Communication between Brain Areas Based on Nested Oscillations

Abstract

Unraveling how brain regions communicate is crucial for understanding how the brain processes external and internal information. Neuronal oscillations within and across brain regions have been proposed to play a crucial role in this process. Two main hypotheses have been suggested for routing of information based on oscillations, namely communication through coherence and gating by inhibition. Here, we propose a framework unifying these two hypotheses that is based on recent empirical findings. We discuss a theory in which communication between two regions is established by phase synchronization of oscillations at lower frequencies (<25 Hz), which serve as temporal reference frame for information carried by high-frequency activity (>40 Hz). Our framework, consistent with numerous recent empirical findings, posits that cross-frequency interactions are essential for understanding how large-scale cognitive and perceptual networks operate.

Keywords: alpha; brain communication; cross-frequency coupling; gamma; slow oscillations; theta.

Figure 1.

The communication through coherence (CTC) and gating through inhibition (GBI) hypotheses. a, Two pools of neurons (A and B; e.g., in V1) are connected to a pool of neurons (C; e.g., V4). In this example, pool A communicates with C (solid line) while functional connectivity between B and C is suppressed (dashed line). b, CTC. The waveforms represent oscillatory population activity (as measured in the LFP) in the three regions, whereas the small vertical lines represent spiking activity. The phase of the oscillatory activity modulates the excitability and thus spike timing. It is the phase relationship between the regions that determines the routing. The neurons in A and C oscillate in phase, whereas the neurons in B do not oscillate in phase with C. It has been proposed that this mechanism is implemented by gamma band oscillations (>30 Hz; Fries 2005) c, GBI. The flow of information is controlled by an increase of alpha-band oscillations (∼10 Hz) which inhibits firing in pool B, and a decrease in alpha oscillations of neurons in A and C, allowing communication by release from inhibition (Jensen and Mazaheri 2010). It is the magnitude of the pulses of inhibition and thus the alpha power that controls the routing.

Figure 2.

The new framework. The synchronization in the alpha-band establishes the functional connection between A and C. This allows for representational specific neuronal firing reflected by the gamma band activity to flow to region C. The blocking of communication between B and C is achieved by high alpha power in B and an asynchrony between B and C. Therefore both modulations in alpha-band power, as in gating by inhibition, and phase synchronization between the regions, as in CTC, are determining the routing of information between regions. Note that phase synchronization is assumed in the alpha band and the information transfer is reflect by gamma-band activity.

Figure 3.

Exchange of phase coded information. a, Two stimuli processed by two pools of neurons A and B, e.g., in V1. The pools both project to a pool of neurons C downstream in the hierarchy, e.g., in V4. Because of this bottleneck in the visual system, it is important that neurons coding for A and B in V1 are not activated simultaneously. For the information related to the two stimuli to be transferred from V1 to V4, we propose two mechanisms. b, A single alpha generator in V1 controls for the timing of activation of neurons in pool A and B as reflected in the gamma band. The activation of the most excitable neurons, i.e., cells in pool A, overcomes the pulse of inhibition early in the alpha cycle followed by neurons in pool B (see Jensen et al. 2014 for details). The temporal organization is then transmitted to the pool of neurons in C. c, Another possibility is that the magnitude of the alpha oscillations is modulated locally and is lower for one of the representations compared with the other. Because the alpha inhibition is lower for A, the respective neurons fire earlier than B. This temporal organization is then transmitted to C.

Figure 4.

Converging feed-forward and diverging feedback pathways. a, Pools of neurons A and B converge on a pool of neurons in C. Black arrows represent the converging feedforward pathway and the gray arrows represent the diverging feedback pathway. b, Example in which two cortical columns in V1 (A and B) are connected to a column in V4 (C). Three layers are represented, the supragranular, the granular, and the infragranular. Dark and light grays represented in the layers are involved in the feedforward and feedback pathways, respectively. The layers associated with each pathway are inspired by Markov et al. (2014). The feedforward connections from the pulvinar are also indicated (purple arrows). c, gamma and alpha oscillations have been shown to be prominent in the granular/supragranular and infragranular/supragranular layers, respectively.