Automatic Detection of the Inner Ears in Head CT Images Using Deep Convolutional Neural Networks

Abstract

Cochlear implants (CIs) use electrode arrays that are surgically inserted into the cochlea to stimulate nerve endings to replace the natural electro-mechanical transduction mechanism and restore hearing for patients with profound hearing loss. Post-operatively, the CI needs to be programmed. Traditionally, this is done by an audiologist who is blind to the positions of the electrodes relative to the cochlea and relies on the patient's subjective response to stimuli. This is a trial-and-error process that can be frustratingly long (dozens of programming sessions are not unusual). To assist audiologists, we have proposed what we call IGCIP for image-guided cochlear implant programming. In IGCIP, we use image processing algorithms to segment the intra-cochlear anatomy in pre-operative CT images and to localize the electrode arrays in post-operative CTs. We have shown that programming strategies informed by image-derived information significantly improve hearing outcomes for both adults and pediatric populations. We are now aiming at deploying these techniques clinically, which requires full automation. One challenge we face is the lack of standard image acquisition protocols. The content of the image volumes we need to process thus varies greatly and visual inspection and labelling is currently required to initialize processing pipelines. In this work we propose a deep learning-based approach to automatically detect if a head CT volume contains two ears, one ear, or no ear. Our approach has been tested on a data set that contains over 2,000 CT volumes from 153 patients and we achieve an overall 95.97% classification accuracy.

Keywords: Cochlear implant; Convolutional Neural Networks; image classification; image-guided cochlear implant programming.

Figure 1.

4 examples from our dataset. Orientations of the slices are labeled in CT #1 and apply to other examples as well.

Figure 2.

The yellow marker is the landmark we use as the position of the left inner ear. From top to bottom, they are the axial, coronal and sagittal views, respectively.

Figure 3.

Architecture of AlexNet

Figure 4.

Four examples, (a)-(d). For each example, the image on the left is a coronal slice of the CT. The two plots represent the probabilities of the slice series containing no ear, both ears, right ear and left ear, generated by models using strategy (1) and (2).