Relating Brain Functional Connectivity to Anatomical Connections: Model Selection

Deligianni, F. , Varoquaux, G., Thirion, B., Robinson, E., Sharp, D. J., Edwards, A. D. and Rueckert, D. (2012) Relating Brain Functional Connectivity to Anatomical Connections: Model Selection. In: International Machine Learning and Interpretation in Neuroimaging Workshop (MLINI 2011), Sierra Nevada, Spain, 16-17 December 2011, pp. 178-185. ISBN 9783642347122 (doi:10.1007/978-3-642-34713-9_23)

Full text not currently available from Enlighten.

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.

Item Type:Conference Proceedings
Status:Published
Refereed:Yes
Glasgow Author(s) Enlighten ID:Deligianni, Dr Fani
Authors: Deligianni, F., Varoquaux, G., Thirion, B., Robinson, E., Sharp, D. J., Edwards, A. D., and Rueckert, D.
College/School:College of Science and Engineering > School of Computing Science
ISSN:0302-9743
ISBN:9783642347122

University Staff: Request a correction | Enlighten Editors: Update this record