A Review of Three-Dimensional Facial Asymmetry Analysis Methods

Does facial asymmetry vary between subjects of different age groups? A 3D stereophotogrammetry analysis

This study was aimed to assess whether facial asymmetry increases with age and to examine potential gender differences using 3D stereophotogrammetry. A prospective cross-sectional study was performed. 3D photographs were acquired from 600 control subjects, 300 male, 300 female, and were stratified into 15 different age groups ranging from 0 to 70+. The 3D photographs were postprocessed and mirrored. The original and mirrored faces were surface-based matched using an iterative closest point algorithm. The primary outcome variable, facial asymmetry, was evaluated by calculating the absolute mean distance between the original and mirrored images. The primary predictor was age. Pearson's correlation was used to assess the correlation between facial asymmetry and age. The average overall facial asymmetry was 0.72 mm (SD 0.72 mm; range 0.25 - 3.04 mm). Mean facial asymmetry increased significantly with age, from 0.45 mm in the age group of 0-4 years to 0.98 mm in the age group of 70+ (p<0.001). Facial asymmetry was positively correlated with age (Pearson's r = 0.55; p<0.001). Male subjects were significantly more asymmetric compared to females, 0.77 mm and 0.67 mm, respectively (p<0.001). This study indicates that facial asymmetry significantly increases with age and is significantly larger in males than in females.

Automated localization of mandibular landmarks in the construction of mandibular median sagittal plane

OBJECTIVE

To use deep learning to segment the mandible and identify three-dimensional (3D) anatomical landmarks from cone-beam computed tomography (CBCT) images, the planes constructed from the mandibular midline landmarks were compared and analyzed to find the best mandibular midsagittal plane (MMSP).

METHODS

A total of 400 participants were randomly divided into a training group (n = 360) and a validation group (n = 40). Normal individuals were used as the test group (n = 50). The PointRend deep learning mechanism segmented the mandible from CBCT images and accurately identified 27 anatomic landmarks via PoseNet. 3D coordinates of 5 central landmarks and 2 pairs of side landmarks were obtained for the test group. Every 35 combinations of 3 midline landmarks were screened using the template mapping technique. The asymmetry index (AI) was calculated for each of the 35 mirror planes. The template mapping technique plane was used as the reference plane; the top four planes with the smallest AIs were compared through distance, volume difference, and similarity index to find the plane with the fewest errors.

RESULTS

The mandible was segmented automatically in 10 ± 1.5 s with a 0.98 Dice similarity coefficient. The mean landmark localization error for the 27 landmarks was 1.04 ± 0.28 mm. MMSP should use the plane made by B (supramentale), Gn (gnathion), and F (mandibular foramen). The average AI grade was 1.6 (min-max: 0.59-3.61). There was no significant difference in distance or volume (P > 0.05); however, the similarity index was significantly different (P < 0.01).

CONCLUSION

Deep learning can automatically segment the mandible, identify anatomic landmarks, and address medicinal demands in people without mandibular deformities. The most accurate MMSP was the B-Gn-F plane.

[Current Status and Analysis of the Clinical Application of Digital Technology in Oral Medicine]

With the increasing maturity and popularization of digital technology in oral medicine, its application has now expanded to various clinical subspecialties of oral medicine. Digitalization has become one of the important development directions of oral medicine. What is the current development status of digital technology in oral medicine? In what ways is digital technology applied across various clinical specialties of oral medicine? Dentists are particularly concerned about these issues in their clinical work and research. In this paper, all the digital technologies applied in oral medicine are organized and categorized from a technical perspective. In this paper, we focused on presenting three-dimensional data acquisition technology, dental computer-aided design technology, dental computer-aided processing technology, and oral surgery implementation technology. Their technical principles, technical characteristics, applications in oral medicine, a secondary discipline of medicine, and the development status of domestically-developed technology are described and reviewed in detail. The other technologies such as oral digital materials, oral virtual simulation teaching, and oral multi-source data management are briefly discussed. We intend to provide references for dentists to apply digital technology in clinical practice and research.

Skeletal facial asymmetry: reliability of manual and artificial intelligence-driven analysis

OBJECTIVES

To compare artificial intelligence (AI)-driven web-based platform and manual measurements for analysing facial asymmetry in craniofacial CT examinations.

METHODS

The study included 95 craniofacial CT scans from patients aged 18-30 years. The degree of asymmetry was measured based on AI platform-predefined anatomical landmarks: sella (S), condylion (Co), anterior nasal spine (ANS), and menton (Me). The concordance between the results of automatic asymmetry reports and manual linear 3D measurements was calculated. The asymmetry rate (AR) indicator was determined for both automatic and manual measurements, and the concordance between them was calculated. The repeatability of manual measurements in 20 randomly selected subjects was assessed. The concordance of measurements of quantitative variables was assessed with interclass correlation coefficient (ICC) according to the Shrout and Fleiss classification.

RESULTS

Erroneous AI tracings were found in 16.8% of cases, reducing the analysed cases to 79. The agreement between automatic and manual asymmetry measurements was very low (ICC < 0.3). A lack of agreement between AI and manual AR analysis (ICC type 3 = 0) was found. The repeatability of manual measurements and AR calculations showed excellent correlation (ICC type 2 > 0.947).

CONCLUSIONS

The results indicate that the rate of tracing errors and lack of agreement with manual AR analysis make it impossible to use the tested AI platform to assess the degree of facial asymmetry.