Paper Info
Title
ManiSMC: a new method using manifold modeling and sequential Monte Carlo sampler for boosting navigated bronchoscopy.
Abstract
This paper presents a new bronchoscope motion tracking method that utilizes manifold modeling and sequential Monte Carlo (SMC) sampler to boost navigated bronchoscopy. Our strategy to estimate the bronchoscope motions comprises two main stages: (1) bronchoscopic scene identification and (2) SMC sampling. We extend a spatial local and global regressive mapping (LGRM) method to Spatial-LGRM to learn bronchoscopic video sequences and construct their manifolds. By these manifolds, we can classify bronchoscopic scenes to bronchial branches where a bronchoscope is located. Next, we employ a SMC sampler based on a selective image similarity measure to integrate estimates of stage (1) to refine positions and orientations of a bronchoscope. Our proposed method was validated on patient datasets. Experimental results demonstrate the effectiveness and robustness of our method for bronchoscopic navigation without an additional position sensor.
Year
DOI
Venue
2011
10.1007/978-3-642-23626-6_31
MICCAI (3)
Keywords
Field
DocType
sequential monte carlo sampler,bronchoscopic navigation,additional position sensor,bronchoscope motion,smc sampler,manifold modeling,new bronchoscope motion tracking,bronchoscopic video sequence,bronchoscopic scene,smc sampling,navigated bronchoscopy,bronchoscopic scene identification,new method
Computer vision,Similarity measure,Pattern recognition,Computer science,Particle filter,Robustness (computer science),Artificial intelligence,Sampling (statistics),Boosting (machine learning),Position sensor,Match moving,Manifold
Conference
Volume
Issue
ISSN
14
Pt 3
0302-9743
Citations 
PageRank 
References 
4
0.50
8
Authors
3
Name
Order
Citations
PageRank
Xiongbiao Luo112422.22
Takayuki Kitasaka252067.91
Kensaku Mori31125160.28