Lateralization of epilepsy using intra-hemispheric brain networks based on resting-state MEG data

Abstract

Focal epilepsy originates within networks in one hemisphere. However, previous studies have investigated network topologies for the entire brain. In this study, magnetoencephalography (MEG) was used to investigate functional intra-hemispheric networks of healthy controls (HCs) and patients with left- or right-hemispheric temporal lobe or temporal plus extra-temporal lobe epilepsy. 22 HCs, 25 left patients (LPs), and 16 right patients (RPs) were enrolled. The debiased weighted phase lag index was used to calculate functional connectivity between 246 brain regions in six frequency bands. Global efficiency, characteristic path length, and transitivity were computed for left and right intra-hemispheric networks. The right global graph measures (GGMs) in the theta band were significantly different (p < .005) between RPs and both LPs and HCs. Right and left GGMs in higher frequency bands were significantly different (p < .05) between HCs and the patients. Right GGMs were used as input features of a Naïve-Bayes classifier to classify LPs and RPs (78.0% accuracy) and all three groups (75.5% accuracy). The complete theta band brain networks were compared between LPs and RPs with network-based statistics (NBS) and with the clustering coefficient (CC), nodal efficiency (NE), betweenness centrality (BC), and eigenvector centrality (EVC). NBS identified a subnetwork primarily composed of right intra-hemispheric connections. Significantly different (p < .05) nodes were primarily in the right hemisphere for the CC and NE and primarily in the left hemisphere for the BC and EVC. These results indicate that intra-hemispheric MEG networks may be incorporated in the diagnosis and lateralization of focal epilepsy.

Keywords: focal epilepsy; functional connectivity; graph measures; intra-hemispheric brain networks; machine learning; magnetoencephalography; network-based statistics.

Figure 1

Overview of the analysis pipeline. Abbreviations: ROI, region of interest; VE, virtual electrode; dwPLI, debiased weighted phase lag index; HCs, healthy controls; LPs, patients with left‐hemispheric focal epilepsy; RPs, patients with right‐hemispheric focal epilepsy; NBS, network‐based statistics

Figure 2

Group comparison of the global efficiency (GE), characteristic path length (CPL), and transitivity (T) of the second quadrant (i.e., right intra‐hemispheric network) of the adjacency matrix in six frequency bands. Bar lengths indicate mean values; error bars indicate standard errors of the mean. p‐values were false discovery rate (FDR) adjusted for six frequency bands, three global graph measures, and two quadrants. (Bottom insert) Adjacency matrix of a representative right patient in the theta band, and a corresponding anatomical depiction showing connections with values above 0.1

Figure 3

Group comparison of the global efficiency (GE), characteristic path length (CPL), and transitivity (T) of the fourth quadrant (i.e., left intra‐hemispheric network) of the adjacency matrix in six frequency bands. Bar lengths indicate mean values; error bars indicate standard errors of the mean. p‐values were false discovery rate (FDR) adjusted for six frequency bands, three global graph measures, and two quadrants. (Bottom insert) Adjacency matrix of a representative left patient in the theta band, and a corresponding anatomical depiction showing connections with values above 0.1

Figure 4

Subnetwork identified using network‐based statistics (NBS) with a 3.45 primary threshold, 5,000 random permutations, and a p < .05 significance level (family‐wise error rate [FWER]‐corrected) on the connection strengths of the complete, un‐thresholded adjacency matrices of patients with right‐hemispheric focal epilepsy (RPs) and patients with left‐hemispheric focal epilepsy (LPs) in the theta band. The network was primarily composed of intra‐hemispheric connections within the right hemisphere (27 were right intra‐hemispheric and 8 interhemispheric) and had 28 nodes located in the right hemisphere (3 were frontal, 11 temporal, 4 parietal, 3 insular, 1 limbic, 3 occipital, 1 basal ganglia, and 2 thalamus) and 5 nodes located in the left hemisphere (2 were frontal and 3 occipital). The most significant connections were intra‐hemispheric connections in the right hemisphere between two nodes in the inferior temporal gyrus (ITG) (t = 4.47), a node in the ITG and a node in the inferior parietal lobule (IPL) (t = 4.20), a node in the fusiform gyrus (FG) and a node in the IPL (t = 4.18), a node in the superior temporal gyrus (STG) and a node in the basal ganglia (BG) (t = 4.09), and a node in the ITG and a node in the IPL (t = 4.00)

Figure 5

Significant nodes (p < .05) identified via comparison of the betweenness centrality (BC), eigenvector centrality (EVC), clustering coefficient (CC), and nodal efficiency (NE) of the complete adjacency matrices in the theta band of patients with right‐hemispheric focal epilepsy (RPs) and patients with left‐hemispheric focal epilepsy (LPs). p‐values were false discovery rate adjusted for one frequency band (i.e., the theta band), four local graph measures, and 246 nodes. The color of the nodes are scaled according to their z‐values, with a darker color indicating a greater value. For BC, there were 8 nodes located in the left hemisphere (1 was frontal, 6 temporal, and 1 parietal). For EVC, there was 1 node located in the right temporal lobe and 13 nodes located in the left hemisphere (2 were frontal, 5 temporal, 3 parietal, 2 insular, and 1 hippocampus). For CC, there were 21 nodes located in the right hemisphere (4 were frontal, 4 temporal, 2 parietal, 2 insular, 2 limbic, 1 occipital, 1 hippocampus, 4 basal ganglia, and 1 thalamus) and 2 nodes located in the left hemisphere (1 was frontal and 1 was in the thalamus). For NE, there were 44 nodes located in the right hemisphere (7 were frontal, 14 temporal, 4 parietal, 2 insular, 2 limbic, 1 occipital, 2 amygdala, 2 hippocampus, 5 basal ganglia, and 5 thalamus) and 1 node located in the left parietal lobe