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

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.

In Vivo 7T MR Quantitative Susceptibility Mapping Reveals Opposite Susceptibility Contrast between Cortical and White Matter Lesions in Multiple Sclerosis.

BACKGROUND AND PURPOSE: Magnetic susceptibility measured with quantitative susceptibility mapping has been proposed as a biomarker for demyelination and inflammation in patients with MS, but investigations have mostly been on white matter lesions. A detailed characterization of cortical lesions has not been performed. The purpose of this study was to evaluate magnetic susceptibility in both cortical and WM lesions in MS by using quantitative susceptibility mapping. MATERIALS AND METHODS: Fourteen patients with MS were scanned on a 7T MR imaging scanner with T1-, T2-, and T2*-weighted sequences. The T2*-weighted sequence was used to perform quantitative susceptibility mapping and generate tissue susceptibility maps. The susceptibility contrast of a lesion was quantified as the relative susceptibility between the lesion and its adjacent normal-appearing parenchyma. The susceptibility difference between cortical and WM lesions was assessed by using a t test. RESULTS: The mean relative susceptibility was significantly negative for cortical lesions (P < 10-7) but positive for WM lesions (P < 10-22). A similar pattern was also observed in the cortical (P = .054) and WM portions (P = .043) of mixed lesions. CONCLUSIONS: The negative susceptibility in cortical lesions suggests that iron loss dominates the susceptibility contrast in cortical lesions. The opposite susceptibility contrast between cortical and WM lesions may reflect both their structural (degree of myelination) and pathologic (degree of inflammation) differences, in which the latter may lead to a faster release of iron in cortical lesions.