Layered spatio-temporal forests for left ventricle segmentation from 4D cardiac MRI data

Abstract : In this paper we present a new method for fully automatic left ventricle segmentation from 4D cardiac MR datasets. To deal with the diverse dataset, we propose a machine learning approach using two layers of spatio-temporal decision forests with almost no assumptions on the data nor explicitly specifying the segmentation rules. We introduce 4D spatio-temporal features to classi cation with decision forests and propose a method for context aware MR intensity standardization and image alignment. The second layer is then used for the nal image segmentation. We present our rst results on the STACOM LV Segmentation Challenge 2011 validation datasets.
Type de document :
Communication dans un congrès
Oscar Camara and Ender Konukoglu and Mihaela Pop and Kawal Rhode and Maxime Sermesant and Alistair Young. STACOM Workshop at MICCAI 2011, Sep 2011, Toronto, Canada. Springer, 7085, pp.109-119, 2011, LNCS. 〈http://link.springer.com/chapter/10.1007%2F978-3-642-28326-0_11〉. 〈10.1007/978-3-642-28326-0_11〉
Liste complète des métadonnées

https://hal.inria.fr/hal-00646674
Contributeur : Jan Margeta <>
Soumis le : mercredi 30 novembre 2011 - 15:11:09
Dernière modification le : jeudi 11 janvier 2018 - 16:20:52

Identifiants

Collections

Citation

Jan Margeta, Ezequiel Geremia, Antonio Criminisi, Nicholas Ayache. Layered spatio-temporal forests for left ventricle segmentation from 4D cardiac MRI data. Oscar Camara and Ender Konukoglu and Mihaela Pop and Kawal Rhode and Maxime Sermesant and Alistair Young. STACOM Workshop at MICCAI 2011, Sep 2011, Toronto, Canada. Springer, 7085, pp.109-119, 2011, LNCS. 〈http://link.springer.com/chapter/10.1007%2F978-3-642-28326-0_11〉. 〈10.1007/978-3-642-28326-0_11〉. 〈hal-00646674〉

Partager

Métriques

Consultations de la notice

184