Development of an Artificial Intelligence System for the Automatic Evaluation of Cervical Vertebral Maturation Status

Background: Cervical vertebral maturation (CVM) is widely used to evaluate growth potential in the field of orthodontics. This study is aimed to develop an artificial intelligence (AI) system to automatically determine the CVM status and evaluate the AI performance. Methods: A total of 1080 cephalometric radiographs, with the age of patients ranging from 6 to 22 years old, were included in the dataset (980 in training dataset and 100 in testing dataset). Two reference points and thirteen anatomical points were labelled and the cervical vertebral maturation staging (CS) was assessed by human examiners as gold standard. A convolutional neural network (CNN) model was built to train on 980 images and to test on 100 images. Statistical analysis was conducted to detect labelling differences between AI and human examiners, AI performance was also evaluated. Results: The mean labelling error between human examiners was 0.48 ± 0.12 mm. The mean labelling error between AI and human examiners was 0.36 ± 0.09 mm. In general, the agreement between AI results and the gold standard was good, with the intraclass correlation coefficient (ICC) value being up to 98%. Moreover, the accuracy of CVM staging was 71%. In terms of F1 score, CS6 stage (85%) ranked the highest accuracy. Conclusions: In this study, AI showed a good agreement with human examiners, being a useful and reliable tool in assessing the cervical vertebral maturation.

Comparison of Deep Learning Models for Cervical Vertebral Maturation Stage Classification on Lateral Cephalometric Radiographs

The purpose of this study is to evaluate and compare the performance of six state-of-the-art convolutional neural network (CNN)-based deep learning models for cervical vertebral maturation (CVM) on lateral cephalometric radiographs, and implement visualization of CVM classification for each model using gradient-weighted class activation map (Grad-CAM) technology. A total of 600 lateral cephalometric radiographs obtained from patients aged 6–19 years between 2013 and 2020 in Pusan National University Dental Hospital were used in this study. ResNet-18, MobileNet-v2, ResNet-50, ResNet-101, Inception-v3, and Inception-ResNet-v2 were tested to determine the optimal pre-trained network architecture. Multi-class classification metrics, accuracy, recall, precision, F1-score, and area under the curve (AUC) values from the receiver operating characteristic (ROC) curve were used to evaluate the performance of the models. All deep learning models demonstrated more than 90% accuracy, with Inception-ResNet-v2 performing the best, relatively. In addition, visualizing each deep learning model using Grad-CAM led to a primary focus on the cervical vertebrae and surrounding structures. The use of these deep learning models in clinical practice will facilitate dental practitioners in making accurate diagnoses and treatment plans.

Bone density assessment for evaluation of gender differences in cervical vertebral maturation: A computed tomography study

INTRODUCTION

The cervical vertebral maturation (CVM) method is a vital tool for assessing the biological maturation of the orthodontic patient to evaluate the amount of mandibular bone growth left.

AIM

To assess and visualize the cervical vertebral morphology (bone density) of orthodontic patients of the age group 9,16,27 years.

MATERIAL AND METHODS

Twenty four subjects with age group of 9,16,27 who were randomly selected and subjected to 3d tomographic study to estimate the biological age of the orthodontic patients by analyzing c1 c2 and c3 vertebrae.

RESULT

The results showed that bone density of males is lesser than females in 9 and 16 years, whereas they have more bone density than females in 27 years.

CONCLUSION

The study provides qualitative method of assessing the biological age of the patient by using images of cervical vertebrae by three dimensional approach. Hence it can be useful for orthodontic diagnosis and treatment plan.

Assessment of skeletal maturation with permanent mandibular second molar calcification stages among a group of Nepalese orthodontic patients

Background

Assessment of growth status of a patient is a key component in orthodontic diagnosis and treatment planning for growing patients with skeletal discrepancy. Skeletal maturation based on hand-wrist radiograph and cervical vertebral maturation (CVM) are commonly used methods of growth assessment. Studies have shown that stages of dental calcification can also be used to assess skeletal maturation status of an individual, whereas other studies have suggested that the relationship between dental calcification and skeletal maturation should be interpreted with caution owing to racial variation.

Objective

To evaluate the relationship between permanent mandibular second molar calcification stages and skeletal maturity assessed by CVM among a group of Nepalese orthodontic patients.

Materials and methods

One hundred and sixty-eight digital radiographs (84 orthopantomograms and 84 lateral cephalograms) were obtained from the records of 84 patients who sought orthodontic treatment in Orthodontic and Dentofacial Orthopaedic Unit, Department of Dentistry, Institute of Medicine, Kathmandu. Two parameters were used in this study, namely, CVM stages from lateral cephalogram and Demirjian index (DI) stages from orthopantomogram. The evaluation of digital radiographs was carried out on a computer screen with a resolution of 1,280×800 pixels. The association between DI stages of permanent mandibular second molar and CVM stages was assessed.

Results

A statistically significant association was found between DI and CVM stages for both male and female subjects with Pearson’s contingency coefficient value of 0.751 and 0.766 for male and female subjects, respectively.

Conclusion

Skeletal maturation can be reliably assessed with dental calcification stages of permanent mandibular second molar for Nepalese orthodontic patients.

Long-term skeletal and dental effects and treatment timing for functional appliances in Class II malocclusion

OBJECTIVE

To analyze the long-term skeletal and dentoalveolar effects and to evaluate treatment timing of Class II treatment with functional appliances followed by fixed appliances.

MATERIALS AND METHODS

A group of 40 patients (22 females and 18 males) with Class II malocclusion consecutively treated either with a Bionator or an Activator followed by fixed appliances was compared with a control group of 20 subjects (9 females and 11 males) with untreated Class II malocclusion. Lateral cephalograms were available at the start of treatment (mean age 10 years), end of treatment with functional appliances (mean age 12 years), and long-term observation (mean age 18.6 years). The treated sample also was divided into two groups according to skeletal maturity. The early-treatment group was composed of 20 subjects (12 females and 8 males) treated before puberty, while the late-treatment group included 20 subjects (10 females and 10 males) treated at puberty. Statistical comparisons were performed with analysis of variance followed by Tukey's post hoc tests.

RESULTS

Significant long-term mandibular changes (Co-Gn) in the treated group (3.6 mm over the controls) were associated with improvements in the skeletal sagittal intermaxillary relationship, overjet, and molar relationship (∼3.0-3.5 mm). Treatment during the pubertal peak was able to produce significantly greater increases in total mandibular length (4.3 mm) and mandibular ramus height (3.1 mm) associated with a significant advancement of the bony chin (3.9 mm) when compared with treatment before puberty.

CONCLUSION

Treatment of Class II malocclusion with functional appliances appears to be more effective at puberty.