Brain Function Analysis Of Insomnia Disorder Based On Hypergraph Combined With Deep Learning
Pages 216 - 224
Abstract
Insomnia (ID) is a chronic sleep disorder with a high prevalence and a heavy socioeconomic burden. Despite extensive research, the relationship between ID and brain activity is complex and the exact etiology is difficult to determine. In this study, we propose a prediction framework for ID categorization. First, a higher-order functional connectivity network was constructed using hypergraphs to capture higher-order interactions between multiple brain ROIs. Then, the high- and low-order functional connectivity networks are fused through a self-attentive mechanism to utilize the complementary information of the features. Finally, a spatio-temporally structured adaptive graph convolutional network was used to classify and predict the ID dataset and the normal control (NC) group collected from Qingdao University Hospital with accuracy and AUC of 83.3% and 83.5%, respectively. Compared with other methods, our method shows excellent performance and provides a promising direction for the development of effective diagnostic methods for insomnia.
References
[1]
Yan CQ, Wang X, Huo JW, Abnormal Global Brain Functional Connectivity in Primary Insomnia Patients: A Resting-State Functional MRI Study. Front Neurol. 2018;9:856. Published 2018 Nov 2.
[2]
Huang S, Zhou F, Jiang J, Regional impairment of intrinsic functional connectivity strength in patients with chronic primary insomnia. Neuropsychiatr Dis Treat. 2017;13:1449-1462. Published 2017 Jun 6.
[3]
Zhao F, Zhang H, Rekik I, An Z, Shen D. Diagnosis of Autism Spectrum Disorders Using Multi-Level High-Order Functional Networks Derived From Resting-State Functional MRI. Front Hum Neurosci. 2018;12:184. Published 2018 May 14. .
[4]
Zhao, F., Chen, Z., Rekik, I., Lee, S. W., & Shen, D. (2020). Diagnosis of Autism Spectrum Disorder Using Central-Moment Features From Low- and High-Order Dynamic Resting-State Functional Connectivity Networks. Frontiers in neuroscience, 14, 258.
[5]
Ji, Y., Zhang, Y., Shi, H., Jiao, Z., Wang, S. H., & Wang, C. (2021). Constructing Dynamic Brain Functional Networks via Hyper-Graph Manifold Regularization for Mild Cognitive Impairment Classification. Frontiers in neuroscience, 15, 669345.
[6]
Ji, J., Ren, Y., & Lei, M. (2022). FC–HAT: Hypergraph attention network for functional brain network classification. Information Sciences, 608, 1301-1316.
[7]
Yang, J., Wang, F., Li, Z., Yang, Z., Dong, X., & Han, Q. (2023). Constructing high-order functional networks based on hypergraph for diagnosis of autism spectrum disorders. Frontiers in neuroscience, 17, 1257982.
[8]
Ktena S I, Parisot S, Ferrante E, Metric learning with spectral graph convolutions on brain connectivity networks[J]. Neuroimage, 2018, 169: 431-442.
[9]
Gopinath K, Desrosiers C, Lombaert H. Adaptive graph convolution pooling for brain surface analysis[C]. International Conference on Information Processing in Medical Imaging, 2019: 86-98.
[10]
Li X, Zhou Y, Dvornek N, BrainGNN: Interpretable Brain Graph Neural Network for fMRI Analysis[J]. Med Image Anal, 2021, 74: 102233.
[11]
Azevedo T, Campbell A, Romero-Garcia R, A deep graph neural network architecture 15 for modelling spatio-temporal dynamics in resting-state functional MRI data[J]. Med Image Anal, 2022, 79: 102471.
[12]
Zhao, F., Li, N., Pan, H., Chen, X., Li, Y., Zhang, H., ... & Cheng, D. (2022). Multi-view feature enhancement based on self-attention mechanism graph convolutional network for autism spectrum disorder diagnosis. Frontiers in human neuroscience, 16, 918969.
[13]
Li Z, Chen R, Guan M, Disrupted brain network topology in chronic insomnia disorder: A resting-state fMRI study[J]. NeuroImage: Clinical, 2018, 18: 178-185.
[14]
Liu X, Zheng J, Liu B-X, Altered connection properties of important network hubs may be neural risk factors for individuals with primary insomnia[J]. Scientific Reports, 2018, 8(1): 1- 13.
[15]
Huang S, Zhou F, Jiang J, Regional impairment of intrinsic functional connectivity strength in patients with chronic primary insomnia[J]. Neuropsychiatr Dis Treat, 2017, 13: 1449- 1462.
[16]
Li C, Mai Y, Dong M, Multivariate Pattern Classification of Primary Insomnia Using Three Types of Functional Connectivity Features[J]. Front Neurol, 2019, 10: 1037.
[17]
Zhu Y, Zhao X, Yin H, Functional connectivity density abnormalities and anxiety in primary insomnia patients[J]. Brain Imaging and Behavior, 2021, 15(1): 114-121.
[18]
Wei Y, Leerssen J, Wassing R, Reduced dynamic functional connectivity between salience and executive brain networks in insomnia disorder[J]. J Sleep Res, 2020, 29(2): e12953.
[19]
Leerssen J, Wassing R, Ramautar J R, Increased hippocampal-prefrontal functional connectivity in insomnia[J]. Neurobiol Learn Mem, 2019, 160: 144-150.
[20]
Pang R, Zhan Y, Zhang Y, Aberrant Functional Connectivity Architecture in Participants with Chronic Insomnia Disorder Accompanying Cognitive Dysfunction: A Whole-Brain, Data-Driven Analysis[J]. Front Neurosci, 2017, 11: 259.
[21]
Zhou F, Zhao Y, Huang M, Disrupted interhemispheric functional connectivity in chronic insomnia disorder: a resting-state fMRI study[J]. Neuropsychiatr Dis Treat, 2018, 14: 1229-1240.
Index Terms
- Brain Function Analysis Of Insomnia Disorder Based On Hypergraph Combined With Deep Learning
Recommendations
Semi-supervised Learning with Graph Convolutional Networks Based on Hypergraph
AbstractGraph convolutional networks (GCNs), which rely on graph structures to aggregate information of neighbors to output robust node embeddings, have been becoming a popular model for semi-supervised classification tasks. However, most existing GCNs ...
Deep Graph Similarity Learning for Brain Data Analysis
CIKM '19: Proceedings of the 28th ACM International Conference on Information and Knowledge ManagementWe propose an end-to-end graph similarity learning framework called Higher-order Siamese GCN for multi-subject fMRI data analysis. The proposed framework learns the brain network representations via a supervised metric-based approach with siamese neural ...
The Ramsey number for hypergraph cycles I
Let Cn denote the 3-uniform hypergraph loose cycle, that is the hypergraph with vertices v1.....,vn and edges v1v2v3, v3v4v5, v5v6v7,.....,vn-1vnv1. We prove that every red-blue colouring of the edges of the complete 3-uniform hypergraph with N vertices ...
Comments
Please enable JavaScript to view thecomments powered by Disqus.Information & Contributors
Information
Published In
July 2024
353 pages
ISBN:9798400717192
DOI:10.1145/3686490
Copyright © 2024 ACM.
Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than the author(s) must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected].
Publisher
Association for Computing Machinery
New York, NY, United States
Publication History
Published: 11 October 2024
Check for updates
Author Tags
Qualifiers
- Research-article
- Research
- Refereed limited
Conference
SPML 2024
SPML 2024: 2024 7th International Conference on Signal Processing and Machine Learning
July 12 - 14, 2024
Qingdao, China
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 21Total Downloads
- Downloads (Last 12 months)21
- Downloads (Last 6 weeks)4
Reflects downloads up to 01 Mar 2025
Other Metrics
Citations
View Options
Login options
Check if you have access through your login credentials or your institution to get full access on this article.
Sign inFull Access
View options
View or Download as a PDF file.
PDFeReader
View online with eReader.
eReaderHTML Format
View this article in HTML Format.
HTML Format