• DocumentCode
    3508784
  • Title

    Demons registration with local affine adaptive regularization: application to registration of abdominal structures

  • Author

    Freiman, Moti ; Voss, Stephan D. ; Warfield, Simon K.

  • Author_Institution
    Med. Sch., Children´´s Hosp., Comput. Radiol. Lab., Harvard Univ., Boston, MA, USA
  • fYear
    2011
  • fDate
    March 30 2011-April 2 2011
  • Firstpage
    1219
  • Lastpage
    1222
  • Abstract
    We present a local affine-based adaptive regularization approach as an alternative to the homogeneous regularization used in Thirion´s demons non-rigid registration algorithm, which does not preserve the deformation field discontinuities related to the independent motion of different organs, as typically occurs during CT and MR imaging of the abdomen and pelvis. By contrast, our method fits local affine transformation to each voxel; identifies the discontinuities between the locally fitted affine transformations; and adaptively smooths the deformation field, while preserving its local affine discontinuities. Experimental results on both synthetic and real CT images demonstrate that our method at once yields a smoother deformation field and preserves registration accuracy.
  • Keywords
    computerised tomography; image registration; medical image processing; CT imaging; MR imaging; Thirion´s demons nonrigid registration; abdominal structure registration; deformation field discontinuity; local affine adaptive regularization; pelvis; Accuracy; Biomedical imaging; Computed tomography; Image segmentation; Kidney; Pelvis; Smoothing methods; Adaptive regularization; Demons nonrigid registration; Locally affine registration;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Biomedical Imaging: From Nano to Macro, 2011 IEEE International Symposium on
  • Conference_Location
    Chicago, IL
  • ISSN
    1945-7928
  • Print_ISBN
    978-1-4244-4127-3
  • Electronic_ISBN
    1945-7928
  • Type

    conf

  • DOI
    10.1109/ISBI.2011.5872621
  • Filename
    5872621