Artifact and head movement compensation in MEG

Abstract

Purpose: Magnetoencephalography (MEG) is traditionally considered impractical if the subject's head moves during measurements. A novel approach to correct the head position and the associated movement-related artifacts does, however, exist: continuous head position monitoring and movement compensation (MC) realized by the signal space separation (SSS) or its temporal extension (tSSS). The latter is especially important for rejection of close-to-sensor artifacts. The goal of the present work was to study how MC-SSS and its temporal extension MC-tSSS would influence MEG results.

Methods: Somatosensory evoked MEG responses to electrical median nerve stimulation were recorded with 204 planar gradiometers and 102 magnetometers. We compared the localization error of the N20m source, the averaged baseline noise, goodness of fit and confidence volume on data processed by MC-SSS vs. MC-tSSS on a subject moving in a controlled manner.

Results: We defined two patterns of disturbances with MC-SSS: stimulus artifact increase and random noise increase mainly on the lowermost sensors in very low head positions (5-6 cm shift). Up to 5-cm head shift, MC-SSS decreased mean localization error from 3.91 to 2.13 cm, but at the same time increased noise on gradiometers from 3.4 to 5.3 fT/cm. The noise increment occurred simultaneously with signal enhancement as MC transformed the head position closer to the sensors. Replacement of SSS by tSSS reduced the noise on gradiometers from 5.3 to 2.8 fT/cm and on magnetometers from 1.4 to 0.8 fT, reduced the mean localization error from 2.13 to 0.89 cm and increased the goodness of fit from 61.5% to 76.5%. Thus, tSSS specifically suppressed the random noise and nearby artifacts without suppressing the signal and thereby improved the signal to noise ratio.

Conclusions: Head position recalculation should be combined with a powerful artifact rejection method. We recommend limiting MC use up to 3 cm head shift and using tSSS-based MC.