Abstract
We aim to learn across several subjects a mapping from brain anatomical connectivity to functional connectivity. Following [1], we formulate this problem as estimating a multivariate autoregressive (MAR) model with sparse linear regression. We introduce a model selection framework based on cross-validation. We select the appropriate sparsity of the connectivity matrices and demonstrate that choosing an ordering for the MAR that lends to sparser models is more appropriate than a random. Finally, we suggest randomized Least Absolute Shrinkage and Selective Operator (LASSO) in order to identify relevant anatomo-functional links with better recovery of ground truth.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Deligianni, F., Varoquaux, G., Thirion, B., Robinson, E., Sharp, D.J., Edwards, A.D., Rueckert, D.: A Probabilistic Framework to Infer Brain Functional Connectivity from Anatomical Connections. In: SzĆ©kely, G., Hahn, H.K. (eds.) IPMI 2011. LNCS, vol.Ā 6801, pp. 296ā307. Springer, Heidelberg (2011)
Sporns, O.: The non-random brain: efficiency, economy, and complex dynamics. Front Comput. Neurosc.Ā 5, 5 (2011)
Burns, J.: An evolutionary theory of schizophrenia: Cortical connectivity, metarepresentation, and the social brain. Behavioral and Brain SciencesĀ 27(6), 831 (2004)
Muller, R.: The study of autism as a distributed disorder. Mental Retardation and Developmental Disability ResearchĀ 13(1), 85ā95 (2007)
Pollonini, L., et al.: Information communication networks in severe traumatic brain injury. Brain Topogr.Ā 23(2), 221ā226 (2010)
Bullmore, E., Sporns, O.: Complex brain networks: graph theoretical analysis of structural and functional systems. Nat. Rev. Neurosci.Ā 10, 186ā198 (2009)
Zhang, D., Raichle, M.E.: Disease and the brainās dark energy. Nat. Rev. Neurol.Ā 6(1), 15ā28 (2010)
Honey, C., et al.: Predicting human resting-state functional connectivity from structural connectivity. P. Natl. Acad. Sci. USAĀ 106(6), 2035ā2040 (2009)
Hagmann, P., et al.: Mapping the structural core of human cerebral cortex. PLoS Biol.Ā 6(7), 1479ā1493 (2008)
Greicius, M.D., et al.: Resting-state functional connectivity reflects structural connectivity in the default mode network. Cerebral CortexĀ 19(1), 72ā78 (2009)
van den Heuvel, M., et al.: Microstructural organization of the cingulum tract and the level of default mode functional connectivity. J. Neurosci.Ā 28(43), 10844ā10851 (2008)
Varoquaux, G., et al.: Brain covariance selection: better individual functional connectivity models using population prior. In: NIPS (2010)
Lauritzen, S.: Graphical models. Oxford University Press, USA (1996)
Amestoy, P., et al.: An approximate minimum degree ordering algorithm. SIAM Journal on Matrix Analysis and ApplicationsĀ 17(4), 886ā905 (1996)
Tibshirani, R.: Regression shrinkage and selection via the lasso. J. Royal Statist. Soc. BĀ 58(1), 267ā288 (1996)
Donoho, D.: For most large underdetermined systems of linear equations the minimal l1-norm solution is also the sparsest solution. Comm. Pure Appl. Math.Ā 59(6), 797ā829 (2006)
Pedregosa, F., et al.: Scikit-learn: Machine learning in Python. JMLRĀ 12, 2825ā2830 (2011)
Varoquaux, G., Baronnet, F., Kleinschmidt, A., Fillard, P., Thirion, B.: Detection of Brain Functional-Connectivity Difference in Post-stroke Patients Using Group-Level Covariance Modeling. In: Jiang, T., Navab, N., Pluim, J.P.W., Viergever, M.A. (eds.) MICCAI 2010, Part I. LNCS, vol.Ā 6361, pp. 200ā208. Springer, Heidelberg (2010)
Meinshausen, N., Buhlmann, P.: Stability selection. Journal of the Royal Statistical Society: Series BĀ 27, 417ā473 (2010)
Zhang, C.-H., Huang, J.: The sparsity and bias of the lasso selection in high-dimensional linear regression. Annals of StatisticsĀ 36, 1567ā1594 (2008)
Smith, S., et al.: Advances in functional and structural MR image analysis and implementation as fsl. NeuroImageĀ 23, 208ā219 (2004)
Aljabar, P., et al.: Multi-atlas based segmentation of brain images: atlas selection and its effect on accuracy. NeuroImageĀ 46(3), 726ā738 (2009)
Friston, K.: Statistical parametric mapping: the analysis of functional brain images. Academic Press (2007)
Behrens, T., et al.: Characterization and propagation of uncertainty in diffusion-weighted MR imaging. Magnet Reson. Med.Ā 50(5), 1077ā1088 (2003)
Robinson, E., et al.: Identifying population differences in whole-brain structural networks: a machine learning approach. NeuroImageĀ 50(3), 910ā919 (2010)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
Ā© 2012 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Deligianni, F. et al. (2012). Relating Brain Functional Connectivity to Anatomical Connections: Model Selection. In: Langs, G., Rish, I., Grosse-Wentrup, M., Murphy, B. (eds) Machine Learning and Interpretation in Neuroimaging. Lecture Notes in Computer Science(), vol 7263. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-34713-9_23
Download citation
DOI: https://doi.org/10.1007/978-3-642-34713-9_23
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-34712-2
Online ISBN: 978-3-642-34713-9
eBook Packages: Computer ScienceComputer Science (R0)