Automatic Extraction of Mandibular Nerve and Bone from Cone-Beam CT Data

Abstract

Abstract. The exact localization of the mandibular nerve with respect to the bone is important for applications in dental implantology and maxillofacial surgery. Cone beam computed tomography (CBCT), often also called digital volume tomography (DVT), is increasingly utilized in maxillofacial or dental imaging. Compared to conventional CT, however, soft tissue discrimination is worse due to a reduced dose. Thus, small structures like the alveolar nerves are even harder recognizable within the image data. We show that it is nonetheless possible to accurately reconstruct the 3D bone surface and the course of the nerve in a fully automatic fashion, with a method that is based on a combined statistical shape model of the nerve and the bone and a Dijkstra-based optimization procedure. Our method has been validated on 106 clinical datasets: the average reconstruction error for the bone is 0.5 ± 0.1 mm, and the nerve can be detected with an average error of 1.0 ± 0.6 mm.

Jaw tissues segmentation in dental 3D CT images using fuzzy-connectedness and morphological processing

“…Considering this diameter, the mean errors of both measures are, expressed as percentages, 5.76 and 6.52 %, respectively. The presented results show that our method obtains higher accuracy values when compared with other state-of-the-art methods [9,13].…”

“…Rueda et al [8] use active appearance models (AAM) for the segmentation of jaw tissues in serial cross-sections of the jaw, but the precision achieved is insufficient. Recently, Kainmuller et al [9] combine a statistical model of the nerve with an optimization of Dijkstra's algorithm.…”

Segmentation of the Mandibular Canal in Cone-Beam CT Data

“…In that case the points describing the nerve will get more influence on the nerve segmentation result. In future work it will be important to train the model on more scans, such as used by Kainmueller et al [33] (106 scans). Also increasing the influence of the points in the mandibular nerve can probably decrease the segmentation error of the canals.…”

“…This can be done by using an ASM or AAM method. These models are trained using manually segmented data sets, as done by Kainmueller et al [33]. Another way to introduce a priori information about shape and appearance is atlas-registration.…”

“…2009 "Automatic Extraction of Mandibular Nerve and Bone from Cone-Beam CT Data", by Kainmueller et al [33]. The method is based on segmenting the mandible using an active shape model (ASM), which is constructed, from 106 clinical data sets.…”