• DocumentCode
    2610609
  • Title

    Shape Decomposition Approach for Ultrasound Color Doppler Image Segmentation

  • Author

    Saad, Ashraf A. ; Shapiro, Linda G.

  • Author_Institution
    Washington Univ., Seattle, WA
  • Volume
    4
  • fYear
    0
  • fDate
    0-0 0
  • Firstpage
    691
  • Lastpage
    694
  • Abstract
    We present a novel technique for segmenting blood vessels in ultrasound color Doppler images based on shape decomposition. Ultrasound color Doppler images frequently suffer from a vessel linking artifact called ´color bleeding´. The proposed technique decomposes a complex binary object representing either two or more vessels artificially linked together or a main vessel with its branches. The resulting simple parts represent distinct vessels that can be used in further object recognition and quantification applications
  • Keywords
    Doppler measurement; biomedical ultrasonics; blood vessels; feature extraction; image colour analysis; image segmentation; medical image processing; object recognition; binary object; blood vessels; color bleeding; object recognition; shape decomposition; ultrasound color Doppler image segmentation; vessel linking artifact; Biomedical imaging; Blood; Cells (biology); Color; Colored noise; Gray-scale; Image segmentation; Object recognition; Shape; Ultrasonic imaging;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Pattern Recognition, 2006. ICPR 2006. 18th International Conference on
  • Conference_Location
    Hong Kong
  • ISSN
    1051-4651
  • Print_ISBN
    0-7695-2521-0
  • Type

    conf

  • DOI
    10.1109/ICPR.2006.1049
  • Filename
    1699935