Neural Dynamics-Informed Pre-trained Framework for Personalized Brain Functional Network Construction

2026-03-08

AI Summary

Existing approaches to constructing brain functional networks rely on predefined atlases and linear assumptions, which struggle to capture the dynamic spatiotemporal characteristics of individual neural activity under heterogeneous conditions, thereby limiting generalizability. This work proposes a pretraining framework that integrates prior knowledge of neural dynamics to adaptively model the nonlinear dynamics of individual neural activity, jointly optimizing personalized brain parcellation and functional connectivity estimation. By moving beyond static atlases and linear correlation assumptions, the method uniquely embeds neurodynamical mechanisms into pretrained representation learning. Experiments across 18 cross-task datasets demonstrate that the framework significantly outperforms existing methods in tasks such as virtual neuromodulation and aberrant circuit identification, substantially improving the accuracy and robustness of brain network modeling in heterogeneous scenarios.

Technology Category

• Cognitive Modeling & Cognitive Systems: Neural Spike Coding
• Machine Learning: Neuro-Symbolic Learning
• Natural Language Processing: Learning & Optimization for NLP

Application Category

• User Modeling, Personalization and Recommendation: Federated recommendation systems and personalization
• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Web Mining and Content Analysis: Large pretrained models with web data

Abstract

Brain activity is intrinsically a neural dynamic process constrained by anatomical space. This leads to significant variations in spatial distribution patterns and correlation patterns of neural activity across variable and heterogeneous scenarios. However, dominant brain functional network construction methods, which relies on pre-defined brain atlases and linear assumptions, fails to precisely capture varying neural activity patterns in heterogeneous scenarios. This limits the consistency and generalizability of the brain functional networks constructed by dominant methods. Here, a neural dynamics-informed pre-trained framework is proposed for personalized brain functional network construction. The proposed framework extracts personalized representations of neural activity patterns in heterogeneous scenarios. Personalized brain functional networks are obtained by utilizing these representations to guide brain parcellation and neural activity correlation estimation. Systematic evaluations were employed on 18 datasets across tasks, such as virtual neural modulation and abnormal neural circuit identification. Experimental results demonstrate that the proposed framework attains superior performance in heterogeneous scenarios. Overall, the proposed framework challenges the dominant brain functional network construction method.

Problem

• brain functional network
• neural dynamics
• heterogeneous scenarios
• personalized representation
• brain parcellation

Innovation

• neural dynamics
• pre-trained framework
• personalized brain functional network
• heterogeneous scenarios
• brain parcellation