1. MR-spectroscopic imaging of glial tumors in the spotlight of the 2016 WHO classification
- Author
-
Elie Diamandis, Horst Urbach, Jürgen Grauvogel, Dieter Henrik Heiland, Urs Würtemberger, Irina Mader, Ori Staszewski, Silke Lassmann, Oliver Schnell, Carl Phillip Simon Gabriel, and Konstanze Guggenberger
- Subjects
In vivo magnetic resonance spectroscopy ,Cancer Research ,Magnetic Resonance Spectroscopy ,Radiogenomics ,Glial tumor ,computer.software_genre ,Machine Learning ,03 medical and health sciences ,0302 clinical medicine ,Voxel ,Glioma ,Image Interpretation, Computer-Assisted ,Biomarkers, Tumor ,medicine ,Cluster Analysis ,Humans ,Prospective Studies ,medicine.diagnostic_test ,Brain Neoplasms ,business.industry ,Brain ,Magnetic resonance imaging ,medicine.disease ,Magnetic Resonance Imaging ,Isocitrate Dehydrogenase ,Random forest ,Exact test ,Neurology ,Oncology ,030220 oncology & carcinogenesis ,Mutation ,Neurology (clinical) ,business ,Nuclear medicine ,computer ,030217 neurology & neurosurgery - Abstract
The purpose of this study is to map spatial metabolite differences across three molecular subgroups of glial tumors, defined by the IDH1/2 mutation and 1p19q-co-deletion, using magnetic resonance spectroscopy. This work reports a new MR spectroscopy based classification algorithm by applying a radiomics analytics pipeline. 65 patients received anatomical and chemical shift imaging (5 × 5 × 20 mm voxel size). Tumor regions were segmented and registered to corresponding spectroscopic voxels. Spectroscopic features were computed (n = 860) in a radiomic approach and selected by a classification algorithm. Finally, a random forest machine-learning model was trained to predict the molecular subtypes. A cluster analysis identified three robust spectroscopic clusters based on the mean silhouette widths. Molecular subgroups were significantly associated with the computed spectroscopic clusters (Fisher’s Exact test p
- Published
- 2018
- Full Text
- View/download PDF