Automatic segmentation of MR brain images

  • Authors:

  • Jyothisha J. Nair;V. K. Govindan

  • Affiliations:

  • National Institute of Technology, Calicut, India;National Institute of Technology, Calicut, India

  • Venue:
  • Proceedings of the 2011 International Conference on Communication, Computing & Security
  • Year:
  • 2011

Quantified Score

Hi-index 0.00

Visualization

Abstract

Intensity based and edge based segmentation methods have its own limitations. Multiscale representation employing Gradient dependent diffusion has been proposed in the literature to get rid of these limitations to some extend. In the present work, a fully automatic segmentation method is proposed. A 'trous algorithm is employed to achieve a multiscale representation of the image to be segmented. Intensity based linking model is used to group pixels into a number of segments. This approach is employed successfully to segment 2-D MR Brain images into White Matter (WM), Gray Matter (GM), and Cerebral Spinal Fluid (CSF) with no user interaction. Faster and better segmentation performances were observed when compared to Gradient dependent diffusion approach proposed in the literature.