• DocumentCode
    1655596
  • Title

    Detection of the lumen and media-adventitia borders in IVUS imaging

  • Author

    Zheng, Mao ; Yubin, Wang ; Yousheng, Wang ; Xiaodi, Sui ; Yali, Wang

  • Author_Institution
    Sch. of Electron. Inf. & Control Eng., Beijing Univ. of Technol., Beijing
  • fYear
    2008
  • Firstpage
    1059
  • Lastpage
    1062
  • Abstract
    The detection of the lumen and media-adventitia borders is a key step in intravascular ultrasound (IVUS) processing. The traditional method for IVUS is based on the snake model or GVF Snake model. Actually, it is not easy to get the precise lumen and adventitia border of the IVUS image by only using the one of the above method. In this paper a new way is used in IVUS image processing. At first, the IVUS original image is preprocessed with the Canny edge detection of the Gaussian filters in different variances and circle Hough transform, or binary image processing. Then the preprocessed image is transformed by GVF. Finally, the noise dots on the GVF transforming image are removed and the desirable lumen and media-adventitia borders of IVUS image are obtained. The experimental results confirm the validity of the new method.
  • Keywords
    Hough transforms; edge detection; filtering theory; medical image processing; Canny edge detection; Gaussian filters; IVUS image processing; IVUS imaging; binary image processing; circle Hough transform; intravascular ultrasound processing; lumen detection; media-adventitia borders; snake model; Active contours; Background noise; Biomedical image processing; Biomedical imaging; Control engineering; Diseases; Filters; Image edge detection; Image processing; Ultrasonic imaging;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Signal Processing, 2008. ICSP 2008. 9th International Conference on
  • Conference_Location
    Beijing
  • Print_ISBN
    978-1-4244-2178-7
  • Electronic_ISBN
    978-1-4244-2179-4
  • Type

    conf

  • DOI
    10.1109/ICOSP.2008.4697311
  • Filename
    4697311