Towards automatic segmentation ofMR brain images

Nigel John, Xiaohong Li, Akmal Younis, Mansur R. Kabuka

Research output: Contribution to journalConference articlepeer-review

3 Scopus citations


An automatic image segmentation for MR brain images based on the gray level characteristics of the images is developed. The method analyses a sequence ofMR brain images to provide region information as well as boundary data for classification and eventual creation of 3-D models. The system incorporates global information from the image set through an analysis of the statistics of the cooccurrence matrices. Local consistency is then applied with the use of a relaxation algorithm on individual images. The cooccurrence matrices provide conditional probabilities for the classification of pixels into specific regions or boundaries based on the matrix distribution. A constrained stochastic relaxation is then used to refine the probabilistic labels using local image information. Results ofthe technique are presented for MR brain images.

Original languageEnglish (US)
Pages (from-to)65-76
Number of pages12
JournalProceedings of SPIE - The International Society for Optical Engineering
StatePublished - May 11 1994
EventMedical Imaging 1994: Image Processing - Newport Beach, United States
Duration: Feb 13 1994Feb 18 1994

ASJC Scopus subject areas

  • Electronic, Optical and Magnetic Materials
  • Condensed Matter Physics
  • Computer Science Applications
  • Applied Mathematics
  • Electrical and Electronic Engineering


Dive into the research topics of 'Towards automatic segmentation ofMR brain images'. Together they form a unique fingerprint.

Cite this