A graph neural network framework for causal inference in brain networks

Abstract A central question in neuroscience is how self-organizing dynamic interactions in the brain emerge on their relatively static structural backbone. Due to the complexity of spatial and temporal dependencies between different brain areas, fully comprehending the interplay between structure an...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	S. Wein, W. M. Malloni, A. M. Tomé, S. M. Frank, G. -I. Henze, S. Wüst, M. W. Greenlee, E. W. Lang
Formato:	article
Lenguaje:	EN
Publicado:	Nature Portfolio 2021
Materias:	Medicine R Science Q
Acceso en línea:	https://doaj.org/article/7f7d58a025724049af9256f180cb585e
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:7f7d58a025724049af9256f180cb585e
record_format	dspace
spelling	oai:doaj.org-article:7f7d58a025724049af9256f180cb585e2021-12-02T18:03:26ZA graph neural network framework for causal inference in brain networks10.1038/s41598-021-87411-82045-2322https://doaj.org/article/7f7d58a025724049af9256f180cb585e2021-04-01T00:00:00Zhttps://doi.org/10.1038/s41598-021-87411-8https://doaj.org/toc/2045-2322Abstract A central question in neuroscience is how self-organizing dynamic interactions in the brain emerge on their relatively static structural backbone. Due to the complexity of spatial and temporal dependencies between different brain areas, fully comprehending the interplay between structure and function is still challenging and an area of intense research. In this paper we present a graph neural network (GNN) framework, to describe functional interactions based on the structural anatomical layout. A GNN allows us to process graph-structured spatio-temporal signals, providing a possibility to combine structural information derived from diffusion tensor imaging (DTI) with temporal neural activity profiles, like that observed in functional magnetic resonance imaging (fMRI). Moreover, dynamic interactions between different brain regions discovered by this data-driven approach can provide a multi-modal measure of causal connectivity strength. We assess the proposed model’s accuracy by evaluating its capabilities to replicate empirically observed neural activation profiles, and compare the performance to those of a vector auto regression (VAR), like that typically used in Granger causality. We show that GNNs are able to capture long-term dependencies in data and also computationally scale up to the analysis of large-scale networks. Finally we confirm that features learned by a GNN can generalize across MRI scanner types and acquisition protocols, by demonstrating that the performance on small datasets can be improved by pre-training the GNN on data from an earlier study. We conclude that the proposed multi-modal GNN framework can provide a novel perspective on the structure-function relationship in the brain. Accordingly this approach appears to be promising for the characterization of the information flow in brain networks.S. WeinW. M. MalloniA. M. ToméS. M. FrankG. -I. HenzeS. WüstM. W. GreenleeE. W. LangNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 11, Iss 1, Pp 1-18 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Medicine R Science Q
spellingShingle	Medicine R Science Q S. Wein W. M. Malloni A. M. Tomé S. M. Frank G. -I. Henze S. Wüst M. W. Greenlee E. W. Lang A graph neural network framework for causal inference in brain networks
description	Abstract A central question in neuroscience is how self-organizing dynamic interactions in the brain emerge on their relatively static structural backbone. Due to the complexity of spatial and temporal dependencies between different brain areas, fully comprehending the interplay between structure and function is still challenging and an area of intense research. In this paper we present a graph neural network (GNN) framework, to describe functional interactions based on the structural anatomical layout. A GNN allows us to process graph-structured spatio-temporal signals, providing a possibility to combine structural information derived from diffusion tensor imaging (DTI) with temporal neural activity profiles, like that observed in functional magnetic resonance imaging (fMRI). Moreover, dynamic interactions between different brain regions discovered by this data-driven approach can provide a multi-modal measure of causal connectivity strength. We assess the proposed model’s accuracy by evaluating its capabilities to replicate empirically observed neural activation profiles, and compare the performance to those of a vector auto regression (VAR), like that typically used in Granger causality. We show that GNNs are able to capture long-term dependencies in data and also computationally scale up to the analysis of large-scale networks. Finally we confirm that features learned by a GNN can generalize across MRI scanner types and acquisition protocols, by demonstrating that the performance on small datasets can be improved by pre-training the GNN on data from an earlier study. We conclude that the proposed multi-modal GNN framework can provide a novel perspective on the structure-function relationship in the brain. Accordingly this approach appears to be promising for the characterization of the information flow in brain networks.
format	article
author	S. Wein W. M. Malloni A. M. Tomé S. M. Frank G. -I. Henze S. Wüst M. W. Greenlee E. W. Lang
author_facet	S. Wein W. M. Malloni A. M. Tomé S. M. Frank G. -I. Henze S. Wüst M. W. Greenlee E. W. Lang
author_sort	S. Wein
title	A graph neural network framework for causal inference in brain networks
title_short	A graph neural network framework for causal inference in brain networks
title_full	A graph neural network framework for causal inference in brain networks
title_fullStr	A graph neural network framework for causal inference in brain networks
title_full_unstemmed	A graph neural network framework for causal inference in brain networks
title_sort	graph neural network framework for causal inference in brain networks
publisher	Nature Portfolio
publishDate	2021
url	https://doaj.org/article/7f7d58a025724049af9256f180cb585e
work_keys_str_mv	AT swein agraphneuralnetworkframeworkforcausalinferenceinbrainnetworks AT wmmalloni agraphneuralnetworkframeworkforcausalinferenceinbrainnetworks AT amtome agraphneuralnetworkframeworkforcausalinferenceinbrainnetworks AT smfrank agraphneuralnetworkframeworkforcausalinferenceinbrainnetworks AT gihenze agraphneuralnetworkframeworkforcausalinferenceinbrainnetworks AT swust agraphneuralnetworkframeworkforcausalinferenceinbrainnetworks AT mwgreenlee agraphneuralnetworkframeworkforcausalinferenceinbrainnetworks AT ewlang agraphneuralnetworkframeworkforcausalinferenceinbrainnetworks AT swein graphneuralnetworkframeworkforcausalinferenceinbrainnetworks AT wmmalloni graphneuralnetworkframeworkforcausalinferenceinbrainnetworks AT amtome graphneuralnetworkframeworkforcausalinferenceinbrainnetworks AT smfrank graphneuralnetworkframeworkforcausalinferenceinbrainnetworks AT gihenze graphneuralnetworkframeworkforcausalinferenceinbrainnetworks AT swust graphneuralnetworkframeworkforcausalinferenceinbrainnetworks AT mwgreenlee graphneuralnetworkframeworkforcausalinferenceinbrainnetworks AT ewlang graphneuralnetworkframeworkforcausalinferenceinbrainnetworks
_version_	1718378762699014144

A graph neural network framework for causal inference in brain networks

Ejemplares similares