A spatio-temporal decomposition framework for dynamic functional connectivity in the human brain

Xiao, Jinming; Uddin, Lucina Q.; Meng, Yao; Li, Lei; Gao, Leying; Shan, Xiaolong; Huang, Xinyue; Liao, Wei; Chen, Huafu; Duan, Xujun

doi:10.1016/j.neuroimage.2022.119618

Cited by 5 publications

(5 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The abnormalities in the brain structure and function of SZ disease [10] and the spatial brain networks are not all involved but follow some regularity, the proposed method imposed L 1 regularization on spatial modules to extract sparse but significant dynamic connectivity and prevent overfitting of the model. References [24,36] also added sparsity in their model and found significant differences between different dynamic modules or temporal states of diseases. In addition, transitions between different brain states are not random but obey a hierarchical organization in temporal [37].…”

Section: Discussionmentioning

confidence: 99%

“…Algorithm 1 summarizes the detailed procedure of our proposed SLRCPD approach for multi-subject dFNC tensor. In algorithm 1, the number of iterations iter1 max is set as 300 referring to [24], the initial values of hyperparameters µ, µ max and iter2 max are respectively selected as 10 −6 , 10 6 and 1000 based on [34]. For the hyperparameters R, λ, γ and φ, we use a grid search method to find the optimal values by changing R from 5 to 10 in steps of 1, λ in the range of {0.001, 0.01, 0.1, 1, 1.1, 1.2, 1.3}, γ in the range of {0.01, 0.1, 1, 10, 20, 30} and φ in the range of {0.9:0.1:1.8}.…”

Section: Slrcpd Of Dfnc Tensormentioning

confidence: 99%

“…Although the majority of dFC/dFNC studies typically examine temporal FC among spatial brain networks, comprehensively investigating the spatial and temporal dFC/dFNC connectivity can provide more adequate FC. As such, some spatio-temporal dFC/d-FNC methods have been proposed, such as dynamic mode decomposition [20], independent vector decomposition [21], and tensor decomposition [22][23][24][25]. Moreover, the spatio-temporal dFC/dFNC features can provide improved classification of different subjects [26].…”

Section: Introductionmentioning

confidence: 99%

“…The orthogonal CPD was exploited by [23] to decompose the three-way dFC tensor (ROIs × ROIs × windows of all subjects), and the estimated subject factor was further investigated to predict biological gender and intelligence. Xiao et al [24] proposed a spatiotemporal CPD framework based on a three-way dFC tensor (ROIs × ROIs × windows of all subjects) which was obtained by temporally concatenating windows of all subjects. The L 1 regularization on dynamic modules and manifold regularization were incorporated into CPD model to prevent model overfitting and smooth time-varying weights.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Dynamic functional network connectivity analysis in schizophrenia based on a spatiotemporal CPD framework

Kuang,

Li,

Zhang

et al. 2024

J. Neural Eng.

View full text Add to dashboard Cite

Objective. Dynamic functional network connectivity (dFNC), basedon data-driven group independent component analysis (GICA), is an importantavenue for investigating underlying patterns of certain brain diseases such asschizophrenia. Canonical polyadic decomposition (CPD) of a higher-way dynamicfunctional connectivity tensor, can offer an innovative spatiotemporal frameworkto accurately characterize potential dynamic spatial and temporal fluctuations.Since multi-subject dFNC data from sliding-window analysis are also naturallya higher-order tensor, we propose an innovative sparse and low-rank CPD(SLRCPD) for the three-way dFNC tensor to excavate significant dynamicspatiotemporal aberrant changes in schizophrenia. Approach. The proposedSLRCPD approach imposes two constraints. First, the L1 regularization onspatial modules is applied to extract sparse but significant dynamic connectivityand avoid overfitting the model . Second, low-rank constraint is added on timevarying weights to enhance the temporal state clustering quality. Shared dynamicspatial modules, group-specific dynamic spatial modules and time-varying weightscan be extracted by SLRCPD. The strength of connections within- and betweenICNs and connection contribution are proposed to inspect the spatial modules.K-means clustering and classification are further conducted to explore temporalgroup difference. Main results. 82-subject resting-state fMRI dataset and openingCOBRE schizophrenia dataset both containing schizophrenia patients (SZs) andhealthy controls (HCs) were utilized in our work. Three typical dFNC patternsbetween different brain functional regions were obtained. Compared to the spatialmodules of HCs, the aberrant negative connections among auditory network,somatomotor, visual and cognitive control networks in 82-subject dataset andCOBRE dataset were detected. Four temporal states reveal significant differencebetween SZs and HCs for these two datasets. Additionally, the accuracy valuesfor SZs and HCs classification based on time-varying weights are larger than0.96. Significance. This study excavates significantly spatio-temporal patternsfor schizophrenia disease.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Slrcpd Of Dfnc Tensormentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Dynamic functional network connectivity analysis in schizophrenia based on a spatiotemporal CPD framework

Kuang,

Li,

Zhang

et al. 2024

J. Neural Eng.

View full text Add to dashboard Cite

show abstract

“…We therefore combine this concept of overlap with spatiotemporal dynamics to investigate the dynamic interaction of abnormal spatiotemporal patterns in the brain hubs of SZ patients. Research reveals abnormal spatiotemporal patterns that indicate disrupted communication and coordination between brain regions in schizophrenia patients [48,49]. Understanding these spatiotemporal changes is critical to uncovering the neural mechanisms of schizophrenia and developing more targeted treatments or interventions [50,51].…”

Section: Reduced Stability Of Spatial Configuration Of Brain Activity...mentioning

confidence: 99%

Abnormal Spatial and Temporal Overlap of Time-Varying Brain Functional Networks in Patients with Schizophrenia

Xiang,

Sun,

et al. 2023

Brain Sciences

View full text Add to dashboard Cite

Schizophrenia (SZ) is a complex psychiatric disorder with unclear etiology and pathological features. Neuroscientists are increasingly proposing that schizophrenia is an abnormality in the dynamic organization of brain networks. Previous studies have found that the dynamic brain networks of people with SZ are abnormal in both space and time. However, little is known about the interactions and overlaps between hubs of the brain underlying spatiotemporal dynamics. In this study, we aimed to investigate different patterns of spatial and temporal overlap of hubs between SZ patients and healthy individuals. Specifically, we obtained resting-state functional magnetic resonance imaging data from the public dataset for 43 SZ patients and 49 healthy individuals. We derived a representation of time-varying functional connectivity using the Jackknife Correlation (JC) method. We employed the Betweenness Centrality (BC) method to identify the hubs of the brain’s functional connectivity network. We then applied measures of temporal overlap, spatial overlap, and hierarchical clustering to investigate differences in the organization of brain hubs between SZ patients and healthy controls. Our findings suggest significant differences between SZ patients and healthy controls at the whole-brain and subnetwork levels. Furthermore, spatial overlap and hierarchical clustering analysis showed that quasi-periodic patterns were disrupted in SZ patients. Analyses of temporal overlap revealed abnormal pairwise engagement preferences in the hubs of SZ patients. These results provide new insights into the dynamic characteristics of the network organization of the SZ brain.

show abstract

DeepGraphDMD: Interpretable Spatio-Temporal Decomposition of Non-linear Functional Brain Network Dynamics

Turja,

Styner,

2023

Lecture Notes in Computer Science

View full text Add to dashboard Cite

A spatio-temporal decomposition framework for dynamic functional connectivity in the human brain

Cited by 5 publications

References 38 publications

Dynamic functional network connectivity analysis in schizophrenia based on a spatiotemporal CPD framework

Dynamic functional network connectivity analysis in schizophrenia based on a spatiotemporal CPD framework

Abnormal Spatial and Temporal Overlap of Time-Varying Brain Functional Networks in Patients with Schizophrenia

DeepGraphDMD: Interpretable Spatio-Temporal Decomposition of Non-linear Functional Brain Network Dynamics

Contact Info

Product

Resources

About