Abstract
This paper introduces a new method to detect group differences in brain images based on spatially regularized support vector machines (SVM). First, we propose to spatially regularize the SVM using a graph encoding the voxels’ proximity. Two examples of regularization graphs are provided. Significant differences between two populations are detected using statistical tests on the margins of the SVM. We first tested our method on synthetic examples. We then applied it to 72 stroke patients to detect brain areas associated with motor outcome at 90 days, based on diffusion-weighted images acquired at the acute stage (one day delay). The proposed method showed that poor motor outcome is associated to changes in the corticospinal bundle and white matter tracts originating from the premotor cortex. Standard mass univariate analyses failed to detect any difference.
Chapter PDF
Similar content being viewed by others
Keywords
- Support Vector Machine
- Stroke Outcome
- Linear Support Vector Machine
- Support Vector Machine Method
- Motor Outcome
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.
References
Chalela, J., et al.: Magnetic resonance imaging and computed tomography in emergency assessment of patients with suspected acute stroke: a prospective comparison. The Lancet 369(9558), 293–298 (2007)
Crafton, K., et al.: Improved understanding of cortical injury by incorporating measures of functional anatomy. Brain 126(7), 1650–1659 (2003)
Domi, T., et al.: Corticospinal tract pre-wallerian degeneration: A novel outcome predictor for pediatric stroke on acute MRI. Stroke 40(3), 780–787 (2009)
Lo, R., et al.: Identification of critical areas for motor function recovery in chronic stroke subjects using voxel-based lesion symptom mapping. NeuroImage 49(1), 9–18 (2010)
Rosso, C., et al.: Prediction of Infarct Growth Based on Apparent Diffusion Coefficients: Penumbral Assessment without Intravenous Contrast Material. Radiology 250(1), 184–192 (2009)
Ashburner, J., Friston, K.J.: Voxel-based morphometry–the methods. NeuroImage 11(6), 805–821 (2000)
Davatzikos, C.: Why voxel-based morphometric analysis should be used with great caution when characterizing group differences. NeuroImage 23(1), 17–20 (2004)
Vapnik, V.N.: The Nature of Statistical Learning Theory. Springer, Heidelberg (1995)
Schölkopf, B., Smola, A.J.: Learning with Kernels. MIT Press, Cambridge (2001)
Lao, Z., et al.: Morphological classification of brains via high-dimensional shape transformations and machine learning methods. NeuroImage 21(1), 46–57 (2004)
Fan, Y., et al.: COMPARE: classification of morphological patterns using adaptive regional elements. IEEE TMI 26(1), 93–105 (2007)
Klöppel, S., et al.: Automatic classification of MR scans in Alzheimer’s disease. Brain 131(3), 681–689 (2008)
Vemuri, P., et al.: Alzheimer’s disease diagnosis in individual subjects using structural MR images: validation studies. NeuroImage 39(3), 1186–1197 (2008)
Mourão-Miranda, J., et al.: Classifying brain states and determining the discriminating activation patterns: Support vector machine on functional MRI data. NeuroImage 28(4), 980–995 (2005); Special Section: Social Cognitive Neuroscience
Chung, F.R.K.: Spectral Graph Theory, vol. 92. AMS (1992)
Golub, G.H., Van Loan, C.F.: Matrix computations. J. Hopkins Univ. Press, Baltimore (1996)
Smola, A.J., Schölkopf, B.: On a kernel-based method for pattern recognition, regression, approximation, and operator inversion. Algorithmica 22, 211–231 (1998)
Kondor, R.I., Lafferty, J.D.: Diffusion kernels on graphs and other discrete input spaces. In: Proc. International Conference on Machine Learning, pp. 315–322 (2002)
Gómez-Chova, L., et al.: Semi-supervised image classification with Laplacian support vector machines. IEEE Geo. Rem. Sens. Let. 5(3), 336–340 (2008)
Smola, A., Kondor, R.: Kernels and regularization on graphs. In: Schölkopf, B., Warmuth, M.K. (eds.) COLT/Kernel 2003. LNCS (LNAI), vol. 2777, p. 144. Springer, Heidelberg (2003)
Rapaport, F., et al.: Classification of microarray data using gene networks. BMC bioinformatics 8(1), 35 (2007)
Benjamini, Y., Hochberg, Y.: Controlling the false discovery rate: a practical and powerful approach to multiple testing. J. Roy. Stat. Soc. B. Met., 289–300 (1995)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2010 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Cuingnet, R. et al. (2010). Spatially Regularized SVM for the Detection of Brain Areas Associated with Stroke Outcome. In: Jiang, T., Navab, N., Pluim, J.P.W., Viergever, M.A. (eds) Medical Image Computing and Computer-Assisted Intervention – MICCAI 2010. MICCAI 2010. Lecture Notes in Computer Science, vol 6361. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-15705-9_39
Download citation
DOI: https://doi.org/10.1007/978-3-642-15705-9_39
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-15704-2
Online ISBN: 978-3-642-15705-9
eBook Packages: Computer ScienceComputer Science (R0)