# Difference between revisions of "Projects:MultiscaleShapeSegmentation"

Line 1: | Line 1: | ||

− | |||

− | |||

Back to [[NA-MIC_Collaborations|NA-MIC_Collaborations]], [[Algorithm:GATech|Georgia Tech Algorithms]], [[Algorithm:UNC|UNC Algorithms]] | Back to [[NA-MIC_Collaborations|NA-MIC_Collaborations]], [[Algorithm:GATech|Georgia Tech Algorithms]], [[Algorithm:UNC|UNC Algorithms]] | ||

− | + | = Multiscale Shape Segmentation = | |

To represent multiscale variations in a shape population in order to drive the segmentation of deep brain structures, such as the caudate nucleus or the hippocampus. | To represent multiscale variations in a shape population in order to drive the segmentation of deep brain structures, such as the caudate nucleus or the hippocampus. | ||

− | '' | + | = Description = |

+ | |||

+ | ''Shape Representation and Prior'' | ||

− | |||

The overview of our shape representation is given in Figure 1. Our technique defines a multiscale parametric model of surfaces belonging to the same population using a compact set of spherical wavelets targeted to that population (Figure 2). We further refine the shape representation by separating into groups wavelet coefficients that describe independent global and/or local biological variations in the population, using spectral graph partitioning. We then learn a prior probability distribution induced over each group to explicitly encode these variations at different scales and spatial locations (Figure 4) [1]. | The overview of our shape representation is given in Figure 1. Our technique defines a multiscale parametric model of surfaces belonging to the same population using a compact set of spherical wavelets targeted to that population (Figure 2). We further refine the shape representation by separating into groups wavelet coefficients that describe independent global and/or local biological variations in the population, using spectral graph partitioning. We then learn a prior probability distribution induced over each group to explicitly encode these variations at different scales and spatial locations (Figure 4) [1]. | ||

Line 21: | Line 20: | ||

We applied our algorithm to the caudate nucleus, a brain structure of interest in the study of schizophrenia [2]. Our validation shows our algorithm is computationally efficient and outperforms the Active Shape Model (ASM) algorithm, by capturing finer shape details. | We applied our algorithm to the caudate nucleus, a brain structure of interest in the study of schizophrenia [2]. Our validation shows our algorithm is computationally efficient and outperforms the Active Shape Model (ASM) algorithm, by capturing finer shape details. | ||

− | + | = Key Investigators = | |

+ | |||

+ | * Georgia Tech: Delphine Nain, Aaron Bobick, Allen Tannenbaum | ||

+ | * Harvard SPL: Steven Haker | ||

+ | |||

+ | |||

+ | = Publications = | ||

+ | |||

* Nain D, Haker S, Bobick A, Tannenbaum A. Multiscale 3D Shape Analysis using Spherical Wavelets. Proc MICCAI, Oct 26-29 2005, p 459-467. | * Nain D, Haker S, Bobick A, Tannenbaum A. Multiscale 3D Shape Analysis using Spherical Wavelets. Proc MICCAI, Oct 26-29 2005, p 459-467. | ||

* Nain D, Haker S, Bobick A, Tannenbaum A. Shape-driven 3D Segmentation using Spherical Wavelets. Proc MICCAI, Oct 2-5, 2006. | * Nain D, Haker S, Bobick A, Tannenbaum A. Shape-driven 3D Segmentation using Spherical Wavelets. Proc MICCAI, Oct 2-5, 2006. | ||

− | |||

− | |||

− | |||

− | |||

''Collaborators'' | ''Collaborators'' | ||

Line 36: | Line 38: | ||

* Core 3: James Levitt, Marc Niethammer, Sylvain Bouix, Martha Shenton (Harvard PNL) | * Core 3: James Levitt, Marc Niethammer, Sylvain Bouix, Martha Shenton (Harvard PNL) | ||

− | + | = Links = | |

* Paper presented in [[MICCAI_2006|MICCAI 2006, Copenhagen, October 2 - 4, 2006 ]] | * Paper presented in [[MICCAI_2006|MICCAI 2006, Copenhagen, October 2 - 4, 2006 ]] |

## Revision as of 21:11, 21 September 2007

Home < Projects:MultiscaleShapeSegmentationBack to NA-MIC_Collaborations, Georgia Tech Algorithms, UNC Algorithms

# Multiscale Shape Segmentation

To represent multiscale variations in a shape population in order to drive the segmentation of deep brain structures, such as the caudate nucleus or the hippocampus.

# Description

*Shape Representation and Prior*

The overview of our shape representation is given in Figure 1. Our technique defines a multiscale parametric model of surfaces belonging to the same population using a compact set of spherical wavelets targeted to that population (Figure 2). We further refine the shape representation by separating into groups wavelet coefficients that describe independent global and/or local biological variations in the population, using spectral graph partitioning. We then learn a prior probability distribution induced over each group to explicitly encode these variations at different scales and spatial locations (Figure 4) [1].

*Segmentation*
Based on this representation, we derive a parametric active surface evolution using the multiscale prior coefficients as parameters for our optimization procedure to naturally include the prior for segmentation. Additionally, the optimization method can be applied in a coarse-to-fine manner.

*Results*
We applied our algorithm to the caudate nucleus, a brain structure of interest in the study of schizophrenia [2]. Our validation shows our algorithm is computationally efficient and outperforms the Active Shape Model (ASM) algorithm, by capturing finer shape details.

# Key Investigators

- Georgia Tech: Delphine Nain, Aaron Bobick, Allen Tannenbaum
- Harvard SPL: Steven Haker

# Publications

- Nain D, Haker S, Bobick A, Tannenbaum A. Multiscale 3D Shape Analysis using Spherical Wavelets. Proc MICCAI, Oct 26-29 2005, p 459-467.
- Nain D, Haker S, Bobick A, Tannenbaum A. Shape-driven 3D Segmentation using Spherical Wavelets. Proc MICCAI, Oct 2-5, 2006.

*Collaborators*

- Core 1: Martin Styner (UNC)
- Core 2: Jim Miller (GE), Luis Ibanez (Kitware)
- Core 3: James Levitt, Marc Niethammer, Sylvain Bouix, Martha Shenton (Harvard PNL)