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.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

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


    Contributors:
    Magee, D. (author) / Bulpitt, A. (author) / Berry, E. (author)


    Publication date :

    2001-01-01


    Size :

    730141 byte




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    3D Automated Segmentation and Structural Analysis of Vascular Trees Using Deformable Models

    Magee, D. / Bulpitt, A. / Berry, E. et al. | British Library Conference Proceedings | 2001


    Automated 3D PDM Construction Using Deformable Models

    Kaus, M. / Pekar, V. / Lorenz, C. et al. | British Library Conference Proceedings | 2001


    Automated 3D PDM construction using deformable models

    Kaus, M.R. / Pekar, V. / Lorenz, C. et al. | IEEE | 2001


    Directional adaptive deformable models for segmentation

    Rougon, N. / Preteux, F. | British Library Online Contents | 1998


    Vehicle Segmentation Using Deformable Templates

    Dubuisson, M.-P. / Lakshmanan, S. / Jain, A. K. et al. | British Library Conference Proceedings | 1995