A digital workflow for pair matching of maxillary anterior teeth using a 3D segmentation technique for esthetic implant restorations

Abstract

We investigated a state-of-the-art algorithm for 3D reconstruction with a pair-matching technique, which enabled the fabrication of individualized implant restorations in the esthetic zone. This method compared 3D mirror images of crowns and emergence profiles between symmetric tooth pairs in the anterior maxilla using digital slicewise DICOM segmentation and the superimposition of STL data. With the outline extraction of each segment provided by 100 patients, the Hausdorff distance (HD) between two point sets was calculated to identify the similarity of the sets. By using HD thresholds as a pair matching criterion, the true positive rates of crowns were 100, 98, and 98%, while the false negative rates were 0, 2, and 2% for central incisors, lateral incisors, and canines, respectively, indicating high pair matching accuracy (> 99%) and sensitivity (> 98%). The true positive rates of emergence profiles were 99, 100, and 98%, while the false negative rates were 1, 0, and 2% for central incisors, lateral incisors, and canines, respectively, indicating high pair matching accuracy (> 99%) and sensitivity (> 98%). Therefore, digitally flipped contours of crown and emergence profiles can be successfully transferred for implant reconstruction in the maxillary anterior region to optimize esthetics and function.

Figure 1

ROC curves for 3D HD thresholds for pair matching central incisors (A, crown; D, emergence profile), lateral incisors (B, crown; E, emergence profile), and canines (C, crown; F, emergence profile). The smallest HD (mm) for 100% sensitivity was marked.

Figure 2

Jitter plot of 3D HDs for central incisor, lateral incisor, and canine pair comparisons. A true positive pair indicates a contralateral element, from the same individual, that was correctly categorized as a pair. For the distribution of true negative pairs, the smallest 100 data points among the 9900 comparisons were illustrated.

Figure 3

Summary of the workflow of the study process.

Figure 4

Dataset superimposition. (A), A scan image in the STL file format. (B), DICOM segmentation and STL conversion. (C), Superimposition of two STL files.

Figure 5

Polygonal annotation of the dataset. (A), Detection of the annotated lines. (B), Annotation of crown and emergence profile elements.

Figure 6

The right element and the left element form a mirrored pair. (A), A mirrored pair of crowns with emergence profiles. (B), A mirrored pair of crowns. In a mirrored configuration, the blue part indicates one side of the crown, while the pink part indicates the other side of the crown. (C), A mirrored pair of emergence profiles. In a mirrored configuration, the green part indicates one side of the emergence profile, while the red part indicates the other side of the emergence profile.

Figure 7

The red dot indicates the apical point (A) and the coronal point (B) of the long axis.

Figure 8

The Hausdorff distance between a pair of crowns. A crown shape must be as close as possible to the other crown shape.