• DocumentCode
    1249595
  • Title

    Automatic segmentation of ultrasound images using morphological operators

  • Author

    Thomas, Judith G. ; Peters, Richard Alan, II ; Jeanty, Philippe

  • Author_Institution
    Vanderbilt Univ., Nashville, TN, USA
  • Volume
    10
  • Issue
    2
  • fYear
    1991
  • fDate
    6/1/1991 12:00:00 AM
  • Firstpage
    180
  • Lastpage
    186
  • Abstract
    A method for the automatic measurement of femur length in fetal ultrasound images is presented. Fetal femur length measurements are used to estimate gestational age by comparing the measurement to a typical growth chart. Using a real-time ultrasound system, sonographers currently indicate the femur endpoints on the ultrasound display station with a mouse-like device. The measurements are subjective, and have been proven to be inconsistent. The automatic approach described exploits prior knowledge of the general range of femoral size and shape by using morphological operators, which process images based on shape characteristics. Morphological operators are used first to remove the background (noise) from the image, next to refine the shape of the femur and remove spurious artifacts, and finally to produce a single pixel-wide skeleton of the femur. The skeleton endpoints are assumed to be the femur endpoints. The length of the femur is calculated as the distance between those endpoints. A comparison of the measurements obtained with the manual and with the automated techniques is included
  • Keywords
    acoustic imaging; biomedical ultrasonics; bone; computerised picture processing; automatic measurement method; femur length; fetal; gestational age; growth chart; medical diagnostic imaging; morphological operators; shape characteristics; single pixel-wide skeleton; spurious artifacts; ultrasound images; Background noise; Displays; Image segmentation; Length measurement; Real time systems; Refining; Shape; Skeleton; Ultrasonic imaging; Ultrasonic variables measurement;
  • fLanguage
    English
  • Journal_Title
    Medical Imaging, IEEE Transactions on
  • Publisher
    ieee
  • ISSN
    0278-0062
  • Type

    jour

  • DOI
    10.1109/42.79476
  • Filename
    79476