Uncertainty Quantification of Cochlear Implant Insertion from CT Images

Abstract

Cochlear implants (CI) are used to treat severe hearing loss by surgically inserting an electrode array into the cochlea. Since current electrodes are designed with various insertion depth, ENT surgeons must choose the implant that will maximise the insertion depth without causing any trauma based on preoperative CT images. In this paper, we propose a novel framework for estimating the insertion depth and its uncertainty from segmented CT images based on a new parametric shape model. Our method relies on the posterior probability estimation of the model parameters using stochastic sampling and a careful evaluation of the model complexity compared to CT and $\mu$CT images. The results indicate that preoperative CT images can be used by ENT surgeons to safely select patient-specific cochlear implants.