A comparison of two methods to segment stent grafts in CT data

Almar Klein, M. Klaassen, L.J. Oostveen, J.A. van der Vliet, Y. Hoogeveen, L.J. Schultze Kool, W.K Renema, Cornelis H. Slump

    Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademic

    Abstract

    Late stent graft failure is a serious complication in endovascular repair of aortic aneurysms. Better understanding of the motion characteristics of stent grafts will be beneficial for designing future devices. In addition, analysis of stent graft movement in individual patients in vivo can be valuable for predicting stent graft failure in these patients. To be able to gather information on stent graft motion in a quick and robust fashion, an automatic segmentation method is required. In this work we compare two segmentation methods that produce a geometric model in the form of an undirected graph. The first method tracks along the centerline of the stent and segments the stent in 2D slices sampled orthogonal to it. The second method used a modified version of the minimum cost path (MCP) method to segment the stent directly in 3D. Using annotated reference data both methods were evaluated in an experiment. The results show that the centerline-based method and the MCP-based method have an accuracy of approximately 65% and 92%, respectively. The difference in accuracy can be explained by the fact that the centerline method makes assumptions about the topology of the stent which do not always hold in practice. This causes difficulties that are hard and sometimes impossible to overcome. In contrast, the MCP-based method works directly in 3D and is capable of segmenting a large variety of stent shapes and stent types.© (2012) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
    Original languageUndefined
    Title of host publicationMedical Imaging 2012: Biomedical Applications in Molecular, Structural, and Functional Imaging
    Place of PublicationBellingham, USA
    PublisherSPIE
    Pages83170H
    Number of pages10
    ISBN (Print)9780819489708
    DOIs
    Publication statusPublished - 4 Feb 2012
    EventSPIE Medical Imaging 2012 - Town & Country Resort and Convention Center, San Diego, United States
    Duration: 4 Feb 20129 Feb 2012

    Publication series

    NameProceedings of SPIE
    PublisherSPIE
    Volume8317

    Conference

    ConferenceSPIE Medical Imaging 2012
    CountryUnited States
    CitySan Diego
    Period4/02/129/02/12

    Keywords

    • geometric model
    • computed tomography
    • EWI-22417
    • METIS-289752
    • Segmentation
    • Stent graft
    • AAA
    • IR-82116

    Cite this