ORIGINAL RESEARCH article
Front. Phys.
Sec. Social Physics
Volume 13 - 2025 | doi: 10.3389/fphy.2025.1665288
Complex-valued Brain Networks for Neurodegenerative Disease Diagnosis via Component-Aware Feature Fusion
Provisionally accepted
Jiejie Fan*
Xiaojuan Ban- University of Science and Technology Beijing, Beijing, China
Select one of your emails
You have multiple emails registered with Frontiers:
Notify me on publication
Please enter your email address:
If you already have an account, please login
You don't have a Frontiers account ? You can register here
Recent advancements in brain network analysis have significantly enhanced the diagnosis of neurodegenerative diseases; however, most existing studies rely on single-frequency EEG representations and neglect the joint modeling of real and imaginary connectivity in the frequency domain. This paper proposes a novel complex-valued brain network framework for diagnosis through component-aware feature fusion. First, frequency-domain filtering transforms EEG signals into complex-valued representations, while a Complex-valued Brain Network Construction (CBNC) module with multi-scale real and imaginary convolutions captures dynamic inter-channel interactions. Then, a Component-Aware Feature Fusion (CAFF) mechanism integrates multicomponent features by modeling cross-component semantic consistency, resulting in more expressive and physiologically meaningful brain networks. Extensive experiments on two benchmark datasets demonstrate that the proposed method achieves superior performance, with an accuracy of 91.59% for mild cognitive impairment detection and 99.99% for stroke detection, consistently outperforming state-of-the-art methods in both accuracy and robustness.
Keywords: Electroencephalogram, Multi-component, Complex-valued learning, Neurodegenerative Diseases, brain networks
Received: 14 Jul 2025; Accepted: 19 Aug 2025.
Copyright: © 2025 Fan and Ban. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) or licensor are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
* Correspondence: Jiejie Fan, University of Science and Technology Beijing, Beijing, China
Disclaimer: All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article or claim that may be made by its manufacturer is not guaranteed or endorsed by the publisher.