COUPÉ, Pierrick; MANSENCAL, Boris; CLÉMENT, Michaël; GIRAUD, Rémi; DENIS DE SENNEVILLE, Baudouin; TA, Vinh-Thong; LEPETIT, Vincent; MANJÓN, José

doi:10.1007/978-3-030-32248-9_52

Métadonnées

Licence d’utilisation du document

COUPÉ, Pierrick
Laboratoire Bordelais de Recherche en Informatique [LaBRI]
Patch-based processing for medical and natural images [PICTURA]

MANSENCAL, Boris
Laboratoire Bordelais de Recherche en Informatique [LaBRI]

CLÉMENT, Michaël
Laboratoire d'Informatique Paris Descartes [LIPADE - EA 2517]

Langue

Communication dans un congrès

Ce document a été publié dans

International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI), 2019-10-10, Shenzhen. 2019-10-10p. 466-474

Résumé en anglais

Whole brain segmentation using deep learning (DL) is a very challenging task since the number of anatomical labels is very high compared to the number of available training images. To address this problem, previous DL methods proposed to use a global convolution neural network (CNN) or few independent CNNs. In this paper, we present a novel ensemble method based on a large number of CNNs processing different overlapping brain areas. Inspired by parliamentary decision-making systems, we propose a framework called Assem-blyNet, made of two "assemblies" of U-Nets. Such a parliamentary system is capable of dealing with complex decisions and reaching a consensus quickly. AssemblyNet introduces sharing of knowledge among neighboring U-Nets, an "amendment" procedure made by the second assembly at higher-resolution to refine the decision taken by the first one, and a final decision obtained by majority voting. When using the same 45 training images, AssemblyNet outperforms global U-Net by 28% in terms of the Dice metric, patch-based joint label fusion by 15% and SLANT-27 by 10%. Finally, AssemblyNet demonstrates high capacity to deal with limited training data to achieve whole brain segmentation in practical training and testing times.< Réduire

Mots clés en anglais

Whole brain segmentation

CNN

Ensemble learning

transfer learning

multiscale framework

URI

https://oskar-bordeaux.fr/handle/20.500.12278/192730

DOI

http://dx.doi.org/10.1007/978-3-030-32248-9_52

Project ANR

Apprentissage profond pour la volumétrie cérébrale : vers le BigData en neuroscience - ANR-18-CE45-0013

Origine

Importé de hal

Unités de recherche

Institut de Mathématiques de Bordeaux (IMB) - UMR 5251