A Novel Unit-Based Personalized Fingerprint Feature Selection Strategy for Dynamic Functional Connectivity Networks

Zhao, Feng; Chen, Zhiyuan; Rekik, Islem; Liu, Peiqiang; Mao, Ning; Lee, Seong Whan; Shen, Dinggang

doi:10.3389/fnins.2021.651574

Cited by 5 publications

(4 citation statements)

References 42 publications

(47 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In fact, similar high-order network methods have been applied in the field of functional magnetic resonance imaging (fMRI) (Zhao et al, 2018(Zhao et al, , 2021Zhou et al, 2018), where experimental results have shown that the high-order network method can explore more advanced features on the basis of the traditional low-order network. However, owing to the low temporal resolution of fMRI, the Gaussian distribution leads to inaccurate estimation results.…”

Section: Introductionmentioning

confidence: 99%

Identifying depression disorder using multi-view high-order brain function network derived from electroencephalography signal

Zhao

Gao²,

Zhi³

et al. 2022

Front. Comput. Neurosci.

Self Cite

View full text Add to dashboard Cite

Brain function networks (BFN) are widely used in the diagnosis of electroencephalography (EEG)-based major depressive disorder (MDD). Typically, a BFN is constructed by calculating the functional connectivity (FC) between each pair of channels. However, it ignores high-order relationships (e.g., relationships among multiple channels), making it a low-order network. To address this issue, a novel classification framework, based on matrix variate normal distribution (MVND), is proposed in this study. The framework can simultaneously generate high-and low-order BFN and has a distinct mathematical interpretation. Specifically, the entire time series is first divided into multiple epochs. For each epoch, a BFN is constructed by calculating the phase lag index (PLI) between different EEG channels. The BFNs are then used as samples, maximizing the likelihood of MVND to simultaneously estimate its low-order BFN (Lo-BFN) and high-order BFN (Ho-BFN). In addition, to solve the problem of the excessively high dimensionality of Ho-BFN, Kronecker product decomposition is used for dimensionality reduction while retaining the original high-order information. The experimental results verified the effectiveness of Ho-BFN for MDD diagnosis in 24 patients and 24 normal controls. We further investigated the selected discriminative Lo-BFN and Ho-BFN features and revealed that those extracted from different networks can provide complementary information, which is beneficial for MDD diagnosis.

show abstract

Section: Introductionmentioning

confidence: 99%

Identifying depression disorder using multi-view high-order brain function network derived from electroencephalography signal

Zhao

Gao²,

Zhi³

et al. 2022

Front. Comput. Neurosci.

Self Cite

View full text Add to dashboard Cite

show abstract

“…FC network has been of great importance for discovering the functional organization of human brain and searching for the biomarkers of the neuropsychiatric disorders, such as Alzheimer’s disease ( Chen et al, 2017 ; Hao et al, 2017 ) and autism spectrum disorder (ASD) ( Zhao et al, 2018 ; Wee, Yap & Shen, 2016 ). Currently, researchers have proposed various FC network modeling methods for ASD assisted diagnosis ( Liu & Huang, 2020 ; Zhao et al, 2020 ; Zhao et al, 2021 ). For example, Liu & Huang (2020) estimated the severity of ASD by multivariate model analysis, and they found that some FCs suffer from abnormal alterations in ASD patients.…”

Section: Introductionmentioning

confidence: 99%

“…For example, Liu & Huang (2020) estimated the severity of ASD by multivariate model analysis, and they found that some FCs suffer from abnormal alterations in ASD patients. Zhao et al (2021) proposed a unit-based personalized fingerprint feature selection (UPFFS) strategy and applied to ASD, they found that the top selected discriminative brain regions by UPFFS are related to visual processing, social cognition, and emotional expression which is associated with ASD. Overall, previous studies have shown that FC networks have great potential for revealing FC deficits and finding abnormal brain regions in ASD patients.…”

Section: Introductionmentioning

confidence: 99%

“…This leads to the sensitivity of LoD-FCN to its subnetwork, which limits its use in comparative studies. In order to eliminate the sensitivity, the central moment method was used to extract features from LoD-FCN ( Zhao et al, 2020 , 2021 ). The central moment feature is a common translation invariant feature, which reflects the shape information of the target and is often used in feature extraction of sequences or waveforms.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Constructing high-order functional connectivity network based on central moment features for diagnosis of autism spectrum disorder

Xie

Zhang

Rekik

et al. 2021

PeerJ

Self Cite

View full text Add to dashboard Cite

The sliding-window-based dynamic functional connectivity network (D-FCN) has been becoming an increasingly useful tool for understanding the changes of brain connectivity patterns and the association of neurological diseases with these dynamic variations. However, conventional D-FCN is essentially low-order network, which only reflects the pairwise interaction pattern between brain regions and thus overlooking the high-order interactions among multiple brain regions. In addition, D-FCN is innate with temporal sensitivity issue, i.e., D-FCN is sensitive to the chronological order of its subnetworks. To deal with the above issues, we propose a novel high-order functional connectivity network framework based on the central moment feature of D-FCN. Specifically, we firstly adopt a central moment approach to extract multiple central moment feature matrices from D-FCN. Furthermore, we regard the matrices as the profiles to build multiple high-order functional connectivity networks which further capture the higher level and more complex interaction relationships among multiple brain regions. Finally, we use the voting strategy to combine the high-order networks with D-FCN for autism spectrum disorder diagnosis. Experimental results show that the combination of multiple functional connectivity networks achieves accuracy of 88.06%, and the best single network achieves accuracy of 79.5%.

show abstract

Investigation of the correlation between brain functional connectivity and ESRD based on low‐order and high‐order feature analysis of rs‐fMRI

et al. 2023

Self Cite

View full text Add to dashboard Cite

Background:The lack of analysis of brain networks in individuals with end-stage renal disease (ESRD) is an obstacle to detecting and preventing neurological complications of ESRD. Purpose: This study aims to explore the correlation between brain activity and ESRD based on a quantitative analysis of the dynamic functional connectivity (dFC) of brain networks. It provides insights into differences in brain functional connectivity between healthy individuals and ESRD patients and aims to identify the brain activities and regions most relevant to ESRD. Methods: Differences in brain functional connectivity between healthy individuals and ESRD patients were analyzed and quantitatively evaluated in this study. Blood oxygen level-dependent (BOLD) signals obtained through resting-state functional magnetic resonance imaging (rs-fMRI) were used as information carriers. First, a connectivity matrix of dFC was constructed for each subject using Pearson correlation. Then a high-order connectivity matrix was built by applying the "correlation's correlation" method. Second, sparsification of the high-order connectivity matrix was performed using the graphical least absolute shrinkage and selection operator (gLASSO) model. The discriminative features of the sparse connectivity matrix were extracted and sifted using central moments and t-tests, respectively. Finally, feature classification was conducted using a support vector machine (SVM). Results: The experiment showed that functional connectivity was reduced to some degree in certain brain regions of ESRD patients. The sensorimotor, visual, and cerebellum subnetworks had the highest numbers of abnormal functional connectivities. It is inferred that these three subnetworks most likely have a direct relationship to ESRD. Conclusions: The low-order and high-order dFC features can identify the positions where brain damage occurs in ESRD patients. In contrast to healthy individuals, the damaged brain regions and the disruption of functional connectivity in ESRD patients were not limited to specific regions. This indicates that ESRD has a severe impact on brain function. Abnormal functional connectivity was mainly associated with the three functional brain regions responsible for visual processing, emotional, and motor control. The findings presented here have the potential for use in the detection, prevention, and prognostic evaluation of ESRD.Peirui Bai and Yulong Wang share co-first authorship and contributed equally to this study.

show abstract

A Novel Unit-Based Personalized Fingerprint Feature Selection Strategy for Dynamic Functional Connectivity Networks

Cited by 5 publications

References 42 publications

Identifying depression disorder using multi-view high-order brain function network derived from electroencephalography signal

Identifying depression disorder using multi-view high-order brain function network derived from electroencephalography signal

Constructing high-order functional connectivity network based on central moment features for diagnosis of autism spectrum disorder

Investigation of the correlation between brain functional connectivity and ESRD based on low‐order and high‐order feature analysis of rs‐fMRI

Contact Info

Product

Resources

About