Skip to main content
placeholder image

Regularized discriminative direction for shape difference analysis

Conference Paper


Download full-text (Open Access)

Abstract


  • The “discriminative direction” has been proven useful to re-

    veal the subtle difference between two anatomical shape classes. When a

    shape moves along this direction, its deformation will best manifest the

    class difference detected by a kernel classifier. However, we observe that

    such a direction cannot maintain a shape’s “anatomical” correctness, in-

    troducing spurious difference. To overcome this drawback, we develop

    a regularized discriminative direction by requiring a shape to conform

    to its population distribution when it deforms along the discriminative

    direction. Instead of iterative optimization, an analytic solution is pro-

    vided to directly work out this direction. Experimental study shows its

    superior performance in detecting and localizing the difference of hip-

    pocampal shapes for sex. The result is supported by other independent

    research in the same domain.

Authors


  •   Zhou, Luping
  •   Hartley, Richard (external author)
  •   Wang, Lei
  •   Lieby, Paulette (external author)
  •   Barnes, Nick (external author)

Publication Date


  • 2008

Citation


  • Zhou, L., Hartley, R., Wang, L., Lieby, P. & Barnes, N. (2008). Regularized discriminative direction for shape difference analysis. 11th International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI) (pp. 628-635). Heidelberg: Spinger.

Scopus Eid


  • 2-s2.0-58849135900

Ro Full-text Url


  • http://ro.uow.edu.au/cgi/viewcontent.cgi?article=1653&context=eispapers

Ro Metadata Url


  • http://ro.uow.edu.au/eispapers/647

Start Page


  • 628

End Page


  • 635

Abstract


  • The “discriminative direction” has been proven useful to re-

    veal the subtle difference between two anatomical shape classes. When a

    shape moves along this direction, its deformation will best manifest the

    class difference detected by a kernel classifier. However, we observe that

    such a direction cannot maintain a shape’s “anatomical” correctness, in-

    troducing spurious difference. To overcome this drawback, we develop

    a regularized discriminative direction by requiring a shape to conform

    to its population distribution when it deforms along the discriminative

    direction. Instead of iterative optimization, an analytic solution is pro-

    vided to directly work out this direction. Experimental study shows its

    superior performance in detecting and localizing the difference of hip-

    pocampal shapes for sex. The result is supported by other independent

    research in the same domain.

Authors


  •   Zhou, Luping
  •   Hartley, Richard (external author)
  •   Wang, Lei
  •   Lieby, Paulette (external author)
  •   Barnes, Nick (external author)

Publication Date


  • 2008

Citation


  • Zhou, L., Hartley, R., Wang, L., Lieby, P. & Barnes, N. (2008). Regularized discriminative direction for shape difference analysis. 11th International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI) (pp. 628-635). Heidelberg: Spinger.

Scopus Eid


  • 2-s2.0-58849135900

Ro Full-text Url


  • http://ro.uow.edu.au/cgi/viewcontent.cgi?article=1653&context=eispapers

Ro Metadata Url


  • http://ro.uow.edu.au/eispapers/647

Start Page


  • 628

End Page


  • 635