Separation of overlapping dental arch objects using digital records of illuminated plaster casts

Abstract

Background: Plaster casts of individual patients are important for orthodontic specialists during the treatment process and their analysis is still a standard diagnostical tool. But the growing capabilities of information technology enable their replacement by digital models obtained by complex scanning systems.

Method: This paper presents the possibility of using a digital camera as a simple instrument to obtain the set of digital images for analysis and evaluation of the treatment using appropriate mathematical tools of image processing. The methods studied in this paper include the segmentation of overlapping dental bodies and the use of different illumination sources to increase the reliability of the separation process. The circular Hough transform, region growing with multiple seed points, and the convex hull detection method are applied to the segmentation of orthodontic plaster cast images to identify dental arch objects and their sizes.

Results: The proposed algorithm presents the methodology of improving the accuracy of segmentation of dental arch components using combined illumination sources. Dental arch parameters and distances between the canines and premolars for different segmentation methods were used as a measure to compare the results obtained.

Conclusion: A new method of segmentation of overlapping dental arch components using digital records of illuminated plaster casts provides information with the precision required for orthodontic treatment. The distance between corresponding teeth was evaluated with a mean error of 1.38% and the Dice similarity coefficient of the evaluated dental bodies boundaries reached 0.9436 with a false positive rate [Formula: see text] and false negative rate [Formula: see text].

Figure 1

Digital data acquisition of the orthodontic plaster cast by a digital camera for a, b top illumination, c right hand side illumination, and d left hand side illumination.

Figure 2

Image enhancement including a combination of images with side illumination, b merging of images with central/outside illumination, c merging of images with top wide/narrow angle illumination, and d fusion of merged images resulting in the final image.

Figure 3

Block diagram of the proposed methodology including a image acquisition and data fusion, b image de-noising and the use of Hough transform for detection of individual objects, c segmentation based on the region growing method, and d evaluation of dental arch parameters.

Figure 4

Identification steps of common boundary detection presenting a selected area of the original image, b dental subimage with two connected neighbouring regions, c, d details of areas (A) and (B) with smoothed boundaries, e, f vectors related to the second derivative of the boundaries showing local convexity in areas (A) and (B), and g resulting segmentation.

Figure 5

Orthodontic image segmentation presenting a the circular Hough transform, b segmentation results using the region-growing method (multiple seed points), c separate areas merged by the convex hull, d segmentation results for the whole dental arch, and e convex hull application for each component.

Figure 6

The results of the proposed segmentation process presenting a evaluated and real object boundaries for the dental arch and b selected tooth (R5) boundaries with false/true positive and false/true negative regions.