Automated tracking of the mandibular canal in CBCT images using matching and multiple hypotheses methods

A method for the automated tracking of the mandibular canal in Cone Beam Computed Tomography images is presented. In contrast to most proposed methods a fully automated method is presented including the detection of the mental and mandibular foramen. Extraction of these points is done by searching for high-contrast gaps in the mandible. The path of the mandibular canal can then be tracked in between these two points using a matching technique consisting of a template function which maps spatial coordinates to a cost. The robustness of the tracking is increased by recursively tracking multiple hypotheses.

I. Introduction

In the field of orthodontics and orthognathic surgery there are a lot of applications for which there are risks of damage and/or increased postoperative sensitivity or other postoperative sensory impairments to the inferior alveolar nerve (IAN). These applications cover a broad range of operations, from the removal of cysts up to osteotomies and dental implantology. To reduce these risks during an intervention, the surgeon should have knowledge of the exact course of the IAN. The IAN is situated in the mandibular canal, a tubular structure in the mandible which is detectable through computed tomography techniques. In figure 1 the canal is indicated by the red ‘wire’ on both sides of the mandible. The endpoints of this wire are the mental and the mandibular foramen which are located respectively on the outside of the mandible close to the chin and on the inside of the mandible behind the molars.