Bayesian co-segmentation of multiple MR images

Jianfeng Xu, Feng Liang, Lixu Gu

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Segmentation is one of the basic problems in MRI analysis. We consider the problem of simultaneously segmenting multiple MR images, which, for example, could be a series of (2D/3D) images of the same tissue scanned over time, different slices of a volume image, or images of symmetric parts. The multiple MR images to be segmented share common structure information and hence they are able to assist each other in the segmentation procedure. We propose a Bayesian co-segmentation algorithm where the shared information across images is utilized via a Markov random field prior, and a Gibbs sampler is employed for efficient posterior sampling. Because our co-segmentation algorithm pulls all the image information into consideration simultaneously, it provides more accurate and robust results than the individual segmentation, as supported by results from both simulated and real examples.

Original languageEnglish (US)
Title of host publicationProceedings - 2009 IEEE International Symposium on Biomedical Imaging
Subtitle of host publicationFrom Nano to Macro, ISBI 2009
Pages53-56
Number of pages4
DOIs
StatePublished - 2009
Event2009 IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI 2009 - Boston, MA, United States
Duration: Jun 28 2009Jul 1 2009

Publication series

NameProceedings - 2009 IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI 2009

Other

Other2009 IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI 2009
CountryUnited States
CityBoston, MA
Period6/28/097/1/09

Keywords

  • Bayesian
  • Co-segmentation
  • MCMC
  • MRI

ASJC Scopus subject areas

  • Biomedical Engineering
  • Radiology Nuclear Medicine and imaging

Fingerprint Dive into the research topics of 'Bayesian co-segmentation of multiple MR images'. Together they form a unique fingerprint.

Cite this