TY - GEN

T1 - Estimation of shape model parameters for 3D surfaces

A1 - Erbou,Søren Gylling Hemmingsen

A1 - Darkner,Sune

A1 - Fripp,Jurgen

A1 - Ourselin,Sébastien

A1 - Ersbøll,Bjarne Kjær

AU - Erbou,Søren Gylling Hemmingsen

AU - Darkner,Sune

AU - Fripp,Jurgen

AU - Ourselin,Sébastien

AU - Ersbøll,Bjarne Kjær

PB - IEEE

PY - 2008

Y1 - 2008

N2 - Statistical shape models are widely used as a compact way of representing shape variation. Fitting a shape model to unseen data enables characterizing the data in terms of the model parameters. In this paper a Gauss-Newton optimization scheme is proposed to estimate shape model parameters of 3D surfaces using distance maps, which enables the estimation of model parameters without the requirement of point correspondence. For applications with acquisition limitations such as speed and cost, this formulation enables the fitting of a statistical shape model to arbitrarily sampled data. The method is applied to a database of 3D surfaces from a section of the porcine pelvic bone extracted from 33 CT scans. A leave-one-out validation shows that the parameters of the first 3 modes of the shape model can be predicted with a mean difference within [-0.01,0.02] from the true mean, with a standard deviation less than 0.34.

AB - Statistical shape models are widely used as a compact way of representing shape variation. Fitting a shape model to unseen data enables characterizing the data in terms of the model parameters. In this paper a Gauss-Newton optimization scheme is proposed to estimate shape model parameters of 3D surfaces using distance maps, which enables the estimation of model parameters without the requirement of point correspondence. For applications with acquisition limitations such as speed and cost, this formulation enables the fitting of a statistical shape model to arbitrarily sampled data. The method is applied to a database of 3D surfaces from a section of the porcine pelvic bone extracted from 33 CT scans. A leave-one-out validation shows that the parameters of the first 3 modes of the shape model can be predicted with a mean difference within [-0.01,0.02] from the true mean, with a standard deviation less than 0.34.

KW - Optimization methods

KW - X-ray tomography

KW - Image shape analysis

KW - Image registration

KW - Biomedical image processing

U2 - 10.1109/ISBI.2008.4541073

DO - 10.1109/ISBI.2008.4541073

SN - 14-24-42002-4

BT - 5th IEEE International Symposium on Biomedical Imaging

T2 - 5th IEEE International Symposium on Biomedical Imaging

SP - 624

EP - 627

ER -