Exploring Structure–Function Coupled Brain Network Construction for Brain Disease-Aided Identification
DOI:
https://doi.org/10.54097/ske13794Keywords:
Brain disease-aided identification, Structural connectivity, Functional connectivity, Coupled brain network, Multimodal neuroimagingAbstract
Brain disorders are often associated with coordinated abnormalities in brain structure, functional interactions, and cross-regional connectivity patterns rather than isolated changes in single regions. Conventional single-modality brain network analysis usually captures only one side of these alterations, either from the perspective of anatomical organization or from the perspective of statistical functional coupling, and therefore may not fully characterize the complexity of disease-related network disruption. With the rapid development of multimodal neuroimaging techniques, especially structural magnetic resonance imaging (sMRI), diffusion tensor imaging (DTI), and functional magnetic resonance imaging (fMRI), increasing attention has been paid to how structural information and functional information can be jointly organized into a unified brain network representation. This paper discusses structure–function coupled brain network construction for brain disease-aided identification. First, the complementary roles of structural connectivity, functional connectivity, and morphology-related association information are analyzed. Second, several representative coupling paradigms are summarized, including structure-prior-constrained construction, graph-level cooperative fusion, and coupling strategies for time-varying functional connectivity. Their respective characteristics are compared in terms of representational completeness, topological stability, and interpretability. Finally, major open issues are discussed, including modality heterogeneity, bias in connectivity estimation, the reliability of dynamic coupling, and the biological interpretability of coupled graphs. The purpose of this paper is to examine multimodal brain network representation from the perspective of coupled graph construction rather than classification model design, and to provide a focused methodological reference for future studies on brain disease-aided identification.
Downloads
References
[1] Fotiadis Panagiotis, Parkes Linden, Davis Kathryn A, et al. Structure–function coupling in macroscale human brain networks [J]. Nature Reviews Neuroscience, 2024, 25(10): 688-704.
[2] Liu Wenxiong, Zuo Chao, Chen Li, et al. The whole-brain structural and functional connectome in Alzheimer’s disease spectrum: A multimodal Bayesian meta-analysis of graph theoretical characteristics [J]. Neuroscience & Biobehavioral Reviews, 2025, 174: 106174.
[3] Facca Massimiliano, Del Felice Alessandra, Bertoldo Alessandra. Multiscale and multimodal signatures of structure-function coupling variability across the human neocortex [J]. NeuroImage, 2024, 302: 120902.
[4] Lu Yinping, Wang Luyao, Murai Toshiya, et al. Detection of structural-functional coupling abnormalities using multimodal brain networks in Alzheimer’s disease: A comparison of three computational models [J]. NeuroImage: Clinical, 2025, 46: 103764.
[5] Billaud Charly Hugo Alexandre, Yu Junhong. Erratum: Structure–function coupling using fixel-based analysis and functional magnetic resonance imaging in Alzheimer’s disease and mild cognitive impairment [J]. Network Neuroscience, 2025, 9(4): i-ii.
[6] Pini Lorenzo, Brusini Lorenza, Griffa Alessandra, et al. Functional dynamic network connectivity differentiates biological patterns in the Alzheimer's disease continuum [J]. Neurobiology of disease, 2025, 208: 106866.
[7] Zheng Qiang, Nan Pengzhi, Cui Yongchao, et al. ConnectomeAE: Multimodal brain connectome-based dual-branch autoencoder and its application in the diagnosis of brain diseases [J]. Computer methods and programs in biomedicine, 2025, 267: 108801.
[8] Zhou Houliang, He Lifang, Chen Brian Y, et al. Multi-modal diagnosis of Alzheimer’s disease using interpretable graph convolutional networks [J]. IEEE Transactions on Medical Imaging, 2024, 44(1): 142-53.
[9] Liang Shengbin, Chen Tingting, Ma Jinfeng, et al. Identification of mild cognitive impairment using multimodal 3D imaging data and graph convolutional networks [J]. Physics in Medicine & Biology, 2024, 69(23): 235002.
[10] Feng Jianxin, Zhao Xinyu, Liu Zhiguo, et al. A multi-view multimodal deep learning framework for Alzheimer's disease diagnosis [J]. Frontiers in Neuroscience, 2025, 19: 1658776.
[11] Ali Shahzad, Piana Michele, Pardini Matteo, et al. Graph neural networks in Alzheimer's disease diagnosis: a review of unimodal and multimodal advances [J]. Frontiers in Neuroscience, 2025, 19: 1623141.
[12] Wang Na, Guo Lingfei, Gao Yian, et al. Disrupted Brain Structure–Function Coupling and Its Mediating Effects on the Associations Between Cerebral Small Vessel Disease Burden and Cognitive Dysfunction [J]. CNS Neuroscience & Therapeutics, 2025, 31(9): e70604.
[13] Zhang Rong, Sheng Jinhua, Zhang Qiao, et al. A review of multimodal fusion–based deep learning for Alzheimer’s disease [J]. Neuroscience, 2025, 576: 80-95.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 International Journal of Advanced Engineering and Technology Research
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
