Pupil dynamics-derived sleep stage classification of a head-fixed mouse using a recurrent neural network

The standard method for sleep state classification is thresholding amplitudes of electroencephalography (EEG) and electromyography (EMG), followed by an experts manual correction. Although popular, the method entails some shortcomings: 1) the time-consuming manual correction by human experts is sometimes a bottleneck hindering sleep studies; 2) EEG electrodes on the skull interfere with wide-field imaging of the cortical activity of a head-fixed mouse under a microscope; 3) invasive surgery to fix the electrodes on the thin skull of a mouse risks brain tissue injury; and 4) metal electrodes for EEG and EMG are difficult to apply to some experiment apparatus such as that for functional magnetic resonance imaging. To overcome these shortcomings, we propose a pupil dynamics-based vigilance state classification for a head-fixed mouse using a long short-term memory (LSTM) model, a variant of recurrent neural networks, for multi-class labeling of NREM, REM, and WAKE states. For supervisory hypnography, EEG and EMG recording were performed for a head-fixed mouse, combined with left eye pupillometry using a USB camera and a markerless tracking toolbox, DeepLabCut. Our open-source LSTM model with feature inputs of pupil diameter, location, velocity, and eyelid opening for 10 s at a 10 Hz sampling rate achieved vigilance state estimation with a higher classification performance (macro F1 score, 0.77; accuracy, 86%) than a feed forward neural network. Findings from diverse pupillary dynamics implied subdivision of a vigilance state defined by EEG and EMG. Pupil dynamics-based hypnography can expand the scope of alternatives for sleep stage scoring of head fixed mice.