Tooth separation from dental model using segmentation field

Tooth segmentation on dental model is an essential step of computer-aided-design systems for orthodontic virtual treatment planning. However, efficiently identifying cutting boundary to separate tooth from dental model still remains a challenge, due to various geometrical shapes of teeth, complex tooth arrangements and varying degrees of crowding problem. Most segmentation approaches presented before are not able to achieve a balance between fine segmentation results and simple operating procedure. In this article, we present a novel and efficient framework that achieves tooth segmentation based on the segmentation field. Specially, the candidate cutting boundaries are able to be detected from the concave regions with large variations of field data. The sensitivity to concave seams of segmentation field facilitates effective tooth partition, as well as avoids obtaining appropriate curvature threshold value, which is unreliable in some case. The experiments indicate that, our tooth segmentation algorithm is robust to different dental models with severe crowding problems and poor distinction.