Objective Evaluation of Multiple Sclerosis Lesion Segmentation using a Data Management and Processing Infrastructure

Olivier Commowick 1 Audrey Istace 2 Michael Kain 1 Baptiste Laurent 3 Florent Leray 1 Mathieu Simon 1 Sorina Pop 4 Pascal Girard 4 Roxana Ameli 2 Jean-Christophe Ferré 5, 1 Anne Kerbrat 6, 1 Thomas Tourdias 7 Frédéric Cervenansky 4 Tristan Glatard 8 Jeremy Beaumont 1 Senan Doyle 9 Florence Forbes 10 Jesse Knight 11 April Khademi 12 Amirreza Mahbod 13 Chunliang Wang 13 Richard Mckinley 14 Franca Wagner 14 John Muschelli 15 Elizabeth Sweeney 15 Eloy Roura 16 Xavier Lladó 16 Michel Santos 17 Wellington Santos 17 Abel Silva-Filho 17 Xavier Tomas-Fernandez 18 Hélène Urien 19 Isabelle Bloch 19 Sergi Valverde 16 Mariano Cabezas 16 Francisco Vera-Olmos 20 Norberto Malpica 20 Charles Guttmann 21 Sandra Vukusic 2 Gilles Edan 1, 22 Michel Dojat 23 Martin Styner 24 Simon Warfield 18 François Cotton 2 Christian Barillot 1
1 VisAGeS - Vision, Action et Gestion d'informations en Santé
INSERM - Institut National de la Santé et de la Recherche Médicale : U1228, Inria Rennes – Bretagne Atlantique , IRISA_D5 - SIGNAUX ET IMAGES NUMÉRIQUES, ROBOTIQUE
10 MISTIS - Modelling and Inference of Complex and Structured Stochastic Systems
Inria Grenoble - Rhône-Alpes, LJK - Laboratoire Jean Kuntzmann, INPG - Institut National Polytechnique de Grenoble
Abstract : We present a study of multiple sclerosis segmentation algorithms conducted at the international MICCAI 2016 challenge. This challenge was operated using a new open-science computing infrastructure. This allowed for the automatic and independent evaluation of a large range of algorithms in a fair and completely automatic manner. This computing infrastructure was used to evaluate thirteen methods of MS lesions segmentation, exploring a broad range of state-of-the-art algorithms, against a high-quality database of 53 MS cases coming from four centers following a common definition of the acquisition protocol. Each case was annotated manually by an unprecedented number of seven different experts. Results of the challenge highlighted that automatic algorithms, including the recent machine learning methods (random forests, deep learning,...), are still trailing human expertise on both detection and delineation criteria. In addition, we demonstrate that computing a statistically robust consensus of the algorithms performs closer to human expertise on one score (segmentation) although still trailing on detection scores.
Type de document :
Pré-publication, Document de travail
2018
Liste complète des métadonnées

Littérature citée [26 références]  Voir  Masquer  Télécharger

http://www.hal.inserm.fr/inserm-01847873
Contributeur : Olivier Commowick <>
Soumis le : mardi 24 juillet 2018 - 10:10:30
Dernière modification le : vendredi 14 septembre 2018 - 10:38:07

Fichier

367557.full.pdf
Publication financée par une institution

Identifiants

Citation

Olivier Commowick, Audrey Istace, Michael Kain, Baptiste Laurent, Florent Leray, et al.. Objective Evaluation of Multiple Sclerosis Lesion Segmentation using a Data Management and Processing Infrastructure. 2018. 〈inserm-01847873v1〉

Partager

Métriques

Consultations de la notice

241

Téléchargements de fichiers

51