• DocumentCode
    1951724
  • Title

    Landmark and intensity based image registration using free form deformation

  • Author

    Ghaffari, Aboozar ; Khorsandi, R. ; Fatemizadeh, Emad

  • Author_Institution
    Dept. of Electr. Eng., Sharif Univ. of Technol., Tehran, Iran
  • fYear
    2012
  • fDate
    17-19 Dec. 2012
  • Firstpage
    768
  • Lastpage
    771
  • Abstract
    The registration of images is a fundamental task in numerous applications in medical image processing. In this paper, a novel registration technique is proposed which combines landmark and intensity based approaches. In this framework, the free form deformation (FFD) is used as transformation which is the key point of our algorithm. Landmarks with FFD transformation define the guidance surface which increases robustness of intensity based registration to bias field (bias noise). In fact, the performance of registration is improved by matching both landmark and intensity information. The experimental results show that the proposed method is more accurate than only intensity based method (Mutual Information). Also, user can identify the region of interest for registration which makes method more applicable and useful for practical uses.
  • Keywords
    image registration; medical image processing; noise; FFD transformation; ROI; bias field; bias noise; free form deformation; guidance surface; image registration; intensity based method; intensity based registration; intensity information; landmark information; medical image processing; mutual information; region of interest; B-spline; Landmark; Mutual Information; image registration;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Biomedical Engineering and Sciences (IECBES), 2012 IEEE EMBS Conference on
  • Conference_Location
    Langkawi
  • Print_ISBN
    978-1-4673-1664-4
  • Type

    conf

  • DOI
    10.1109/IECBES.2012.6498156
  • Filename
    6498156