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

2025-03-16

AI Summary

Static functional brain connectomes fail to capture the temporal dynamics of neural activity, limiting early and precise diagnosis of Autism Spectrum Disorder (ASD). Method: This paper proposes a novel dynamic functional connectome representation framework that integrates temporal random walks with a Transformer architecture to explicitly model the evolution of brain network topology across time. It further introduces a temporal structural prediction–based dynamic embedding learning paradigm to efficiently encode fMRI-derived dynamic connectivity patterns. Contribution/Results: Evaluated on the ABIDE dataset, the method achieves significantly higher classification accuracy for ASD versus neurotypical controls than state-of-the-art static and dynamic approaches. Results demonstrate that explicitly modeling spatiotemporal topological evolution in functional connectomes is critical for identifying neurodevelopmental disorders, offering both methodological innovation and clinical relevance for ASD biomarker discovery.

Technology Category

• Cognitive Modeling & Cognitive Systems: Neural Spike Coding
• Search and Optimization: Metareasoning and Metaheuristics
• Humans and AI: Brain-Sensing and Analysis

Application Category

• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Web Mining and Content Analysis: Models for Web evolution
• Search and Retrieval-Augmented AI: Web query analysis, representation and understanding

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.

Problem

• Develops BrainTWT for dynamic brain connectome analysis.
• Enhances ASD classification using temporal network embeddings.
• Leverages Transformer to model temporal brain activity dynamics.

Innovation

• Temporal random walks for dynamic network analysis
• Transformer-based embedding for long-term dependencies
• Dynamic brain connectome for ASD classification