STNAGNN: Data-driven Spatio-temporal Brain Connectivity beyond FC

Jiyao Wang, Nicha C Dvornek, Peiyu Duan, Lawrence H. Staib, Pamela Ventola, James S Duncan
Proceedings of The 8th International Conference on Medical Imaging with Deep Learning, PMLR 301:1688-1705, 2026.

Abstract

In recent years, graph neural networks (GNNs) have been widely applied in the analysis of brain fMRI, yet defining the connectivity between ROIs remains a challenge in noisy fMRI data. Among all approaches, Functional Connectome (FC) is the most popularmethod. Computed by the correlation coefficients between ROI time series, FC is a powerful and computationally efficient way to estimate ROI connectivity. However, it is well known for neglecting structural connections and causality in ROI interactions. Also, FCbecomes much more noisy in the short spatio-temporal sliding-window subsequences of fMRI. Effective Connectome (EC) is proposed as a directional alternative, but it is difficult to accurately estimate. Furthermore, for optimal GNN performance, usually only a small percentage of the strongest connections are selected as sparse edges, resulting in oversimplification of complex brain connections. To tackle these challenges, we propose the Spatio-Temporal Node Attention Graph Neural Network (STNAGNN) as a data-driven alternative that combines sparse predefined FC with dense data-driven spatio-temporal connections, allowing for flexible and spatio-temporal learning of ROI interaction patterns.

Cite this Paper

BibTeX
@InProceedings{pmlr-v301-wang26a, title = {STNAGNN: Data-driven Spatio-temporal Brain Connectivity beyond FC}, author = {Wang, Jiyao and Dvornek, Nicha C and Duan, Peiyu and Staib, Lawrence H. and Ventola, Pamela and Duncan, James S}, booktitle = {Proceedings of The 8th International Conference on Medical Imaging with Deep Learning}, pages = {1688--1705}, year = {2026}, editor = {Tasdizen, Tolga and Elhabian, Shireen and Summers, Ronald and Chen, Chen and Koch, Lisa and Zhuang, Yan}, volume = {301}, series = {Proceedings of Machine Learning Research}, month = {09--11 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v301/main/assets/wang26a/wang26a.pdf}, url = {https://proceedings.mlr.press/v301/wang26a.html}, abstract = {In recent years, graph neural networks (GNNs) have been widely applied in the analysis of brain fMRI, yet defining the connectivity between ROIs remains a challenge in noisy fMRI data. Among all approaches, Functional Connectome (FC) is the most popularmethod. Computed by the correlation coefficients between ROI time series, FC is a powerful and computationally efficient way to estimate ROI connectivity. However, it is well known for neglecting structural connections and causality in ROI interactions. Also, FCbecomes much more noisy in the short spatio-temporal sliding-window subsequences of fMRI. Effective Connectome (EC) is proposed as a directional alternative, but it is difficult to accurately estimate. Furthermore, for optimal GNN performance, usually only a small percentage of the strongest connections are selected as sparse edges, resulting in oversimplification of complex brain connections. To tackle these challenges, we propose the Spatio-Temporal Node Attention Graph Neural Network (STNAGNN) as a data-driven alternative that combines sparse predefined FC with dense data-driven spatio-temporal connections, allowing for flexible and spatio-temporal learning of ROI interaction patterns.} }
Endnote
%0 Conference Paper %T STNAGNN: Data-driven Spatio-temporal Brain Connectivity beyond FC %A Jiyao Wang %A Nicha C Dvornek %A Peiyu Duan %A Lawrence H. Staib %A Pamela Ventola %A James S Duncan %B Proceedings of The 8th International Conference on Medical Imaging with Deep Learning %C Proceedings of Machine Learning Research %D 2026 %E Tolga Tasdizen %E Shireen Elhabian %E Ronald Summers %E Chen Chen %E Lisa Koch %E Yan Zhuang %F pmlr-v301-wang26a %I PMLR %P 1688--1705 %U https://proceedings.mlr.press/v301/wang26a.html %V 301 %X In recent years, graph neural networks (GNNs) have been widely applied in the analysis of brain fMRI, yet defining the connectivity between ROIs remains a challenge in noisy fMRI data. Among all approaches, Functional Connectome (FC) is the most popularmethod. Computed by the correlation coefficients between ROI time series, FC is a powerful and computationally efficient way to estimate ROI connectivity. However, it is well known for neglecting structural connections and causality in ROI interactions. Also, FCbecomes much more noisy in the short spatio-temporal sliding-window subsequences of fMRI. Effective Connectome (EC) is proposed as a directional alternative, but it is difficult to accurately estimate. Furthermore, for optimal GNN performance, usually only a small percentage of the strongest connections are selected as sparse edges, resulting in oversimplification of complex brain connections. To tackle these challenges, we propose the Spatio-Temporal Node Attention Graph Neural Network (STNAGNN) as a data-driven alternative that combines sparse predefined FC with dense data-driven spatio-temporal connections, allowing for flexible and spatio-temporal learning of ROI interaction patterns.
APA
Wang, J., Dvornek, N.C., Duan, P., Staib, L.H., Ventola, P. & Duncan, J.S.. (2026). STNAGNN: Data-driven Spatio-temporal Brain Connectivity beyond FC. Proceedings of The 8th International Conference on Medical Imaging with Deep Learning, in Proceedings of Machine Learning Research 301:1688-1705 Available from https://proceedings.mlr.press/v301/wang26a.html.

Related Material