A Novel Approach for Dental Panoramic Radiograph Segmentation

Segmentation of dental panoramic radiographs is a critical element in a typical image analysis and understanding system such as in biomedical or biometric applications. It enables the detection and the classification of various components, including jaws, teeth, lesions and carries. However, available methods have demonstrated limited results due to the challenging complexity of the panoramic images. In this paper we propose a novel automatic segmentation method that separates maxillary and mandibular jaws with a shape-free model and distinguishes teeth using lines defined within a precise scheme. The developed approaches are implemented and tested over a database of dental panoramic radiographs. Obtained results demonstrate good performance and showed the suitability of the proposed method.