Graph Neural Networks (GNNs) have been widely used in diverse brain network analysis tasks based on preprocessed functional magnetic resonance imaging (fMRI) data. However, their performances are cons... Activation: LLM, fMRI, graph neural network, brain network, neuroimaging
Graph Neural Networks (GNNs) have been widely used in diverse brain network analysis tasks based on preprocessed functional magnetic resonance imaging (fMRI) data. However, their performances are constrained due to high feature sparsity and inherent limitations of domain knowledge. We propose BLEG (Brain LLM-Enhanced Graph), a novel framework that leverages LLMs to enhance fMRI-based brain network analysis by encoding anatomical and functional region descriptions.
LLM-enhanced features for brain network graph analysis
The paper tackles fundamental challenges in brain signal analysis and network dynamics, proposing novel solutions that advance the state-of-the-art in computational neuroscience.
LLM-enhanced features for brain network graph analysis
This work builds upon and extends:
Generated from arXiv paper on 2026-04-13
execreadwriteUser: 请帮我应用此技能
Agent: 我将按照标准流程执行...
User: 有更复杂的场景需要处理
Agent: 针对复杂场景，我将采用以下策略...