High Resolution Hippocampus Subfield Segmentation Using Multispectral Multiatlas Patch-Based Label Fusion

Abstract : The hippocampus is a brain structure that is involved in several cog-nitive functions such as memory and learning. It is a structure of grate interest due to its relationship to neurodegenerative processes such as the Alzheimer's disease. In this work, we propose a novel multispectral multiatlas patch-based method to automatically segment hippocampus subfields using high resolution T1-weighted and T2-weighted magnetic resonance images (MRI). The proposed method works well also on standard resolution images after superresolu-tion and consistently performs better than monospectral version. Finally, the proposed method was compared with similar state-of-the-art methods showing better results in terms of both accuracy and efficiency.
Type de document :
Communication dans un congrès
Patch-Based Techniques in Medical Imaging, Oct 2016, Athènes, Greece. Lecture Notes in Computer Science, pp.117 - 124, 2016, Patch-Based Techniques in Medical Imaging. <10.1007/978-3-319-47118-1_15>
Liste complète des métadonnées


https://hal.archives-ouvertes.fr/hal-01398769
Contributeur : Pierrick Coupé <>
Soumis le : jeudi 17 novembre 2016 - 16:49:47
Dernière modification le : mardi 22 novembre 2016 - 01:02:05
Document(s) archivé(s) le : jeudi 16 mars 2017 - 16:25:40

Fichier

PatchMI_HIPS_submission_final....
Fichiers produits par l'(les) auteur(s)

Identifiants

Collections

Citation

José Romero, Pierrick Coupe, José Manjón. High Resolution Hippocampus Subfield Segmentation Using Multispectral Multiatlas Patch-Based Label Fusion. Patch-Based Techniques in Medical Imaging, Oct 2016, Athènes, Greece. Lecture Notes in Computer Science, pp.117 - 124, 2016, Patch-Based Techniques in Medical Imaging. <10.1007/978-3-319-47118-1_15>. <hal-01398769>

Partager

Métriques

Consultations de
la notice

17

Téléchargements du document

84