Individual tooth segmentation from CT images scanned with contacts of maxillary and mandible teeth

• Published in: Computer methods and programs in biomedicine Vol. 138; pp. 1 - 12
• Main Authors: Xia, Zeyang, Gan, Yangzhou, Chang, Lichao, Xiong, Jing, Zhao, Qunfei
• Format: Journal Article
• Language: English
• Published: Ireland Elsevier B.V 01.01.2017
• Subjects: Computed tomography images; Dental Models; Humans; Internal Medicine; Level set method; Mandible - diagnostic imaging; Maxilla - diagnostic imaging; Mesh segmentation; Other; Radon transform; Tomography, X-Ray Computed - methods; Tooth - diagnostic imaging; Tooth segmentation; Radon transform; Tooth segmentation; Computed tomography images; Level set method; Mesh segmentation
• ISSN: 0169-2607; 1872-7565; 1872-7565
• DOI: 10.1016/j.cmpb.2016.10.002

•A method for individual tooth segmentation from CT images scanned with contacts of maxillary and mandible teeth is proposed.•The Radon transform is applied to extract a line to separate neighboring teeth into independent ones.•A parameter adaptive selection scheme is developed to determine the parameters of hybrid level set model adaptively .•Contacted maxillary and mandible tooth models are separated by threshold segmentation and fast marching watershed method. Tooth segmentation from computed tomography (CT) images is a fundamental step in generating the three-dimensional models of tooth for computer-aided orthodontic treatment. Individual tooth segmentation from CT images scanned with contacts of maxillary and mandible teeth is especially challenging, and no method has been reported previously. This study aimed to develop a method for individual tooth segmentation from these images. Tooth contours of maxilla and mandible are first segmented from the volumetric CT images slice-by-slice. For each slice, a line is extracted using the Radon transform to separate neighboring teeth, and each tooth contour is then segmented by a level set model from the corresponding side of the line. Then, each maxillary tooth whose contours overlap with that of mandible ones is detected, and a mesh model is reconstructed from all the contours of these maxillary and mandible teeth with contour overlap. The reconstructed mesh model is segmented using threshold and fast marching watershed method to separate the touched maxillary and mandible teeth. Finally, the separated tooth models are restored to fill the holes to obtain complete tooth models. The proposed method was tested on CT images of ten subjects scanned with natural contacts of maxillary and mandible teeth. For all the tested images, individual tooth regions are extracted successfully, and the segmentation accuracy and efficiency of the proposed method is promising. The proposed method is effective to segment individual tooth from CT images scanned with contacts of maxillary and mandible teeth.