Visualization of Decision Tree State for the Classification of Parkinson's Disease

Williams, D., Mudali, D., Buddelmeijer, H., Noorishad, P., Meles, S., Renken, R., Leenders, K., Valentijn, E. & Roerdink, J., 1-Aug-2016, In : Journal of Biomedical Engineering and Medical Imaging. 3, 3, p. 25-41 25 p.

Research output: Contribution to journalArticleAcademicpeer-review

Copy link to clipboard


  • Visualization_of_Decision_Tree_State_for_the_Classification_of_Parkinsons_Disease

    Submitted manuscript, 2 MB, PDF document

    Request copy

  • Visualization of Decision Tree State for the Classification of Parkinson’s Disease

    Final publisher's version, 1 MB, PDF document

    Request copy


Decision trees have been shown to be effective at classifying subjects with Parkinson's disease when provided with features (subject scores) derived from FDG-PET data. Such subject scores have strong discriminative power but are not intuitive to understand. We therefore augment each decision node with thumbnails of the principal component (PC) images from which the subject scores are computed, and also provide labeled scatter plots of the distribution of scores. These plots allow the progress of individual subjects to be traced through the tree and enable the user to focus on complex or unexpected classifications. In addition, we present a visual representation of a typical brain activity pattern arriving at each leaf node, and show how this can be compared to a known reference to validate the behaviour of the tree.
Original languageEnglish
Pages (from-to)25-41
Number of pages25
JournalJournal of Biomedical Engineering and Medical Imaging
Issue number3
Publication statusPublished - 1-Aug-2016


  • Decision tree; Visualization; Medical imaging; Parkinson's Disease; Computer aided diagnosis;

ID: 34421693