Dataset Information

MR Imaging-Based Radiomic Signatures of Distinct Molecular Subgroups of Medulloblastoma.

ABSTRACT: BACKGROUND AND PURPOSE:Distinct molecular subgroups of pediatric medulloblastoma confer important differences in prognosis and therapy. Currently, tissue sampling is the only method to obtain information for classification. Our goal was to develop and validate radiomic and machine learning approaches for predicting molecular subgroups of pediatric medulloblastoma. MATERIALS AND METHODS:In this multi-institutional retrospective study, we evaluated MR imaging datasets of 109 pediatric patients with medulloblastoma from 3 children's hospitals from January 2001 to January 2014. A computational framework was developed to extract MR imaging-based radiomic features from tumor segmentations, and we tested 2 predictive models: a double 10-fold cross-validation using a combined dataset consisting of all 3 patient cohorts and a 3-dataset cross-validation, in which training was performed on 2 cohorts and testing was performed on the third independent cohort. We used the Wilcoxon rank sum test for feature selection with assessment of area under the receiver operating characteristic curve to evaluate model performance. RESULTS:Of 590 MR imaging-derived radiomic features, including intensity-based histograms, tumor edge-sharpness, Gabor features, and local area integral invariant features, extracted from imaging-derived tumor segmentations, tumor edge-sharpness was most useful for predicting sonic hedgehog and group 4 tumors. Receiver operating characteristic analysis revealed superior performance of the double 10-fold cross-validation model for predicting sonic hedgehog, group 3, and group 4 tumors when using combined T1- and T2-weighted images (area under the curve = 0.79, 0.70, and 0.83, respectively). With the independent 3-dataset cross-validation strategy, select radiomic features were predictive of sonic hedgehog (area under the curve = 0.70-0.73) and group 4 (area under the curve = 0.76-0.80) medulloblastoma. CONCLUSIONS:This study provides proof-of-concept results for the application of radiomic and machine learning approaches to a multi-institutional dataset for the prediction of medulloblastoma subgroups.

SUBMITTER: Iv M

PROVIDER: S-EPMC6330121 | biostudies-literature | 2019 Jan

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

MR Imaging-Based Radiomic Signatures of Distinct Molecular Subgroups of Medulloblastoma.

Iv M M Zhou M M Shpanskaya K K Perreault S S Wang Z Z Tranvinh E E Lanzman B B Vajapeyam S S Vitanza N A NA Fisher P G PG Cho Y J YJ Laughlin S S Ramaswamy V V Taylor M D MD Cheshier S H SH Grant G A GA Young Poussaint T T Gevaert O O Yeom K W KW

AJNR. American journal of neuroradiology 20181206 1

<h4>Background and purpose</h4>Distinct molecular subgroups of pediatric medulloblastoma confer important differences in prognosis and therapy. Currently, tissue sampling is the only method to obtain information for classification. Our goal was to develop and validate radiomic and machine learning approaches for predicting molecular subgroups of pediatric medulloblastoma.<h4>Materials and methods</h4>In this multi-institutional retrospective study, we evaluated MR imaging datasets of 109 pediatr ...[more]

PMID: 30523141

Similar Datasets

Project description:BackgroundCardiac magnetic resonance (MR) images are often collected with different imaging parameters, which may impact the calculated values of myocardial radiomic features.PurposeTo investigate the sensitivity of myocardial radiomic features to changes in imaging parameters in cardiac MR images.Study typeProspective.PopulationA total of 11 healthy participants/five patients.Field strength/ sequenceA 3 T/cine balanced steady-state free-precession, T1 -weighted spoiled gradient-echo, T2 -weighted turbo spin-echo, and quantitative T1 and T2 mapping. For each sequence, the flip angle, in-plane resolution, slice thickness, and parallel imaging technique were varied to study the sensitivity of radiomic features to alterations in imaging parameters.AssessmentMyocardial contours were manually delineated by experienced readers, and a total of 1023 radiomic features were extracted using PyRadiomics with 11 image filters and six feature families.Statistical testsSensitivity was defined as the standardized mean difference (D effect size), and the robust features were defined at sensitivity < 0.2. Sensitivity analysis was performed on predefined sets of reproducible features. The analysis was performed using the entire cohort of 16 subejcts.Results64% of radiomic features were robust (sensitivity < 0.2) to changes in any imaging parameter. In qualitative sequences, radiomic features were most sensitive to changes in in-plane spatial resolution (spatial resolution: 0.6 vs. flip angle: 0.19, parallel imaging: 0.18, slice thickness: 0.07; P < 0.01 for all); in quantitative sequences, radiomic features were least sensitive to changes in spatial resolution (spatial resolution: 0.07 vs. slice thickness: 0.16, flip angle: 0.24; P < 0.01 for all). In an individual feature level, no singular feature family/image filter was identified as robust (sensitivity < 0.2) across sequences; however, highly sensitive features were predominantly associated with high-frequency wavelet filters across all sequences (32/50 features).Data conclusionIn cardiac MR, a considerable number of radiomic features are sensitive to changes in sequence parameters.Evidence level1 TECHNICAL EFFICACY: Stage 1.

Project description:"Transcriptionally different" medulloblastoma groups are associated with specific signaling pathway abnormalities; hence, they may present with distinct imaging manifestations. In this study, we sought to describe the MR imaging features of wingless-type-subgroup medulloblastomas with embryologic correlations.Pre- and postoperative imaging studies of 16 patients with wingless-type-subgroup medulloblastoma were evaluated for tumor location, involvement of surrounding CSF spaces or parenchymal structures, conventional and DWI signal properties, and postsurgical damage patterns. Laterality scores were assigned to tumors at each step in the evaluation process. Continuous variables were summarized by using descriptive statistics. The Wilcoxon signed rank test was performed to compare laterality scores. To determine the interobserver variability, we computed the intraclass correlation and Cohen κ coefficients.Wingless-type-subgroup medulloblastomas in our series were histopathologically "classic." Wingless-type-subgroup medulloblastomas occur in specific sites, with involvement of the foramen of Luschka (75%), the fourth ventricle (68.75%), the cisterna magna (31.25%), and the cerebellopontine angle cistern (18.75%). Laterality scores were low (<2) when preoperative primary and secondary anatomic features were evaluated separately, but they increased (>2) when all pre- and postoperative anatomic features were considered. Results were statistically shown to be reproducible (interclass correlation coefficient, 0.71-0.94; Cohen κ, 0.63-1.00). On the basis of anatomic lesion patterns, 4 location-based subtypes may be distinguished: 1) midline-intraventricular, 2) midline-extraventricular, 3) off-midline-intraventricular, and 4) off-midline-extraventricular, which represent a continuum.Wingless-type-subgroup medulloblastomas are lateralized tumors arising from the brain stem and cerebellum around the foramen of Luschka. Our current understanding of their embryologic origins is in concordance with the spatial distribution of these tumors.

Dataset Information

MR Imaging-Based Radiomic Signatures of Distinct Molecular Subgroups of Medulloblastoma.

Publications

MR Imaging-Based Radiomic Signatures of Distinct Molecular Subgroups of Medulloblastoma.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets