Classifying Phenotypes Based on the Community Structure of Human Brain Networks

Kurmukov, Anvar; Ananyeva, Marina; Dodonova, Yulia; Gutman, Boris A.; Faskowitz, Joshua; Jahanshad, Neda; Thompson, Paul M.; Zhukov, Leonid

doi:10.1007/978-3-319-67675-3_1

Cited by 10 publications

(10 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…First, we discuss the results for binary classification problem. We start by reminding the state-of-the-art results for ADNI2 dataset [18] obtained by kernel algorithm based on community structure, see Table 2. AD vs NC AD vs LMCI LMCI vs EMCI EMCI vs NC Community (SVM) 0.831 ± 0.009 0.762 ± 0.018 0.523 ± 0.028 0.628 ± 0.018 Table 2 Quality of classification for the method based on community structures of networks. Tables 3 and 4 show the mean ROC AUC values for the classification based on eigenvalues L i and diagonal values of simultaneously diagonalized matrices λ λ λ i respectively.…”

Section: Resultsmentioning

confidence: 99%

See 1 more Smart Citation

Simultaneous Matrix Diagonalization for Structural Brain Networks Classification

Mokrov¹,

Panov²,

Gutman³

et al. 2017

Complex Networks &Amp; Their Applications VI

Self Cite

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

Section: Resultsmentioning

confidence: 99%

“…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%

Simultaneous Matrix Diagonalization for Structural Brain Networks Classification

Mokrov¹,

Panov²,

Gutman³

et al. 2017

Complex Networks &Amp; Their Applications VI

Self Cite

View full text Add to dashboard Cite

show abstract

“…We use the Louvain modularity algorithm (Blondel et al, 2008), as it has shown good results in multiple neuroimaging studies (Kurmukov et al, 2017;Meunier et al, 2010;Nicolini et al, 2017;Taylor et al, 2017;Williams et al, 2019). We note that the overall goal of this work-approximating average parcellations-is agnostic with respect to the individual clustering algorithm.…”

Section: Individual Parcellationmentioning

confidence: 99%

Optimizing Connectivity-Driven Brain Parcellation Using Ensemble Clustering

et al. 2020

Self Cite

View full text Add to dashboard Cite

This work addresses the problem of constructing a unified, topologically optimal connectivity-based brain atlas. The proposed approach aggregates an ensemble partition from individual parcellations without label agreement, providing a balance between sufficiently flexible individual parcellations and intuitive representation of the average topological structure of the connectome. The methods exploit a previously proposed dense connectivity representation, first performing graph-based hierarchical parcellation of individual brains, and subsequently aggregating the individual parcellations into a consensus parcellation. The search for consensus-based on the hard ensemble (HE) algorithm-approximately minimizes the sum of cluster membership distances, effectively estimating a pseudo-Karcher mean of individual parcellations. Computational stability, graph structure preservation, and biological relevance of the simplified representation resulting from the proposed parcellation are assessed on the Human Connectome Project data set. These aspects are assessed using (1) edge weight distribution divergence with respect to the dense connectome representation, (2) interhemispheric symmetry, (3) network characteristics' stability and agreement with respect to individually and anatomically parcellated networks, and (4) performance of the simplified connectome in a biological sex classification task. Ensemble parcellation was found to be highly stable with respect to subject sampling, outperforming anatomical atlases and other connectome-based parcellations in classification as well as preserving global connectome properties. The HEbased parcellation also showed a degree of symmetry comparable with anatomical atlases and a high degree of spatial contiguity without using explicit priors.

show abstract

“…For example, Pearson correlation has been used in order to construct undirected functional connectivity graphs at different frequency resolutions in Richiardi et al (2011). Also, pairwise correlations and mutual information have been used in order to build functional brain networks in various studies aiming to investigate the network differences between patients with Schizophrenia or Alzheimer's disease and healthy subjects (Lynall et al, 2010;Menon, 2011;Kurmukov et al, 2017). Others used partial correlation along with constrained linear regression to generate brain networks in Lee et al (2011).…”

Section: Introductionmentioning

confidence: 99%

Analyzing Complex Problem Solving by Dynamic Brain Networks

Alchihabi

Ekmekci

Kivilcim

et al. 2021

Front. Neuroinform.

View full text Add to dashboard Cite

Complex problem solving is a high level cognitive task of the human brain, which has been studied over the last decade. Tower of London (TOL) is a game that has been widely used to study complex problem solving. In this paper, we aim to explore the underlying cognitive network structure among anatomical regions of complex problem solving and its subtasks, namely planning and execution. A new computational model for estimating a brain network at each time instant of fMRI recordings is proposed. The suggested method models the brain network as an Artificial Neural Network, where the weights correspond to the relationships among the brain anatomic regions. The first step of the model is preprocessing that manages to decrease the spatial redundancy while increasing the temporal resolution of the fMRI recordings. Then, dynamic brain networks are estimated using the preprocessed fMRI signal to train the Artificial Neural Network. The properties of the estimated brain networks are studied in order to identify regions of interest, such as hubs and subgroups of densely connected brain regions. The representation power of the suggested brain network is shown by decoding the planning and execution subtasks of complex problem solving. Our findings are consistent with the previous results of experimental psychology. Furthermore, it is observed that there are more hubs during the planning phase compared to the execution phase, and the clusters are more strongly connected during planning compared to execution.

show abstract

Classifying Phenotypes Based on the Community Structure of Human Brain Networks

Cited by 10 publications

References 12 publications

Simultaneous Matrix Diagonalization for Structural Brain Networks Classification

Simultaneous Matrix Diagonalization for Structural Brain Networks Classification

Optimizing Connectivity-Driven Brain Parcellation Using Ensemble Clustering

Analyzing Complex Problem Solving by Dynamic Brain Networks

Contact Info

Product

Resources

About