Skip to Main content Skip to Navigation
New interface
Conference papers

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.
Complete list of metadata

https://hal.inria.fr/hal-00646674
Contributor : Jan Margeta Connect in order to contact the contributor
Submitted on : Wednesday, September 14, 2022 - 8:53:17 PM
Last modification on : Friday, November 4, 2022 - 1:44:31 PM

File

MargetaMICCAI-STACOM2011.pdf
Files produced by the author(s)

Identifiers

Citation

Jan Margeta, Ezequiel Geremia, Antonio Criminisi, Nicholas Ayache. Layered spatio-temporal forests for left ventricle segmentation from 4D cardiac MRI data. STACOM 2011 - Second International Workshop on Statistical Atlases and Computational Models of the Heart. Imaging and Modelling Challenges, Held in Conjunction with MICCAI 2011, Oscar Camara; Ender Konukoglu; Mihaela Pop; Kawal Rhode; Maxime Sermesant, Sep 2011, Toronto, Canada. pp.109-119, ⟨10.1007/978-3-642-28326-0_11⟩. ⟨hal-00646674⟩

Share

Metrics

Record views

207

Files downloads

3