• DocumentCode
    2358544
  • Title

    PS-8 Sparse Appearance Model Based Registration and Segmentation of 3D Echocardiographic Images

  • Author

    Leung, K. Y Esther ; Van Stralen, Marijn ; Van Burken, Gerard ; Voormolen, Marco M. ; Nemes, Attila ; Ten Cate, Folkert J. ; Geleijnse, Marcel L. ; De Jong, Nico ; Van der Steen, Antonius F W ; Reiber, Johan H C ; Bosch, Johan G.

  • Author_Institution
    Biomed. Eng., Thoraxcenter, Rotterdam
  • fYear
    2006
  • fDate
    2-6 Oct. 2006
  • Firstpage
    2413
  • Lastpage
    2416
  • Abstract
    In this study, active appearance model segmentation and intensity-based image registration were combined for detecting contours in three-dimensional (3D) echocardiograms fully automatically. An appearance model was built in 3D sparsely, consisting of the anatomical 4-chamber, 2-chamber, and short-axis views, which were extracted from end-diastolic 3D data sets. The model was used to segment an unseen image in a registration framework, by optimizing appearance and pose parameters simultaneously. Encouraging results were obtained with leave-one-out experiments on 16 patient data sets. The method may help inter- and intrapatient comparison of images, and is intended as an initialization for a complete 3D segmentation
  • Keywords
    echocardiography; image segmentation; medical image processing; 3D echocardiogram contour detection; 3D echocardiographic image registration; 3D echocardiographic image segmentation; active appearance model segmentation; anatomical 2-chamber view; anatomical 4-chamber view; anatomical short-axis view; end-diastolic 3D data sets; intensity based image registration; sparse appearance model; Active appearance model; Biomedical imaging; Cardiology; Echocardiography; Image registration; Image segmentation; Predictive models; Principal component analysis; Shape; Ultrasonic imaging;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Ultrasonics Symposium, 2006. IEEE
  • Conference_Location
    Vancouver, BC
  • ISSN
    1051-0117
  • Print_ISBN
    1-4244-0201-8
  • Electronic_ISBN
    1051-0117
  • Type

    conf

  • DOI
    10.1109/ULTSYM.2006.605
  • Filename
    4152461