Classification of Normal and Pathological Brain Networks Based on Similarity in Graph Partitions

Kurmukov, Anvar; Dodonova, Yulia; Zhukov, Leonid

doi:10.1109/icdmw.2016.0023

Cited by 8 publications

(6 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Each node represented a different time window of DFNs, and the different edges indicated the correlations between the corresponding time windows of DFNs. We utilized the Frobenius norm for distance measurement to calculate the similarity between networks ( Kurmukov et al, 2016 ), and the distance measure was inversely proportional to similarity. The calculation formula is as follows:…”

Section: Methodsmentioning

confidence: 99%

Association of Plasma and Electroencephalography Markers With Motor Subtypes of Parkinson’s Disease

Yang

Li²,

Bai³

et al. 2022

Front. Aging Neurosci.

View full text Add to dashboard Cite

ObjectiveThe aim of this study was to investigate the correlations of plasma neurodegenerative proteins and electroencephalography (EEG) dynamic functional network (DFN) parameters with disease progression in early Parkinson’s disease (PD) with different motor subtypes, including tremor-dominant (TD) and postural instability and gait disorder (PIGD).MethodsIn our study, 33 patients with PD (21 TD and 12 PIGD) and 33 healthy controls (HCs) were enrolled. Plasma neurofilament light chain (NfL), α-synuclein (α-syn), total-tau (t-tau), β-amyloid 42 (Aβ42), and β-amyloid 40 (Aβ40) levels were measured using an ultrasensitive single-molecule array (Simoa) immunoassay. All the patients with PD underwent EEG quantified by DFN analysis. The motor and non-motor performances were evaluated by a series of clinical assessments. Subsequently, a correlation analysis of plasma biomarkers and EEG measures with clinical scales was conducted.ResultsIn the TD group, plasma NfL exhibited a significant association with MDS-UPDRS III and Montreal Cognitive Assessment (MoCA). A higher Aβ42/40 level was significantly related to a decrease in Hamilton Depression Rating Scale (HAMD) and Hamilton Anxiety Rating Scale (HAMA) in the PIGD group. In terms of the correlation between EEG characteristic parameters and clinical outcomes, trapping time (TT) delta was positively correlated with MDS-UPDRS III and MoCA scores in the TD group, especially in the prefrontal and frontal regions. For other non-motor symptoms, there were significant direct associations of kPLI theta with HAMD and HAMA, especially in the prefrontal region, and kPLI gamma was particularly correlated with Rapid Eye Movement Sleep Behavior Disorder Screening Questionnaire (RBDSQ) scores in the prefrontal, frontal, and parietal regions in the TD group. Furthermore, there was a significant positive correlation between plasma t-tau and kPLI, and pairwise correlations were found among plasma NfL, theta TT, and MoCA scores in the TD group.ConclusionThese results provide evidence that plasma neurodegenerative proteins and EEG measures have great potential in predicting the disease progression of PD subtypes, especially for the TD subtype. A combination of these two kinds of markers may have a superposition effect on monitoring and estimating the prognosis of PD subtypes and deserves further research in larger, follow-up PD cohorts.

show abstract

Section: Methodsmentioning

confidence: 99%

Association of Plasma and Electroencephalography Markers With Motor Subtypes of Parkinson’s Disease

Yang

Li²,

Bai³

et al. 2022

Front. Aging Neurosci.

View full text Add to dashboard Cite

show abstract

“…The Frobenius norm of the difference between a pair of networks is given by (Kurmukov, Dodonova, & Zhukov, 2016).…”

Section: Recurrence Plots and Distance Measuresmentioning

confidence: 99%

“…First, we used the Frobenius norm of the difference between a pair of networks, which is given by (Kurmukov et al, 2016)…”

Section: Recurrence Plots and Distance Measuresmentioning

confidence: 99%

Recurrence quantification analysis of dynamic brain networks

Lopes

Zhang

Krzemiński

et al. 2020

Eur J of Neuroscience

View full text Add to dashboard Cite

show abstract

“…The problem of brain network classification has been paid much attention recently [17,9,21,19,18]. This problem is non-trivial as most modern classification algorithms can work only with vectorial data while in our case each object in the dataset is represented by graph.…”

Section: Existing Approachesmentioning

confidence: 99%

“…By community structure we mean the existence of groups of nodes that are much more strongly linked inside the group compared to the rest of the graph. We note that the community detection approach has been recently used for connectome classification [19,18], where a certain kernel function was used to measure similarity between graph partitions, which were again obtained independently for each graph.…”

Section: Existing Approachesmentioning

confidence: 99%

Simultaneous Matrix Diagonalization for Structural Brain Networks Classification

Mokrov¹,

Panov²,

Gutman³

et al. 2017

Complex Networks &Amp; Their Applications VI

View full text Add to dashboard Cite

This paper considers the problem of brain disease classification based on connectome data. A connectome is a network representation of a human brain. The typical connectome classification problem is very challenging because of the small sample size and high dimensionality of the data. We propose to use simultaneous approximate diagonalization of adjacency matrices in order to compute their eigenstructures in more stable way. The obtained approximate eigenvalues are further used as features for classification. The proposed approach is demonstrated to be efficient for detection of Alzheimer's disease, outperforming simple baselines and competing with state-of-the-art approaches to brain disease classification.

show abstract

Classification of Normal and Pathological Brain Networks Based on Similarity in Graph Partitions

Cited by 8 publications

References 11 publications

Association of Plasma and Electroencephalography Markers With Motor Subtypes of Parkinson’s Disease

Association of Plasma and Electroencephalography Markers With Motor Subtypes of Parkinson’s Disease

Recurrence quantification analysis of dynamic brain networks

Simultaneous Matrix Diagonalization for Structural Brain Networks Classification

Contact Info

Product

Resources

About