Comparison of continuously acquired resting state and extracted analogues from active tasks

Abstract

Functional connectivity analysis of brain networks has become an important tool for investigation of human brain function. Although functional connectivity computations are usually based on resting-state data, the application to task-specific fMRI has received growing attention. Three major methods for extraction of resting-state data from task-related signal have been proposed (1) usage of unmanipulated task data for functional connectivity; (2) regression against task effects, subsequently using the residuals; and (3) concatenation of baseline blocks located in-between task blocks. Despite widespread application in current research, consensus on which method best resembles resting-state seems to be missing. We, therefore, evaluated these techniques in a sample of 26 healthy controls measured at 7 Tesla. In addition to continuous resting-state, two different task paradigms were assessed (emotion discrimination and right finger-tapping) and five well-described networks were analyzed (default mode, thalamus, cuneus, sensorimotor, and auditory). Investigating the similarity to continuous resting-state (Dice, Intraclass correlation coefficient (ICC), R(2) ) showed that regression against task effects yields functional connectivity networks most alike to resting-state. However, all methods exhibited significant differences when compared to continuous resting-state and similarity metrics were lower than test-retest of two resting-state scans. Omitting global signal regression did not change these findings. Visually, the networks are highly similar, but through further investigation marked differences can be found. Therefore, our data does not support referring to resting-state when extracting signals from task designs, although functional connectivity computed from task-specific data may indeed yield interesting information.

Keywords: brain network; resting-state fMRI; task regression; task-derived resting state.

Figure 1

The networks used for analysis, represented via one‐sample t‐tests as conducted with SPM. The maps are based on the individual z‐score maps of the first resting‐state measurement of the test‐retest measurements (n=20). Maps represent t‐values, thresholded between 4 and 35. Although the auditory and sensorimotor networks look similar, one seed was placed in the motor cortex (“auditory”), and the second in the temporal gyrus (“sensorimotor”) as published previously [Smith et al., 2009]. [Color figure can be viewed in the online issue, which is available at http://wileyonlinelibrary.com.]

Figure 2

Comparison between continuous and extracted resting‐state connectivity for the default mode network. Maps represent one‐sample t‐tests across the entire group for each method. In the scatter plots, resting state (x‐axis) and the according method of extraction (y‐axis) are compared for all brain voxels across all individual z‐score maps. Hence, the top left scatterplot represent test‐retest evaluation of two resting‐state scans. Scaling is uniform for all images (t‐values from 6.09–50, P<0.05 FWE‐corrected), and scatter‐plots (−6 to +6). For the finger‐tapping the BLOCK method is not shown, as the resulting signal comprised less then 30 s, and therefore considered too short. Visually, the networks are highly similar, but through further investigation marked differences can be found. [Color figure can be viewed in the online issue, which is available at http://wileyonlinelibrary.com.]