Title
A deep Boltzmann machine-driven level set method for heart motion tracking using cine MRI images.
Abstract
•The DBM needs small-sized data set to train, but imposes strong modeling ability.•A three-layer DBM can capture both local and global properties of heart contours.•An efficient layer-wise block-Gibbs sampling is used to infer heart shape priors.•The DBM-induced heart shape priors are used as constraints of DRLSE evolution.
Year
DOI
Venue
2018
10.1016/j.media.2018.03.015
Medical Image Analysis
Keywords
Field
DocType
Heart motion tracking,Generative shape model,Deep Boltzmann machine,Distance regularized level-set evolution,MRI-guided radiation therapy
Heart shape,Computer vision,Boltzmann machine,Pattern recognition,Level set method,Markov chain,Spatial relationship,Artificial intelligence,Initialization,Mathematics,Match moving,Heart motion
Journal
Volume
ISSN
Citations 
47
1361-8415
1
PageRank 
References 
Authors
0.37
26
13
Name
Order
Citations
PageRank
Jian Wu111.05
Thomas Mazur211.05
Ruan Su355953.00
Chunfeng Lian413222.61
Nalini Daniel510.71
Hilary Lashmett610.71
Laura Ochoa710.71
Imran Zoberi810.71
Mark A. Anastasio910525.53
h michael gach1011.73
Sasa Mutic1111.39
Maria Thomas1210.71
Hua Li13459.03