Comparison of abnormalities in the sequence of growth stages in the skeletal maturity index vs cervical vertebral maturation: A retrospective study

ABSTRACT Objectives To evaluate the frequency of abnormal progression that could ultimately affect the reliability of the skeletal maturity index (SMI) and the cervical vertebral maturation (CVM) method that are most commonly used analyses for skeletal age assessment. Materials and Methods A retrospective design was used to compare 299 hand-wrist radiographs with 299 lateral skull radiographs regarding the number of abnormalities in the proposed sequence of maturation in the SMI and CVM methods. Results A significantly greater number of abnormalities occurred in the sequence of CVM progression compared with SMI (P < .001). Sex and age did not have an effect. Conclusions Skeletal age assessment based on SMI is more accurate than CVM regarding the progressive sequence of stages.

Differences of anteroposterior facial dimensions in male and female children on intermediate mixed and early permanent dentition using Cervical Vertebrae Maturation Index

Introduction: Cervical vertebrae are one of the indicators for craniofacial bones maturation. Timing of craniofacial bone maturation determined achievement of orthodontic early treatment. Some previous researchers recommended cervical vertebral maturation to assess craniofacial growth. This study was aimed to analyse the differences of anteroposterior facial dimensions in male and female children on intermediate mixed and early permanent dentition using Cervical Vertebrae Maturation Index (CVMI). Methods: An analytic observational study with a cross-sectional design was conducted on the students of Islamic Elementary School (Madrasah Ibtidaiyah) in Depok district, Sleman, Yogyakarta, from July 2019 to January 2020. Subjects consisted of 22 males and 22 females aged 8-11 years, obtained by a consecutive sampling technique. The anteroposterior facial analysis was performed on the lateral cephalometry for measuring the distance of Sella turcica to Nasion (S-N) representing the anterior cranial base, Posterior Nasal Spine to Anterior Nasal Spine (PNS-ANS) representing the maxilla and Gonion-Menton (Go-Me) and Condylion-Gnathion (Co-Gn) represents the mandible. Assessment of CVMI was decided by the Hassel and Farman methods. Data were analysed by One Way ANOVA. Results: The mean value of S-N, PNS-ANS, Go-Me, and Co-Gn dimensions, generally were higher in males than females; however, only dimensions of maxillary and mandibular were showed significant difference (p<0.05), while the S-N dimension was not significantly different (p>0.05). At the interval of CVMI 3 and 4, the Go-Me and Co-Gn dimensions showed a significant difference (p<0.05) both in males and females. Conclusion: There was a difference in anteroposterior dimensions of the maxillary and mandibular in cervical vertebral maturation in children with intermediate mixed and early permanent dentition, however, no difference was found in the anterior cranial base.

Dentoskeletal effects of early class III treatment protocol based on timing of intervention in children

Background To detect the optimal timing of intervention based on different cervical vertebral maturation stage (CS1-2 vs. CS3-4) for the treatment of Class III malocclusion with early Class III protocol. Methods A total sample of 43 patients (23 females, 20 males) ranging between 7 and 13 years of age with dentoskeletal Class III malocclusion treated with the modified SEC III (Splints, Elastic and Chincup) protocol divided into two groups based on the cervical vertebral maturation stages (CS1-2 and CS3-4) was included in this retrospective observational longitudinal study. Patient compliance was assessed using a 2-point Likert scale. Statistical comparisons between the two groups were performed with independent sample t tests. Results No statistically significant differences for any of the cephalometric variables describing the baseline dentoskeletal features were found between the two groups except for the mandibular unit length that was significantly greater in the pubertal group (P = 0.005). The modified SEC III protocol produced favorable sagittal outcomes in both groups, whereas no statistically significant T1-T2 changes were found between the CS1-2 and CS3-4 groups for any of the angular and linear measurements. No significant differences were found in the prevalence rates of the degree of collaboration between the two groups (P = 1.000). Conclusions No significant differences between prepubertal and pubertal patients were found in the sagittal and vertical dentoskeletal changes with the modified SEC III protocol. Thus, this early Class III treatment produced similar favorable effects in growing subjects regardless of the cervical vertebral maturation stages from CS1 to CS4.

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.

Estimating Cervical Vertebral Maturation with a Lateral Cephalogram Using the Convolutional Neural Network

Recently, the estimation of bone maturation using deep learning has been actively conducted. However, many studies have considered hand–wrist radiographs, while a few studies have focused on estimating cervical vertebral maturation (CVM) using lateral cephalograms. This study proposes the use of deep learning models for estimating CVM from lateral cephalograms. As the second, third, and fourth cervical vertebral regions (denoted as C2, C3, and C4, respectively) are considerably smaller than the whole image, we propose a stepwise segmentation-based model that focuses on the C2–C4 regions. We propose three convolutional neural network-based classification models: a one-step model with only CVM classification, a two-step model with region of interest (ROI) detection and CVM classification, and a three-step model with ROI detection, cervical segmentation, and CVM classification. Our dataset contains 600 lateral cephalogram images, comprising six classes with 100 images each. The three-step segmentation-based model produced the best accuracy (62.5%) compared to the models that were not segmentation-based.

Evaluation of Maxillary and Mandibular Growth Pattern Based on Cervical Vertebral Maturation in Japanese

Appropriate evaluation of maxillofacial growth and development is important for effective orthodontic treatment. The evaluation of growth is not based on chronological age, but on the physiological age that is evaluated according to individual development. The cervical vertebral bone age is one approach to evaluate physiological age. In the present study, we evaluated the growth pattern of maxilla and mandible in Japanese patients using the age of the cervical vertebrae as an index. Lateral cephalometric radiographs taken before the start of the orthodontic treatment were traced to evaluate the age of the cervical vertebrae and mandible. Altogether, 400 patients were allocated to groups based on the cervical vertebral maturation stages (CVMS), namely, CVMS I to V, with 80 patients in each group. In this study, stratified random sampling was used to obtain the required samples. We measured ANS-PNS as an index of maxillary length, whereas Ar-Go as an index of mandibular height and Go-Pog as an index of mandibular length on the cephalograms. It was found that ANS-PNS increased significantly between CVMS II and CVMS III, while both Ar-Go and Go-Pog increased significantly between CVMS III and CVMS IV in men. On the other hand, such significant increases in consecutive stages were not found in women. Based on these observations, it was suggested that CVMS is effective in evaluating the growth pattern of the maxilla and mandible.

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.

Reliability of cervical vertebral maturation compared to hand-wrist for skeletal maturation assessment in growing subjects: A systematic review

BACKGROUND: Radiographic methods to assess skeletal maturity (SM) have a key role in adolescent idiopathic scoliosis (AIS) management, allowing to predict risk of spinal curve progression. Cervical vertebral maturation (CVM) has been recently introduced as an alternative tool to assess skeletal maturity; however, its clinical role is still debated. OBJECTIVE: This systematic review aimed to investigate the reliability of CVM in the SM assessment of growing subjects, comparing it to hand wrist maturation (HVM). METHODS: PubMed, Scopus, and Web of Science databases were systematically searched from inception until 31st December 2020 to identify observational studies presenting: growing subjects as participants; CVM methods as intervention; HVM methods as comparator; reliability for SM assessment as outcome. A 10-item quality tool has been used to assess study quality. RESULTS: Out of 205 papers, 12 papers were included in the data synthesis. We classified 10 studies (83.3%) as medium-quality studies and 2 studies (16.7%) as high-quality studies. Eight studies reported a significant correlation between CVM Baccetti and different HWM methods. CONCLUSION: Taken together, these findings suggested that CVM might be considered as reliable SM assessment method compared to HWM in growing subjects. However, further studies are warranted to confirm these findings.