Dynamic and low-dimensional modeling of brain functional connectivity on Riemannian manifolds

Modeling brain functional connectivity (FC) is key in investigating brain functions and dysfunctions. FC is typically quantified by symmetric positive definite (SPD) matrices that are located on a Riemannian manifold rather than the regular Euclidean space, whose modeling faces three challenges. Fir...

Full description

Saved in:
Bibliographic Details
Main Authors: Mingyu Wang, Yueming Wang, Yuxiao Yang
Format: Article
Language:English
Published: Elsevier 2025-07-01
Series:NeuroImage
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S1053811925002460
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849387383059906560
author Mingyu Wang
Yueming Wang
Yuxiao Yang
author_facet Mingyu Wang
Yueming Wang
Yuxiao Yang
author_sort Mingyu Wang
collection DOAJ
description Modeling brain functional connectivity (FC) is key in investigating brain functions and dysfunctions. FC is typically quantified by symmetric positive definite (SPD) matrices that are located on a Riemannian manifold rather than the regular Euclidean space, whose modeling faces three challenges. First, FC can be time-varying and the temporal dynamics of FC matrix time-series need to be modeled within the constraint of the SPD Riemannian manifold geometry, which remains elusive. Second, the FC matrix time-series exhibits considerable stochasticity, whose probability distribution is difficult to model on the Riemannian manifold. Third, FC matrices are high-dimensional and dimensionality reduction methods for SPD matrix time-series are still lacking. Here, we develop a Riemannian state-space modeling framework to simultaneously address the challenges. First, we construct a new Riemannian state-space model (RSSM) to define a hidden SPD matrix state to achieve dynamic, stochastic, and low-dimensional modeling of FC matrix time-series on the SPD Riemannian manifold. Second, we develop a new Riemannian Particle Filter (RPF) algorithm to estimate the hidden low-dimensional SPD matrix state and predict the FC matrix time-series. Third, we develop a new Riemannian Expectation Maximization (REM) algorithm to fit the RSSM parameters. We evaluate the proposed RSSM, RPF, and REM using simulation and real-world EEG datasets, demonstrating that the RSSM enables accurate prediction of the EEG FC time-series and classification of emotional states, outperforming traditional Euclidean methods. Our results have implications for modeling brain FC on the SPD Riemannian manifold to study various brain functions and dysfunctions.
format Article
id doaj-art-85fe99485311414bb5f3adf4b1ffb84f
institution Kabale University
issn 1095-9572
language English
publishDate 2025-07-01
publisher Elsevier
record_format Article
series NeuroImage
spelling doaj-art-85fe99485311414bb5f3adf4b1ffb84f2025-08-20T03:53:51ZengElsevierNeuroImage1095-95722025-07-0131412124310.1016/j.neuroimage.2025.121243Dynamic and low-dimensional modeling of brain functional connectivity on Riemannian manifoldsMingyu Wang0Yueming Wang1Yuxiao Yang2MOE Frontier Science Center for Brain Science and Brain-machine Integration, Zhejiang University, Hangzhou, China; Nanhu Brain-computer Interface Institute, Hangzhou, China; School of Computer Science and Technology, Zhejiang University, Hangzhou, ChinaNanhu Brain-computer Interface Institute, Hangzhou, China; School of Computer Science and Technology, Zhejiang University, Hangzhou, ChinaMOE Frontier Science Center for Brain Science and Brain-machine Integration, Zhejiang University, Hangzhou, China; Nanhu Brain-computer Interface Institute, Hangzhou, China; School of Computer Science and Technology, Zhejiang University, Hangzhou, China; State Key Laboratory of Brain-machine Intelligence, Zhejiang University, Hangzhou, China; Second Affiliated Hospital, School of Medicine, Zhejiang University, Hangzhou, China; Correspondence to: Zhejiang University, Hangzhou, China.Modeling brain functional connectivity (FC) is key in investigating brain functions and dysfunctions. FC is typically quantified by symmetric positive definite (SPD) matrices that are located on a Riemannian manifold rather than the regular Euclidean space, whose modeling faces three challenges. First, FC can be time-varying and the temporal dynamics of FC matrix time-series need to be modeled within the constraint of the SPD Riemannian manifold geometry, which remains elusive. Second, the FC matrix time-series exhibits considerable stochasticity, whose probability distribution is difficult to model on the Riemannian manifold. Third, FC matrices are high-dimensional and dimensionality reduction methods for SPD matrix time-series are still lacking. Here, we develop a Riemannian state-space modeling framework to simultaneously address the challenges. First, we construct a new Riemannian state-space model (RSSM) to define a hidden SPD matrix state to achieve dynamic, stochastic, and low-dimensional modeling of FC matrix time-series on the SPD Riemannian manifold. Second, we develop a new Riemannian Particle Filter (RPF) algorithm to estimate the hidden low-dimensional SPD matrix state and predict the FC matrix time-series. Third, we develop a new Riemannian Expectation Maximization (REM) algorithm to fit the RSSM parameters. We evaluate the proposed RSSM, RPF, and REM using simulation and real-world EEG datasets, demonstrating that the RSSM enables accurate prediction of the EEG FC time-series and classification of emotional states, outperforming traditional Euclidean methods. Our results have implications for modeling brain FC on the SPD Riemannian manifold to study various brain functions and dysfunctions.http://www.sciencedirect.com/science/article/pii/S1053811925002460Brain functional connectivityRiemannian manifoldStochastic matrix dynamicsDimensionality reductionEEG
spellingShingle Mingyu Wang
Yueming Wang
Yuxiao Yang
Dynamic and low-dimensional modeling of brain functional connectivity on Riemannian manifolds
NeuroImage
Brain functional connectivity
Riemannian manifold
Stochastic matrix dynamics
Dimensionality reduction
EEG
title Dynamic and low-dimensional modeling of brain functional connectivity on Riemannian manifolds
title_full Dynamic and low-dimensional modeling of brain functional connectivity on Riemannian manifolds
title_fullStr Dynamic and low-dimensional modeling of brain functional connectivity on Riemannian manifolds
title_full_unstemmed Dynamic and low-dimensional modeling of brain functional connectivity on Riemannian manifolds
title_short Dynamic and low-dimensional modeling of brain functional connectivity on Riemannian manifolds
title_sort dynamic and low dimensional modeling of brain functional connectivity on riemannian manifolds
topic Brain functional connectivity
Riemannian manifold
Stochastic matrix dynamics
Dimensionality reduction
EEG
url http://www.sciencedirect.com/science/article/pii/S1053811925002460
work_keys_str_mv AT mingyuwang dynamicandlowdimensionalmodelingofbrainfunctionalconnectivityonriemannianmanifolds
AT yuemingwang dynamicandlowdimensionalmodelingofbrainfunctionalconnectivityonriemannianmanifolds
AT yuxiaoyang dynamicandlowdimensionalmodelingofbrainfunctionalconnectivityonriemannianmanifolds