# Classification of Mild Cognitive Impairment Based on Dynamic Functional Connectivity Using Spatio-Temporal Transformer

arXiv: https://arxiv.org/abs/2501.16409 · HTML: https://mlsanity.com/paper/2501.16409/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 27 Jan 2025.

## Built on by (most cited first, 5 of 5)

- [Core-Periphery Principle Guided State Space Model for Functional Connectome Classification](https://mlsanity.com/paper/2503.14655/) (2025)
- [BrainNet-MoE: Brain-Inspired Mixture-of-Experts Learning for Neurological Disease Identification](https://mlsanity.com/paper/2503.07640/) (2025)
- [Domain-Adaptive Diagnosis of Lewy Body Disease with Transferability Aware Transformer](https://mlsanity.com/paper/2507.08839/) (2025)
- [Bridging Brain Connectomes and Clinical Reports for Early Alzheimer's Disease Diagnosis](https://mlsanity.com/paper/2508.06565/) (2025)
- [Brain-Atlas-Guided Generative Counterfactual Attention for Explainable Cognitive Decline Diagnosis Using Multimodal Connectomes](https://mlsanity.com/paper/2606.01237/) (2026)

## Abstract (arXiv)

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 these feature representations by reducing the dependency on 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.