Abstract
Discriminative supervised learning algorithms, such as Support Vector Machines, are becoming increasingly popular in biomedical image computing. One of their main uses is to construct image-based prediction models, e.g., for computer aided diagnosis or “mind reading.” A major challenge in these applications is the biological interpretation of the machine learning models, which can be arbitrarily complex functions of the input features (e.g., as induced by kernel-based methods). Recent work has proposed several strategies for deriving maps that highlight regions relevant for accurate prediction. Yet most of these methods either rely on strong assumptions about the prediction model (e.g., linearity, sparsity) and/or data (e.g., Gaussianity), or fail to exploit the covariance structure in the data. In this work, we propose a computationally efficient and universal framework for quantifying associations captured by black box machine learning models. Furthermore, our theoretical perspective reveals that examining associations with predictions, in the absence of ground truth labels, can be very informative. We apply the proposed method to machine learning models trained to predict cognitive impairment from structural neuroimaging data. We demonstrate that our approach yields biologically meaningful maps of association.
Chapter PDF
Similar content being viewed by others
References
Breiman, L.: Statistical modeling: The two cultures (with comments and a rejoinder by the author). Statistical Science 16(3), 199–231 (2001)
Kawasaki, Y., et al.: Multivariate voxel-based morphometry successfully differentiates schizophrenia patients from healthy controls. Neuroimage 34(1) (2007)
Davatzikos, C., et al.: Individual patient diagnosis of ad and ftd via high-dimensional pattern classification of mri. Neuroimage 41(4), 1220–1227 (2008)
Klöppel, S., et al.: Automatic detection of preclinical neurodegeneration presymptomatic huntington disease. Neurology 72(5), 426–431 (2009)
Zhang, D., et al.: Multimodal classification of alzheimer’s disease and mild cognitive impairment. Neuroimage 55(3), 856–867 (2011)
Plant, C., et al.: Automated detection of brain atrophy patterns based on mri for the prediction of alzheimer’s disease. Neuroimage 50(1), 162–174 (2010)
Ashburner, J., Friston, K.J.: Voxel-based morphometry–the methods. Neuroimage 11(6), 805–821 (2000)
Sabuncu, M.R., Van Leemput, K.: The Relevance Voxel Machine (RVoxM): A self-tuning bayesian model for informative image-based prediction. IEEE Transactions on Medical Imaging (2012)
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)
Konukoglu, E., Ganz, M., Van Leemput, K., Sabuncu, M.R.: On feature relevance in image-based prediction models: An empirical study. In: Wu, G., Zhang, D., Shen, D., Yan, P., Suzuki, K., Wang, F. (eds.) MLMI 2013. LNCS, vol. 8184, pp. 171–178. Springer, Heidelberg (2013)
Haufe, S., et al.: On the interpretation of weight vectors of linear models in multivariate neuroimaging. NeuroImage 87, 96–110 (2014)
Golland, P.: Discriminative direction for kernel classifiers. Advances in Neural Information Processing Systems 1, 745–752 (2002)
Strobl, C., et al.: Conditional variable importance for random forests. BMC Bioinformatics 9(1), 307 (2008)
Zien, A., Krämer, N., Sonnenburg, S., Rätsch, G.: The feature importance ranking measure. In: Buntine, W., Grobelnik, M., Mladenić, D., Shawe-Taylor, J. (eds.) ECML PKDD 2009, Part II. LNCS (LNAI), vol. 5782, pp. 694–709. Springer, Heidelberg (2009)
Meinshausen, N., Bühlmann, P.: Stability selection. Journal of the Royal Statistical Society: Series B (Statistical Methodology) 72(4), 417–473 (2010)
Goldstein, A., et al.: Peeking inside the black box: Visualizing statistical learning with plots of individual conditional expectation. J. of Comp. and Graph. Stat. (2014)
Dosenbach, N.U.F., et al.: Prediction of individual brain maturity using fMRI. Science 329(5997), 1358 (2010)
Sonnenburg, S., et al.: Poims: positional oligomer importance matricesunderstanding support vector machine-based signal detectors. Bioinformatics 24(13), i6–i14 (2008)
Zheng, S., et al.: Generalized measures of correlation for asymmetry, nonlinearity, and beyond. J. of the American Statistical Association 107(499), 1239–1252 (2012)
Dickerson, B., et al.: The cortical signature of alzheimer’s disease. Cerebral Cortex 19(3), 497–510 (2009)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2014 Springer International Publishing Switzerland
About this paper
Cite this paper
Sabuncu, M.R. (2014). A Universal and Efficient Method to Compute Maps from Image-Based Prediction Models. In: Golland, P., Hata, N., Barillot, C., Hornegger, J., Howe, R. (eds) Medical Image Computing and Computer-Assisted Intervention – MICCAI 2014. MICCAI 2014. Lecture Notes in Computer Science, vol 8675. Springer, Cham. https://doi.org/10.1007/978-3-319-10443-0_45
Download citation
DOI: https://doi.org/10.1007/978-3-319-10443-0_45
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-10442-3
Online ISBN: 978-3-319-10443-0
eBook Packages: Computer ScienceComputer Science (R0)