FALCON or how to compute measures time efficiently on dynamically evolving dense complex networks?

A Critical Comparison of Pipelines for Structural Brain Network Analysis

The human brain could be understood as a vast network composed of interconnected regions forming hierarchical and overlapping subnetworks. Cortical thickness (CT) correlations, as measure of structural connectedness, can be transformed into structural networks. Those can be analyzed via cluster detection algorithms to investigate their organization. An analysis pipeline from CT to links, networks, clusters and beyond is composed of a lot of consecutive reasoned or just arbitrary steps. How much can different pipeline components alter the result? Which step is to be considered most influential? In order to give a sufficient answer, we critically compare 96 different pipelines. The results of this study are to some extent surprising as the choice of a specific CT correlation and correction procedure can lead to more diverse results than the decision between taking only absolute CT correlations or ignoring all negative ones. Even more crucial, exemplary cluster detectors were found to pair-wisely correlate from r = 0.98 to even r = -0.20 on the same data. Thus, a summary of multiple detector results with different but suited properties is highly advisable until a theory based neuroscientific recommendation for the best approach will be found.