A feature-selective independent component analysis method for functional MRI

In this work, we propose a simple and effective scheme to incorporate prior knowledge about thesources of interest (SOIs) in independent component analysis (ICA) and apply the method to estimatebrain activations from functional magnetic resonance imaging (fMRI) data. We name the proposedmethod as feature-selective ICA since it incorporates the features in the sample space of the independentcomponents during ICA estimation. The feature-selective scheme is achieved through a filtering operationin the source sample space followed by a projection onto the demixing vector space by a least squaresprojection in an iterative ICA process. We perform ICA estimation of artificial activations superimposedinto a resting state fMRI dataset to show that the feature-selective scheme improves the detection ofinjected activation from the independent component estimated by ICA. We also compare the task-relatedsources estimated from true fMRI data by a feature-selective ICA algorithm versus an ICA algorithmand show evidence that the feature-selective scheme helps improve the estimation of the sources in bothspatial activation patterns and the time courses.