LesionBrain: An Online Tool for White Matter Lesion Segmentation

José Romero 1 Pierrick Coupé 2, 3 Thomas Tourdias 4 Pierre Linck Jose Romero 1 Jose Manjon 1
1 ITACA
2 LaBRI - Laboratoire Bordelais de Recherche en Informatique
3 PICTURA
LaBRI - Laboratoire Bordelais de Recherche en Informatique
4 CHU Bordeaux [Bordeaux]
Abstract : In this paper, we present a new tool for white matter lesion seg-mentation called lesionBrain. Our method is based on a 3-stage strategy including multimodal patch-based segmentation, patch-based regularization of probability map and patch-based error correction using an ensemble of shallow neural networks. Its robustness and accuracy have been evaluated on the MSSEG challenge 2016 datasets. During our validation, the performance obtained by lesionBrain was competitive compared to recent deep learning methods. Moreover, lesionBrain proposes automatic lesion categorization according to location. Finally, complementary information on gray matter atrophy is included in the generated report. LesionBrain follows a software as a service model in full open access.
Keywords : White Matter Lesion Segmentation Patch-based Segmentation Service as a Software
Type de document :
Article dans une revue
Lecture Notes in Computer Science, Springer, 2018, pp.95 - 103. 〈10.1007/978-3-030-00500-9_11〉
Liste complète des métadonnées
https://hal.archives-ouvertes.fr/hal-01918438
Contributeur : Pierrick Coupé <>
Soumis le : dimanche 25 novembre 2018 - 09:52:07
Dernière modification le : jeudi 29 novembre 2018 - 01:05:26

Fichier

lesionBrain_PatchMI2018.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

Collections

UNIV-BORDEAUX | LABRI

Citation

José Romero, Pierrick Coupé, Thomas Tourdias, Pierre Linck, Jose Romero, et al.. LesionBrain: An Online Tool for White Matter Lesion Segmentation. Lecture Notes in Computer Science, Springer, 2018, pp.95 - 103. 〈10.1007/978-3-030-00500-9_11〉. 〈hal-01918438〉

Exporter

BibTeX TEI DC DCterms EndNote

Partager

Métriques

Consultations de la notice

16

Téléchargements de fichiers

42

Contact

support.ccsd.cnrs.fr
hal.support@ccsd.cnrs.fr
Logo CCSD