Classification of Brain Functional Connectivity using Convolutional Neural Networks

Abstract

Abnormalities and alterations in brain connectivity networks as measured using neuroimaging data has been increasingly used as biomarkers for various neuropsychiatric disorders. Schizophrenia (SCZ) is a complex neuropsychiatric disorder associated with dysconnectivity in brain networks. In this paper, we develop a framework for automatic classification of healthy control and SCZ patient based on electroencephalogram (EEG) connectivity and compare the classification performance with conventional artificial neural network (ANN). We propose to use convolutional neural network (CNN) for the classification of brain functional connectivity between healthy control and SCZ groups. Vector autoregression (VAR) model is used to extract connectivity features from schizophrenia EEG signals and directed connectivity at different EEG frequency bands is computed via partial directed coherence (PDC). Results show that the classification with high accuracy is achievable using VAR model. From the result, the performance of CNN reaches 86.9% over five-fold cross validation that considered to be good accuracy for the CNN to do a good prediction. The results also show that time-domain VAR features performed better than frequency domain PDC features. CNN provides a more practical method in classification between healthy and schizophrenic brain connectivity.

Effective brain connectivity related to non-painful thermal stimuli using EEG

“…Our findings highlight the activation of the frontal and temporal regions in response to non-painful thermal stimuli in the theta and alpha frequency bands, and the interconnection between these regions in cognitive and sensory processes. The networks emerging from these regions are crucial in emotional assessments, sensory perceptions, and cognitive processes related to non-painful thermal stimuli [46][47][48][49][50][51][52][53]. The opposite direction of information flow between warmth and cold, especially in the frontal and temporal regions, is consistent with the existence of specialized neural pathways for each type of stimulus.…”

“…Brain connectivity analysis is a prominent approach that is being used to gain a deeper understanding of the involvement of different regions of the brain in various applications, such as neuropsychiatric disorders [46][47][48], sensory processing [49,50], and cognitive task evaluations [51,52]. Effective connectivity, which is the focus of our study, involves the analysis of direct and indirect causal influences among brain regions, providing insights into the directional effects and potential mechanisms underlying these interactions.…”

A Patient-Centered Text-Derived Neural Network Paradigm for Diagnosis of Schizophrenia

“…One study, Shahriman et al [23] proposed a CNN model for the classification of brain functional connectivity in healthy subjects and schizophrenic subjects. The proposed model uses Vector auto-regression (VAR) to extract connectivity features from EEG signals.…”