Objective source selection in Blind Source Separation of AEPs in children with Cochlear Implants

Abstract

Multi-channel Auditory Evoked Potentials (AEPs) are a useful methodology for evaluating the auditory performance of children with Cochlear Implants (CIs). These recordings are generally contaminated, not only with well known physiological artifacts (blinking, muscle) and line noise etc., but also by CI artifact. The CI induces an artifact in the recording at the electrodes in the temporal lobe area (where it is implanted) when specific tones are presented, this artifact in particular makes the detection and analysis of AEPs much more challenging. This paper evaluates the convenience of using Blind Source Separation (BSS) and Independent Component Analysis (ICA) in order to identify the AEPs from ongoing recordings and to isolate the artifact when testing a child with a CI. We propose a new procedure to elicit an objective differentiation between the independent components (ICs) related to the AEPs and CI artifact; two concepts are fundamental in this procedure Mutual Information (MI) and Clustering. Finally, the variability of three BSS/ICA algorithms is assessed; in order to determine which one is more convenient to isolate the respective ICs of interest. Temporal decorrelation based ICA showed the least change in the estimation of both the AEPs and the CI artifact; this has allowed for considerable autonomy in the construction of relevant, consistent clusters.