BrainATCL: Adaptive Temporal Brain Connectivity Learning for Functional Link Prediction and Age Estimation

2025-08-09

AI Summary

Addressing the challenges of modeling long-range temporal dependencies in dynamic fMRI data and the limited generalizability of functional connectivity prediction and age estimation, this paper proposes BrainATCL: an unsupervised, non-parametric adaptive temporal brain connectivity learning framework. Methodologically, BrainATCL introduces a dynamic backtracking window mechanism and incorporates structural–functional priors (e.g., hemisphere identity, subsystem membership) to define edge attributes, thereby enhancing the biological interpretability of spatiotemporal representations. It employs a GINE-Mamba2 hybrid backbone to jointly encode graph-structured time series for efficient spatiotemporal modeling. Evaluated on the large-scale Human Connectome Project (HCP) resting-state fMRI dataset, BrainATCL achieves state-of-the-art performance on both functional connectivity link prediction and chronological age estimation. Notably, it demonstrates superior cross-session generalization—outperforming existing methods in out-of-distribution temporal settings—while preserving neurobiologically plausible connectivity dynamics.

Technology Category

• Cognitive Modeling & Cognitive Systems: Neural Spike Coding
• Machine Learning: Graph-based Machine Learning
• 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: Large pretrained models with web data
• User Modeling, Personalization and Recommendation: Federated recommendation systems and personalization

Abstract

Functional Magnetic Resonance Imaging (fMRI) is an imaging technique widely used to study human brain activity. fMRI signals in areas across the brain transiently synchronise and desynchronise their activity in a highly structured manner, even when an individual is at rest. These functional connectivity dynamics may be related to behaviour and neuropsychiatric disease. To model these dynamics, temporal brain connectivity representations are essential, as they reflect evolving interactions between brain regions and provide insight into transient neural states and network reconfigurations. However, conventional graph neural networks (GNNs) often struggle to capture long-range temporal dependencies in dynamic fMRI data. To address this challenge, we propose BrainATCL, an unsupervised, nonparametric framework for adaptive temporal brain connectivity learning, enabling functional link prediction and age estimation. Our method dynamically adjusts the lookback window for each snapshot based on the rate of newly added edges. Graph sequences are subsequently encoded using a GINE-Mamba2 backbone to learn spatial-temporal representations of dynamic functional connectivity in resting-state fMRI data of 1,000 participants from the Human Connectome Project. To further improve spatial modeling, we incorporate brain structure and function-informed edge attributes, i.e., the left/right hemispheric identity and subnetwork membership of brain regions, enabling the model to capture biologically meaningful topological patterns. We evaluate our BrainATCL on two tasks: functional link prediction and age estimation. The experimental results demonstrate superior performance and strong generalization, including in cross-session prediction scenarios.

Problem

• Captures long-range temporal dependencies in dynamic fMRI data
• Models adaptive temporal brain connectivity for link prediction
• Improves age estimation using spatial-temporal brain connectivity

Innovation

• Adaptive temporal window adjustment for connectivity learning
• GINE-Mamba2 backbone for spatial-temporal representation learning
• Incorporating brain structure and function-informed edge attributes