Automatic dental CT image segmentation using mean shift algorithm

Identifying the structure and arrangement of theteeth is one of the dentists' requirements for performing variousprocedures such as diagnosing abnormalities, dental implant andorthodontic planning. In this regard, robust segmentation ofdental Computerized Tomography (CT) images is required.However, dental CT images present some major challenges forthe segmentation that make it difficult process. In this research,we propose a multi-step approach for automatic segmentation ofthe teeth in dental CT images. The main steps of this method arepresented as follows: 1-Primary segmentation to classify bonytissues from nonbony tissues. 2- Separating the general region ofthe teeth structure from the other bony structures and arc curvefitting in the region. 3- Individual tooth region detection. 4- Finalsegmentation using mean shift algorithm by defining a newfeature space. The proposed algorithm has been applied toseveral Cone Beam Computed Tomography (CBCT) data setsand quality assessment metrics are used to evaluate theperformance of the algorithm. The evaluation indicates that theaccuracy of proposed method is more than 97 percent. Moreover,we compared the proposed method with thresholding, watershed,level set and active contour methods and our method shows animprovement in compare with other techniques

Keywords:

image segmentation , CBCT image , tooth segmentation , mean shift