@CONFERENCE\{IMM2007-04974,
    author       = "H. \'{O}lafsd\'{o}ttir and M. S. Hansen and K. Sj{\"{o}}strand and T. A. Darvann and N. V. Hermann and E. Oubel and B. K. Ersb{\o}ll and R. Larsen and A. F. Frangi and P. Larsen and C. A. Perlyn and G. M. Morriss-Kay and S. Kreiborg",
    title        = "Sparse Statistical Deformation Model for the Analysis of Craniofacial Malformation in the Crouzon Mouse",
    year         = "2007",
    month        = "jun",
    pages        = "112-121",
    booktitle    = "Scandinavian Conference on Image Analysis 2007",
    volume       = "4522",
    series       = "LNCS",
    editor       = "B.K. Ersb{\o}ll and K.S. Pedersen",
    publisher    = "Springer",
    organization = "",
    address      = "",
    url          = "http://www2.compute.dtu.dk/pubdb/pubs/4974-full.html",
    abstract     = "Crouzon syndrome is characterised by the premature fusion of cranial sutures. Recently the first genetic Crouzon mouse model was
generated. In this study, Micro {CT} skull scannings of wild-type mice and
Crouzon mice were investigated. Using nonrigid registration, a wild-type
craniofacial mouse atlas was built. The atlas was registered to all mice
providing parameters controlling the deformations for each subject. Our
previous {PCA-}based statistical deformation model on these parameters
revealed only one discriminating mode of variation. Aiming at distributing
the discriminating variation over more modes we built a different
model using Independent Component Analysis (ICA). Here, we focus on
a third method, sparse {PCA} (SPCA), which aims at approximating the
properties of a standard {PCA} while introducing sparse modes of variation.
The results show that {SPCA} outperforms both {ICA} and {PCA} with
respect to the Fisher discriminant, although many similarities are found
with respect to {ICA}.Crouzon syndrome is characterised by the premature fusion
of cranial sutures. Recently the rst genetic Crouzon mouse model was
generated. In this study, Micro {CT} skull scannings of wild-type mice and
Crouzon mice were investigated. Using nonrigid registration, a wild-type
craniofacial mouse atlas was built. The atlas was registered to all mice
providing parameters controlling the deformations for each subject. Our
previous {PCA-}based statistical deformation model on these parameters
revealed only one discriminating mode of variation. Aiming at distributing
the discriminating variation over more modes we built a dierent
model using Independent Component Analysis (ICA). Here, we focus on
a third method, sparse {PCA} (SPCA), which aims at approximating the
properties of a standard {PCA} while introducing sparse modes of variation.
The results show that {SPCA} outperforms both {ICA} and {PCA} with
respect to the Fisher discriminant, although many similarities are found
with respect to {ICA}."
}