An official website of the United States government
This paper describes a group-level classification of 14 patients with prefrontal cortex (pFC) lesions from 20 healthy controls using multi-layer graph convolutional networks (GCN) with features inferred from the scalp EEG recorded from the encoding phase of working memory (WM) trials. We first construct undirected and directed graphs to represent the WM encoding for each trial for each subject using distance correlation- based functional connectivity measures and differential directed information-based effective connectivity measures, respectively. Centrality measures of betweenness centrality, eigenvector centrality, and closeness centrality are inferred for each of the 64 channels from the brain connectivity. Along with the three centrality measures, each graph uses the relative band powers in the five frequency bands - delta, theta, alpha, beta, and gamma- as node features. The summarized graph representation is learned using two layers of GCN followed by mean pooling, and fully connected layers are used for classification. The final class label for a subject is decided using majority voting based on the results from all the subject's trials. The GCN-based model can correctly classify 28 of the 34 subjects (82.35% accuracy) with undirected edges represented by functional connectivity measure of distance correlation and classify all 34 subjects (100% accuracy) with directed edges characterized by effective connectivity measure of differential directed information.
more »
« less
This content will become publicly available on January 8, 2026
Graph Convolution Network Based Classification of Subjects with Prefrontal Cortex Lesion via Information-theoretic Brain Network Features
This paper investigates scalp electroencephalogram (EEG) data from 14 subjects with unilateral prefrontal cortex (pFC) lesions and 20 healthy controls during lateral visuospatial working memory (WM) tasks. The goal is to differentiate the brain networks involved in WM processing between these groups. The EEG recordings are transformed into graph signals, with proximity-weighted brain connectivity measures as edges and centrality measures as nodal features. Graph convolutional network (GCN) layers are used for feature representation, followed by a fully connected layer for classification. The GCN-based model effectively handles nine classification tasks, proving that graph-based network representation is versatile for describing brain interactions. The sparse MI-GCI-based graph model’s accuracy effectively captures the functional segregation of distinct WM tasks. The classifier using mutual information-guided Granger causality index (MI-GCI) with 20% of top edges matched prior classification performance with 67% fewer parameters and 80% less graph density, identifying the correct class of all 34 subjects in group identification using leave-one-out cross-validation and two-thirds majority voting.
more »
« less
- Award ID(s):
- 1954749
- PAR ID:
- 10565401
- Publisher / Repository:
- Springer
- Date Published:
- Journal Name:
- Journal of Signal Processing Systems
- ISSN:
- 1939-8018
- Subject(s) / Keyword(s):
- Brain network effective connectivity graph convolution (GCN) networks mutual information prefrontal cortex (pFC) lesions
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
null (Ed.)In this paper, we propose a supervised graph representation learning method to model the relationship between brain functional connectivity (FC) and structural connectivity (SC) through a graph encoder-decoder system. The graph convolutional network (GCN) model is leveraged in the encoder to learn lower-dimensional node representations (i.e. node embeddings) integrating information from both node attributes and network topology. In doing so, the encoder manages to capture both direct and indirect interactions between brain regions in the node embeddings which later help reconstruct empirical FC networks. From node embeddings, graph representations are learnt to embed the entire graphs into a vector space. Our end-to-end model utilizes a multi-objective loss function to simultaneously learn node representations for FC network reconstruction and graph representations for subject classification. The experiment on a large population of non-drinkers and heavy drinkers shows that our model can provide a characterization of the population pattern in the SC-FC relationship, while also learning features that capture individual uniqueness for subject classification. The identified key brain subnetworks show significant between-group difference and support the promising prospect of GCN-based graph representation learning on brain networks to model human brain activity and function.more » « less
-
Brain Connectivity (BC) features of multichannel EEG have been proposed for Motor Imagery (MI) decoding in Brain-Computer Interface applications, but the advantages of BC features vs. single-channel features are unclear. Here, we consider three BC features, i.e., Phase Locking Value (PLV), Granger Causality, and weighted Phase Lag Index, and investigate the relationship between the most central nodes in BC-based networks and the most influential EEG channels in single-channel classification based on common spatial pattern filtering. Then, we compare the accuracy of MI decoders that use BC features in source vs. sensor space. Applied to the BCI Competition VI Dataset 2a (left- vs. right-hand MI decoding), our study found that PLV in sensor space achieves the highest classification accuracy among BC features and has similar performance compared to single-channel features, while the transition from sensor to source space reduces the average accuracy of BC features. Across all BC measures, the network topology is similar in left- vs. right-hand MI tasks, and the most central nodes in BC-based networks rarely overlap with the most influential channels in single-channel classification.more » « less
-
null (Ed.)A recent paper [1] claims to classify brain processing evoked in subjects watching ImageNet stimuli as measured with EEG and to employ a representation derived from this processing to construct a novel object classifier. That paper, together with a series of subsequent papers [2] , [3] , [4] , [5] , [6] , [7] , [8] , claims to achieve successful results on a wide variety of computer-vision tasks, including object classification, transfer learning, and generation of images depicting human perception and thought using brain-derived representations measured through EEG. Our novel experiments and analyses demonstrate that their results crucially depend on the block design that they employ, where all stimuli of a given class are presented together, and fail with a rapid-event design, where stimuli of different classes are randomly intermixed. The block design leads to classification of arbitrary brain states based on block-level temporal correlations that are known to exist in all EEG data, rather than stimulus-related activity. Because every trial in their test sets comes from the same block as many trials in the corresponding training sets, their block design thus leads to classifying arbitrary temporal artifacts of the data instead of stimulus-related activity. This invalidates all subsequent analyses performed on this data in multiple published papers and calls into question all of the reported results. We further show that a novel object classifier constructed with a random codebook performs as well as or better than a novel object classifier constructed with the representation extracted from EEG data, suggesting that the performance of their classifier constructed with a representation extracted from EEG data does not benefit from the brain-derived representation. Together, our results illustrate the far-reaching implications of the temporal autocorrelations that exist in all neuroimaging data for classification experiments. Further, our results calibrate the underlying difficulty of the tasks involved and caution against overly optimistic, but incorrect, claims to the contrary.more » « less
-
Seizure onset zone (SOZ) identification using effective brain connectivity of epileptogenic networksAbstract Objective. To demonstrate the capability of utilizing graph feature-based supervised machine learning (ML) algorithm on intracranial electroencephalogram recordings for the identification of seizure onset zones (SOZs) in individuals with drug-resistant epilepsy.Approach. Utilizing three model-free measures of effective connectivity (EC)-directed information, mutual information-guided Granger causality index (MI-GCI), and frequency-domain convergent cross-mapping (FD-CCM) - directed graphs are generated. Graph centrality measures at different sparsity are used as the classifier’s features.Main results. The centrality features achieve high accuracies exceeding 90% in distinguishing SOZ electrodes from non-SOZ electrodes. Notably, a sparse graph representation with just ten features and simple ML models effectively achieves such performance. The study identifies FD-CCM centrality measures as particularly significant, with a mean AUC of 0.93, outperforming prior literature. The FD-CCM-based graph modeling also highlights elevated centrality measures among SOZ electrodes, emphasizing heightened activity relative to non-SOZ electrodes during ictogenesis.Significance. This research not only underscores the efficacy of automated SOZ identification but also illuminates the potential of specific EC measures in enhancing discriminative power within the context of epilepsy research.more » « less
