Automatic Segmentation Of White Matter Lesions


Creative Commons License

KEÇELİ A. S., CAN A. B.

IEEE 17th Signal Processing and Communications Applications Conference, Antalya, Turkey, 9 - 11 April 2009, pp.443-446 identifier identifier identifier

  • Publication Type: Conference Paper / Full Text
  • Doi Number: 10.1016/j.media.2012.09.004
  • City: Antalya
  • Country: Turkey
  • Page Numbers: pp.443-446
  • Hacettepe University Affiliated: Yes

Abstract

This paper introduces a method to detect white matter lesions in brain automatically. Our method tries to determine the regions of lesions unsupervisedly on magnetic resonance (AM) images of a group of patient by using image processing techniques. As a first step, skull is removed from brain tissue using watershed transform and morphological operations. After skull-stripping, seed points selected by using fuzzy, c-means clustering (FCM) algorithm are used in region-growing method. This operation generates the binary mask containing the regions of lesions.