Dataset Information

Learning dynamic graph embeddings for accurate detection of cognitive state changes in functional brain networks.

ABSTRACT: Mounting evidence shows that brain functions and cognitive states are dynamically changing even in the resting state rather than remaining at a single constant state. Due to the relatively small changes in BOLD (blood-oxygen-level-dependent) signals across tasks, it is difficult to detect the change of cognitive status without requiring prior knowledge of the experimental design. To address this challenge, we present a dynamic graph learning approach to generate an ensemble of subject-specific dynamic graph embeddings, which allows us to use brain networks to disentangle cognitive events more accurately than using raw BOLD signals. The backbone of our method is essentially a representation learning process for projecting BOLD signals into a latent vertex-temporal domain with the greater biological underpinning of brain activities. Specifically, the learned representation domain is jointly formed by (1) a set of harmonic waves that govern the topology of whole-brain functional connectivities and (2) a set of Fourier bases that characterize the temporal dynamics of functional changes. In this regard, our dynamic graph embeddings provide a new methodology to investigate how these self-organized functional fluctuation patterns oscillate along with the evolving cognitive status. We have evaluated our proposed method on both simulated data and working memory task-based fMRI datasets, where our dynamic graph embeddings achieve higher accuracy in detecting multiple cognitive states than other state-of-the-art methods.

SUBMITTER: Lin Y

PROVIDER: S-EPMC8091140 | biostudies-literature | 2021 Apr

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Learning dynamic graph embeddings for accurate detection of cognitive state changes in functional brain networks.

Lin Yi Y Yang Defu D Hou Jia J Yan Chengang C Kim Minjeong M Laurienti Paul J PJ Wu Guorong G

NeuroImage 20210202

Mounting evidence shows that brain functions and cognitive states are dynamically changing even in the resting state rather than remaining at a single constant state. Due to the relatively small changes in BOLD (blood-oxygen-level-dependent) signals across tasks, it is difficult to detect the change of cognitive status without requiring prior knowledge of the experimental design. To address this challenge, we present a dynamic graph learning approach to generate an ensemble of subject-specific d ...[more]

PMID: 33545348

Similar Datasets

Project description:Dealing with relational data always required significant computational resources, domain expertise and task-dependent feature engineering to incorporate structural information into a predictive model. Nowadays, a family of automated graph feature engineering techniques has been proposed in different streams of literature. So-called graph embeddings provide a powerful tool to construct vectorized feature spaces for graphs and their components, such as nodes, edges and subgraphs under preserving inner graph properties. Using the constructed feature spaces, many machine learning problems on graphs can be solved via standard frameworks suitable for vectorized feature representation. Our survey aims to describe the core concepts of graph embeddings and provide several taxonomies for their description. First, we start with the methodological approach and extract three types of graph embedding models based on matrix factorization, random-walks and deep learning approaches. Next, we describe how different types of networks impact the ability of models to incorporate structural and attributed data into a unified embedding. Going further, we perform a thorough evaluation of graph embedding applications to machine learning problems on graphs, among which are node classification, link prediction, clustering, visualization, compression, and a family of the whole graph embedding algorithms suitable for graph classification, similarity and alignment problems. Finally, we overview the existing applications of graph embeddings to computer science domains, formulate open problems and provide experiment results, explaining how different networks properties result in graph embeddings quality in the four classic machine learning problems on graphs, such as node classification, link prediction, clustering and graph visualization. As a result, our survey covers a new rapidly growing field of network feature engineering, presents an in-depth analysis of models based on network types, and overviews a wide range of applications to machine learning problems on graphs.

Project description:In accordance with the physiological networks that underlie it, human cognition is characterized by both the segregation and interdependence of a number of cognitive domains. Cognition itself, therefore, can be conceptualized as a network of functions. A network approach to cognition has previously revealed topological differences in cognitive profiles between healthy and disease populations. The present study, therefore, used graph theory to determine variation in cognitive profiles across healthy aging and cognitive impairment. A comprehensive neuropsychological test battery was administered to 415 participants. This included three groups of healthy adults aged 18-39 (n = 75), 40-64 (n = 75), and 65 and over (n = 70) and three patient groups with either amnestic (n = 75) or non-amnestic (n = 60) mild cognitive impairment or Alzheimer's type dementia (n = 60). For each group, cognitive networks were created reflective of test-to-test covariance, in which nodes represented cognitive tests and edges reflected statistical inter-nodal significance (p < 0.05). Network metrics were derived using the Brain Connectivity Toolbox. Network-wide clustering, local efficiency and global efficiency of nodes showed linear differences across the stages of aging, being significantly higher among older adults when compared with younger groups. Among patients, these metrics were significantly higher again when compared with healthy older controls. Conversely, average betweenness centralities were highest in middle-aged participants and lower among older adults and patients. In particular, compared with controls, patients demonstrated a distinct lack of centrality in the domains of semantic processing and abstract reasoning. Network composition in the amnestic mild cognitive impairment group was similar to the network of Alzheimer's dementia patients. Using graph theoretical methods, this study demonstrates that the composition of cognitive networks may be measurably altered by the aging process and differentially impacted by pathological cognitive impairment. Network alterations characteristic of Alzheimer's disease in particular may occur early and be distinct from alterations associated with differing types of cognitive impairment. A shift in centrality between domains may be particularly relevant in identifying cognitive profiles indicative of underlying disease. Such techniques may contribute to the future development of more sophisticated diagnostic tools for neurodegenerative disease.

Dataset Information

Learning dynamic graph embeddings for accurate detection of cognitive state changes in functional brain networks.

Publications

Learning dynamic graph embeddings for accurate detection of cognitive state changes in functional brain networks.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets