Diffeomorphic Statistical Deformation Models

Michael Sass Hansen, Mads/Fogtman Hansen, Rasmus Larsen

    Research output: Chapter in Book/Report/Conference proceedingArticle in proceedingsResearchpeer-review

    399 Downloads (Pure)

    Abstract

    In this paper we present a new method for constructing diffeomorphic statistical deformation models in arbitrary dimensional images with a nonlinear generative model and a linear parameter space. Our deformation model is a modified version of the diffeomorphic model introduced by Cootes et al. The modifications ensure that no boundary restriction has to be enforced on the parameter space to prevent folds or tears in the deformation field. For straightforward statistical analysis, principal component analysis and sparse methods, we assume that the parameters for a class of deformations lie on a linear manifold and that the distance between two deformations are given by the metric introduced by the L2-norm in the parameter space. The chosen L2-norm is shown to have a clear and intuitive interpretation on the usual nonlinear manifold. Our model is validated on a set of MR images of corpus callosum with ground truth in form of manual expert annotations, and compared to Cootes's model. We anticipate applications in unconstrained diffeomorphic synthesis of images, e.g. for tracking, segmentation, registration or classification purposes.
    Original languageEnglish
    Title of host publication2007 IEEE 11th International Conference on Computer Vision
    PublisherIEEE
    Publication date2007
    Pages2626-2633
    ISBN (Print)978-1-4244-1631-8
    DOIs
    Publication statusPublished - 2007
    EventWorkshop on Non-rigid Registration and Tracking through learning - Rio de Janeiro, Brazil
    Duration: 14 Oct 200720 Oct 2007

    Workshop

    WorkshopWorkshop on Non-rigid Registration and Tracking through learning
    CountryBrazil
    CityRio de Janeiro
    Period14/10/200720/10/2007
    OtherPart of 2007 IEEE 11th International Conference on Computer Vision

    Bibliographical note

    Copyright: 2007 IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE

    Fingerprint Dive into the research topics of 'Diffeomorphic Statistical Deformation Models'. Together they form a unique fingerprint.

    Cite this