Graph Metrics Based Brain Hypergraph Learning in Schizophrenia Patients

Hypergraphs have been widely used in the analysis of brain network because of its ability to capture high order interaction among multiple brain regions. Most of the recent work is based on sparse representation to construct hypergraph, in which vertices represent brain regions. This kind of approaches is at the subject-level and does not take account of topological properties. To overcome this limitation, we propose a new method to identify biomarkers helpful to the diagnosis of brain disease. Firstly, we construct a graph-based network for each subject and derive graph metrics. Then we construct a group-level hypergraph based on similarities of topological properties. Graph metrics are introduced to guide the construction of hypergraph. We obtain the weights of each hyperedges by hypergraph learning. We evaluate our framework on the COBRE dataset and achieve good classification accuracy by merely selecting a small amount of features. Moreover, we find that the hyperedges with larger weights and smaller weights show good discriminability. Our method extends the framework of hypergraph learning and reveals the differences caused by the disease at the group-level.

• Publication year

  2022

• Venue

  ACM Cloud and Autonomic Computing Conference

• Publication date

  2022-11-25

• Fields of study

  Not labeled

• Identifiers
  DOI 10.1109/CAC57257.2022.10055125
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Multi-Band Brain Network Analysis for Functional Neuroimaging Biomarker Identification

  2021cited by this paper
• Introducing Hypergraph Signal Processing: Theoretical Foundation and Practical Applications

  2019cited by this paper
• Multi-Hypergraph Learning-Based Brain Functional Connectivity Analysis in fMRI Data

  2019cited by this paper
• Multimodal hyper‐connectivity of functional networks using functionally‐weighted LASSO for MCI classification

  2019cited by this paper
• Resting-State Brain Functional Hyper-Network Construction Based on Elastic Net and Group Lasso Methods

  2018cited by this paper
• Identifying disease-related subnetwork connectome biomarkers by sparse hypergraph learning

  2018cited by this paper
• Graph Signal Processing: Overview, Challenges, and Applications

  2017cited by this paper
• Quantifying the Interaction and Contribution of Multiple Datasets in Fusion: Application to the Detection of Schizophrenia

  2017cited by this paper
• Hyper-connectivity of functional networks for brain disease diagnosis

  2016cited by this paper
• Diagnostic and Statistical Manual of Mental Disorders (DSM-5)

  2015cited by this paper
• Group-constrained sparse fMRI connectivity modeling for mild cognitive impairment identification

  2013cited by this paper
• Behavioral / Systems / Cognitive Functional Connectivity and Brain Networks in Schizophrenia

  2010cited by this paper
• Complex brain networks: graph theoretical analysis of structural and functional systems

  2009cited by this paper
• Disrupted small-world networks in schizophrenia.

  2008cited by this paper

• No citing papers are available for this paper.