Combined EEG-fMRI and tractography to visualise propagation of epileptic activity

Abstract

In a patient with refractory temporal lobe epilepsy, EEG-fMRI showed activation in association with left anterior temporal interictal discharges, in the left temporal, parietal and occipital lobes. Dynamic causal modelling suggested propagation of neural activity from the temporal focus to the area of occipital activation. Tractography showed connections from the site of temporal lobe activation to the site of occipital activation. This demonstrates the principle of combining EEG-fMRI and tractography to delineate the pathways of propagation of epileptic activity.

Figure 1. Left panel shows EEG recorded during fMRI scanning (10–20 system, upper 10 channels referential, lower 8 bipolar (OSC channel marks scanner gradient switching)) demonstrating left temporal activity in the delta/theta band with frequent intermixed spikes phase reversing at T3 (bold arrow). (A) Significant anterior temporal IED-related fMRI activations SPM{T} overlaid onto structural echo planar image (b = 0), showing left temporal and bilateral occipital fMRI activations. There were no significant deactivations. Scale represents z-score. (B) Tractography findings overlaid onto structural echo planar image, showing white matter connectivity to occipital and frontal areas. Cross hairs at left temporal fMRI maximum and the tractography seed region. The colour bar represents a measure of connection probability or connection confidence to the start point.

Figure 2. Two dynamic causal models were constructed, each comprising two structurally connected regions (6 mm diameter spheres), both showing interictal epileptiform discharge (IED)-correlated activation in the conventional SPM fMRI analysis: left parahippocampal gyrus (pHip) and left lingual gyrus (lingG). In both models, pHip and lingG were reciprocally connected. In model A (in bold print), IED acted on pHip and its connection to lingG (IED propagation from temporal to occipital lobe); in model B (grey print), IED acted on lingG and its connection to pHip (IED propagation from occipital to temporal lobe). DCM model comparison revealed strong evidence for model A over model B. In dynamic systems, coupling strength is expressed as a rate—typically, 0.5–1 Hz for regional activity. In both models, intrinsic connectivity was stronger from lingG to pHip (1.19 Hz in A, 0.7 in B) than vice versa (0.66 Hz in A and improbable in B). The induced response of IED on pHip was 0.3 Hz in model A and 0.15 Hz on lingG in model B. Combining both models in one to facilitate direct comparison (data not shown), the probability was 99.8% for IED, inducing a direct response in pHip, but only 61.8% in lingG.