Meeting Banner
Abstract #0899

Machine learning and rapid multi-parametric relaxometry can differentiate demyelinating disorders with high accuracy

Gabriel Mangeat1,2, Russell Ouellette2,3,4, Maxime Wabartha1, Virginija Danylaité Karrenbauer3,5, Nikola Stikov1, Marcel Warntjes6,7, Nikola Stikov1,8, Caterina Mainero2,9, Julien Cohen-Adad1,10, and Tobias Granberg2,3,4,9

1NeuroPoly Lab, Institute of Biomedical Engineering, Polytechnique Montreal, Montreal, QC, Canada, 2Athinoula A. Martinos Center for Biomedical Imaging, MGH, Charlestown, MA, United States, 3Department of Clinical Neuroscience, Karolinska Institutet, Stockholm, Sweden, 4Department of Radiology, Division of Neuroradiology, Karolinska University Hospital, Stockholm, Sweden, 5Department of Neurology, Karolinska University Hospital, Stockholm, Sweden, 6Center for Medical Imaging Science and Visualization, CMIV, Linköping, Sweden, 7SyntheticMR, Linköping, Sweden, 8Montreal Health Institute, Montreal, QC, Canada, 9Harvard Medical School, Boston, MA, United States, 10Functional Neuroimaging Unit, CRIUGM, Université de Montréal, Montreal, QC, Canada

Hereditary diffuse leukoencephalopathy with spheroids (HDLS) and multiple sclerosis (MS) are both demyelinating and neurodegenerative disorders that can be hard to distinguish clinically and radiologically. Here, we present a machine learning method that relies on rapid multi-parametric relaxometry and volumetry to achieve a robust classification of HDLS vs. MS. Linear discriminant analysis was shown to be a favorable approach compared to non-linear options. A leave-one-out cross-validation show a detection rate of 100% and 0% false positives for both conditions, which suggests that computer-assistance maybe helpful in accurately diagnosing these disorders.

This abstract and the presentation materials are available to members only; a login is required.

Join Here