Abstract #2844

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

Aldo Marzullo^1,2, Claudio Stamile¹, Gabriel Kocevar¹, Francesco Calimeri², Giorgio Terracina², Françoise Durand-Dubief^1,3, and Dominique Sappey-Marinier^1,4

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