Lesion detection in noisy MR brain images using constrained GMM and active contours

Oren Freifeld, Hayit Greenspan, Jacob Goldberger

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

29 Scopus citations

Abstract

This paper focuses on the detection and segmentation of multiple sclerosis (MS) lesions in magnetic resonance images. The proposed method performs healthy tissue segmentation using a probabilistic model for normal brain images. MS lesions are simultaneously identified as outlier Gaussian components. The probablistic model, termed constrained-GMM, is based on a mixture of many spatially-oriented Gaussians per tissue. The intensity of a tissue is considered a global parameter and is constrained to be the same value for a set of related Gaussians per tissue. An active contour algorithm is used to delineate lesion boundaries. Experimental results on both standard brain MR simulation data and real data, indicate that our method outperforms previously suggested approaches especially for highly noisy data.

Original languageEnglish
Title of host publication2007 4th IEEE International Symposium on Biomedical Imaging
Subtitle of host publicationFrom Nano to Macro - Proceedings
Pages596-599
Number of pages4
DOIs
StatePublished - 27 Nov 2007
Externally publishedYes
Event2007 4th IEEE International Symposium on Biomedical Imaging: From Nano to Macro; ISBI'07 - Arlington, VA, United States
Duration: 12 Apr 200715 Apr 2007

Publication series

Name2007 4th IEEE International Symposium on Biomedical Imaging: From Nano to Macro - Proceedings

Conference

Conference2007 4th IEEE International Symposium on Biomedical Imaging: From Nano to Macro; ISBI'07
Country/TerritoryUnited States
CityArlington, VA
Period12/04/0715/04/07

Keywords

  • MRI
  • MS-lesions
  • Statistical modeling

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Medicine (all)

Fingerprint

Dive into the research topics of 'Lesion detection in noisy MR brain images using constrained GMM and active contours'. Together they form a unique fingerprint.

Cite this