inserm-00607794, version 1
Evaluation of Registration Methods on Thoracic CT: The EMPIRE10 Challenge.
Keelin Murphy 1Bram Van Ginneken
1Joseph M. Reinhardt 2Sven Kabus 3Kai Ding 2Xiang Deng 4Kunlin Cao 2, 5Kaifang Du 2Gary E. Christensen 2Vincent Garcia 6Tom Vercauteren 7Nicholas Ayache 8Olivier Commowick 9Grégoire Malandain
8Ben Glocker 10Nikolaos Paragios 11, 12Nassir Navab 10Vladlena Gorbunova 13Jon Sporring 13Marleen De Bruijne 13, 14Xiao Han 15Mattias P. Heinrich 16, 17Julia A. Schnabel 16Mark Jenkinson 17Cristian Lorenz 3Marc Modat 18Jamie R. Mcclelland 18Sébastien Ourselin 18Sacha Ea Muenzing 1Max A. Viergever 1Dante De Nigris 19Louis D. Collins 20, 21Tal Arbel 19Marta Peroni 22Rui Li 22Gregory C. Sharp 22Alexander Schmidt-Richberg 23Jan Ehrhardt 23René Werner 23Dirk Smeets 24Dirk Loeckx 24Gang Song 25Nicholas Tustison 26Brian Avants 25James C. Gee 25Marius Staring 27Stefan Klein 14Berend C. Stoel 27Martin Urschler 28Manuel Werlberger 28Jef Vandemeulebroucke 29Simon Rit 30David Sarrut 29Josien Pw Pluim 1
IEEE Transactions on Medical Imaging (2011) epub ahead of print
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 intra-patient thoracic CT image pairs. Evaluation of non-rigid registration techniques is a non trivial 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 article details the organisation 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.
- 1: Image sciences institute - University of Utrecht (ISI)
- University Medical Center Utrecht
- 2: Department of Electrical and Computer Engineering [Iowa]
- University of Iowa
- 3: Philips Research [Germany]
- Philips Research
- 4: Siemens [Beijing]
- China Corporate Technology
- 5: State Key Laboratory of Chemical Engineering (Polymerization Division)
- Zhejiang University
- 6: Institut des Nanosciences de Paris (INSP)
- CNRS : UMR7588 – Université Paris VI - Pierre et Marie Curie
- 7: Mauna Kea Technologies
- Mauna Kea Technologies
- 8: ASCLEPIOS (INRIA Sophia Antipolis)
- INRIA
- 9: VISAGES : Vision Action et Gestion d'Informations en Santé (VISAGES)
- INSERM : U746 – CNRS : UMR6074 – INRIA – Université de Rennes 1
- 10: Computer Aided Medical Procedures & Augmented Reality (CAMPAR)
- Technische Universität München (TUM)
- 11: GALEN (INRIA Saclay - Ile de France)
- INRIA – Ecole Centrale Paris
- 12: Mathématiques Appliquées aux Systèmes - EA 4037 (MAS)
- Ecole Centrale Paris
- 13: Department of computer Science [Copenhagen] (DIKU)
- University of Copenhagen
- 14: Biomedical Imaging Group [Rotterdam] (BIG)
- Erasmus MC – University Medical Center Rotterdam
- 15: CMS Software
- Elekta Inc.
- 16: Institute of Biomedical Engineering [Oxford]
- Department of Engineering Science – University of Oxford
- 17: Department of Clinical Neurology [Oxford]
- FMRIB Centre – University of Oxford – John Radcliffe Hospital
- 18: Centre for Medical Image Computing (CMIC)
- University College of London (UCL)
- 19: Centre for Intelligent Machines (CIM)
- McGill University
- 20: Montreal Neurological Institute
- McGill University
- 21: McConnell Brain Imaging Centre (MNI)
- Montreal Neurological Institute – McGill University
- 22: Massachusetts General Hospital (MGH)
- Massachusetts General Hospital
- 23: Institute of Medical Informatics [Lübeck]
- University of Lübeck
- 24: Medical imaging research center [Leuven]
- K.U. LEUVEN – Faculty of Engineering
- 25: Penn Image Computing & Science Lab (PICSL)
- University of Pennsylvania
- 26: Department of radiology and medical imaging [Charlottesville]
- University of Virginia
- 27: Division of image processing [Leiden]
- Department of Radiology – Leiden University Medical Center (LUMC)
- 28: Institute for Computer Graphics and Vision [Graz] (ICG)
- Graz University of Technology
- 29: Centre de recherche en applications et traitement de l'image pour la santé (CREATIS)
- INSA - Institut National des Sciences Appliquées – CNRS : UMR5220 – Université Claude Bernard - Lyon I – INSERM : U1044 – Hospices Civils de Lyon
- 30: Laboratoire d'InfoRmatique en Images et Systèmes d'Information (LIRIS)
- CNRS : UMR5205 – Université Claude Bernard - Lyon I – Université Lumière - Lyon II – Institut National des Sciences Appliquées de Lyon – Ecole Centrale de Lyon
- Domain : Life Sciences/Bioengineering
Computer Science/Medical Imaging - Keywords : Registration – Chest – Computed Tomography – Evaluation
- inserm-00607794, version 1
- http://www.hal.inserm.fr/inserm-00607794
- oai:www.hal.inserm.fr:inserm-00607794
- From: Olivier Commowick
- Submitted on: Monday, 11 July 2011 12:46:19
- Updated on: Tuesday, 19 July 2011 15:58:26






Associated documents
Export