Meeting Banner
Abstract #2844

Exploiting Heterogeneous Data for Automatic Classification of Multiple Sclerosis Clinical Forms through Neural Networks

Aldo Marzullo1,2, Claudio Stamile1, Gabriel Kocevar1, Francesco Calimeri2, Giorgio Terracina2, Françoise Durand-Dubief1,3, and Dominique Sappey-Marinier1,4

1CREATIS, University Claude Bernard Lyon 1, Lyon, France, 2Department of Mathematics and Computer Science, University of Calabria, Rende, Italy, 3Hôpital Neurologique, Service de Neurologie A, Hospices Civils de Lyon, Lyon, France, 4CERMEP - Imagerie du Vivant, Université de Lyon, Lyon, France

This work is aimed at producing a fully automatic model for the classification of MS clinical profiles exploiting heterogeneous source of data. The task is addressed by extracting the connectivity graph of the subject as well as the corresponding MRI-derived feature vector, and then by applying a two-branches NN procedure to obtain the corresponding classification.

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

Join Here