• The korean journal of orthodontics
• /
• v.51 no.2
• /
• pp.77-85
• /
• 2021

Objective: To evaluate the accuracy of a multi-stage convolutional neural network (CNN) model-based automated identification system for posteroanterior (PA) cephalometric landmarks. Methods: The multi-stage CNN model was implemented with a personal computer. A total of 430 PA-cephalograms synthesized from cone-beam computed tomography scans (CBCT-PA) were selected as samples. Twenty-three landmarks used for Tweemac analysis were manually identified on all CBCT-PA images by a single examiner. Intra-examiner reproducibility was confirmed by repeating the identification on 85 randomly selected images, which were subsequently set as test data, with a two-week interval before training. For initial learning stage of the multi-stage CNN model, the data from 345 of 430 CBCT-PA images were used, after which the multi-stage CNN model was tested with previous 85 images. The first manual identification on these 85 images was set as a truth ground. The mean radial error (MRE) and successful detection rate (SDR) were calculated to evaluate the errors in manual identification and artificial intelligence (AI) prediction. Results: The AI showed an average MRE of 2.23 ± 2.02 mm with an SDR of 60.88% for errors of 2 mm or lower. However, in a comparison of the repetitive task, the AI predicted landmarks at the same position, while the MRE for the repeated manual identification was 1.31 ± 0.94 mm. Conclusions: Automated identification for CBCT-synthesized PA cephalometric landmarks did not sufficiently achieve the clinically favorable error range of less than 2 mm. However, AI landmark identification on PA cephalograms showed better consistency than manual identification.

• The korean journal of orthodontics
• /
• v.48 no.1
• /
• pp.39-47
• /
• 2018

Objective: The aim of this study was to establish the normative data of dentofacial transverse dimensions according to the skeletal maturation stage in Korean adolescents with good occlusion, assess gender differences and determine correlations between transverse variables. Methods: A total of 577 Korean subjects between ages 7 to 19 years and exhibiting skeletal Class I occlusion were categorized by skeletal maturation index (SMI) of Fishman using hand-wrist radiographs. Dentofacial transverse dimensions were assessed using posteroanterior cephalograms. Independent two-sample t-tests were used to analyze differences between genders. Pearson correlation coefficient was used to determine the correlation between transverse measurements. Results: Dentofacial transverse norms relevant to skeletal maturation stages were established. The average maxillomandibular width difference and ratio at growth completion was 22.16 mm and 77.01% for males; 23.70 mm and 74.06% for females, respectively. Males had greater facial, maxillary and mandibular widths compared to females at every SMI stage. The maxillary and mandibular intermolar widths showed the strongest correlation for both sexes (r = 0.826 for males, r = 0.725 for females). Conclusions: Dentofacial transverse norms of Korean adolescents were established according to developmental stage. All dentofacial widths were greater in males at growth completion. Maxillary and mandibular intermolar widths were strongly correlated. This study may serve as a guideline for the assessment of dentofacial transverse growth according to skeletal maturation stage in Korean adolescents with good occlusion.

• The korean journal of orthodontics
• /
• v.52 no.2
• /
• pp.131-141
• /
• 2022

Objective: The purpose of this study was to compare the differences in dentoskeletal and soft tissue changes following conventional tooth-borne rapid maxillary expansion (RME) between adolescents and adults. Methods: Dentoskeletal and soft tissue variables of 17 adolescents and 17 adults were analyzed on posteroanterior and lateral cephalograms and frontal photographs at pretreatment (T1) and after conventional RME using tooth-borne expanders (T2). Changes in variables within each group between T1 and T2 were analyzed using Wilcoxon signed-rank test. Mann-Whitney U test was used to determine the differences in the pretreatment age, expansion and post-expansion durations, and dentoskeletal and soft tissue changes after RME between the groups. Spearman's correlation between pretreatment age and transverse dentoskeletal changes in the adolescent group was calculated. Results: Despite similar amounts of expansion at the crown level in both groups, the adult group underwent less skeletal expansion with less intermolar root expansion after RME than the adolescent group. The skeletal vertical dimension increased significantly in both groups without significant intergroup difference. The anteroposterior position of the maxilla was maintained in both groups, while a greater backward displacement of the mandible was evident in the adult group than that in the adolescent group after RME. The soft tissue alar width increased in both groups without a significant intergroup difference. In the adolescent group, pretreatment age was not significantly correlated with transverse dentoskeletal changes. Conclusions: Conventional RME may induce similar soft tissue changes but different dentoskeletal changes between adolescents and adults.

• The korean journal of orthodontics
• /
• v.29 no.3 s.74
• /
• pp.317-325
• /
• 1999

In proper diagnosis of skeletal Class III malocclusion, it was important to know the pattern of three dimensional skeletal & facial disharmony. The purpose of this study was to obtain P-A cephalometric characteristics in skeletal Class III malocclusion comparing with normal occlusion. The samples were consisted of 120 subjects, divided into four groups : Male normal occlusion, Female normal occlusion, Male skeletal Class III malocclusion, Female skeletal Class III malocclusion. Posteroanterior and lateral cephalogram were taken from the subjects with a x-ray apparatus (ASHAI CX90SP, Japan) and traced on acetate paper with routine manner. The transverse and vertical values from posteroanterior cephalometry, the sagittal values from lateral cephalometry and their ratio were obtained. The results were as follows: 1. The anteroposterior discrepancy in skeletal Class III group was not due to short maxillary length(Cd-A), but to longer mandibular length(Cd-Gn) than normal occlusion group. 2. The faces of skeletal Class III group were longer than normal occlusion group. It was not due to increase of upper face height(Cg-ANS) but to increase of the lower face height(ANS-Me) especially mandibular height(Cd-Me). 3. There was no difference in the facial width values between normal occlusion group and skeletal Class III group, except upper molar width(U6-U6), lower molar width(L6-L6) and mandibular width(Ag-Ag) of female skeletal Class III group which were larger than normal occlusion group. 4. The increase of mandibular length of skeletal Class III group was reflected in the increase of lower facial height but did not have an effect on the mandibular width.

• The korean journal of orthodontics
• /
• v.47 no.1
• /
• pp.50-58
• /
• 2017

Introduction: Identifying menton (Me) on posteroanterior cephalograms and three-dimensional (3D) cone-beam computed tomography (CBCT) images is difficult, because the midpoint of the symphyseal area is not identifiable after the mandibular symphysis fuses at an early age. The aim of this study was to evaluate the reliability of the identification of the genial tubercle (GT) in patients with mandibular asymmetry and to compare it with that of the traditional landmark, Me. Methods: The samples comprised 20 CBCT images of adults with mandibular asymmetry. Two examiners performed the identifications and measurements. Me and GT were marked, and the anteroposterior, vertical, and transverse distances to the three reference planes were measured on 3D-reconstructed CBCT images. The intra- and inter-examiner reliability of landmark identification of Me and GT were assessed using the intraclass correlation coefficient (ICC) and Bland-Altman plots. Results: The Me and GT landmarks showed excellent reliability ($ICC{\geq}0.993$) three-dimensionally. In the transverse evaluation, the ICC values of the GT (range, 0.997-0.999) tended to be slightly higher than those of Me (range, 0.993-0.996). In the Bland-Altman plots for the two separate assessments, Me showed a maximum error of 1.76 mm in the transverse direction, whereas the GT showed a maximum error of 0.96 mm in the 95% limit. Conclusions: Our results suggest that both Me and GT are clinically reliable and equally useful landmarks for the evaluation of mandibular asymmetry on CBCT images.