to the processing parameters. Neither image normalization, using a variety of approaches, nor the use of pre-filtering options resulted in consistent improvements in repeatability. We urge caution when interpreting radiomics features and advise paying close attention to the processing configuration details of reported results. Furthermore, we advocate reporting all processing details in radiomics studies and strongly recommend the use of open source implementations.

SUBMITTER: Schwier M

PROVIDER: S-EPMC6602944 | biostudies-literature | 2019 Jul

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Repeatability of Multiparametric Prostate MRI Radiomics Features.

Schwier Michael M van Griethuysen Joost J Vangel Mark G MG Pieper Steve S Peled Sharon S Tempany Clare C Aerts Hugo J W L HJWL Kikinis Ron R Fennessy Fiona M FM Fedorov Andriy A

Scientific reports 20190701 1

In this study we assessed the repeatability of radiomics features on small prostate tumors using test-retest Multiparametric Magnetic Resonance Imaging (mpMRI). The premise of radiomics is that quantitative image-based features can serve as biomarkers for detecting and characterizing disease. For such biomarkers to be useful, repeatability is a basic requirement, meaning its value must remain stable between two scans, if the conditions remain stable. We investigated repeatability of radiomics fe ...[more]

PMID: 31263116

Similar Datasets

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.

Project description:BackgroundRenal multiparametric magnetic resonance imaging (MRI) is a promising tool for diagnosis, prognosis, and treatment monitoring in kidney disease.PurposeTo determine intrasubject test-retest repeatability of renal MRI measurements.Study typeProspective.PopulationNineteen healthy subjects aged over 40 years.Field strength/sequencesT1 and T2 mapping, R2 * mapping or blood oxygenation level-dependent (BOLD) MRI, diffusion tensor imaging (DTI), and intravoxel incoherent motion (IVIM) diffusion-weighted imaging (DWI), 2D phase contrast, arterial spin labelling (ASL), dynamic contrast enhanced (DCE) MRI, and quantitative Dixon for fat quantification at 3T.AssessmentSubjects were scanned twice with ~1 week between visits. Total scan time was ~1 hour. Postprocessing included motion correction, semiautomated segmentation of cortex and medulla, and fitting of the appropriate signal model.Statistical testTo assess the repeatability, a Bland-Altman analysis was performed and coefficients of variation (CoVs), repeatability coefficients, and intraclass correlation coefficients were calculated.ResultsCoVs for relaxometry (T1 , T2 , R2 */BOLD) were below 6.1%, with the lowest CoVs for T2 maps and highest for R2 */BOLD. CoVs for all diffusion analyses were below 7.2%, except for perfusion fraction (FP ), with CoVs ranging from 18-24%. The CoV for renal sinus fat volume and percentage were both around 9%. Perfusion measurements were most repeatable with ASL (cortical perfusion only) and 2D phase contrast with CoVs of 10% and 13%, respectively. DCE perfusion had a CoV of 16%, while single kidney glomerular filtration rate (GFR) had a CoV of 13%. Repeatability coefficients (RCs) ranged from 7.7-87% (lowest/highest values for medullary mean diffusivity and cortical FP , respectively) and intraclass correlation coefficients (ICCs) ranged from -0.01 to 0.98 (lowest/highest values for cortical FP and renal sinus fat volume, respectively).Data conclusionCoVs of most MRI measures of renal function and structure (with the exception of FP and perfusion as measured by DCE) were below 13%, which is comparable to standard clinical tests in nephrology.Level of evidence2 TECHNICAL EFFICACY: Stage 1.

Project description:ObjectiveTo identify which patient with prostate cancer (PCa) could safely avoid extended pelvic lymph node dissection (ePLND) by predicting lymph node invasion (LNI), via a radiomics-based machine learning approach.MethodsAn integrative radiomics model (IRM) was proposed to predict LNI, confirmed by the histopathologic examination, integrating radiomics features, extracted from prostatic index lesion regions on MRI images, and clinical features via SVM. The study cohort comprised 244 PCa patients with MRI and followed by radical prostatectomy (RP) and ePLND within 6 months between 2010 and 2019. The proposed IRM was trained in training/validation set and evaluated in an internal independent testing set. The model's performance was measured by area under the curve (AUC), sensitivity, specificity, negative predictive value (NPV), and positive predictive value (PPV). AUCs were compared via Delong test with 95% confidence interval (CI), and the rest measurements were compared via chi-squared test or Fisher's exact test.ResultsOverall, 17 (10.6%) and 14 (16.7%) patients with LNI were included in training/validation set and testing set, respectively. Shape and first-order radiomics features showed usefulness in building the IRM. The proposed IRM achieved an AUC of 0.915 (95% CI: 0.846-0.984) in the testing set, superior to pre-existing nomograms whose AUCs were from 0.698 to 0.724 (p < 0.05).ConclusionThe proposed IRM could be potentially feasible to predict the risk of having LNI for patients with PCa. With the improved predictability, it could be utilized to assess which patients with PCa could safely avoid ePLND, thus reduce the number of unnecessary ePLND.Key points• The combination of MRI-based radiomics features with clinical information improved the prediction of lymph node invasion, compared with the model using only radiomics features or clinical features. • With improved prediction performance on predicting lymph node invasion, the number of extended pelvic lymph node dissection (ePLND) could be reduced by the proposed integrative radiomics model (IRM), compared with the existing nomograms.

Project description:Radiomics is an emerging field of image analysis with potential applications in patient risk stratification. This study developed and evaluated machine learning models using quantitative radiomic features extracted from multiparametric magnetic resonance imaging (mpMRI) to detect and classify prostate cancer (PCa). In total, 191 patients that underwent prostatic mpMRI and combined targeted and systematic fusion biopsy were retrospectively included. Segmentations of the whole prostate glands and index lesions were performed manually in apparent diffusion coefficient (ADC) maps and T2-weighted MRI. Radiomic features were extracted from regions corresponding to the whole prostate gland and index lesion. The best performing combination of feature setup and classifier was selected to compare its predictive ability of the radiologist's evaluation (PI-RADS), mean ADC, prostate specific antigen density (PSAD) and digital rectal examination (DRE) using receiver operating characteristic (ROC) analysis. Models were evaluated using repeated 5-fold cross-validation and a separate independent test cohort. In the test cohort, an ensemble model combining a radiomics model, with models for PI-RADS, PSAD and DRE achieved high predictive AUCs for the differentiation of (i) malignant from benign prostatic lesions (AUC = 0.889) and of (ii) clinically significant (csPCa) from clinically insignificant PCa (cisPCa) (AUC = 0.844). Our combined model was numerically superior to PI-RADS for cancer detection (AUC = 0.779; p = 0.054) as well as for clinical significance prediction (AUC = 0.688; p = 0.209) and showed a significantly better performance compared to mADC for csPCa prediction (AUC = 0.571; p = 0.022). In our study, radiomics accurately characterizes prostatic index lesions and shows performance comparable to radiologists for PCa characterization. Quantitative image data represent a potential biomarker, which, when combined with PI-RADS, PSAD and DRE, predicts csPCa more accurately than mADC. Prognostic machine learning models could assist in csPCa detection and patient selection for MRI-guided biopsy.

Project description:PURPOSE:In this study, we aimed to analyze the repeatability of quantitative multiparametric rectal magnetic resonance imaging (MRI) parameters with different measurement techniques. METHODS:All examinations were performed with 3 T MRI system. In addition to routine sequences for rectal cancer imaging protocol, small field-of-view diffusion-weighted imaging and perfusion sequences were acquired in each patient. Apparent diffusion coefficient (ADC) was used for diffusion analysis and ktrans was used for perfusion analysis. Three different methods were used in measurement of these parameters; measurements were performed twice by one radiologist for intraobserver and separately by three radiologists for interobserver variability analysis. ADC was measured by the lowest value, the value at maximum wall thickness, and freehand techniques. Ktrans was measured at the slice with maximum wall thickness, by freehand drawn region of interest (ROI), and at the dark red spot with maximum value. RESULTS:A total of 30 patients with biopsy-proven rectal adenocarcinoma were included in the study. The mean values of the parameters measured by the first radiologist on the first and second measurements were as follows: mean lowest ADC, 721.31±147.18 mm2/s and 718.96±135.71 mm2/s; mean ADC value on the slice with maximum wall thickness, 829.90±144.24 mm2/s and 829.48±149.23 mm2/s; mean ADC value measured by freehand ROI on the slice with maximum wall thickness, 846.56±136.31 mm2/s and 848.23±144.15 mm2/s; mean ktrans value on the slice with maximum wall thickness, 0.219±0.080 and 0.214±0.074; mean ktrans by freehand ROI technique (including as much tumoral tissue as possible), 0.208±0.074 and 0.207±0.069; mean ktrans measured from the dark red foci, 0.308±0.109 and 0.311±0.105. Intraobserver agreement was very good among diffusion and perfusion parameters obtained with all three measurement techniques. Interobserver agreement was very good, except for one of the measurement techniques. As far as interobserver variability is considered, only ADC value measured on the slice with maximum wall thickness differed significantly. CONCLUSION:Multiparametric MRI of rectum, using ADC as the diffusion and ktrans as the perfusion parameter is a repeatable technique. This technique may potentially be used in prediction and evaluation of neoadjuvant treatment response. New studies with larger patient groups are needed to validate the role of multiparametric MRI.

Dataset Information

Repeatability of Multiparametric Prostate MRI Radiomics Features.

Publications

Repeatability of Multiparametric Prostate MRI Radiomics Features.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets