Rapid Eye Movements in Sleep Furnish a Unique Probe into the Ontogenetic and Phylogenetic Development of the Visual Brain: Implications for Autism Research

Abstract

With positron emission tomography followed by functional magnetic resonance imaging (fMRI), we demonstrated that rapid eye movements (REMs) in sleep are saccades that scan dream imagery. The brain "sees" essentially the same way while awake and while dreaming in REM sleep. As expected, an event-related fMRI study (events = REMs) showed activation time-locked to REMs in sleep ("REM-locked" activation) in the oculomotor circuit that controls saccadic eye movements and visual attention. More crucially, the fMRI study provided a series of unexpected findings, including REM-locked multisensory integration. REMs in sleep index the processing of endogenous visual information and the hierarchical generation of dream imagery through multisensory integration. The neural processes concurrent with REMs overlap extensively with those reported to be atypical in autism spectrum disorder (ASD). Studies on ASD have shown atypical visual processing and multisensory integration, emerging early in infancy and subsequently developing into autistic symptoms. MRI studies of infants at high risk for ASD are typically conducted during natural sleep. Simply timing REMs may improve the accuracy of early detection and identify markers for stratification in heterogeneous ASD patients. REMs serve as a task-free probe useful for studying both infants and animals, who cannot comply with conventional visual activation tasks. Note that REM-probe studies would be easier to implement in early infancy because REM sleep, which is markedly preponderant in the last trimester of pregnancy, is still pronounced in early infancy. The brain may practice seeing the world during REM sleep in utero before birth. The REM-probe controls the level of attention across both the lifespan and typical-atypical neurodevelopment. Longitudinal REM-probe studies may elucidate how the brain develops the ability to "see" and how this goes awry in autism. REMs in sleep may allow a straightforward comparison of animal and human data. REM-probe studies of animal models of autism have great potential. This narrative review puts forth every reason to believe that employing REMs as a probe into the development of the visual brain will have far-reaching implications.

Keywords: animal model; autism spectrum disorders; functional MRI; multisensory integration; neurodevelopment; rapid eye movements in sleep; saccadic eye movements; visual perception.

Figure 1

Peak rapid eye movement (REM)-locked activation in adults (functional magnetic resonance imaging study; n = 24, one-sample t-test).

Figure 2

Rapid eye movement (REM)-locked deactivation in the retrosplenial cortex in the left hemisphere (RSC-Lt) and peak activation in the adjacent RSC in the right hemisphere (RSC-Rt). (A) Group analysis (n = 24). In the upper row, an uncorrected p < 0.05 was used to show areas of undetectable or attenuated activation. In the bottom row, the threshold was raised to a very high level of corrected p < 0.00005 (T = 10.1) to show the REM-locked peak activation. The green lines pass the RSC-Rt peak activity point (Talairach coordinates: 4, –46, 12, t = 10.5) and show the location of the sagittal view. The blue line passes the corresponding location in the contralateral hemisphere and shows the location of the sagittal view. PCu/PCC, precuneus/posterior cingulate cortex; mPFC, medial prefrontal cortex; CeM, central medial thalamic nucleus. (B) Individual study (one of six that showed an REM-locked functional magnetic resonance imaging (fMRI) signal decrease in the RSC-Lt). Cluster size = 86 voxels (voxel size = 2 mm × 2 mm × 2 mm). Blue lines pass the maximum fMRI blood oxygenation level-dependent signal decrease voxel. The white line indicates the mid-sagittal plane. Uncorrected p < 0.05. REM-locked deactivation in RSC-Lt was replicated in 6 of 24 independent individual studies. Adapted with permission from Hong et al. [20,25].

Figure 3

Areas of undetectable or attenuated rapid eye movement (REM)-locked activation. (A,B) Areas of undetectable or attenuated REM-locked activation correspond closely to the core of the default mode network (DMN) identified by a large-scale meta-analysis. An uncorrected p-value of <0.05 was used to identify areas of undetectable or attenuated activation in group-level random effects analysis (n = 24; one-sample t-test). The top and bottom parts of the brain are out of the field of view and thus truncated. (A) The precuneus/posterior cingulate cortex (PCu/PCC) and medical prefrontal cortex (mPFC) in the left and right hemispheres. Crosshair at the retrosplenial cortex in the right hemisphere (RSC-Rt) (Talairach coordinates: 4, −46, 12) and at the corresponding location in the contralateral hemisphere (Talairach coordinates: −4, −46, 12). The pocket of no activation in the retrosplenial cortex in the left hemisphere (RSC-Lt) contrasts dramatically with the adjacent robust activation in the RSC-Rt (t = 10.5). (B) Effects of REM-locked activation projected onto a surface rendering of a template brain. Note the absence of activation in the inferior parietal cortex (IPC) in the right hemisphere: there was attenuated activation of the IPC in the left hemisphere and bilateral deactivation in the inferior lateral temporal cortex and inferior frontal gyrus. (A,B) Adapted with permission from Hong et al. [21]. (C) Adapted with permission from the large-scale meta-analyses of Andrews-Hanna et al. [85]. DMN core (yellow), dorsal medial subsystem (blue), and medial temporal subsystem (green).