The video Head Impulse Test (vHIT) detects vertical semicircular canal dysfunction

Abstract

Background: The video head impulse test (vHIT) is a useful clinical tool to detect semicircular canal dysfunction. However vHIT has hitherto been limited to measurement of horizontal canals, while scleral search coils have been the only accepted method to measure head impulses in vertical canals. The goal of this study was to determine whether vHIT can detect vertical semicircular canal dysfunction as identified by scleral search coil recordings.

Methods: Small unpredictable head rotations were delivered by hand diagonally in the plane of the vertical semicircular canals while gaze was directed along the same plane. The planes were oriented along the left-anterior-right-posterior (LARP) canals and right-anterior-left-posterior (RALP) canals. Eye movements were recorded simultaneously in 2D with vHIT (250 Hz) and in 3D with search coils (1000 Hz). Twelve patients with unilateral, bilateral and individual semicircular canal dysfunction were tested and compared to seven normal subjects.

Results: Simultaneous video and search coil recordings were closely comparable. Mean VOR gain difference measured with vHIT and search coils was 0.05 (SD = 0.14) for the LARP plane and -0.04 (SD = 0.14) for the RALP plane. The coefficient of determination R(2) was 0.98 for the LARP plane and 0.98 for the RALP plane and the results of the two methods were not significantly different. vHIT and search coil measures displayed comparable patterns of covert and overt catch-up saccades.

Conclusions: vHIT detects dysfunction of individual vertical semicircular canals in vestibular patients as accurately as scleral search coils. Unlike search coils, vHIT is non-invasive, easy to use and hence practical in clinics.

Figure 1. Modified head impulse procedure for vertical semicircular canals.

Head impulses for RALP (right anterior – left posterior), LARP (left anterior – right posterior) and lateral canal stimulation (arrows), as viewed from the fixation point. For testing the vertical canals, a modified procedure has been used, which elicits mainly vertical eye movements to dispense with complex video processing of torsional eye movements : The person's head is positioned turned with respect to the body, so that gaze is directed along the plane of head rotation in the direction of the named canals as represented by the vertical arrows. For testing horizontal canals the movement is in the plane of the horizontal canals as shown. These images are modified from the free iPhone or iPad app ‘aVOR’ developed by the first author . For the examination procedure, see also accompanying Video S1.

Figure 2. Simultaneous video and search coil head impulse recordings of all semicircular canals in a healthy subject.

The six double panels in each figure show simultaneous measures by scleral search coils (lower half of each panel) and the video head impulse system (upper half of each panel). The records here show that for a healthy subject the traces of head and eye velocity are almost superimposed for the direction of each semicircular canal. The VOR gain values for head turns in every canal plane are in the normal range. The plots themselves in this and the following figures are time series showing superimposed records of the head velocity stimulus (head velocity – green traces) and the slow-phase eye-velocity responses (eye velocity VOR – blue traces) to about 20 brief unpredictable head turns in the direction of each semicircular canal. Overt or covert saccades are shown as red traces . Tiny overt catch-up saccades are normal in healthy subjects. In these figures eye velocity has been inverted to allow easy comparison with head velocity, and for purposes of illustration both leftward and rightward head movements are shown as positive. The average VOR gain value is shown next to each group of responses. The inset at the centre shows the rotation axes of the semicircular canals being tested.

Figure 3. Simultaneous video and search coil head impulse recordings of all semicircular canals in a patient with idiopathic bilateral vestibular loss.

For every direction of head rotation (green traces), there is no effective compensatory slow-phase eye velocity response (blue traces). There is a shower of saccades at the end of each head rotation (red traces). The VOR gain for all canals is close to zero.

Figure 4. Simultaneous video and search coil head impulse recordings of all semicircular canals in a patient with left unilateral vestibular loss after surgery for vestibular Schwannoma.

For every rotation direction activating canals on the healthy (right) side, the eye velocity response is around normal. However, for every rotation direction activating canals on the affected (left) side, there is a reduced or absent VOR response. In particular the vertical canals on the affected side have a clearly reduced function. To correct for the deficit on the affected left side, covert saccades appear during and overt saccades after head rotation (red traces).

Figure 5. Simultaneous video and search coil head impulse recordings of all semicircular canals in a patient with single isolated loss of the right posterior semicircular canal.

Results for a patient with a single isolated loss of the right posterior semicircular canal, as shown by prior testing using scleral search coils. For rotations, which would activate this single canal, there is a clear reduction of eye velocity (blue traces) during the head velocity stimulus (green traces), quickly followed by covert saccades (red traces). The responses for all other canals were in the normal range.

Figure 6. VOR gain comparison of simultaneous search coils and video measures.

Bar plots of VOR gain for simultaneous search coils (red) and video measures (blue) for 6 representative subjects and patients. Bars are plotted side by side to facilitate comparison and arranged radially to indicate the results from head impulses delivered in planes of the: Right Anterior (RA), Left Anterior (LA), Right Horizontal (RH), Left Horizontal (LH), Right Posterior (RP), and Left Posterior (LP) semicircular canals. The data shown are for a range of patient conditions: Normal (same subject as in Figure 2); idiopathic Bilateral Vestibular Loss (iBVL; same patient as in Figure 3); left Unilateral Vestibular Deafferentation (lUVD; same patient as in Figure 4) after surgery for vestibular Schwannoma; right Lateral Canal Occlusion (rLCO) for intractable benign paroxysmal positional vertigo; idiopathic right Posterior Canal Dysfunction (rPCD; same patient as in Figure 5); and Bilateral Posterior Canal Occlusion (bPCO; same patient as Figure S1) for intractable benign paroxysmal positional vertigo. Results show a range of responses from canals in these patients, each with a pattern of canal responses that usually matches the expectation based on previous literature, but importantly the pattern of response on coils and video measures remains similar across a broad range of canal responses and diagnoses. (For individual VOR gain values, see Data S1.)

Figure 7. VOR regression plots from coils vs. video for lateral, anterior and posterior canals.

The coefficients of determination (R²) for each regression are listed. In each case the correspondence is extremely strong as shown by both graphical data and statistical analysis.

Figure 8. Head impulse gain calculation model.

Gain calculation model for head impulses measured with video (cyan trace) and search coils (blue trace) taking into account movement artifacts from video goggle slippage (black trace) in the video signal. The video recording artifact around peak head acceleration (green dashed line) probably results from relative movement of the facial skin (on which the goggles ride) when the head is passively rotated (green trace). Since traditional VOR gain measurement over a narrow window, usually around peak head acceleration (green dashed line), is very sensitive to the influence of this artifact, we measured gain over a wide window from the beginning of the head impulse until the head velocity returns to 0°/s (black dashed lines). This gain calculation method is relatively unaffected by the biphasic movement artifact, because its positive component (manual acceleration of the head) and its negative component (deceleration) tend to cancel out (grey shaded areas) during the impulse. It is, however, susceptible to the influence of catch-up saccades (red trace), so eye velocity is desaccaded first. Gains calculated using this method are very similar for video and coils and quite comparable to the traditional gain measurement method for search coils around peak head acceleration.