Feature Selection Based on SVM Significance Maps for Classification of Dementia

  • Esther Bron
  • Marion Smits
  • John van Swieten
  • Wiro Niessen
  • Stefan Klein
Part of the Lecture Notes in Computer Science book series (LNCS, volume 8679)


Support vector machine significance maps (SVM p-maps) previously showed clusters of significantly different voxels in dementia-related brain regions. We propose a novel feature selection method for classification of dementia based on these p-maps. In our approach, the SVM p-maps are calculated on the training set with a time-efficient analytic approximation. The features that are most significant on the p-map are selected for classification with an SVM classifier. We validated our method using MRI data from the Alzheimer’s Disease Neuroimaging Initiative (ADNI), classifying Alzheimer’s disease (AD) patients, mild cognitive impairment (MCI) patients who converted to AD within 18 months, MCI patients who did not convert to AD, and cognitively normal controls (CN). The voxel-wise features were based on gray matter morphometry. We compared p-map feature selection to classification without feature selection and feature selection based on t-tests and expert knowledge. Our method obtained in all experiments similar or better performance and robustness than classification without feature selection with a substantially reduced number of features. In conclusion, we proposed a novel and efficient feature selection method with promising results.


Support Vector Machine Feature Selection Mild Cognitive Impairment Feature Selection Method Mild Cognitive Impairment Patient 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Cuingnet, R., Gerardin, E., Tessieras, J., et al.: Automatic classification of patients with Alzheimer’s disease from structural MRI: A comparison of ten methods using the ADNI database. Neuroimage 56(2), 766–781 (2011)CrossRefGoogle Scholar
  2. 2.
    Chu, C., Hsu, A., Chou, K., et al.: Does feature selection improve classification accuracy? Impact of sample size and feature selection on classification using anatomical magnetic resonance images. Neuroimage 60, 59–70 (2012)CrossRefGoogle Scholar
  3. 3.
    Bron, E., Steketee, R., et al.: Diagnostic classification of arterial spin labeling and structural MRI in presenile early stage dementia. Hum. Brain Mapp. 35(9) (2014)Google Scholar
  4. 4.
    Gaonkar, B., Davatzikos, C.: Analytic estimation of statistical significance maps for support vector machine based multi-variate image analysis and classification. Neuroimage 78, 270–283 (2013)CrossRefGoogle Scholar
  5. 5.
    Mourão Miranda, J., Bokde, A.L.W., Born, C., et al.: Classifying brain states and determining the discriminating activation patterns: Support Vector Machine on functional MRI data. Neuroimage 28(4), 980–995 (2005)CrossRefGoogle Scholar
  6. 6.
    Wang, Z., Childress, A.R., Wang, J., Detre, J.A.: Support vector machine learning-based fMRI data group analysis. Neuroimage 36(4), 1139–1151 (2007)CrossRefGoogle Scholar
  7. 7.
    Jack, C., Bernstein, M., Fox, N., et al.: The Alzheimer’s Disease Neuroimaging Initiative (ADNI): MRI methods. J. Magn. Reson. Imaging 27(4), 685–691 (2008)CrossRefGoogle Scholar
  8. 8.
    Seghers, D., D’Agostino, E., Maes, F., Vandermeulen, D., Suetens, P.: Construction of a brain template from MR images using state-of-the-art registration and segmentation techniques. In: Barillot, C., Haynor, D.R., Hellier, P. (eds.) MICCAI 2004. LNCS, vol. 3216, pp. 696–703. Springer, Heidelberg (2004)CrossRefGoogle Scholar
  9. 9.
    Chang, C.C., Lin, C.J.: LIBSVM: A library for support vector machines. ACM TIST 2(3), 27 (2011)Google Scholar
  10. 10.
    Gousias, I., Rueckert, D., Heckemann, R., et al.: Automatic segmentation of brain MRIs of 2-year-olds into 83 regions of interest. Neuroimage 40, 672–684 (2008)CrossRefGoogle Scholar
  11. 11.
    Bastos Leite, A., Scheltens, P., Barkhof, F.: Pathological aging of the brain: an overview. Top Magn. Reson. Imaging 15(6), 369–389 (2004)CrossRefGoogle Scholar
  12. 12.
    Frisoni, G., et al.: Detection of grey matter loss in mild Alzheimer’s disease with voxel based morphometry. J. Neurol. Neurosurg. Psychiatry 73, 657–664 (2002)CrossRefGoogle Scholar
  13. 13.
    Chételat, G., et al.: Mapping gray matter loss with voxel-based morphometry in mild cognitive impairment. Neuroreport 13, 1939–1943 (2002)CrossRefGoogle Scholar
  14. 14.
    Pennanen, C., Testa, C., Laakso, M.P., et al.: A voxel based morphometry study on mild cognitive impairment. J. Neurol. Neurosurg Psychiatry 76(1), 11–14 (2005)CrossRefGoogle Scholar

Copyright information

© Springer International Publishing Switzerland 2014

Authors and Affiliations

  • Esther Bron
    • 1
  • Marion Smits
    • 2
  • John van Swieten
    • 3
  • Wiro Niessen
    • 1
    • 4
  • Stefan Klein
    • 1
  1. 1.Biomedical Imaging Group Rotterdam, Departments of Medical Informatics and RadiologyErasmus MCRotterdamThe Netherlands
  2. 2.Department of RadiologyErasmus MCRotterdamThe Netherlands
  3. 3.Department of NeurologyErasmus MCRotterdamThe Netherlands
  4. 4.Imaging Physics, Applied SciencesDelft University of TechnologyThe Netherlands

Personalised recommendations