Sparse classification with MRI based markers for neuromuscular disease categorization

Katerina Gkirtzou 1, 2 Jean-François Deux 3 Guillaume Bassez 4 Aristeidis Sotiras 5 Alain Rahmouni 3 Thibault Varacca 3 Nikos Paragios 1, 6, 7, 8, 9, 10 Matthew Blaschko 1, 2
1 GALEN - Organ Modeling through Extraction, Representation and Understanding of Medical Image Content
Inria Saclay - Ile de France, Ecole Centrale Paris
2 CVN - Centre de vision numérique
3 Hôpital Henri Mondor
4 Centre de reference des maladies rares neuromusculaires, APHP, GH Henri Mondor, Creteil
5 SBIA - Section of Biomedical Image Analysis [Philadelphia]
6 MAS - Mathématiques Appliquées aux Systèmes - EA 4037
7 IMAGINE [Marne-la-Vallée]
CSTB - Centre Scientifique et Technique du Bâtiment, LIGM - Laboratoire d'Informatique Gaspard-Monge, ENPC - École des Ponts ParisTech
8 LIGM - Laboratoire d'Informatique Gaspard-Monge
9 UPEM - Université Paris-Est Marne-la-Vallée
10 ENPC - École des Ponts ParisTech
Abstract : In this paper, we present a novel method for disease classification between two patient populations based on features extracted from Magnetic Resonance Imaging (MRI) data. Anatomically meaningful features are extracted from structural data (T1- and T2-weighted MR images) and Diffusion Tensor Imaging (DTI) data, and used to train a new machine learning algorithm, the k-support SVM (ksup-SVM). The k-support regularized SVM has an inherent feature selection property, and thus it eliminates the requirement for a separate feature selection step. Our dataset consists of patients that suffer from facioscapulohumeral muscular dystrophy (FSH) and Myotonic muscular dystrophy type 1 (DM1) and our proposed method achieves a high performance. More specifically, it achieves a mean Area Under the Curve (AUC) of 0.7141 and mean accuracy 77% ± 0.013. Moreover, we provide a sparsity visualization of the features in order to indentify their discriminative value. The results suggest the potential of the combined use of MR markers to diagnose myopathies, and the general utility of the ksup-SVM. Source code is also available at https://gitorious.org/ksup-svm.
Keywords : myopathies Diffusion Tensor Imaging k-support regularized SVM
Type de document :
Communication dans un congrès
4th International Workhop on Machine Learning in Medical Imaging, Sep 2013, Nagoya, Japan. Springer, 2013
Liste complète des métadonnées
https://hal.inria.fr/hal-00845126
Contributeur : Katerina Gkirtzou <>
Soumis le : jeudi 18 juillet 2013 - 14:00:24
Dernière modification le : mercredi 30 mai 2018 - 17:22:02
Document(s) archivé(s) le : mercredi 5 avril 2017 - 12:49:59

Fichiers

MLMI-8.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : hal-00845126, version 1

Collections

INRIA | EC-PARIS | ENPC | IMAGINE | PARISTECH | ECP-DR | MAS | UPEC-UPEM | CVN | LIGM

Citation

Katerina Gkirtzou, Jean-François Deux, Guillaume Bassez, Aristeidis Sotiras, Alain Rahmouni, et al.. Sparse classification with MRI based markers for neuromuscular disease categorization. 4th International Workhop on Machine Learning in Medical Imaging, Sep 2013, Nagoya, Japan. Springer, 2013. 〈hal-00845126〉

Exporter

BibTeX TEI DC DCterms EndNote

Partager

Métriques

Consultations de la notice

793

Téléchargements de fichiers

336

Contact


archive-ouverte@inria.fr