Multisensory Interactions between Vestibular, Visual and Somatosensory Signals

Introduction

Perception frequently involves interactions between sensory modalities. Sensory signals presented simultaneously in more than one sensory channel tend to be detected more accurately and at lower thresholds than the same signals presented individually [1]. For example, neural responses are enhanced when stimuli in the different sensory modalities are spatially and temporally congruent [2,3,4,5]. Some of these responses may reflect subadditive or superadditive interactions between individual modalities, although the nonlinearity of multisensory responses remains controversial [6,7,8].

Vestibular input contributes to several complex brain functions through its interactions with inputs from other senses. Consistent with this view, vestibular inputs do not project to any primary unimodal cortex. Rather electrophysiological studies have identified a widespread vestibular network whose core area is the parieto-insular vestibular cortex (PIVC) [9,10]. The human homologue of the primate PIVC may not be a single area, so much as a distributed set of regions including the posterior and anterior insula, temporoparietal junction, superior temporal gyrus, inferior parietal lobule, and somatosensory cortices [11,12].

Multisensory neurons coding for visual, vestibular and somatosensory stimuli have been found in the macaque ventral intraparietal area (VIP) [13]. This area is considered homologous to human vestibular areas in the posterior parietal cortex [14]. Evidence suggests that analogous multisensory interactions occur in human perception. For instance, several studies described a convergence between vestibular and visual signals for perception of self-motion [15,16,17].

Multisensory interactions also occur between vestibular and somatosensory signals. Anatomical projections subserving these interactions were inferred from the extensive activation of somatosensory cortices following vestibular stimulation [18]. However, the impact of these interactions for functional perception remains unclear. Vestibular stimulation improves low-level somatosensory perception, such as detection of near-threshold stimuli [19,20,21]. Whereas vestibular-visual interactions can be read as an intermodal combination of cues for a single underlying perceptual dimension of heading direction, the common perceptual content underlying vestibular-somatosensory interactions seems less obvious.

In addition, the behavioural effect of a multisensory interaction depends on the architecture of the projections between the different brain areas involved. For example, Haggard et al. [22] distinguished between multisensory convergence, multisensory modulation, and multisensory transformation, all of which could potentially produce changes in perception. Multisensory convergence involves bimodal neurons which receive inputs from two or more modalities. The visual-vestibular perception of heading discussed above represents an example of multisensory convergence [15,16,17]. The second form of multisensory interaction is modulation by one sensory signal of the gain in a second sensory pathway. The third involves transformation of information from one modality into the spatial reference frame of another. Such transformations involve a change in spatial coding, but may not produce any overall change in neural firing rate. In addition, several studies have reported vestibular-induced changes in activations of classically unimodal cortex. Since multimodal neurons are relatively infrequent in these areas (but see [23]) these effects presumably reflect modulation of processing in one modality by another, rather than multisensory convergence of information. For instance, inhibitory visual-vestibular interactions are fundamental in maintaining and controlling gaze [24]. Accordingly, PET studies using artificial vestibular stimulation demonstrated not only an activation of the PIVC but also a decrease in rCBF of the visual cortex [25,26]. Similarly, Bense and co-workers [27] showed bilateral deactivation of the occipital visual cortex induced by vestibular stimulation.

The multiply-connected aspect of vestibular cortical anatomy led us to investigate whether vestibular signals could participate in multi-way interactions with visual and somatosensory inputs. For example, visual and vestibular signals might independently modulate somatosensation. Alternatively, vestibular signals might interact with the effects of vision on somatosensation, by facilitating or suppressing a visual signal that in turn influences somatosensation. A marker of the former arrangement would be that somatosensory effects of combined visual and vestibular stimulation should be predictable from independent effects of vision, and of vestibular stimulation on somatosensation. Conversely, a marker of the latter arrangement would be that results of trimodal stimulation differ from simple superposition of vestibular-somatosensory and visual-somatosensory response patterns.

We investigated bimodal and trimodal interactions between vestibular, visual and somatosensory systems. We used a recently-developed technique that artificially stimulates the vestibular system by a gradual non-contact thermal stimulus of the horizontal semicircular canals via the external auditory canal (Near infrared Caloric Vestibular Stimulation, NirCVS) [28,29,30,31]. A somatosensory detection task was administered immediately after NirCVS. Participants were instructed to detect near-threshold somatosensory stimuli (i.e. digital nerve shocks) that occurred on the left index finger in one half of experimental trials (stimulus present trials). In the other half of the trials the somatosensory stimulus was not present (stimulus absent trials). A simultaneous visual signal occurred close to the finger in half of all trials at random. The visual signal therefore was irrelevant to the participant’s somatosensory detection task. In previous studies, such visual signals were reported to increase somatosensory sensitivity, and also to influence response bias. Specifically, visual signals increased the likelihood of a “yes” response, regardless of whether the somatosensory stimulus was present or not [32,33,34,35]. Based on previous results, we therefore hypothesized an enhancement in somatosensory sensitivity in both bimodal visual-somatosensory and vestibular-somatosensory conditions.

Simple schematic models of interactions between different sensory systems may be able to generate predictions about somatosensory detection performance. We wanted to compare patterns of interaction that (a) differ strongly in terms of implied connectivity between the different sensory areas, and (b) make plausibly different predictions about likely effects on somatosensory sensitivity. These constraints led us to focus on three specific patterns. First, the three sensory events might combine along the lines of other reported multisensory interactions [1,2,3,4,5], resulting in the superadditive multisensory enhancement of somatosensory sensitivity (Fig 1A). This account predicts a trimodal increase in somatosensory sensitivity greater than the sum of the visual-somatosensory enhancement and vestibular-somatosensory enhancement alone, due to an additional facilitatory link between vestibular and visual signals. Second, visual and vestibular signals might interact through inhibitory connections. Inhibitory interactions between visual and vestibular signals have been described for controlling gaze fixation [24,27,36]. A model based on inhibitory connections between visual and vestibular inputs might predict multisensory suppression of somatosensory sensitivity (Fig 1B). This model makes the important assumption that inter-areal inhibitory connections reduce functional processing in the target area. However, inhibition in sensory processing does not necessarily impair perception. For example, local inhibitory connections within a single sensory representation are important for enhancing perceptual sensitivity, particularly in acuity tasks [37,38]. Moreover, inhibitory integrative neurons in the multisensory parietal cortex were reported to outnumber facilitatory ones [39]. Therefore, multisensory inhibition of perceptual performance must be interpreted with caution. Finally, visual and vestibular inputs might directly, but independently, influence somatosensory sensitivity through separate unimodal-unimodal connections. This model would predict two independent multisensory modulations of somatosensory sensitivity, by vestibular and visual input respectively, with the two interactions being simply additive (Fig 1C). Disentangling these three different possibilities provides a novel insight into interactions between these three sensory systems, and may clarify how and where the vestibular system influences somatosensory sensitivity.

Material and Methods

Results

Raw mean data for each experimental condition are reported in Table 2.

The sensitivity range in the Baseline condition was between 0.99 and 1.92, consistent with the setting of somatosensory stimulus intensity at a level that avoided floor or ceiling detection performance. Response bias was conservative overall, showing a general reluctance to respond “yes”, irrespective of whether the somatosensory stimulus is present or not (Table 2).

Discussion

No primary vestibular cortex has been identified in the primate brain [14]. Rather, vestibular inputs share the cortical projections of other sensory pathways, such as vision and touch [9,49]. Thus, anatomical links between vestibular input and other sensory modalities abound. Several physiological studies have considered the function of vestibular-visual links, but vestibular-somatosensory links remain relatively unstudied. Moreover, the existence, and possible functional significance of a three-way vestibular-visual-somatosensory interaction has rarely been considered. Multisensory neurons coding for vestibular, visual and somatosensory stimuli were found in the macaque VIP [13], homologous to the human vestibular areas in the posterior parietal cortex [14]. Bimodal neurons responding to vestibular and somatosensory stimulation were found in primate posterior parietal cortex (area 2v) immediately adjacent to primary somatosensory areas of hand and mouth [9,49]. Multisensory neurons coding for vestibular and somatosensory signals were also described in the PIVC and such neurons responded to vestibular stimulation of the semicircular canals and otolith organs, as well as touch applied on the arms, shoulders, neck, and legs. Similarly, neurons responding to visual and vestibular stimulation have been recorded in the fundus of the intraparietal sulcus, in the ventral and medial intraparietal areas (MIP) [13,50,51,52,53].

The existence of specialised neurons integrating vestibular and other inputs makes it unsurprising that vestibular, visual and somatosensory systems interact. In particular, vestibular-visual-somatosensory convergence has been described in almost all vestibular relays, including the vestibular nuclei, the thalamus and several areas in the cerebral cortex. However, the detailed form of this interaction has not been studied at a behavioural or systems level. Here we hypothesized that this interaction could involve trimodal multisensory enhancement, trimodal multisensory suppression, or independent bimodal multisensory influences of visual inputs on somatosensation [32,33,34,35] and of vestibular inputs on somatosensation [19,20,21]. We used detection of near-threshold somatosensory stimuli as a potential method for gauging the effect of multisensory visual and vestibular inputs on early somatosensory processes. Based on known anatomical projections between vestibular, visual and somatosensory regions, we hypothesised a number of possible models for multisensory interaction (Fig 1A, 1B and 1C), and we predicted their likely implications for somatosensory detection performance.

We found a near-significant trend for enhancement of somatosensory sensitivity by visual stimuli [32]. We also found a significant vestibular enhancement of somatosensory sensitivity. These findings replicate previous results [19], but importantly extend them to the novel NirCVS method of vestibular stimulation used. Our data in the trimodal vestibular, visual and somatosensory condition are clearly inconsistent with a multisensory enhancement model. Instead of enhancement, we found a trend towards under-additivity, with the combined vestibular and visual modulation of somatosensation being weaker than the sum of the two modulations independently. However, our data cannot conclusively rule out a simple additive model, since the trimodal effect did not quite reach the conventional boundary of statistical significance. In the additive model, the trimodal effect corresponds to the sum of the effects induced by bimodal visual-somatosensory and vestibular-somatosensory influences independently.

Previous anatomical studies demonstrated reciprocal inhibitory cortical interactions between visual and vestibular systems [24,25,26,27]. In particular, functional neuroimaging studies described activation of multiple cortical structures by means of vestibular stimulation, including the PIVC, the retroinsular cortex, the superior temporal gyrus (STG), the inferior parietal lobule (IPL), the precuneus, the anterior cingulum, and the hippocampus, accompanied by deactivations in the occipital and parietal visual areas [24,25,26,27]. This suppression may play a role in controlling eye movements and gaze stabilisation. Thus, if we assume that visual signals facilitate somatosensory sensation, and that vestibular stimulation inhibits visual signals, then an underadditive interaction between vestibular and visual processing should be present in our data. Specifically, vestibular stimulation should suppress the normal facilitation of touch by vision. We found a trend towards this pattern in our data.

The enhancement of somatosensory sensitivity by vestibular stimulation confirmed previous results [19,20,21]. Human neuroimaging studies showed that somatosensory cortical areas, as well as the insular cortex, were found to respond to vestibular and somatosensory inputs [11,12,18]. These studies provide a potential anatomical basis for the multisensory interaction found here. We thus suggest that vestibular inputs could act to enhance somatosensory sensitivity. One possible neural mechanism would be modulation of primary somatosensory cortical circuits by vestibular signals, along the lines previously proposed to explain visual enhancement of touch [54].

Caution is required in interpreting the non-significant difference that we found between left ear NirCVS and right ear NirCVS. Our data suggest that left ear and right ear stimulations have similar effects on somatosensory sensitivity. This lack of lateralization contrasts with previous findings using traditional cold caloric vestibular stimulation, which found stronger somatosensory effects following vestibular stimulation designed to activate the vestibular network in the right hemisphere (i.e. left cold CVS) [55,56]. Accordingly, neuroimaging studies identified the same asymmetry in the cortical vestibular system, suggesting that the cortical vestibular network is primarily located in the non-dominant right hemisphere in right-handed subjects [41]. However, these results have been collected in brain-damaged patients. The present data suggest that previous reports of vestibular hemispheric lateralisation might be related both to the unusual strong unilateral nature of traditional caloric vestibular stimulation and also to impaired cortical processing in the lesioned brain. In the present study, we found that NirCVS in healthy participants had similar effects on somatosensory sensitivity, irrespective of whether the left or right vestibular organs were stimulated.

Finally, our somatosensory detection task was confined to the left hand. We chose this condition because the strongest effects of vestibular stimulation have previously been found when stimulating the left vestibular organs, and thus the contralateral right hemisphere [56]. Methodological constraints due to NirCVS duration did not allow us to investigate possible changes in somatosensory sensitivity for the right hand. In particular, we applied the same precautionary principle with NirCVS as is generally applied to caloric vestibular stimulation studies: we performed no more than one stimulation per side per session. Given the limited window of NirCVS effectiveness, it was not possible to deliver somatosensory stimulation to both hands in the NirCVS conditions. Importantly, previous studies described bilateral enhancement of tactile sensitivity induced by vestibular stimulation [19]. Future, larger studies might factorially combine the side of vestibular and somatosensory stimulations, in multi-session experiments, to investigate this question more fully.

An additive effect of vestibular and visual signals on somatosensation could be explained by either of two alternative mechanisms. First, vestibular and visual signals could both influence somatosensation by a common but non-specific mechanism, such as arousal or attention. For example, the vestibular stimulation could increase arousal relative to baseline, and visual stimulation could also independently increase arousal. In particular, vestibular stimulation has been often associated with shifts of spatial attention. Vestibular-induced enhancement in sensitivity in some previous studies (though not the present one) depended on the side of vestibular stimulation, and thus on the hemisphere preferentially activated [20]. These hemisphere-specific effects cannot be explained by general arousal or changes in attention, since the peripheral vestibular organs receive comparable stimulation in both cases.

Alternatively, vestibular and visual stimuli might evoke separate and independent influences on the neural circuits responsible for somatosensory detection. For example, two independent projections, arising from vestibular and visual inputs, might converge in the somatosensory cortex, providing independent modulating influences. Behavioural and population-level measures cannot easily distinguish between multisensory convergence and multisensory modulation. However, there may be theoretical grounds for preferring a modulation account in this case. Recent theories of multisensory perception emphasise optimal integration of different channels of sensory information, by weighting each source according to reliability [57]. This integration aims at combining information about a spatio-temporally coherent common source object [57]. For example, two visual and somatosensory sensory channels may be combined to generate a perceptual representation of a single external object or event that is experienced both visually and tactually [58,59]. For instance, when manipulating objects, the object's size can be judged simultaneously by vision and touch. Information from these two modalities should therefore be integrated in the nervous system to benefit from their redundancy [58]. Integrating the information from the two modalities yields a more certain estimate of an object’s size, compared with the noisy estimate from each modality alone [58].

In contrast, the “common source object” concept that underlies these studies may not readily apply to the trimodal situation studied here. The vestibular system may not describe an external physical object or source in the same way that visual or haptic exteroception do. Instead, modern accounts characterise the vestibular system as representing self-motion: when moving the head, visual, vestibular, and somatosensory signals all give rise to an estimate of the heads' position and orientation. Hence, the sensory system integrates these signals into a coherent representation of bodily position. However, such experience is rather different compared with the perceptual representation of an external object [58,59]. Further, our vestibular stimulation was spatially and temporally distinct from our somatosensory stimuli, and occurrences of all three stimuli (vestibular, somatosensory and visual) were statistically independent. Therefore, the concept of converging multisensory information used in previous multisensory studies may not readily apply in this case. Instead, our modulations of somatosensory detection could be considered as probing the state of the corresponding early “unimodal” cortex, prior to the stage at which spatiotemporally coherent source objects are bound from multiple sensory inputs. We suggest that the vestibular influence on somatosensory sensitivity may be an example of modulation of early somatosensory cortex via the anatomical projections identified by previous vestibular stimulation studies.

In conclusion, we investigated interactions between vestibular, visual and somatosensory inputs in a simple somatosensory detection task. We rejected a model of multisensory interaction based on supra-additive multisensory enhancement. Rather, we found additive influences of vestibular and of visual signals on somatosensory processing, or even a trend towards underadditivity. This trend is consistent with a model in which visual and vestibular inputs have additive, facilitatory influences on somatosensory processing, while vestibular inputs additionally suppress visual processing. These perceptual results are consistent with known neuroanatomical interactions between these three sensory systems.

Supporting Information

Data Availability

All relevant data are within the paper and its Supporting Information files.

Funding Statement

ERF and PH were supported by EU Project VERE Workpackage 1. PH was additionally supported by a Professorial Fellowship from ESRC and by ERC Advanced Grant HUMVOL. The funders had no role in study design, data collection and analysis, decision to publish, or preparation of the manuscript.