Joint segmentation via patient-specific latent anatomy model

Abstract : We present a generative approach for joint 3D segmentation of patient-speciØc MR scans across diÆerent modalities or time points. The latent anatomy, in the form of spatial parameters, is inferred si- multaneously with the evolution of the segmentations. The individual segmentation of each scan supports the segmentation of the group by sharing common information. The joint segmentation problem is solved via a statistically driven level-set framework. We illustrate the method on an example application of multimodal and longitudinal brain tumor segmentation, reporting promising segmentation results
Type de document :
Communication dans un congrès
MICCAI Workshop on Probabilistic Methods in Medical Image Analysis (PMMIA'09)), 2009, London, UK, United Kingdom. 2009
Liste complète des métadonnées

https://hal.inria.fr/inria-00616174
Contributeur : Project-Team Asclepios <>
Soumis le : vendredi 19 août 2011 - 19:47:05
Dernière modification le : jeudi 11 janvier 2018 - 16:44:45

Identifiants

  • HAL Id : inria-00616174, version 1

Collections

Citation

Tammy Riklin-Raviv, Bjoern H. Menze, Koen Van Leemput, Bram Stieltjes, Marc-André Weber, et al.. Joint segmentation via patient-specific latent anatomy model. MICCAI Workshop on Probabilistic Methods in Medical Image Analysis (PMMIA'09)), 2009, London, UK, United Kingdom. 2009. 〈inria-00616174〉

Partager

Métriques

Consultations de la notice

87