Biomedical Engineering Reference
In-Depth Information
13
EFFICIENT KERNEL DENSITY ESTIMATION
OF SHAPE AND INTENSITY PRIORS
FOR LEVEL SET SEGMENTATION
Daniel Cremers
Department of Computer Science,
University of Bonn
Bonn, Germany
Mikael Rousson
Department of Imaging and Visualization
Siemens Corporate Research,
Princeton, New Jersey, USA
We propose a nonlinear statistical shape model for level set segmentation that can be effi-
ciently implemented. Given a set of training shapes, we perform a kernel density estimation
in the low-dimensional subspace spanned by the training shapes. In this way, we are able to
combine an accurate model of the statistical shape distribution with efficient optimization in
a finite-dimensional subspace. In a Bayesian inference framework, we integrate the nonlin-
ear shape model with a nonparametric intensity model and a set of pose parameters that are
estimated in a more direct data-driven manner than in previously proposed level set meth-
ods. Quantitative results show superior performance (regarding runtime and segmentation
accuracy) of the proposed nonparametric shape prior over existing approaches.
1.
INTRODUCTION
Originally proposed in [1, 2] as a means to propagate interfaces in time,
the level set method has become increasingly popular as a framework for image
