Resting State fMRI in Mice Reveals Anesthesia Specific Signatures of Brain Functional Networks and Their Interactions

Abstract

fMRI studies in mice typically require the use of anesthetics. Yet, it is known that anesthesia alters responses to stimuli or functional networks at rest. In this work, we have used Dual Regression analysis Network Modeling to investigate the effects of two commonly used anesthetics, isoflurane and medetomidine, on rs-fMRI derived functional networks, and in particular to what extent anesthesia affected the interaction within and between these networks. Experimental data have been used from a previous study (Grandjean et al., 2014). We applied multivariate ICA analysis and Dual Regression to infer the differences in functional connectivity between isoflurane- and medetomidine-anesthetized mice. Further network analysis was performed to investigate within- and between-network connectivity differences between these anesthetic regimens. The results revealed five major networks in the mouse brain: lateral cortical, associative cortical, default mode, subcortical, and thalamic network. The anesthesia regime had a profound effect both on within- and between-network interactions. Under isoflurane anesthesia predominantly intra- and inter-cortical interactions have been observed, with only minor interactions involving subcortical structures and in particular attenuated cortico-thalamic connectivity. In contrast, medetomidine-anesthetized mice displayed subcortical functional connectivity including interactions between cortical and thalamic ICA components. Combining the two anesthetics at low dose resulted in network interaction that constituted the superposition of the interaction observed for each anesthetic alone. The study demonstrated that network modeling is a promising tool for analyzing the brain functional architecture in mice and comparing alterations therein caused by different physiological or pathological states. Understanding the differential effects of anesthetics on brain networks and their interaction is essential when interpreting fMRI data recorded under specific physiological and pathological conditions.

Keywords: anesthesia; brain network analysis; dual regression; fMRI; isoflurane; medetomidine; network interactions; rodent fMRI.

Figure 1

ICA derived components were grouped into the lateral cortical (LCN), associative cortical network (ACN), default mode network (DMN), subcortical network (SuCN), and the thalamic network (ThN).

Figure 2

Results of Dual Regression analysis for eight components derived from ICA (red color overlay). The reference of the components to anatomical structures is indicated in the figure. Bonferroni corrected DR results showing the regions whose co-activation with the ICA components (as shown in the figure) was significantly higher (green color) or lower (blue color) in isoflurane as compared to medetomidine-anesthetized mice.

Figure 3

Cortico-thalamic connectivity differences in isoflurane vs. medetomidine anesthetized mice. Connectivity strength is shown for the network between (A) somatosensory cortex (S1) and ventral thalamus (vTh) and (B) between secondary somatosensory cortex (S2) and ventral thalamus (vTh). Under isoflurane anesthesia these connectivities are largely suppressed, while a significant negative correlation has been found for medetomidine-anesthetized mice.

Figure 4

Functional networks and their interaction as derived from DR analysis: (A) Matrices displaying within- and between-network interactions under the various anesthesia regimens. Matrices have been structured according to the five functional networks identified. Colors indicate significant interactions observed under isoflurane (blue) or medetomidine anesthesia (red). For the group receiving the combination anesthesia, elements are indicated in different colors depending on whether they apparently arise from the isoflurane group (blue), from the medetomidine group (red), from both groups (blue/red) or were observed in the combination group exclusively (green). Positive correlations are indicated by dark colors, while light colors represent negative correlations. Gray blocks indicate the absence of any significant interaction. Significant group differences (with Bonferroni correction) in connectivity have been observed for all the interactions displayed. (B) Within- and between-network interactions detected in isoflurane (blue lines), medetomidine (red lines) and medetomidine/ isoflurane anesthetized mice. In isoflurane/medetomidine anesthetized mice network interactions, blue lines represent interactions observed in mice under isoflurane anesthesia only, red under medetomidine only, and violet represents interactions observed for both anesthesia regimes. The width of the lines in the figure indicates the strength of the connectivity.