Decoupling Time and Space: A Temporally Conditioned Refinement for EEG Source Imaging

2026-10-05

AI Summary

This study addresses the ill-posed nature of spatial inversion in EEG source imaging and the inherent trade-off between temporal modeling capability and inference cost. To this end, we propose a dual-stream decoupled framework that explicitly separates spatiotemporal processing to reduce computational overhead. Methodologically, a Transformer-based temporal encoder extracts global dynamic conditions, while a factorized spatiotemporal attention mechanism preserves sensor-level features. A source-space refiner then enables high-fidelity, time-step-wise reconstruction. Experimental results demonstrate that the proposed model significantly outperforms baselines under challenging high-noise, multi-source scenarios on synthetic data. Furthermore, it successfully transfers to real-world EEG age-group decoding tasks, achieving synergistic improvements in both accuracy and efficiency.

Abstract

Electroencephalography (EEG) offers millisecond temporal resolution, but inferring underlying neural sources is a severely ill-posed spatial inverse problem. While deep learning has advanced spatial reconstruction, current architectures face a critical dilemma: frame-by-frame models discard vital temporal context, whereas full 4D spatiotemporal networks introduce an architectural trade-off between reconstruction accuracy and inference cost. We propose a novel two-stream framework that explicitly decouples global temporal representation learning from per-time-point spatial refinement. A Transformer-based Temporal Condition Encoder processes the entire EEG sequence via factorized spatiotemporal attention, retaining sensor-resolved features. A fixed inverse then maps these features into source-indexed conditioning for a per-timestep Source-Space Transformer or volumetric convolutional refiner. Extensive evaluations on realistic synthetic data demonstrate that this temporal prior dramatically improves spatial localization, outperforming classical and spatiotemporal baselines, particularly in high-noise and multi-source regimes. Training across diverse leadfields and explicit operator mismatches improves transfer to unseen head geometries and brings template-based reconstruction closer to subject-specific inversion. Furthermore, we apply the model trained only on synthetic EEG data to real-world EEG. A logistic regressor fit on source power differences in eyes-open, eyes-closed conditions successfully decodes age groups.

Problem

• EEG source imaging
• spatial inverse problem
• spatiotemporal trade-off
• temporal context
• generalization

Innovation

• EEG Source Imaging
• Spatiotemporal Decoupling
• Transformer
• Temporal Conditioning
• Domain Generalization