By Topic

3D automated segmentation and structural analysis of vascular trees using deformable models

Sign In

Cookies must be enabled to login.After enabling cookies , please use refresh or reload or ctrl+f5 on the browser for the login options.

Formats Non-Member Member
$31 $13
Learn how you can qualify for the best price for this item!
Become an IEEE Member or Subscribe to
IEEE Xplore for exclusive pricing!
close button

puzzle piece

IEEE membership options for an individual and IEEE Xplore subscriptions for an organization offer the most affordable access to essential journal articles, conference papers, standards, eBooks, and eLearning courses.

Learn more about:

IEEE membership

IEEE Xplore subscriptions

3 Author(s)
Magee, D. ; Sch. of Comput., Leeds Univ., UK ; Bulpitt, A. ; Berry, E.

This paper describes novel automated methods for the segmentation of complex structures and their subsequent analysis. The methods have been developed as parts of a system to provide decision support in the assessment of patient suitability for endovascular repair of abdominal aortic aneurysms from spiral CT data. Our segmentation technique provides a new method for controlling the deformation: a 3D deformable model using a model of expected structure. This approach introduces knowledge of anatomy into the deformable model through an expected structure model (ESM), mimicking the knowledge of the observer in an interactive system. The expected structure model is used to improve robustness of the deformable model to noise within the image, without globally over-constraining the model. The model also permits the identification of features of interest that can be used for clinical assessment. In order to obtain useful measurements from the segmentations, the geometric structure of the arterial tree is required. Our method automates this procedure using a stochastic growing algorithm based on a particle filter to determine the centre lines and locations of bifurcations of the arterial tree. The results demonstrate how the ESM and stochastic growing algorithm can be used to both identify features and to produce measurements required for patient assessment

Published in:

Variational and Level Set Methods in Computer Vision, 2001. Proceedings. IEEE Workshop on

Date of Conference:

2001