Automatic Segmentation of Digital Orthopantomograms for Forensic Human Identification

Abstract

Dental radiographic images are one of the most popular biometrics used in the process of forensic human identification. This led to the creation of the Automatic Dental Identification System with the goal of decreasing the time it takes to perform a single search in a large database of dental records. A fully automated system identifying people based on dental X-ray images requires a prior segmentation of the radiogram into sections containing a single tooth. In this paper, a novel method for such segmentation is presented, developed for the dental radiographic images depicting the full dentition-pantomograms. The described method utilizes the locations of areas between necks of teeth in order to determine the separating lines and does not depend on the articulation of gaps between adjacent teeth, thus improving the results achieved in the situation of severe occlusions.

Automatic segmentation of mandible in panoramic x-ray

“…The closest study to the current one was carried out by Frejlichowski and Wanat, 4 in which they segmented dental panoramic x-rays into regions, each containing a single tooth. It needs to be noted that the proposed method suffered from some theoretical shortcomings regarding the removal of areas below the roots of the teeth, where they translated the curve separating the upper and lower jaws vertically in search of an alignment, where the sum of pixels it passed through was lower than the surrounding results.…”

“…Automatic detection of maxillofacial landmarks in lateral cephalometric radiography has recently attracted some attention; 1,2 whereas other researchers focused on panoramic x-rays (i.e., orthopantomogram) and introduced methods for their registration to give clinicians the complementary information provided by different modalities, 3 extracted the region of interest of each tooth by means of vertical and horizontal integral projections, 4 or presented methods for detection of carotid artery calcification. 5 Segmentation of anatomical structures is a vital step for many applications.…”

Unsupervised Caries Detection in Non-standardized Bitewing Dental X-Rays

“…This was further developed by Frejlichowski and Wanat [34] with the primary focus of their research being on the development of a segmentation method for panoramic X-rays.…”

“…In order to determine the best separation lines, the algorithm proposed in [34] was used as a starting point. The proposed algorithm works primarily due to the nature of panoramic X-rays, where all teeth are in view and as such it is able to use the uniform nature of teeth sizing to determine spacing.…”

“…Despite this, by combining the rotation algorithms used in [29] and [33] with an altered probability model of [34], it is possible to develop a combination of a rotational and probabilistic algorithm for segmenting the dataset outlined above. …”