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, 2) , Sorina Camarasu Pop (4) , Pascal Girard (4) , Roxana Ameli (2) , Jean-Christophe Ferré (5, 1) , Anne Kerbrat (1, 6) , Thomas Tourdias (7) , Frédéric Cervenansky (4) , Tristan Glatard (8) , Jeremy Beaumont (1) , Senan Doyle (9) , Florence Forbes (10, 9) , 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 Llado (16) , Michel Santos (17) , Wellington P Santos (17) , Abel G Silva-Filho (17) , Xavier Tomas-Fernandez (18) , Hélène Urien (19) , Isabelle Bloch (19) , Sergi Valverde (16) , Mariano Cabezas (16) , Francisco Javier Vera-Olmos (20) , Norberto Malpica (20) , Charles R G Guttmann (21) , Sandra Vukusic (22) , Gilles Edan (1, 4) , Michel Dojat (23) , Martin Styner (24) , Simon K. Warfield (18) , François Cotton (2) , Christian Barillot (1)

1 VisAGeS - Vision, Action et Gestion d'informations en Santé
2 CHLS - Centre Hospitalier Lyon Sud [CHU - HCL]
3 LaTIM - Laboratoire de Traitement de l'Information Medicale
4 CREATIS - Centre de Recherche en Acquisition et Traitement de l'Image pour la Santé
5 Département de Radiologie [CHU de Rennes]
6 Centre Hospitalier Universitaire de Rennes [CHU Rennes] = Rennes University Hospital [Ponchaillou]
7 CHU Bordeaux
8 Concordia University [Montreal]
9 Pixyl Medical [Grenoble]
10 MISTIS - Modelling and Inference of Complex and Structured Stochastic Systems
11 University of Guelph
12 Ryerson University [Toronto]
13 KTH - KTH Royal Institute of Technology [Stockholm]
14 UNIBE - Universität Bern / University of Bern
15 Johns Hopkins Bloomberg School of Public Health [Baltimore]
16 VICOROB - Research institute of Computer Vision and Robotics [Girona]
17 UFPE - Universidade Federal de Pernambuco [Recife]
18 CRL - Computational Radiology Laboratory [Boston]
19 LTCI - Laboratoire Traitement et Communication de l'Information
20 URJC - Universidad Rey Juan Carlos [Madrid]
21 Brigham and Women's Hospital [Boston]
22 Service de Neurologie [Lyon]
23 GIN - [GIN] Grenoble Institut des Neurosciences
24 UNC - University of North Carolina [Chapel Hill]

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-theart 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.

Domaines: Neurosciences [q-bio.NC]

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. Scientific Reports, 2018, 8 (1), pp.13650. ⟨10.1038/s41598-018-31911-7⟩. ⟨inserm-01847873v3⟩