Early detection of Alzheimer's disease using histograms in a dissimilarity-based classification framework

Anne Luchtenberg, Rita Lopes Simoes, Anne-Marie van Cappellen van Walsum, Cornelis H. Slump

    Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

    Abstract

    Classication methods have been proposed to detect early-stage Alzheimer's disease using Magnetic Resonance images. In particular, dissimilarity-based classication has been applied using a deformation-based distance measure. However, such approach is not only computationally expensive but it also considers large-scale alterations in the brain only. In this work, we propose the use of image histogram distance measures, determined both globally and locally, to detect very mild to mild Alzheimer's disease. Using an ensemble of local patches over the entire brain, we obtain an accuracy of 84% (sensitivity 80% and specicity 88%).
    Original languageUndefined
    Title of host publicationMedical Imaging 2014: Computer-Aided Diagnosis
    EditorsS. Aylward, L.M. Hadjiski
    Place of PublicationBellingham, WA, USA
    PublisherSPIE
    Pages903502
    Number of pages10
    ISBN (Print)978-0-8194-9835-9
    DOIs
    Publication statusPublished - 15 Feb 2014

    Publication series

    NameProceedings of SPIE
    PublisherSPIE
    Volume9035

    Keywords

    • EWI-24913
    • local patches
    • histogram
    • dissimilarity-based classication
    • METIS-305946
    • IR-92126
    • MRI
    • Alzheimer's disease
    • Early detection

    Cite this

    Luchtenberg, A., Lopes Simoes, R., van Cappellen van Walsum, A-M., & Slump, C. H. (2014). Early detection of Alzheimer's disease using histograms in a dissimilarity-based classification framework. In S. Aylward, & L. M. Hadjiski (Eds.), Medical Imaging 2014: Computer-Aided Diagnosis (pp. 903502). (Proceedings of SPIE; Vol. 9035). Bellingham, WA, USA: SPIE. https://doi.org/10.1117/12.2042670