On Feature Relevance in Image-Based Prediction Models: An Empirical Study

  • Ender Konukoglu
  • Melanie Ganz
  • Koen Van Leemput
  • Mert R. Sabuncu
  • for the Alzheimers Disease Neuroimaging Initiative
Part of the Lecture Notes in Computer Science book series (LNCS, volume 8184)


Determining disease-related variations of the anatomy and function is an important step in better understanding diseases and developing early diagnostic systems. In particular, image-based multivariate prediction models and the “relevant features” they produce are attracting attention from the community. In this article, we present an empirical study on the relevant features produced by two recently developed discriminative learning algorithms: neighborhood approximation forests (NAF) and the relevance voxel machine (RVoxM). Specifically, we examine whether the sets of features these methods produce are exhaustive; that is whether the features that are not marked as relevant carry disease-related information. We perform experiments on three different problems: image-based regression on a synthetic dataset for which the set of relevant features is known, regression of subject age as well as binary classification of Alzheimer’s Disease (AD) from brain Magnetic Resonance Imaging (MRI) data. Our experiments demonstrate that aging-related and AD-related variations are widespread and the initial sets of relevant features discovered by the methods are not exhaustive. Our findings show that by knocking-out features and re-training models, a much larger set of disease-related features can be identified.


Synthetic Dataset Relevance Vector Machine Common Coordinate System Random Permutation Test Relevant Pixel 
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.
    Sabuncu, M., Van Leemput, K.: The relevance voxel machine (rvoxm): A self-tuning bayesian model for informative image-based prediction. IEEE Transactions on Medical Imaging 31(12), 2290–2306 (2012)CrossRefGoogle Scholar
  2. 2.
    Gaonkar, B., Davatzikos, C.: Deriving statistical significance maps for svm based image classification and group comparisons. In: Ayache, N., Delingette, H., Golland, P., Mori, K. (eds.) MICCAI 2012, Part I. LNCS, vol. 7510, pp. 723–730. Springer, Heidelberg (2012)CrossRefGoogle Scholar
  3. 3.
    Konukoglu, E., Glocker, B., Zikic, D., Criminisi, A.: Neighbourhood approximation using randomized forests. Medical Image Analysis (2013)Google Scholar
  4. 4.
    Marcus, D., Wang, T., Parker, J., Csernansky, J., Morris, J., Buckner, R.: Open access series of imaging studies (oasis): cross-sectional mri data in young, middle aged, nondemented, and demented older adults. Journal of Cognitive Neuroscience 19(9), 1498–1507 (2007)CrossRefGoogle Scholar
  5. 5.
    Good, P.I.: Permutation, parametric and bootstrap tests of hypotheses. Springer Science+Business Media (2005)Google Scholar
  6. 6.
    Amit, Y., Geman, D.: Shape quantization and recognition with randomized trees. Neural Computation 9(7), 1545–1588 (1997)CrossRefGoogle Scholar
  7. 7.
    Strobl, C., Boulesteix, A.L., Zeileis, A., Hothorn, T.: Bias in random forest variable importance measures: Illustrations, sources and a solution. BMC Bioinformatics 8(1) 25 (2007)Google Scholar
  8. 8.
    Dale, A.M., Fischl, B., Sereno, M.I.: Cortical surface-based analysis: I. Segmentation and surface reconstruction. Neuroimage 9(2), 179–194 (1999)CrossRefGoogle Scholar
  9. 9.
    Fischl, B., Sereno, M.I., Dale, A.M.: Cortical surface-based analysis ii: Inflation, flattening, and a surface-based coordinate system. Neuroimage 9(2), 195–207 (1999)CrossRefGoogle Scholar
  10. 10.
    Fischl, B., Dale, A.M.: Measuring the thickness of the human cerebral cortex from magnetic resonance images. Proceedings of the National Academy of Sciences 97(20), 11050–11055 (2000)CrossRefGoogle Scholar
  11. 11.
    Fischl, B., Sereno, M.I., Tootell, R.B., Dale, A.M., et al.: High-resolution intersubject averaging and a coordinate system for the cortical surface. Human Brain Mapping 8(4), 272–284 (1999)CrossRefGoogle Scholar

Copyright information

© Springer International Publishing Switzerland 2013

Authors and Affiliations

  • Ender Konukoglu
    • 1
  • Melanie Ganz
    • 1
  • Koen Van Leemput
    • 2
    • 1
    • 3
  • Mert R. Sabuncu
    • 1
  • for the Alzheimers Disease Neuroimaging Initiative
    • 1
  1. 1.Martinos Center for Biomedical Imaging, Harvard Medical SchoolMGHUSA
  2. 2.Department of Applied Mathematics and Computer ScienceDTUDenmark
  3. 3.Departments of Information and Computer Science and of Biomedical, Engineering and Computational ScienceAalto UniversityFinland

Personalised recommendations