Free-form image registration of human cochlear μ CT data using skeleton similarity as anatomical prior

Kjer, Hans Martin; Fagertun, Jens; Vera, Sergio; Gil, Debora; González Ballester, Miguel Ángel, 1973-; Paulsen, Rasmus R.

doi:http://dx.doi.org/10.1016/j.patrec.2015.07.017

Free-form image registration of human cochlear μ CT data using skeleton similarity as anatomical prior

License

Citation

Kjer HM, Fagertun J, Vera S, Gil D, González MÁ, Paulsen RR. Free-form image registration of human cochlear μ CT data using skeleton similarity as anatomical prior. Pattern Recognition Letters. 2016 Jun 1;76:76-82. DOI: 10.1016/j.patrec.2015.07.017

Abstract

Better understanding of the anatomical variability of the human cochlear is important for the design and function of Cochlear Implants. Proper non-rigid alignment of high-resolution cochlear μCT data is a challenge for the typical cubic B-spline registration model. In this paper we study one way of incorporating skeleton-based similarity as an anatomical registration prior. We extract a centerline skeleton of the cochlear spiral, and generate corresponding parametric pseudo-landmarks between samples. These correspondences are included in the cost function of a typical cubic B-spline registration model to provide a more global guidance of the alignment. The resulting registrations are evaluated using different metrics for accuracy and model behavior, and compared to