Generative AI Enables EEG Super-Resolution via Spatio-Temporal Adaptive Diffusion Learning

2024-07-03

AI Summary

To address the limited spatial resolution of low-density EEG (≤64 channels) and the high cost and clinical impracticality of high-density EEG (256 channels), this paper introduces, for the first time, diffusion modeling to EEG super-resolution. We propose the Spatio-Temporal Adaptive Diffusion (STAD) model, which innovatively integrates a spatio-temporal conditional module with a multi-scale Transformer-based denoising module, enabling subject-specific modeling and reverse generative inference. Quantitatively, STAD consistently outperforms existing methods across multiple metrics. Critically, the synthesized 256-channel EEG signals achieve classification and source localization performance comparable to ground-truth high-density recordings, demonstrating strong clinical utility. This work establishes a novel paradigm for low-cost, high-fidelity spatial enhancement of EEG data.

Technology Category

• Computer Vision: Diffusion Models for Vision
• Cognitive Modeling & Cognitive Systems: Neural Spike Coding
• Machine Learning: Mixture of Experts (MoE)

Application Category

• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Web Mining and Content Analysis: Content-based information diffusion

Abstract

Electroencephalogram (EEG) technology, particularly high-density EEG (HD EEG) devices, are widely used in fields such as neuroscience. HD EEG devices improve the spatial resolution of EEG by placing more electrodes on the scalp, which meet the requirements of clinical diagnostic applications such as epilepsy focus localization. However, this technique faces challenges, such as high acquisition costs and limited usage scenarios. In this paper, spatio-temporal adaptive diffusion models (STAD) are proposed to pioneer the use of diffusion models for achieving spatial SR reconstruction from low-resolution (LR, 64 channels or fewer) EEG to high-resolution (HR, 256 channels) EEG. Specifically, a spatio-temporal condition module is designed to extract the spatio-temporal features of LR EEG, which then used as conditional inputs to direct the reverse denoising process. Additionally, a multi-scale Transformer denoising module is constructed to leverage multi-scale convolution blocks and cross-attention-based diffusion Transformer blocks for conditional guidance to generate subject-adaptive SR EEG. Experimental results demonstrate that the STAD significantly enhances the spatial resolution of LR EEG and quantitatively outperforms existing methods. Furthermore, STAD demonstrate their value by applying synthetic SR EEG to classification and source localization tasks, indicating their potential to Substantially boost the spatial resolution of EEG.

Problem

• Enhances EEG spatial resolution via diffusion models
• Reduces high-density EEG acquisition costs effectively
• Improves EEG for clinical diagnostic applications

Innovation

• Adaptive diffusion models enhance EEG resolution
• Multi-scale Transformer for denoising EEG data
• Spatio-temporal features guide super-resolution reconstruction