A brain functional network analysis framework integrating multi-scale temporal feature fusion with adaptive high-order hypergraph convolution with adaptive high-order hypergraph convolution is proposed, providing methodological support for the early identification of MCI and the discovery of potential neuroimaging biomarkers.
Abstract
Mild cognitive impairment (MCI) is an important prodromal stage of Alzheimer's disease, and its early identification is critical for risk assessment and timely intervention. Resting-state functional magnetic resonance imaging (rs-fMRI) can noninvasively characterize brain functional activity and connectivity. However, most existing methods rely on static second-order functional connectivity, limiting their ability to capture dynamic coordination and high-order interactions among multiple brain regions. To address these limitations, we propose a brain functional network analysis framework integrating multi-scale temporal feature fusion with adaptive high-order hypergraph convolution. Specifically, the multi-scale temporal fusion module captures functional dynamics at different temporal resolutions, while the adaptive hypergraph convolutional network learns high-order associations among brain regions in an end-to-end manner. Spatiotemporal feature encoding is further incorporated to facilitate automatic MCI identification. The proposed framework was evaluated using rs-fMRI data from the ADNI dataset, with regional BOLD time series extracted based on the AAL atlas. Under five-fold cross-validation, the proposed method achieved an accuracy of 82.66%, a sensitivity of 82.07%, and a specificity of 83.07% on ADNI-2, while maintaining an accuracy of 81.50% on ADNI-3, outperforming existing methods on both datasets. Further analysis identified abnormal high-order coordination patterns involving the default mode network, limbic system, and hippocampus-related memory circuits in patients with MCI. These findings provide methodological support for the early identification of MCI and the discovery of potential neuroimaging biomarkers.
HyperAMS-Net is proposed, a deep learning framework for brain disorder classification using neuroimaging representations derived from resting-state functional MRI or structural MRI that integrates adaptive multi-scale convolution, hypergraph attention, spatial-channel attention, and adaptive feature fusion.
A reproducible and explainable deep learning framework, termed the multidimensional feature adaptive gating network (MDFAG-Net), for sMRI-based AD classification and neuroimaging analysis, which demonstrated competitive classification performance and outperformed representative two-dimensional, three-dimensional, and m...
Yi-Peng Zhou, Lin Zhu, Zhen-Qiao Liu et al.· Journal of Visualized Experi...· 0 citations
In worldwide, Alzheimer's Disease (AD) is one of the leading cause of death and requires earlier diagnosis for timely and effective treatment management. Neuroimaging, particularly Magnetic Resonance Imaging (MRI) provides a promising solution to detect the AD at earlier stages. Timely detection of variations in brain...
Revathi Mohan, Shital S. Mali, Poonguzhali Ilango et al.· Psychiatry research. Neuroim...· 0 citations
Resting-state functional magnetic resonance imaging (rs-fMRI) serves as a widely used non-invasive brain imaging tool for investigating neurological disorders through functional brain networks (FBN) modeling among brain regions of interest (ROIs). Deep learning frameworks, notably graph neural networks and Transformers...
Li-Na Zhou, Yue-Ying Zhou, Yun-Ling Ma et al.· IEEE journal of biomedical a...· 0 citations
A deep cross-modal structural correspondence framework is developed to model the relationship between macrostructural features derived from T1-weighted MRI and microstructural features derived from diffusion tensor imaging (DTI), suggesting that altered macrostructural-microstructural correspondence may represent an im...
Miao He, Qian-Ying Liu, Xinwei Que et al.· Journal of Physics, Conferen...· 0 citations
A hypergraph was employed to model high-order functional relations across brain regions, introducing algebraic connectivity ($a(\mathcal {G})$) for estimating the hyperedge weights, suggesting that $a(\mathcal {G})$ can be an effective approach for extracting the hyperedge weights, including important functional inform...
Giorgio Dolci, Silvia Saglia, Lorenza Brusini et al.· IEEE journal of biomedical a...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.