Predicting mandibular growth based on CVM stage and gender and with chronological age as a curvilinear variable

Assessment of mandibular trabecular structure and cervical vertebral maturation using fractal analysis

BACKGROUND

Changes in bone trabeculae occur during skeletal maturation. Fractal analysis is a technique for assessing changes in the internal structure of the bone.

OBJECTIVE

The aim of this study was to investigate correlation of bone trabeculation measured on panoramic and lateral cephalometric radiographs with cervical vertebral maturation stages (CVMS).

METHODS

CVMS was evaluated on lateral cephalometric radiographs of 120 individuals aged 6 to 18 years. The subjects were divided into 6 groups (n= 20 each) according to CVMS. On panoramic and lateral cephalometric radiographs, fractal dimension (FD) analyses were performed in mandibular corpus, gonial and condylar regions and cervical vertebral bodies (C2, C3, C4).

RESULTS

FD measurements from the mandibular corpus region bilaterally and C2-C4 vertebral bodies showed significant positive correlations with CVMS (r= 0.418, r= 0.412, r= 0.324, r= 0.304, r= 0.263, respectively). Significant differences were found in the FD values of the right/left mandibular corpus and C2 and C3 vertebrae compared to CVMS (P< 0.001, P< 0.001, P= 0.005, P= 0.019, respectively).

CONCLUSION

Significant positive moderate correlations between the FD values of the right and left mandibular corpus and CVMS suggest that fractal analysis may be useful in determining skeletal maturity stage. The significant FD values obtained from the right/left mandibular corpus, and C2 and C3 vertebra indicate that the complexity of the internal trabecular structure increases with maturation.

Deep learning-based prediction of mandibular growth trend in children with anterior crossbite using cephalometric radiographs

BACKGROUND

It is difficult for orthodontists to accurately predict the growth trend of the mandible in children with anterior crossbite. This study aims to develop a deep learning model to automatically predict the mandibular growth result into normal or overdeveloped using cephalometric radiographs.

METHODS

A deep convolutional neural network (CNN) model was constructed based on the algorithm ResNet50 and trained on the basis of 256 cephalometric radiographs. The prediction behavior of the model was tested on 40 cephalograms and visualized by equipped with Grad-CAM. The prediction performance of the CNN model was compared with that of three junior orthodontists.

RESULTS

The deep-learning model showed a good prediction accuracy about 85%, much higher when compared with the 54.2% of the junior orthodontists. The sensitivity and specificity of the model was 0.95 and 0.75 respectively, higher than that of the junior orthodontists (0.62 and 0.47 respectively). The area under the curve value of the deep-learning model was 0.9775. Visual inspection showed that the model mainly focused on the characteristics of special regions including chin, lower edge of the mandible, incisor teeth, airway and condyle to conduct the prediction.

CONCLUSIONS

The deep-learning CNN model could predict the growth trend of the mandible in anterior crossbite children with relatively high accuracy using cephalometric images. The deep learning model made the prediction decision mainly by identifying the characteristics of the regions of chin, lower edge of the mandible, incisor teeth area, airway and condyle in cephalometric images.

Evaluation of maxillary and mandibular growth patterns with cephalometric analysis based on cervical vertebral maturation: A Japanese cross-sectional study

Background

Appropriate maxillofacial growth and development evaluation is important for effective orthodontic treatment. Growth evaluation is based on physiological age determined by individual development, but not chronological age. One strategy for determining physiological age is using the cervical vertebral bone age.

Objectives

This study aimed to clarify the standard size of the upper and lower jawbones in Japanese patients using the cervical vertebral maturation stages (CVMS) as an index and clarify the growth pattern. And to use the cervical spine age as a diagnostic aid in orthodontic treatment.

Material and methods

Random sampling was performed from the outpatients who visited the Orthodontics department, Tokyo Medical and Dental University Dental Hospital, and 400 patients were enrolled before treatment. Lateral cephalometric radiographs were obtained to measure the height and length of the mandible and the maxilla length with cephalometric analysis. Standard values were calculated for each cervical-spine-age group to analyze changes during mandibular and maxillary growth. Furthermore, we compared the differences between males and females. The Kruskal–Wallis test was used to compare cervical-spine-age groups, and the Steel–Dwass test was used for multiple comparisons. The reliability of CVMS was confirmed by calculating the weighted kappa coefficient (κ).

Results

κ for the degree of intra-evaluator agreement and the degree of the inter-evaluator agreement were calculated, and both indicated almost perfect agreement. We found that the distance between the anterior nasal spine (ANS) and posterior nasal spine (PNS) (i.e., ANS–PNS) increased significantly between CVMS II and CVMS III in males. The distance between Articulare (Ar) and Gonion (Go) (i.e., Ar–Go) and the distance between Go and Pogonion (Pog) (i.e., Go–Pog) increased significantly between CVMS III and CVMS IV in males.

Conclusion

The findings suggested that CVMS is a reliable indicator of the growth stage of the maxilla and mandible.