EBlini/FCnet: Analysis of Functional Connectivity matrices through elastic NETs

The analysis of (Functional Connectivity) neuroimaging data can be daunting due to the very high dimensionality of the features involved. In time, several approaches to the problem have been devised. `FCnet` allows one to easily implement a three steps procedure consisting of: i) Feature reduction: the functional connectivity matrices are first summarized through data reduction techniques such as Principal Component Analysis or Independent Components Analysis. ii) Robust regression: the reduced matrix of Weights is then entered into a robust regression model (with either ridge or LASSO penalty). The model is crossvalidated internally by means of Leave-One-Out (nested) crossvalidation. ii) Back-projection: models' coefficients can be back-projected onto the original space, in order to rank the most predictive edges of a matrix. Starting from version 0.1.5, experimental support is also provided for the analysis of brain volumes.

install.packages("remotes")
remotes::install_github("EBlini/FCnet")