Task-guided Spatiotemporal Network with Diffusion Augmentation for EEG-based Dementia Diagnosis and MMSE Prediction

TL;DR

This paper introduces a task-guided spatiotemporal neural network with diffusion-based data augmentation for improved EEG-based dementia diagnosis and MMSE score prediction, outperforming existing methods.

Contribution

The proposed TGSN model integrates spectral, spatiotemporal, and task-specific modules, along with diffusion augmentation, to enhance EEG analysis for dementia-related tasks.

Findings

Achieves 97.78% accuracy in AD/FTD classification, surpassing baselines by 16.39%.

Reduces MMSE prediction RMSE to 1.93, outperforming previous methods.

Demonstrates strong cross-dataset generalization on multiple EEG datasets.

Abstract

Patients with dementia typically exhibit cognitive impairment, which is routinely assessed using the Mini-Mental State Examination (MMSE). Concurrently, their underlying neurophysiological abnormalities are reflected in Electroencephalography (EEG), providing a basis for joint modeling. However, traditional multi-task approaches suffer from feature entanglement, which leads to inter-task interference when handling heterogeneous objectives.To address this challenge, we propose a task-guided spatiotemporal network (TGSN) with diffusion augmentation for EEG-based dementia diagnosis and MMSE prediction. Specifically, TGSN integrates a multi-band feature fusion module to capture complementary spectral information from EEG. Meanwhile, a pre-trained data augmentation module utilizing a diffusion process is introduced toincrease sample diversity. To model the complex spatiotemporal patterns of EEG, we propose a gated spatiotemporal attention module that captures long-range spatial dependencies and temporal dynamics. Moreover, we design a task-guided query module to achieve task-specific feature extraction, thereby mitigating task interference. The effectiveness of TGSN is evaluated on the XY02 dataset. Experimental results demonstrate that the proposed network outperforms several state-of-the-art methods, achieving classification accuracies of 97.78\% for Alzheimer's Disease (AD)/Frontotemporal Dementia (FTD) and 83.93\% for AD/FTD/Vascular Cognitive Impairment (VCI), which exceed the best baselines by 16.39\% and 8.28\%, respectively. In parallel, it reduces the RMSE for MMSE prediction to 1.93 and 2.38, achieving significant error reductions of 1.44 and 1.43 compared to the best baselines. Additionally, validation on the DS004504 dataset demonstrates strong cross-dataset generalization...