Evaluation of registration methods on thoracic CT: the EMPIRE10 challenge.

Keelin Murphy 1 Bram Van Ginneken 1, * Joseph Reinhardt 2 Sven Kabus 3 Kai Ding 2 Xiang Deng 4 Kunlin Cao 2, 5 Kaifang Du 2 Gary Christensen 2 Vincent Garcia 6 Tom Vercauteren 7 Nicholas Ayache 8 Olivier Commowick 9 Grégoire Malandain 8 Ben Glocker 10 Nikolaos Paragios 11, 12 Nassir Navab 10 Vladlena Gorbunova 13 Jon Sporring 13 Marleen De Bruijne 13, 14 Xiao Han 15 Mattias Heinrich 16, 17 Julia Schnabel 16 Mark Jenkinson 17 Cristian Lorenz 3 Marc Modat 18 Jamie Mcclelland 18 Sébastien Ourselin 18 Sacha Muenzing 1 Max Viergever 1 Dante De Nigris 19 Louis Collins 20, 21 Tal Arbel 19 Marta Peroni 22 Rui Li 22 Gregory Sharp 22 Alexander Schmidt-Richberg 23 Jan Ehrhardt 23 René Werner 23 Dirk Smeets 24 Dirk Loeckx 24 Gang Song 25 Nicholas Tustison 26 Brian Avants 25 James Gee 25 Marius Staring 27 Stefan Klein 14 Berend Stoel 27 Martin Urschler 28 Manuel Werlberger 28 Jef Vandemeulebroucke 29 Simon Rit 30 David Sarrut 29 Josien Pluim 1
* Auteur correspondant
8 ASCLEPIOS - Analysis and Simulation of Biomedical Images
CRISAM - Inria Sophia Antipolis - Méditerranée
9 VisAGeS - Vision, Action et Gestion d'informations en Santé
INSERM - Institut National de la Santé et de la Recherche Médicale : U746, Inria Rennes – Bretagne Atlantique , IRISA-D5 - SIGNAUX ET IMAGES NUMÉRIQUES, ROBOTIQUE
Abstract : EMPIRE10 (Evaluation of Methods for Pulmonary Image REgistration 2010) is a public platform for fair and meaningful comparison of registration algorithms which are applied to a database of intrapatient thoracic CT image pairs. Evaluation of nonrigid registration techniques is a nontrivial task. This is compounded by the fact that researchers typically test only on their own data, which varies widely. For this reason, reliable assessment and comparison of different registration algorithms has been virtually impossible in the past. In this work we present the results of the launch phase of EMPIRE10, which comprised the comprehensive evaluation and comparison of 20 individual algorithms from leading academic and industrial research groups. All algorithms are applied to the same set of 30 thoracic CT pairs. Algorithm settings and parameters are chosen by researchers expert in the configuration of their own method and the evaluation is independent, using the same criteria for all participants. All results are published on the EMPIRE10 website (http://empire10.isi.uu.nl). The challenge remains ongoing and open to new participants. Full results from 24 algorithms have been published at the time of writing. This paper details the organization of the challenge, the data and evaluation methods and the outcome of the initial launch with 20 algorithms. The gain in knowledge and future work are discussed.
Type de document :
Article dans une revue
IEEE Transactions on Medical Imaging, Institute of Electrical and Electronics Engineers, 2011, 30 (11), pp.1901-20. 〈10.1109/TMI.2011.2158349〉
Liste complète des métadonnées

Littérature citée [59 références]  Voir  Masquer  Télécharger

http://www.hal.inserm.fr/inserm-00607794
Contributeur : Olivier Commowick <>
Soumis le : lundi 11 juillet 2011 - 12:46:19
Dernière modification le : lundi 11 décembre 2017 - 11:20:19
Document(s) archivé(s) le : jeudi 30 mars 2017 - 12:59:29

Fichier

 Accès restreint
Fichier visible le : jamais

Connectez-vous pour demander l'accès au fichier

Identifiants

Citation

Keelin Murphy, Bram Van Ginneken, Joseph Reinhardt, Sven Kabus, Kai Ding, et al.. Evaluation of registration methods on thoracic CT: the EMPIRE10 challenge.. IEEE Transactions on Medical Imaging, Institute of Electrical and Electronics Engineers, 2011, 30 (11), pp.1901-20. 〈10.1109/TMI.2011.2158349〉. 〈inserm-00607794〉

Partager

Métriques

Consultations de la notice

1264