• DocumentCode
    951213
  • Title

    Improving the accuracy of volumetric segmentation using pre-processing boundary detection and image reconstruction

  • Author

    Archibald, Rick ; Hu, Jiuxiang ; Gelb, Anne ; Farin, Gerald

  • Author_Institution
    Center for Syst. Sci. & Eng. Res., Arizona State Univ., Tempe, AZ, USA
  • Volume
    13
  • Issue
    4
  • fYear
    2004
  • fDate
    4/1/2004 12:00:00 AM
  • Firstpage
    459
  • Lastpage
    466
  • Abstract
    The concentration edge -detection and Gegenbauer image-reconstruction methods were previously shown to improve the quality of segmentation in magnetic resonance imaging. In this study, these methods are utilized as a pre-processing step to the Weibull E-SD field segmentation. It is demonstrated that the combination of the concentration edge detection and Gegenbauer reconstruction method improves the accuracy of segmentation for the simulated test data and real magnetic resonance images used in this study.
  • Keywords
    Weibull distribution; edge detection; image reconstruction; image segmentation; magnetic resonance imaging; Gegenbauer image reconstruction; Weibull E-SD field segmentation; Weibull distribution; concentration edge detection; expectancy-standard deviation; magnetic resonance imaging; preprocessing boundary detection; volumetric segmentation; Image edge detection; Image reconstruction; Image segmentation; Magnetic field measurement; Magnetic resonance; Magnetic resonance imaging; Multidimensional systems; Reconstruction algorithms; Systems engineering and theory; Testing; Algorithms; Animals; Brain; Computer Simulation; Image Enhancement; Image Interpretation, Computer-Assisted; Imaging, Three-Dimensional; Information Storage and Retrieval; Magnetic Resonance Imaging; Mice; Pattern Recognition, Automated; Quality Control; Reproducibility of Results; Sensitivity and Specificity; Signal Processing, Computer-Assisted;
  • fLanguage
    English
  • Journal_Title
    Image Processing, IEEE Transactions on
  • Publisher
    ieee
  • ISSN
    1057-7149
  • Type

    jour

  • DOI
    10.1109/TIP.2003.819862
  • Filename
    1284382