Abstract

The robust delineation of the cochlea and its inner structures combined with the detection of the electrode of a cochlear implant within these structures is essential for envisaging a safer, more individualized, routine image-guided cochlear implant therapy. We present Nautilus—a web-based research platform for automated pre- and post-implantation cochlear analysis. Nautilus delineates cochlear structures from pre-operative clinical CT images by combining deep learning and Bayesian inference approaches. It enables the extraction of electrode locations from a post-operative CT image using convolutional neural networks and geometrical inference. By fusing pre- and post-operative images, Nautilus is able to provide a set of personalized pre- and post-operative metrics that can serve the exploration of clinically relevant questions in cochlear implantation therapy. In addition, Nautilus embeds a self-assessment module providing a confidence rating on the outputs of its pipeline. We present a detailed accuracy and robustness analyses of the tool on a carefully designed dataset. The results of these analyses provide legitimate grounds for envisaging the implementation of image-guided cochlear implant practices into routine clinical workflows.

Key Words: Cochlear Implantation, Image Processing, Nautilus, Cochlear Anatomy, CT, CBCT, Hounsfield Units, Advanced Mattes Mutual Information, Histogram Bins, Invalid Voxels, Unique Version Identifier, Processing Pipeline, Export File, Cochlear Metrics

Main points

Proposes a set of features for exploring many relevant clinical and basic questions related to cochlear anatomy.
Introduces a statistical model of the electrode insertion trajectory from pre-operative images.
Observes that even for CT or CBCT images in Hounsfield units, the Advanced Mattes mutual information with 64 histogram bins performs adequately.
Tags analysis results with the unique version identifier for the specific processing pipeline version that was used for processing.

Citation

@article{Margeta2022,
  doi = {10.3390/jcm11226640},
  url = {https://doi.org/10.3390/jcm11226640},
  year = {2022},
  month = nov,
  publisher = {MDPI},
  volume = {11},
  number = {22},
  pages = {6640},
  author = {Jan Margeta and Raabid Hussain and Paula L{\'{o}}pez Diez and Anika Morgenstern and Thomas Demarcy and Zihao Wang and Dan Gnansia and Octavio Martinez Manzanera and Clair Vandersteen and Herv{\'{e}} Delingette and Andreas Buechner and Thomas Lenarz and Fran{\c{c}}ois Patou and Nicolas Guevara},
  title = {A Web-Based Automated Image Processing Research Platform for Cochlear Implantation-Related Studies},
  journal = {Journal of Clinical Medicine}
}