Paper Info
Title
Segmentation of the evolving left ventricle by learning the dynamics
Abstract
ABSTRACT We propose a method,for recursive segmentation of the left ventricle (LV) across a temporal sequence,of magnetic,resonance (MR) im- ages. The approach involves a technique for learning the LV bound- ary dynamics,together with a particle-based inference algorithm on a loopy graphical model,capturing the temporal periodicity of the heart. The dynamic,system state is a low-dimensional representa- tion of the boundary, and boundary estimation involves incorporat- ing curve evolution into state estimation. By formulating the prob- lem as one of state estimation, the segmentation at each particular time is based not only on the data observed at that instant, but also on predictions based on past and future boundary,estimates. We as- sess and demonstrate,the effectiveness of the proposed,framework on a large data set of breath-hold cardiac MR image sequences. Index Terms— Magnetic resonance imaging, cardiac imaging,
Year
DOI
Venue
2008
10.1109/ISBI.2008.4540974
ISBI
Keywords
Field
DocType
biomedical MRI,cardiology,image segmentation,medical image processing,boundary estimation,breath-hold cardiac MR image sequences,curve evolution,dynamic system state,left ventricle,loopy graphical model,low-dimensional representation,magnetic resonance images,particle-based inference algorithm,recursive segmentation,state estimation,temporal periodicity,Magnetic resonance imaging,cardiac imaging,curve evolution,graphical models,image segmentation,learning,left ventricle,particle filtering,recursive estimation
Computer vision,Scale-space segmentation,Pattern recognition,Segmentation,Inference,Computer science,Particle filter,Level set,Image segmentation,Artificial intelligence,Graphical model,Recursion
Conference
ISSN
Citations 
PageRank 
1945-7928
2
0.49
References 
Authors
8
4
Name
Order
Citations
PageRank
Walter Sun1162.00
Müjdat Çetin21342112.26
Ray Chand320.49
Alan S. Willsky47466847.01