Automatic techniques for cochlear implant CT image analysis
This work addresses the problem of automating post-operative cochlear implant analysis for medical professionals, but it appears incremental as it builds on existing techniques.
The dissertation tackled automating cochlear implant image analysis by developing methods for localizing electrode arrays and selecting configurations, enabling an end-to-end process from CT images to patient-customized outputs.
The goals of this dissertation are to fully automate the image processing techniques needed in the post-operative stage of IGCIP and to perform a thorough analysis of (a) the robustness of the automatic image processing techniques used in IGCIP and (b) assess the sensitivity of the IGCIP process as a whole to individual components. The automatic methods that have been developed include the automatic localization of both closely- and distantly-spaced CI electrode arrays in post-implantation CTs and the automatic selection of electrode configurations based on the stimulation patterns. Together with the existing automatic techniques developed for IGCIP, the proposed automatic methods enable an end-to-end IGCIP process that takes pre- and post-implantation CT images as input and produces a patient-customized electrode configuration as output.