Both activated and less-activated regions identified by functional MRI reconfigure to support task executions

Abstract

Introduction: Functional magnetic resonance imaging (fMRI) has become very important for noninvasively characterizing BOLD signal fluctuations, which reflect the changes in neuronal firings in the brain. Unlike the activation detection strategy utilized with fMRI, which only emphasizes the synchronicity between the functional nodes (activated regions) and the task design, brain connectivity and network theory are able to decipher the interactive structure across the entire brain. However, little is known about whether and how the activated/less-activated interactions are associated with the functional changes that occur when the brain changes from the resting state to a task state. What are the key networks that play important roles in the brain state changes?

Methods: We used the fMRI data from the Human Connectome Project S500 release to examine the changes of network efficiency, interaction strength, and fractional modularity contributions of both the local and global networks, when the subjects change from the resting state to seven different task states.

Results: We found that, from the resting state to each of seven task states, both the activated and less-activated regions had significantly changed to be in line with, and comparably contributed to, a global network reconfiguration. We also found that three networks, the default mode network, frontoparietal network, and salience network, dominated the flexible reconfiguration of the brain.

Conclusions: This study shows quantitatively that contributions from both activated and less-activated regions enable the global functional network to respond when the brain switches from the resting state to a task state and suggests the necessity of considering large-scale networks (rather than only activated regions) when investigating brain functions in imaging cognitive neuroscience.

Keywords: activation; brain network; functional connectivity; functional magnetic resonance imaging; network reconfiguration.

Figure 1

The analysis strategy in this work. First, the activated and less‐activated regions were identified based on the global fMRI time course, and the global connectivity matrices were generated. Second, the networks were partitioned by the activity and nonactivity masks. Using the above, the modularity indices for the global and for the two classes of regions were determined. Finally, the interactions between the two regions and the individual changes in these two regions were also characterized

Figure 2

The efficiency indices for the whole brain in different mental states, including the resting state and the seven tasks, that is, gambling, motor, social cognition, emotion processing, language, relational processing, and working memory tasks. The red (long) and blue (short) horizontal lines in each box, respectively, denote the median and mean efficiency indexes across all of the 453 subjects. For a closer look at the distribution of the indices for the 453 subjects, the scatter plot of each subject's index is overlaid as the background of each plot

Figure 3

Global changes by alluvial diagram (Rosvall & Bergstrom, 2010) of the node assignments to the two different regions (Act and L‐Act) between the baseline (resting state) and the seven task states. The region partitions for each state are the average partitions obtained by maximizing the similarity across the 453 participants separately for each state (Bassett et al., 2013). Here, only large partitions are labeled by C _i (i = 1, 2, …), and different regions are separated by white gaps in the horizontal direction. The seven panels indicate the seven resting‐task pairs where the left one is for the resting and the right one is for the task. The last row indicates the similarity, measured by the z‐score of the random coefficient (RC) (Traud et al., 2011) between the partitions from the resting state and the task state

Figure 4

Comparisons of the strength of the interaction between the Act and L‐Act regions in the resting and task states. Within each column pair, the left shows the interaction between the two regions in the task state and the right shows the resting state

Figure 5

Correlations between the changes in the interactions between the two regions and the changes in the global efficiency. The individual correlation strength R and significance level p‐value appear in each panel

Figure 6

Comparisons of efficiency between the task states and resting state for Act (top panel)/L‐Act (bottom panel) regions. The 7 column pairs in each panel indicate each of the seven task states. The left one of each column pair shows the task state, and the right shows the resting state. The results for the Act regions do not show consistent increase trends from the resting state to the task state although there was a statistically significant difference between the resting and task states

Figure 7

Correlations between the changes in the efficiency indices between the two classes of regions and the changes in the global efficiency. The individual correlation strength R and significance level p‐value are presented in each panel. Panels a and b indicate the Act and L‐Act regions, respectively

Figure 8

Comparisons of the participant coefficients (the central one for the resting state) and the flexibilities (the surrounding ones for the seven resting‐tasks pairs) for the subnetworks. As the right‐bottom panel shows, each colored bar indicates the specific subnetworks. Except for the subcortical network, the DMN, FPN, and SN networks had the greatest flexibility (p < 1.0 × 10⁻²⁸ after FDR correction when comparing their mean flexibility with the mean flexibility of the other six networks across the 453 subjects)