DMCA
Active-Contour-Based Image Segmentation using Machine Learning Techniques (2007)
Cached
Download Links
- [www.enpc.fr]
- [www.di.ens.fr]
- [certis.enpc.fr]
- DBLP
Other Repositories/Bibliography
| Venue: | in "10th IEEE International Conference on Medical Image Computing and Computer Assisted Intervention |
| Citations: | 7 - 0 self |
BibTeX
@INPROCEEDINGS{Etyngier07active-contour-basedimage,
author = {Patrick Etyngier and Florent Ségonne and Renaud Keriven},
title = {Active-Contour-Based Image Segmentation using Machine Learning Techniques},
booktitle = {in "10th IEEE International Conference on Medical Image Computing and Computer Assisted Intervention},
year = {2007},
pages = {891--899}
}
Share
 |
 |
 |
 |
||
OpenURL
Abstract
Abstract. We introduce a non-linear shape prior for the deformable model framework that we learn from a set of shape samples using recent manifold learning techniques. We model a category of shapes as a finite dimensional manifold which we approximate using Diffusion maps. Our method computes a Delaunay triangulation of the reduced space, considered as Euclidean, and uses the resulting space partition to identify the closest neighbors of any given shape based on its Nyström extension. We derive a non-linear shape prior term designed to attract a shape towards the shape prior manifold at given constant embedding. Results on shapes of ventricle nuclei demonstrate the potential of our method for segmentation tasks. Fig. 1. Aligned shape samples of the right ventricle nucleus from different subjects corresponding, from left to right, to 2 young, 2 mid-age, and 2 old subjects; the last shape sample originates from a subject with Alzheimer’s Disease. While shapes appear quite similar, they usually cannot be considered as small deformations around a mean shape.
Keyphrases
machine learning technique active-contour-based image segmentation shape sample right ventricle reduced space mean shape alzheimer disease deformable model framework small deformation last shape sample non-linear shape prior term segmentation task nystr extension constant embedding diffusion map ventricle nucleus recent manifold old subject non-linear shape different subject delaunay triangulation finite dimensional manifold space partition
