Robustness of Representative Signals Relative to Data Loss Using Atlas-Based Parcellations

Investor logo


This publication doesn't include Faculty of Medicine. It includes Central European Institute of Technology. Official publication website can be found on



Year of publication 2018
Type Article in Periodical
Magazine / Source BRAIN TOPOGRAPHY
MU Faculty or unit

Central European Institute of Technology

Keywords Parcellation; fMRI; Atlas; Representative signal; Coverage
Description Parcellation-based approaches are an important part of functional magnetic resonance imaging data analysis. They are a necessary processing step for sorting data in structurally or functionally homogenous regions. Real functional magnetic resonance imaging datasets usually do not cover the atlas template completely; they are often spatially constrained due to the physical limitations of MR sequence settings, the inter-individual variability in brain shape, etc. When using a parcellation template, many regions are not completely covered by actual data. This paper addresses the issue of the area coverage required in real data in order to reliably estimate the representative signal and the influence of this kind of data loss on network analysis metrics. We demonstrate this issue on four datasets using four different widely used parcellation templates. We used two erosion approaches to simulate data loss on the whole-brain level and the ROI-specific level. Our results show that changes in ROI coverage have a systematic influence on network measures. Based on the results of our analysis, we recommend controlling the ROI coverage and retaining at least 60% of the area in order to ensure at least 80% of explained variance of the original signal.
Related projects:

You are running an old browser version. We recommend updating your browser to its latest version.

More info