Robust automated vertebra motion tracking from Videofluoroscopy sequences

Author

Lam, S.C.B. ; Allen, Ross

Author_Institution

Inst. of Sound & Vibration Res., Southampton Univ., Southampton

fYear

2008

fDate

14-16 July 2008

Firstpage

1

Lastpage

4

Abstract

This paper proposed a robust and reliable automated tracking technique using a particle filter. A constant velocity random walk model is adopted in the state transition model. The observation model is an amalgam of histogram matching from Markov random fields segmentation and gradient intensity measurements. The accuracy of tracking the vertebrae from a calibration model is of 1deg and the variability among 5 initialisations is less than 0.5deg.

Keywords

Markov processes; image motion analysis; image segmentation; image sequences; medical image processing; particle filtering (numerical methods); radiography; Markov random fields segmentation; amalgam; automated tracking; calibration model; constant velocity random walk model; gradient intensity; histogram matching; particle filter; state transition model; vertebra motion tracking; Digitised Videofluoroscopy (DVF); Markov random fields (MRF); image gradient; particle filter; vertebrae;

fLanguage

English

Publisher

iet

Conference_Titel

Advances in Medical, Signal and Information Processing, 2008. MEDSIP 2008. 4th IET International Conference on

Conference_Location

Santa Margherita Ligure

ISSN

0537-9989

Print_ISBN

978-0-86341-934-8

Type

conf

Filename

4609090