Relating Brain Functional Connectivity to Anatomical Connections: Model Selection

Fani Deligianni, Gaël Varoquaux, Bertrand Thirion, Emma C. Robinson, David J. Sharp, A. David Edwards, Daniel Rueckert

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.