Vessel bifurcation detection in scale space

File(s): 
Date created: 
2011-03-03
Identifier: 
etd6562
Supervisor(s): 
Ghassan Hamarneh
Department: 
Applied Science: School of Computing Science
Keywords: 
Scale-space
Bifurcation detection
Hessian eigenvalue
Interest points
Vascular enhancement
Codimension
Abstract: 

Several methods have been proposed for segmentation of vessels, many based on scale-space. However, none of the existing methods for blood vessel segmentation is appropriate for extension to bifurcation detection. Existing bifurcation detection algorithms use an inherently serial “track and detect” approach, requiring a seed point. We present a comprehensive scale space analysis of vascular bifurcations, resulting in a simple, novel algorithm for direct detection of blood vessel bifurcation points based not only on spatial variation across scales, but also on the variation at a single spatial point across scales, without training data or seed points. We present an analytical model for the bifurcation evolution with scale, combined with eigenvalue analysis to create a "bifurcationness" filter. We reveal, for the first time, a hybrid structure of bifurcations in scale-space. The algorithm was tested for validation in both 2D and 3D, with synthetic data and medical images.

Thesis type: 
((Computing Science) Thesis) M.Sc.
Document type: 
Thesis
Rights: 
Copyright remains with the author. The author granted permission for the file to be printed and for the text to be copied and pasted.
Statistics: