Segmenting Multiple Sclerosis Lesions using a Spatially Constrained K-Nearest Neighbour approach

Mark Lyksborg, Rasmus Larsen, Per Soelberg Sørensen, Morten Blinkenberg, Ellen Garde, Hartwig R. Siebner, Tim Bjørn Dyrby

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

    1 Downloads (Pure)

    Abstract

    We propose a method for the segmentation of Multiple Sclerosis lesions. The method is based on probability maps derived from a K-Nearest Neighbours classication. These are used as a non parametric likelihood in a Bayesian formulation with a prior that assumes connectivity of neighbouring voxels. The formulation is solved using the method of Iterated Conditional Modes (ICM). The parameters of the method are found through leave-one-out cross validation on training data after which it is evaluated on previously unseen test data. The multi modal features investigated are 3 structural MRI modalities, the diusion MRI measures of Fractional Anisotropy (FA), Mean Diusivity (MD) and several spatial features. Results show a benet from the inclusion of diusion primarily to the most dicult cases. Results shows that combining probabilistic K-Nearest Neighbour with a Markov Random Field formulation leads to a slight improvement of segmentations.
    Original languageEnglish
    Title of host publicationICIAR Proceedings : Springer Lecture Notes
    Number of pages8
    PublisherSpringer
    Publication date2012
    Publication statusPublished - 2012
    EventInternational Conference on Image Analysis and Recognition, ICIAR 2012 - Aveiro, Portugal
    Duration: 25 Jun 201227 Jun 2012
    http://www.iciar.uwaterloo.ca/iciar12/

    Conference

    ConferenceInternational Conference on Image Analysis and Recognition, ICIAR 2012
    CountryPortugal
    CityAveiro
    Period25/06/201227/06/2012
    Internet address

    Cite this

    Lyksborg, M., Larsen, R., Sørensen, P. S., Blinkenberg, M., Garde, E., Siebner, H. R., & Dyrby, T. B. (2012). Segmenting Multiple Sclerosis Lesions using a Spatially Constrained K-Nearest Neighbour approach. In ICIAR Proceedings: Springer Lecture Notes Springer.