Paper Info
Title
Segmentation of 4D cardiac MRI: Automated method based on spatio-temporal watershed cuts
Abstract
Based on discrete mathematical morphology, we introduce in this paper a new watershed framework which allows for segmenting spatio-temporal images, that we apply to medical image analysis. Specifically, we propose a new automated and fast procedure to segment the left ventricular myocardium in 4D (3D+t) cine-MRI sequences. Both quantitative and qualitative evaluation are provided. Thanks to the comparison with manual segmentation performed by two cardiologists, we demonstrate the accuracy of the proposed method. The relevance of the ejection fraction and myocardium mass measured from segmentations is also assessed. Furthermore, we show that the proposed 4D procedure allows to keep the temporal coherency between the successive 3D segmentations obtained along the time sequence. In an effort to promote open science, both the data and the software are available on-line.
Year
DOI
Venue
2010
10.1016/j.imavis.2010.01.001
Image Vision Comput.
Keywords
Field
DocType
spatio-temporal watershed cut,4d-cine-mri,discrete mathematical morphology.,automated method,cardiac imagery,fast procedure,manual segmentation,cine-mri sequence,4d watershed cut,4d topological watershed,myocardium mass,left ventricular myocardium,cardiac mri,new watershed framework,medical image analysis,discrete mathematical morphology,ejection fraction,discrete mathematics
Computer vision,Pattern recognition,Segmentation,Computer science,Mathematical morphology,Watershed,Software,Open science,Artificial intelligence,Left ventricular myocardium
Journal
Volume
Issue
ISSN
28
8
Image and Vision Computing
Citations 
PageRank 
References 
40
1.34
40
Authors
6
Name
Order
Citations
PageRank
J. Cousty1401.34
L. Najman21187.52
M. Couprie3712.53
S. Clément-Guinaudeau4401.34
T. Goissen5401.34
J. Garot6532.37