Scholarlink

Functional Magnetic Resonance Imaging (fMRI) provides rich, time-resolved signals of neural activity, yet standard correlation-based analyses obscure the direction and temporal order of interregional influences. We present a unified framework that embeds Granger-causal inference within Graph Convolutional Networks (GCNs) to capture effective connectivity. We compare three models: (1) an MLP on flattened BOLD time series, (2) a GCN over undirected Pearson-correlation graphs, and (3) a directed GCN incorporating Granger-causal edges. Lag orders are selected via Akaike and Bayesian criteria. On large-scale fMRI cohorts, our directed GCN matches undirected performance in both classification and regression tasks while uncovering biologically plausible, asymmetric information flows that remain stable across hyperparameter settings. These results demonstrate that Granger-causality-informed graph models can enrich interpretability without sacrificing predictive power, marking a step toward causality-aware, graph-based analysis of brain networks.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Causal Brain Connectivity: Integrating Granger Directed Graphs in fMRI Analysis

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • Tianyi Zhang,
  • Keqi Han,
  • Jiawei Nie,
  • Chenyu You,
  • Sanne van Rooij,
  • Jennifer Stevens,
  • Boadie Dunlop,
  • Charles Gillespie,
  • Carl Yang

摘要

Functional Magnetic Resonance Imaging (fMRI) provides rich, time-resolved signals of neural activity, yet standard correlation-based analyses obscure the direction and temporal order of interregional influences. We present a unified framework that embeds Granger-causal inference within Graph Convolutional Networks (GCNs) to capture effective connectivity. We compare three models: (1) an MLP on flattened BOLD time series, (2) a GCN over undirected Pearson-correlation graphs, and (3) a directed GCN incorporating Granger-causal edges. Lag orders are selected via Akaike and Bayesian criteria. On large-scale fMRI cohorts, our directed GCN matches undirected performance in both classification and regression tasks while uncovering biologically plausible, asymmetric information flows that remain stable across hyperparameter settings. These results demonstrate that Granger-causality-informed graph models can enrich interpretability without sacrificing predictive power, marking a step toward causality-aware, graph-based analysis of brain networks.