ASD Classification on Dynamic Brain Connectome using Temporal Random Walk with Transformer-based Dynamic Network Embedding

TL;DR

The paper addresses ASD classification from dynamic brain connectomes by introducing BrainTWT, a Transformer-based dynamic network embedding that jointly captures temporal evolution within snapshots and inter-snapshot dynamics through temporal random walks. By formulating a temporal and graph-level joint loss, BrainTWT learns discriminative embeddings that improve ASD classification on the ABIDE dataset, outperforming static and snapshot-based baselines. The approach demonstrates the importance of modeling temporal structure in functional connectivity and offers a scalable framework for leveraging dynamic brain networks in clinical prediction and potential multimodal extensions. Overall, BrainTWT advances dynamic graph representation learning in neuroimaging, with practical implications for early and accurate ASD diagnosis.

Abstract

Autism Spectrum Disorder (ASD) is a complex neurological condition characterized by varied developmental impairments, especially in communication and social interaction. Accurate and early diagnosis of ASD is crucial for effective intervention, which is enhanced by richer representations of brain activity. The brain functional connectome, which refers to the statistical relationships between different brain regions measured through neuroimaging, provides crucial insights into brain function. Traditional static methods often fail to capture the dynamic nature of brain activity, in contrast, dynamic brain connectome analysis provides a more comprehensive view by capturing the temporal variations in the brain. We propose BrainTWT, a novel dynamic network embedding approach that captures temporal evolution of the brain connectivity over time and considers also the dynamics between different temporal network snapshots. BrainTWT employs temporal random walks to capture dynamics across different temporal network snapshots and leverages the Transformer's ability to model long term dependencies in sequential data to learn the discriminative embeddings from these temporal sequences using temporal structure prediction tasks. The experimental evaluation, utilizing the Autism Brain Imaging Data Exchange (ABIDE) dataset, demonstrates that BrainTWT outperforms baseline methods in ASD classification.

Figures (1)

• Figure 1: The dynamic brain network is obtained from Pearson’s correlation between the BOLD time-series of each pair of regions of interest (ROIs) in the brain. The dynamic brain network is then converted into a series of temporal random walk sequences, capturing the temporal evolution of brain connectivity. Each temporal sequence is then tokenized and embedded. The embedded sequences are processed through a Transformer model that uses self-attention mechanisms on node interactions based on their temporal and contextual significance. Parts of the sequence are masked, and the model predicts these masked nodes, refining the embeddings using contextual data. The model incorporates joint learning to optimize both the temporal dynamics and graph-level loss. The final embeddings are used as input features for ASD classification task.