Paper Info
Title
Development of a Particle Filter Framework for Respiratory Motion Correction in Nuclear Medicine Imaging
Abstract
This research aims to develop a methodological framework based on a data driven approach known as particle filters, often found in computer vision methods, to correct the effect of respiratory motion on Nuclear Medicine imaging data. Particles filters are a popular class of numerical methods for solving optimal estimation problems and we wish to use their flexibility to make an adaptive framework. In this work we use the particle filter for estimating the deformation of the internal organs of the human torso, represented by X, over a discrete time index k. The particle filter approximates the distribution of the deformation of internal organs by generating many propositions, called particles. The posterior estimate is inferred from an observation Z(k) of the external torso surface. We demonstrate two preliminary approaches in tracking organ deformation. In the first approach, X-k represent a small set of organ surface points. In the second approach, X-k represent a set of affine organ registration parameters to a reference time index r. Both approaches are contrasted to a comparable technique using direct mapping to infer X-k from the observation Z(k). Simulations of both approaches using the XCAT phantom suggest that the particle filter-based approaches, on average performs, better.
Year
DOI
Venue
2010
10.1117/12.844424
Proceedings of SPIE
Keywords
Field
DocType
Particle Filter,Respiratory Motion Correction,Nuclear Medicine Imaging
Nuclear medicine,Affine transformation,Computer vision,Torso,Data-driven,Imaging phantom,Particle filter,Optimal estimation,Artificial intelligence,Discrete time and continuous time,Small set,Physics
Conference
Volume
ISSN
Citations 
7623
0277-786X
2
PageRank 
References 
Authors
0.57
3
7
Name
Order
Citations
PageRank
Ashrani A. Abd. Rahni197.17
Emma Lewis265.48
k wells33113.29
m guy420.91
B. Goswami5343.27
Benoit M. Dawant61388223.11
haynor720.57