Smooth tracking of visual targets distinguishes lucid REM sleep dreaming and waking perception from imagination

Abstract

Humans are typically unable to engage in sustained smooth pursuit for imagined objects. However, it is unknown to what extent smooth tracking occurs for visual imagery during REM sleep dreaming. Here we examine smooth pursuit eye movements during tracking of a slow-moving visual target during lucid dreams in REM sleep. Highly similar smooth pursuit tracking was observed during both waking perception and lucid REM sleep dreaming, in contrast to the characteristically saccadic tracking observed during visuomotor imagination. Our findings suggest that, in this respect, the visual imagery that occurs during REM sleep is more similar to perception than imagination. The data also show that the neural circuitry of smooth pursuit can be driven by a visual percept in the absence of retinal stimulation and that specific voluntary shifts in the direction of experienced gaze within REM sleep dreams are accompanied by corresponding rotations of the physical eyes.

Fig. 1

Line tracking during lucid REM sleep dreaming in a single participant. a Enlarged section showing LRLR eye movement signals and smooth tracking task as recorded in the horizontal EOG (HEOG). Upon awakening, the subject reported becoming lucid in the dream, making a LRLR signal (1), fully extending his right thumb, and tracking his thumb nail as he slowly swung his arm horizontally from center to approximately 30° left, back through center to 30° right, and finally leftward back to center. While tracking to the right, he noticed moving his head slightly in the direction of tracking both rightward and leftward as he reversed motion back to the center (2). He marked the end of the smooth tracking task (estimated 10 s) with a second LRLR signal (3). Having completed the task, he spent the remainder of his lucid dream exploring the dream environment, waking approximately 60 s later. See Supplementary Note 1 “Report of line tracking task” for the report associated with this figure. b Six channels of physiological data (HEOG, vertical EOG (VEOG), skin potential response (SPR)), occipital EEG bandpass filtered for alpha (OZ (8–12 Hz)), H-reflex amplitude (a measure of spinal reflex excitability) (upward black triangles mark H-reflex STIM), and electromyogram (EMG)) are shown during an initial period of wakefulness, REM period onset (REMP onset), transition to lucid REM sleep and awakening. Suppression of EMG and H-reflex amplitude along with reduced alpha in EEG confirm that the participant remained in uninterrupted REM sleep during lucid dreaming, including LRLR signals and during completion of the slow tracking task. Lucid dream onset is localized by the autonomic nervous system surprise response (scalp skin potential response (SPR; black asterisk)) before the LRLR signal

Fig. 2

Classification of 1D horizontal meridian tracking for a single participant. Eye-tracking is shown during a waking perception, b lucid REM sleep dreaming and c visuomotor imagination conditions. Slow tracking during imagination showed intrusions of saccadic eye movements during the tracking movement, while waking perception and REM sleep dreaming showed predominately smooth pursuit eye movements. Bottom panels show velocity (degrees/s) as the derivative of the best-fit sine function plus saccades

Fig. 3

Pursuit ratio scores for perception, dreaming and imagination tracking. a Median values of normalized pursuit ratio scores in horizontal line tracking (Line tracking), horizontal (H comp circle), vertical (V Comp Circle) and joint (Circle tracking) components of circle tracking during imagination (I, red line and symbols), perception (P, blue line and symbols) and dreaming (D, green line and symbols). Symbols designate medians for individual subjects. Green stars to the right of D indicate pursuit ratio z-score values for the non-lucid REM sleep dream tracking trial. Given that the data were not normally distributed and contained varied numbers of repeated observations within subjects, data were analyzed using a linear mixed model and nonparametric bootstrapping (two-sided, paired test) was used to compare P (circle tracking: N = 5, trials = 28; line tracking: N = 2, trials = 3), D (circle tracking: N = 5, trials = 21; line tracking: N = 3, trials = 5) and I (circle tracking: N = 5, trials = 28; line tracking: N = 2, trials = 3) conditions (replications = 1), *P < 0.001, *P < 0.0001, ***P < 0.00001. Error bars show s.e.m. b Boxplot showing pursuit ratio z-scores during horizontal line tracking task for imagination (I), imagination in the dream (I in D), perception (P) and dreaming (D) conditions. The bottoms and tops of the boxes show the 25th and 75th percentiles (the lower and upper quartiles), respectively; the inner band shows the median; and the whiskers show the upper and lower quartiles ± 1.5 × the interquartile range (IQR). c Area under the ROC curve (AUC) for perception versus imagination (PvI) H (horizontal EOG) (thin blue solid line) and V (vertical EOG) (thin blue dotted line) and dreaming versus imagination (DvI) H (thick green solid line) and V (thick green dotted line) components of eye movements