Abstract
One of the biggest challenges in preprocessing pipelines for neuroimaging data is to increase the signal-to-noise ratio of the data which will be used for subsequent analyses. In the same line, we suggest in the present work that the application of consensus clustering for brain connectivity matrices to find subgroups of subjects can be a valid additional”connectome processing” step helpful to reduce intra-group variability and therefore increase the separability of distinct classes. In addition, by partitioning the data before any group comparison, we demonstrate that unique regions within each cluster arise and bring new information that could be relevant from a clinical point of view.
Copyright
The copyright holder for this preprint is the author/funder, who has granted bioRxiv a license to display the preprint in perpetuity. It is made available under a CC-BY 4.0 International license.
Posted June 16, 2018.
Connectome preprocessing by Consensus Clustering increases separability in group neuroimaging studies
