Dissecting Transient Burst Events

Abstract

Increasing efforts are being made to understand the role of intermittent, transient, high-power burst events of neural activity. These events have a temporal, spectral, and spatial domain. Here, we argue that considering all three domains is crucial to fully reveal the functional relevance of these events in health and disease.

Keywords: burst events; multidimensional; oscillations.

Figure 1

Main Temporal, Spectral, and Spatial Event Characteristics. Events can be characterised in the temporal, spectral, and spatial domains. For each domain, the main event characteristics are presented. Each event characteristic is illustrated using two exemplary data (red and blue) relative to a reference data (black) and their derived static spectral power estimates. (A) Temporal domain: event amplitude (traditionally seen as a temporal event characteristic), event duration, and event interval time. (B) Spectral domain: frequency spread and frequency boundaries of the event. (C) Spatial domain: spatial width and spatial location of the event. As evident, the mechanism underlying differences in spectral power can be manifold within and across domains. As an example, an increase in spectral power can be caused by larger event amplitude, longer event duration, shorter event interval time, narrower event frequency spread, and larger event spatial width. Furthermore, the characteristics depicted in (A–C) can also interact, or can be conditionally dependent within and/or across domains (for details on domain interactions, see Figure 2 in the main text).

Figure 2

Problems of Domain Reduction and Opportunities of the Multidomain Approach. For a Figure360 author presentation of Figure 2C, see the figure legend at https://doi.org/10.1016/j.tics.2020.07.004 Exemplary data were acquired using head casts [12] beamformed onto individual cortical surface mesh. Time–frequency analysis (dpss-based multitaper, 1 Hz resolution) was applied before binarisation (using a two-state amplitude-envelope; HMM [8]) and n-dimensional clustering. (A) Temporal × spectral properties of sensorimotor β activity of a single trial. (i) Power time-course and events for average β (13–30 Hz). (ii) As in (i), but for the β peak frequency (15 Hz). (iii) Power and events are shown as a function of time and frequency. Green horizontal line indicates the peak β frequency. (iv) Different domain reduction methods yield different temporal event characteristics. (B) As (A), but for temporal × spatial properties. (C) Temporal × spectral × spatial properties of β activity of a single event. Coloured voxels are part of the event. (i) Interaction between duration and spatial location. Voxels are colour coded by their duration (sampling rate = 20 Hz). (ii) Interaction between the latency of the peak in power and spatial location, showing propagating patterns of beta power. Voxels are colour coded by their peak latency. (iii) Interaction between upper frequency boundary and spatial location. Voxels are colour coded by their upper frequency boundary. (iv) Interaction between frequency spread and spatial location. Voxels are colour coded by their frequency spread. Abbreviation: PC, principal component.