Title
Medial-based Bayesian tracking for vascular segmentation: Application to coronary arteries in 3D CT angiography
Abstract
We propose a new Bayesian, stochastic tracking algorithm for the segmentation of blood vessels from 3D medical image data. Inspired by the recent developments in particle filtering, it relies on a constrained, medial-based geometric model and on an original sampling scheme for the selection of tracking hypotheses. A key property of this new sampling scheme is the ability to take into account a distribution of hypotheses broader than similar methods such as classical particle filters, while remaining computationally efficient. The proposed method was applied to the challenging and medically critical task of coronary artery segmentation from 3D cardiac computed tomography (CT) images. Prior knowledge, injected in the process, was learned from a manually segmented database of 19 cases. Qualitative and quantitative evaluation is presented on clinical data, including pathologies and local anomalies.
Year
DOI
Venue
2008
10.1109/ISBI.2008.4540984
Paris
Keywords
Field
DocType
belief networks,biology computing,blood vessels,computerised tomography,diagnostic radiography,image segmentation,stochastic processes,3D CT angiography,3D medical image data,blood vessels,classical particle filters,computed tomography,coronary arteries,medial-based Bayesian tracking,pathology,stochastic tracking algorithm,vascular segmentation,Bayesian tracking,Cardiac CTA,Geometric model,Monte-Carlo method,Vascular segmentation
Computer vision,Coronary arteries,Pattern recognition,Computer science,Segmentation,Geometric modeling,Particle filter,Stochastic process,Image segmentation,Artificial intelligence,Angiography,Bayesian probability
Conference
ISSN
ISBN
Citations 
1945-7928
978-1-4244-2003-2
21
PageRank 
References 
Authors
1.13
11
4
Name
Order
Citations
PageRank
David Lesage144118.16
Elsa D. Angelini274060.44
Isabelle Bloch32123170.75
Gareth Funka-Lea4138363.84