ABSTRACT
Purpose: The assessment of bone age has applications in a wide variety of fields: from orthodontics to immigration. The traditional non?automated methods are time?consuming and subject to inter? and intra?observer variability. This is the first study of its kind done on the Indian population. In this study, we analyse different pre?processing techniques and architectures to determine the degree of maturation (i.e. cervical vertebral maturation [CVM]) from cephalometric radiographs using machine learning algorithms. Methods: Cephalometric radiographs—labelled with the correct CVM stage using Baccetti et al. method—from 383 individuals aged between 10 and 36 years were used in the study. Data expansion and in?place data augmentation were used to handle high data imbalances. Different pre?processing techniques like Sobel filters and canny edge detectors were employed. Several deep learning convolutional neural network (CNN) architectures along with numerous pre?trained models like ResNet?50 and VGG?19 were analysed for their efficacy on the dataset. Results: Models with 6 and 8 convolutional layers trained on 64 × 64–size grayscale images trained the fastest and achieved the highest accuracy of 94%. Pre?trained ResNet?50 with the first 49 layers frozen and VGG?19 with 10 layers frozen to training had remarkable performances on the dataset with accuracies of 91% and 89%, respectively. Conclusions: Custom deep CNN models with 6–8 layers on 64 × 64–sized greyscale images were successfully used to achieve high accuracies to classify the majority classes. This study is a launchpad in the development of an automated method for bone age assessment from lateral cephalograms for clinical purposes.
ABSTRACT
OBJECTIVE@#The accuracy of the occlusion vertical dimensions of edentulous Han patients from Yunnan province was compared and analyzed on the basis of cone-beam computed tomography (CBCT)-synthesized cephalograms, closest speaking space method, and interocclusal distance.@*METHODS@#A database correlating the CBCT head lateral images of Han patients from Yunnan province with normal occlusal conditions was first constructed. Then, five edentulous Han patients aged 63-78 years old from Yunnan Province were selected. NNT.View software was used to measure and analyze hard tissue cephalometric radiographs that had been transformed by the CBCT marker. The radiographs were then combined with the normal population database for the assessment of occlusion vertical dimensions. The occlusion vertical dimensions determined on the basis of CBCT-synthesized cephalograms, the closest speaking space method, and the free-way space were analyzed.@*RESULTS@#The closest speaking space method was used as the standard control group, the differences between seven methods and the closest speaking space method were analyzed. The seven methods include free-way space method and six CBCT-synthesized cephalograms methods (N-ANS/ANS-Me, S-Go/N-Me, ANS-Gn/N-ANS, ANS-FH/Me-FH, ANS-Xi-Pm, and CA/LA). The seven methods were highly consistent with the closest speaking space method (intraclass correlation coefficient>0.986). The absolute values of the differences between the methods of free-way space, N-ANS/ANS-Me, S-Go/N-Me and the closest speaking space method were lower than those of the other four groups (P<0.05), while the differences between ANS-FH/Me-FH and the closest speaking space method was higher than those other groups (P<0.05).@*CONCLUSIONS@#CBCT-synthesized cephalograms, with the exception of ANS-FH/Me-FH, can provide references for the clinical evaluation of the occlusion vertical dimensions of patients with edentulous jaws.
Subject(s)
Aged , Humans , Middle Aged , Cephalometry , China , Cone-Beam Computed Tomography , Imaging, Three-Dimensional , Mouth, Edentulous , Vertical DimensionABSTRACT
The purpose of this study was to investigate immediate changes in the mandibular dentition after maxillary molar distalization using headgear in non-growing patients. Sixteen patients (mean age, 18.9 ± 2.0 years) with Class II molar relationship and crowding were included in the present study. To correct the molar relationship, headgear was used for maxillary molar distalization. Cone-beam computed tomography-generated half-cephalograms (CG Cephs) and dental casts were used to evaluate dental changes for each subject before and immediately after molar distalization using headgear. The mean duration that subjects wore the headgear was 6.3 months. CG Cephs showed that the first maxillary molars were distalized 4.2 ± 1.6 mm with 9.7°± 6.1° of distal angulation. The intercanine, interpremolar, and intermolar widths of the mandible increased after maxillary molar distalization. The present study's results suggest that maxillary molar distalization using headgear induces a spontaneous response in the untreated mandibular dentition of non-growing patients.
Subject(s)
Humans , Dentition , Malocclusion , Mandible , MolarABSTRACT
Aim: Determination of the plane of occlusion in completely edentulous patients with the help of the ala‑tragus line (Camper’s plane) may be questioned. An attempt to devise an alternative method to determine the orientation of the plane of occlusion was made. Materials and Methods: Cephalometric analysis was used to identify whether a correlation exists between the plane of occlusion of dentulous Indian individuals and other stable cranial landmarks. Results: A negative correlation was found to exist between the occlusal Plane–FH plane angle and the porion–nasion–anterior nasal spine (PoNANS) angle. Conclusions: From the derived mathematical correlation, it was concluded that the angulation of the occlusal plane in completely edentulous subjects may be determined by taking a cephalogram at the diagnostic stage. Further, the clinical applicability of the derived mathematical formula (while determining the plane of occlusion) was tested on completely edentulous patients.
ABSTRACT
Objective To evaluate the soft tissue profile in adults with unoperated isolated cleft palate. Methods Twenty patients older than 16 years(median age,18.4) with unoperated isolated cleft palate were enrolled.Soft tissue lateral cephalograms were traced and compared with those of cleft operated patients and class-Ⅰocclusion individuals.The results of various measurements were analyzed with ANOVA by SPSS11.5. Results In adults with unoperated isolated cleft palate,there was restriction at the top of the upper lip,and the antelabrum of upper lip and the lower lip were found normal. Conclusion The soft tissue profile in adults with unoperated isolated cleft palate exhibits almost the same characteristics as the corresponding hard tissue,and there is covering over effect of the soft tissue to some extent.
ABSTRACT
This study aimed at investigating the skeletal, dentoalveolar, and soft tissue changes of Class III malocclusion cases treated by second molar extraction. The lateral cephalograms of 15 subjects with moderate Class III malocclusion by average ANB -1.4degrees and IMPA 85degrees were traced and the computerized superimposition of average craniofacial change was made. The data was gathered and statistically analyzed. The results were as follows: 1. Lower anterior facial height/anterior facial height increased by 0.6%(P<0.01), mandibular plane increased by 1.5degrees (P<0.05). 2. There was a slightly downward & backward rotation of the mandible. 3. Lower first molar tipped distally by 4.06mm(P<0.001), lower anterior teeth lingually tipped by 3.2degrees (P<0.05). 4. Retracted lower lip improved facial profile. This study may suggest that second molar extraction could be effective for a moderate Class III malocclusion to make distalization of the lower first molar easier and avoid severe lingual tipping of the lower incisor, if the lower third molar has a normal shape, good direction of eruption and adequate time for lower second molar extraction.
Subject(s)
Incisor , Lip , Malocclusion , Mandible , Molar , Molar, Third , ToothABSTRACT
Conventional cephalometrics have inherent errors because their evaluation is performed in two-dimension for threedimensional object. To compensate these errors, three-dimensional cephalograms - derivation of three-dimensional data from conventional lateral and postero-anterior cephalograms - were developed. In this study, the accuracy and precision of three dimensional cephalograms were determined by means of 10 linear and 12 angular measurements on 36 acrylic skull models and by the comparison of conventional lateral cephalograms. The results were as follows 1. Mean difference between three-dimensional cephalograms and actual models in linear measurements was 0.94+/-0.62 mm and mean rate of magnification of three-dimensional cephalograms was 100.31+/-0.91%. There were no statistically significant differences between three-dimensional cephalograms and actual models in linear measurements(alpha=0.1). 2. Mean difference between conventional lateral cephalograms and actual models in linear measurements was 6.44+/-1.48 mm and mean rate of magnification of lateral cephalograms was 106.99+/-1.45%. There were statistically significant differences between lateral cephalograms and actual models in linear measurements(P<0.005). 3. Mean difference between three-dimensional cephalograms and actual models in angular measurements was 1.22+/-0.82degrees and mean rate of magnification of three-dimensional cephalograms was 105.71+/-12.07%. There were no statistically significant differences between three-dimensional cephalograms and actual models in angular measurements(alpha=0.1). 4. Mean difference between conventional lateral cephalograms and actual models in angular measurements was 1.70+/-0.94degrees and mean rate of magnification of lateral cephalograms was 106.35+/-15.70%. There were no statistically significant differences between lateral cephalograms and actual models in angular measurements(alpha=0.1). There were similarity between three-dimensional and lateral cephalograms in angular measurements.
Subject(s)
SkullABSTRACT
The purpose of this study was to assess the skeletal characteristics of the maxillofacial norms and the interpretation of craniofacial relations in Korean adults by applying the Ricketts Analysis. The factors of the applied lateral cephalometric measurements were composed of the 10 factor analysis (Summary Analysis) and 7 internal structures to be suggested by Ricketts. Lateral cephalograms were obtained from 60 subjects over 21 years old that consisted of 30 males and 30 females with normal occlusion, acceptable profile. The results were as follow: 1. The tables of means, standard deviations in each item and sex were made. 2. The author performed whether there was significance (P<0.05) between the registered male and female's measurement in each item.