Analysis of correlated activity in fMRI data by artificial neural networks

Clusters of correlated activity in fMRI data can identify regions of interest and indicate interacting brain areas. Because the extraction of clusters is computationally complex, we apply an approximative method which is based on Hopfield networks. It allows to find clusters of various degrees of connectivity ranging between the two extreme cases of cliques and connectivity components. Further we propose a criterion which allows to evaluate the relevance of such structures based on the robustness with respect to parameter variations.