• DocumentCode
    3070256
  • Title

    Initial Contour for Ultrasound Carotid Artery Snakes

  • Author

    Moursi, Sherif G. ; El-Sakka, Mahmoud R.

  • Author_Institution
    Univ. of Western Ontario, London
  • fYear
    2007
  • fDate
    15-18 Dec. 2007
  • Firstpage
    390
  • Lastpage
    395
  • Abstract
    Since it was introduced by Kass et al., the active contour model (also known as snake model, balloon model, or deformable model) has been extensively studied and widely used in segmenting medical images, due to its robustness to both image noise and boundary gaps. Yet, active contouring is very sensitive to the initial contour that is provided by the user. In this paper we present an algorithm for determining a good initial carotid artery lumen contour in ultrasound images. Our algorithm reduces user interaction as a user is only required to place a seed point inside the region of interest. It attempts to adjust the contour to be close enough to the actual contour. The results of our extracted initial contours have good overlap with contours that are manually delineated by an experienced clinician. In addition, the output of our proposed scheme can be perfectly used as an input to any active contour algorithm to produce even better results.
  • Keywords
    biomedical ultrasonics; blood vessels; cardiovascular system; feature extraction; image segmentation; medical image processing; active contour model; feature extraction; initial carotid artery lumen contour; medical image segmentation; snake model; ultrasound image; Active contours; Blood; Carotid arteries; Deformable models; Image segmentation; Information technology; Noise robustness; Signal processing; Signal processing algorithms; Ultrasonic imaging; Initial contour; active contours models; carotid artery; ultrasound image;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Signal Processing and Information Technology, 2007 IEEE International Symposium on
  • Conference_Location
    Giza
  • Print_ISBN
    978-1-4244-1835-0
  • Electronic_ISBN
    978-1-4244-1835-0
  • Type

    conf

  • DOI
    10.1109/ISSPIT.2007.4458120
  • Filename
    4458120