Comparison of Feature Selection Techniques in Machine Learning for Anatomical Brain MRI in Dementia

Jussi Tohka, Elaheh Moradi, Heikki Huttunen, Alzheimer’s Disease Neuroimaging Initiative, Alzheimer’s Disease Neuroimaging Initiative 2

    Research output: Contribution to journalArticleScientificpeer-review

    49 Citations (Scopus)

    Abstract

    We present a comparative split-half resampling analysis of various data driven feature selection and classification methods for the whole brain voxel-based classification analysis of anatomical magnetic resonance images. We compared support vector machines (SVMs), with or without filter based feature selection, several embedded feature selection methods and stability selection. While comparisons of the accuracy of various classification methods have been reported previously, the variability of the out-of-training sample classification accuracy and the set of selected features due to independent training and test sets have not been previously addressed in a brain imaging context. We studied two classification problems: 1) Alzheimer’s disease (AD) vs. normal control (NC) and 2) mild cognitive impairment (MCI) vs. NC classification. In AD vs. NC classification, the variability in the test accuracy due to the subject sample did not vary between different methods and exceeded the variability due to different classifiers. In MCI vs. NC classification, particularly with a large training set, embedded feature selection methods outperformed SVM-based ones with the difference in the test accuracy exceeding the test accuracy variability due to the subject sample. The filter and embedded methods produced divergent feature patterns for MCI vs. NC classification that suggests the utility of the embedded feature selection for this problem when linked with the good generalization performance. The stability of the feature sets was strongly correlated with the number of features selected, weakly correlated with the stability of classification accuracy, and uncorrelated with the average classification accuracy.

    Original languageEnglish
    Pages (from-to)279-296
    Number of pages18
    JournalNeuroinformatics
    Volume14
    Issue number3
    DOIs
    Publication statusPublished - 2016
    Publication typeA1 Journal article-refereed

    Keywords

    • Alzheimer’s Disease
    • Classification
    • Feature selection
    • Machine Learning
    • Magnetic Resonance Imaging
    • Multivariate pattern analysis

    Publication forum classification

    • Publication forum level 2

    ASJC Scopus subject areas

    • General Neuroscience
    • Information Systems
    • Software

    Fingerprint

    Dive into the research topics of 'Comparison of Feature Selection Techniques in Machine Learning for Anatomical Brain MRI in Dementia'. Together they form a unique fingerprint.

    Cite this