Learning Interpretable Brain Functional Connectivity Via Self-Supervised Triplet Network With Depth-Wise Attention.

Abstract

Brain functional connectivity has been routinely explored to reveal the functional interaction dynamics between the brain regions. However, conventional functional connectivity measures rely on deterministic models fixed for all participants, usually demanding application-specific empirical analysis, while deep learning approaches focus on finding discriminative features for state classification, thus having limited capability to capture the interpretable functional connectivity characteristics. To address the challenges, this study proposes a self-supervised triplet network with depth-wise attention(TripletNet-DA) to generate the functional connectivity: 1) TripletNet-DA firstly utilizes channel-wise transformations for temporal data augmentation, where the correlated & uncorrelated sample pairs are constructed for self-supervised training, 2) Channel encoder is designed with a convolution network to extract the deep features, while similarity estimator is employed to generate the similarity pairs and the functional connectivity representations with prominent patterns emphasized via depth-wise attention mechanism, 3) TripletNet-DA applies Triplet loss with anchor-negative similarity penalty for model training, where the similarities of uncorrelated sample pairs are minimized to enhance model's learning capability. Experimental results on pathological EEG datasets(Autism Spectrum Disorder, Major Depressive Disorder) indicate that 1) TripletNet-DA demonstrates superiority in both ASD discrimination and MDD classification than the state-of-the-art counterparts in various frequency bands, where the connectivity features in beta & gamma bands have respectively achieved the accuracy of 97.05%,98.32% for ASD discrimination, 89.88%,91.80% for MDD classification in the eyes-closed condition, and 90.90%,92.26% for MDD classification in the eyes-open condition, 2) TripletNet-DA enables to uncover significant differences of functional connectivity between the ASD EEG and the TD ones, and the prominent connectivity links are in accordance with the empirical findings that frontal lobe demonstrates more connectivity links and significant frontal-temporal connectivity occurs in the beta band, thus providing potential biomarkers for clinical ASD analysis.