Workshop on Bioimaging II / PDEs, Tue, 20 Nov, 2007
Speaker: Oliver Gloger
Abstract
In this work we propose an adapted level set segmentation technique for the recognition of atherosclerotic plaque tissue on magnetic resonance images. We extended a method for the curvature based anisotropic diffusion and applied it to denoise magnetic resonance images from plaques. The denoised images serve as an appropriate basis for the application of our level set segmentation technique.
The segmentation technique is subdivided into three steps whereas the result of every phase serves as prior knowledge for the next step. By analyzing and combining carefully all available channel information during the first and second step we are capable to border the vessel walls on the images. For achieving local exact segmentation results we support the plaque detection with so-called Canny edges.
The third step controls an enclosing level set which circumvents the plaque patterns from healthy media tissue. In this step we introduce a local weighting concept for intensity information of plaque patterns. Furthermore, we justify the introduction of a maximal shrinking distance for the third level set and show very promising results of this method in special figures during the level set propagation.
The extension of the level set segmentation with locally weighted intensity information and a maximal shrinking distance allows the algorithm to automatically distinguish plaque from healthy media tissue. Furthermore, we are capable to detect and segment plaque patterns which are complicated to recognize for the human observer.
URL: www.ricam.oeaw.ac.at/specsem/ssqbm/participants/abstracts/index.php
This page was made with 100% valid HTML & CSS - Send comments to Webmaster
Today's date and time is 04/26/24 - 10:44 CEST and this file (/specsem/ssqbm/participants/abstracts/index.php) was last modified on 12/18/12 - 11:01 CEST