• DocumentCode
    318267
  • Title

    MAGNET: an active ditch extraction model

  • Author

    Hirano, Shoji ; Kamiura, Naotake ; Hata, Yutaka ; Ishikawa, Makoto

  • Author_Institution
    Dept. of Comput. Eng., Himeji Inst. of Technol., Japan
  • Volume
    2
  • fYear
    1997
  • fDate
    26-29 Oct 1997
  • Firstpage
    124
  • Abstract
    Presents a novel model to detect the deepest point of a ditch as cerebral sulcus. The authors model demonstrates magnetic behavior and consists of four ideal magnetic poles: an N-pole and three S-poles. Due to their Coulomb forces as the inverse square of the distance, one of S-poles automatically reaches the deepest point of the ditch. This model can also detect the point in case of ditch with implicit branches. The authors´ experimental results on sliced human brain MR images show that their method can detect the points at 90% correct detection ratio
  • Keywords
    biomedical NMR; brain models; feature extraction; magnetoencephalography; medical image processing; Coulomb forces; N-pole; S-poles; active ditch extraction model; brain MRI; cerebral sulcus; ditch deepest point detection; ideal magnetic poles; inverse square; medical diagnostic imaging; sliced human brain MR images; Anatomical structure; Biomedical image processing; Brain modeling; Deformable models; Feature extraction; Hospitals; Humans; Labeling; Shape; Topology;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Image Processing, 1997. Proceedings., International Conference on
  • Conference_Location
    Santa Barbara, CA
  • Print_ISBN
    0-8186-8183-7
  • Type

    conf

  • DOI
    10.1109/ICIP.1997.638689
  • Filename
    638689