Neuro-Eye: Decoding of High-Temporal Resolution Eye Movements via Functional Magnetic Resonance Imaging

Eye movements reflect changes in human behavior and thought to some extent, but many functional magnetic resonance imaging (fMRI) studies are limited by equipment and do not perform eye movement tracking. Recently, a deep learning method has been proposed for the regression problem of a single volume's gaze point. In this paper, we propose an end-to-end pipeline called Neuro-Eye, which includes eye signal extraction, and eye-movement behavior recognition from fMRI scanning slices. The method was tested on the human connectome project (HCP) fMRI dataset and achieved promising results. The visualization analysis revealed prominent areas in the eye balls and adjacent anterior-posterior regions, indicating the presence of features associated with eye movement artifacts. Furthermore, the Neuro-Eye pipeline shows great potential for widespread utilization in future cognitive science and clinical research studies.