EEGLAB, SIFT, NFT, BCILAB, and ERICA: new tools for advanced EEG processing

Abstract

We describe a set of complementary EEG data collection and processing tools recently developed at the Swartz Center for Computational Neuroscience (SCCN) that connect to and extend the EEGLAB software environment, a freely available and readily extensible processing environment running under Matlab. The new tools include (1) a new and flexible EEGLAB STUDY design facility for framing and performing statistical analyses on data from multiple subjects; (2) a neuroelectromagnetic forward head modeling toolbox (NFT) for building realistic electrical head models from available data; (3) a source information flow toolbox (SIFT) for modeling ongoing or event-related effective connectivity between cortical areas; (4) a BCILAB toolbox for building online brain-computer interface (BCI) models from available data, and (5) an experimental real-time interactive control and analysis (ERICA) environment for real-time production and coordination of interactive, multimodal experiments.

Figure 1

Complete electrophysiological experiment control, data collection, analysis, archiving, and meta-analysis suite: the EEGLAB environment for data analysis; the ERICA framework for data recording, online analysis, and stimulus control; the BCILAB toolbox for online and offline classification and BCI; the SIFT toolbox for information flow modeling; HeadIT, an archival data and tools resource under development for laboratory or archival data storage, retrieval and meta-analysis; dashed lines indicates planned interfaces under construction.

Figure 2

EEGLAB STUDY design interface using the tutorial STUDY data available via the EEGLAB wiki (http://sccn.ucsd.edu/wiki/eeglab). The three push buttons at the top may be used to add a new design (“Add design”), rename a design (“Rename design”), or delete a design (“Delete design”). The “Independent variable 1” list helps define independent variables. The list of independent variables is automatically generated based on the STUDY definition information and individual data set event types. For a given independent variable, it is also possible to select a subset of its values or to combine some of its values. For instance, in this example the user has selected “ignore” and “memorize” stimuli as values for the independent variable “condition”. The “Subject” list contains the subjects to include in a specific design. Unselecting a given subject from the list excludes him/her from further data analysis within the design. Once a design is selected, measures including ERPs, mean spectra or event-related spectral perturbations (ERSP) may be plotted. Here, we have plotted the event-related spectral perturbations of an independent component (IC) cluster in the selected STUDY.design. In the top right panel, the scalp maps of one IC cluster are shown—the large map representing the average scalp map. In the bottom right panel, mean cluster ERSPs are shown for Ignore versus Memorize letter trials, and their significant differences are assessed using permutation-based statistics and a false discovery rate method to correct for multiple comparisons.

Figure 3

Two examples of (a) a set of subject head BEM meshes (modeling scalp, skull, cerebrospinal fluid (CSF), and cortex tissue boundaries) and (b) a FEM head volume for the same subject with 3-D voxels for scalp, skull, and brain tissues shown in different colors.

Figure 4

EEG-based brain connectivity analysis and visualization using SIFT. (a) An interactive time-frequency grid demonstrating transient bursts of theta (3–7 Hz) and delta (1–3 Hz) band information flow during error commission, estimated using the direct directed transfer function (dDTF), between a subset of independent component (IC) sources. Dashed vertical line denotes time of erroneous button press. Callout shows an expanded view of information flow to/from sources 8 and 13, obtained by clicking on the respective grid cell. (b) Several frames from an interactive BrainMovie3D animation showing an event-related causal relationship in the theta band between these sources (200 ms (top) and −520, 40, and 600 ms (bottom) relative to an erroneous button press). Ball (node) color and size denotes asymmetry ratio (red: causal source, blue: causal sink) and outflow strength, respectively, for that IC. Cylinder (edge) color and size denote connectivity strength. The event-related potential of IC8 (red, medial), back-projected to a superior electrode is superimposed below each frame (blue bar denotes frame index). This shows a network interpretation of the classic “error-related negativity” (ERN) phenomenon observed during error-processing. (c) A frame from a causal projection movie showing mean net causal inflow (green) and causal outflow (red) in the theta band at each brain location during error commission across 24 subjects. Note the significant causal outflow from or near anterior cingulate cortex, thought to be critically involved in error-processing, during and following the negative peak of the ERN.

Figure 5

An ERICA data flow involving two separate computers each running an instance of the DataRiver application. Dashed lines indicate control signals. Here, computer visualization is performed using the Matlab DataRiver client MatRiver.