Meeting Banner
Abstract #1993

Clustering of Multiple Sclerosis Patient's Clinical Courses with White Matter Fiber-Bundle Profiles

Gabriel Kocevar1, Claudio Stamile1, François Cotton1,2, Françoise Durand-Dubief1,3, and Dominique Sappey-Marinier1,4

1CREATIS Laboratory, Université Claude Bernard - Lyon 1, Lyon, France, 2Centre Hospitalier Lyon-Sud - Service de Radiologie, Hospices Civils de Lyon, Lyon, France, 3Hôpital Neurologique - Service de Neurologie A, Hospices Civils de Lyon, Lyon, France, 4CERMEP - Imagerie du Vivant, Université de Lyon, Lyon, France

Predicting the individual multiple sclerosis (MS) patients evolution, based on markers available from disease onset, may help the neurologist in the patient care. However, such a prediction remains a challenge. In this study, we merged spatial information of fiber tracking with diffusivity metrics, measured in 68 patients presenting the three forms of MS, in order to classify patients using a white matter fiber-bundle profile analysis. The good performances of the clustering, reached with fractional anisotropy and mean diffusivity together, make our method a potential tool to better predict the disease evolution, especially the conversion of RR-MS to SP-MS.

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

Join Here