3D Consistent Biventricular Myocardial Segmentation Using Deep Learning for Mesh Generation

Abstract : We present a novel automated method to segment the my-ocardium of both left and right ventricles in MRI volumes. The segmen-tation is consistent in 3D across the slices such that it can be directly used for mesh generation. Two specific neural networks with multi-scale coarse-to-fine prediction structure are proposed to cope with the small training dataset and trained using an original loss function. The former segments a slice in the middle of the volume. Then the latter iteratively propagates the slice segmentations towards the base and the apex, in a spatially consistent way. We perform 5-fold cross-validation on the 15 cases from STACOM to validate the method. For training, we use real cases and their synthetic variants generated by combining motion simulation and image synthesis. Accurate and consistent testing results are obtained.
Liste complète des métadonnées

Littérature citée [10 références]  Voir  Masquer  Télécharger

https://hal.inria.fr/hal-01755317
Contributeur : Qiao Zheng <>
Soumis le : vendredi 30 mars 2018 - 15:32:50
Dernière modification le : samedi 31 mars 2018 - 01:25:47

Fichier

miccai2017paper1_version2.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : hal-01755317, version 1

Collections

Citation

Qiao Zheng, Hervé Delingette, Nicolas Duchateau, Nicholas Ayache. 3D Consistent Biventricular Myocardial Segmentation Using Deep Learning for Mesh Generation. 2018. 〈hal-01755317〉

Partager

Métriques

Consultations de la notice

219

Téléchargements de fichiers

47