Skip to main content
placeholder image

Hippocampal shape analysis for Alzheimer's disease using an efficient hypothesis test and regularized discriminative deformation

Journal Article


Abstract


  • In this paper, we present a framework to perform statistical shape analysis for manually segmented hippocampi, which includes an efficient permutation test for detecting subtle class differences, and a regularized ``discriminative direction" method for visualizing the shape discrepancy. Fisher permutation and bootstrap tests are preferred to traditional hypothesis tests which impose assumptions on the distribution of the samples. In this paper, an efficient algorithm is adopted to rapidly perform the {\em exact} tests. We extend this algorithm to multivariate data by projecting the shape descriptors onto an ``informative direction'' that preserves the original discriminative information as much as possible to generate a scalar test statistic. This ``informative direction'' is further used to seek a ``discriminative direction'' to isolate the discriminative shape difference between classes from the individual variability. Compared with the existing method, the ``discriminative direction" used in this paper is regularized by requiring the newly generated shapes to respect the underlying shape manifold as well as reflecting the essential shape differences in two populations. Hence a more accurate localization of difference is produced. We apply our methods to analyzing the hippocampal shapes between controls and Alzheimer's Disease (AD) based on the publicly available OASIS MRI database, and report the findings.

Authors


  •   Zhou, Luping
  •   Lieby, Paulette (external author)
  •   Barnes, Nick (external author)
  •   Reglade-Meslin, Chantal (external author)
  •   Walker, Janine (external author)
  •   Cherbuin, Nicolas (external author)
  •   Hartley, Richard (external author)

Publication Date


  • 2009

Citation


  • Zhou, L., Lieby, P., Barnes, N., Reglade-Meslin, C., Walker, J., Cherbuin, N. & Hartley, R. (2009). Hippocampal shape analysis for Alzheimer's disease using an efficient hypothesis test and regularized discriminative deformation. The Hippocampus, 19 (6), 533-540.

Scopus Eid


  • 2-s2.0-66249126820

Ro Metadata Url


  • http://ro.uow.edu.au/eispapers/1856

Has Global Citation Frequency


Number Of Pages


  • 7

Start Page


  • 533

End Page


  • 540

Volume


  • 19

Issue


  • 6

Place Of Publication


  • United States

Abstract


  • In this paper, we present a framework to perform statistical shape analysis for manually segmented hippocampi, which includes an efficient permutation test for detecting subtle class differences, and a regularized ``discriminative direction" method for visualizing the shape discrepancy. Fisher permutation and bootstrap tests are preferred to traditional hypothesis tests which impose assumptions on the distribution of the samples. In this paper, an efficient algorithm is adopted to rapidly perform the {\em exact} tests. We extend this algorithm to multivariate data by projecting the shape descriptors onto an ``informative direction'' that preserves the original discriminative information as much as possible to generate a scalar test statistic. This ``informative direction'' is further used to seek a ``discriminative direction'' to isolate the discriminative shape difference between classes from the individual variability. Compared with the existing method, the ``discriminative direction" used in this paper is regularized by requiring the newly generated shapes to respect the underlying shape manifold as well as reflecting the essential shape differences in two populations. Hence a more accurate localization of difference is produced. We apply our methods to analyzing the hippocampal shapes between controls and Alzheimer's Disease (AD) based on the publicly available OASIS MRI database, and report the findings.

Authors


  •   Zhou, Luping
  •   Lieby, Paulette (external author)
  •   Barnes, Nick (external author)
  •   Reglade-Meslin, Chantal (external author)
  •   Walker, Janine (external author)
  •   Cherbuin, Nicolas (external author)
  •   Hartley, Richard (external author)

Publication Date


  • 2009

Citation


  • Zhou, L., Lieby, P., Barnes, N., Reglade-Meslin, C., Walker, J., Cherbuin, N. & Hartley, R. (2009). Hippocampal shape analysis for Alzheimer's disease using an efficient hypothesis test and regularized discriminative deformation. The Hippocampus, 19 (6), 533-540.

Scopus Eid


  • 2-s2.0-66249126820

Ro Metadata Url


  • http://ro.uow.edu.au/eispapers/1856

Has Global Citation Frequency


Number Of Pages


  • 7

Start Page


  • 533

End Page


  • 540

Volume


  • 19

Issue


  • 6

Place Of Publication


  • United States