Abstract
Dynamic functional connectivity (dFC) using resting-state functional magnetic resonance imaging (rs-fMRI) is an advanced technique for capturing the dynamic changes of neural activities and can be very useful in the studies of brain diseases such as Alzheimer's disease (AD). Yet, existing studies have not fully leveraged the sequential information embedded within dFC that can potentially provide valuable information when identifying brain conditions. In this paper, we propose a novel framework that jointly learns the embedding of both spatial and temporal information within dFC based on the transformer architecture. Specifically, we first construct dFC networks from rs-fMRI data through a sliding window strategy. Then, we simultaneously employ a temporal block and a spatial block to capture higher-order representations of dynamic spatio-temporal dependencies, via mapping them into an efficient fused feature representation. To further enhance the robustness of this feature representations by reducing the dependency of labeled data, we also introduce a contrastive learning strategy to manipulate different brain states. Experimental results on 345 subjects with 570 scans from the Alzheimer's Disease Neuroimaging Initiative (ADNI) demonstrate the superiority of our proposed method for MCI (Mild Cognitive Impairment, the prodromal stage of AD) prediction, highlighting its potential for early identification of AD. The code is available at: https://github.com/Nancy-Zhang-0/MCI_dFC_STT.
Recommended Citation
J. Zhang and Y. Lyu and X. Yu and L. Zhang and C. Cao and T. Chen and M. Chen and Y. Zhuang and T. Liu and D. Zhu, "Classiffication Of Mild Cognitive Impairment Based On Dynamic Functional Connectivity Using Spatio-Temporal Transformer," Proceedings International Symposium on Biomedical Imaging, Institute of Electrical and Electronics Engineers, Jan 2025.
The definitive version is available at https://doi.org/10.1109/ISBI60581.2025.10980922
Department(s)
Computer Science
Keywords and Phrases
contrastive learning; deep learning; Dynamic functional connectivity; spatial-temporal transformer
International Standard Serial Number (ISSN)
1945-8452; 1945-7928
Document Type
Article - Conference proceedings
Document Version
Citation
File Type
text
Language(s)
English
Rights
© 2025 Institute of Electrical and Electronics Engineers, All rights reserved.
Publication Date
01 Jan 2025
Comments
National Institutes of Health, Grant R01AG075582