RESUMEN
INTRODUCTION: The purpose of this study was to evaluate the accuracy of auto-identification of the posteroanterior (PA) cephalometric landmarks using the cascade convolution neural network (CNN) algorithm and PA cephalogram images of a different quality from nationwide multiple centers nationwide. METHODS: Of the 2798 PA cephalograms from 9 university hospitals, 2418 images (2075 training set and 343 validation set) were used to train the CNN algorithm for auto-identification of 16 PA cephalometric landmarks. Subsequently, 99 pretreatment images from the remaining 380 test set images were used to evaluate the accuracy of auto-identification of the CNN algorithm by comparing with the identification by a human examiner (gold standard) using V-Ceph 8.0 (Ostem, Seoul, South Korea). Pretreatment images were used to eliminate the effects of orthodontic bracket, tube and wire, surgical plate, and surgical screws. Paired t test was performed to compare the x- and y-coordinates of each landmark. The point-to-point error and the successful detection rate (range, within 2.0 mm) were calculated. RESULTS: The number of landmarks without a significant difference between the location identified by the human examiner and by auto-identification by the CNN algorithm were 8 on the x-coordinate and 5 on the y-coordinate, respectively. The mean point-to-point error was 1.52 mm. The low point-to-point error (<1.0 mm) was observed at the left and right antegonion (0.96 mm and 0.99 mm, respectively) and the high point-to-point error (>2.0 mm) was observed at the maxillary right first molar root apex (2.18 mm). The mean successful detection rate of auto-identification was 83.3%. CONCLUSIONS: Cascade CNN algorithm for auto-identification of PA cephalometric landmarks showed a possibility of an effective alternative to manual identification.
Asunto(s)
Algoritmos , Redes Neurales de la Computación , Puntos Anatómicos de Referencia , Cefalometría/métodos , Humanos , Radiografía , Reproducibilidad de los ResultadosRESUMEN
INTRODUCTION: Vertical bony step (VBS) occurs between proximal and distal segments of the mandible during mandibular setback surgery with bilateral sagittal split ramus osteotomy. The purpose of this study was to investigate whether VBS is correlated with the relapse of mandibular setback using 3-dimensional models constructed from cone-beam computed tomography. METHODS: The subjects consisted of 30 patients who underwent bilateral sagittal split ramus osteotomy for a mandibular setback. Double jaw surgery was performed in 18 patients, and isolated mandibular setback surgery was performed in 12 patients. Cone-beam computed tomography scans were taken at pretreatment (T0), postsurgery (T1), and posttreatment (T2). Treatment changes and the correlations between measurements were evaluated. RESULTS: The mean mandibular setback was -11.9 mm, and the mean VBS was -5.6 mm. Correlations with the relapse of mandibular setback were found in the amount of mandibular setback (T1 - T0), development of VBS (T1 - T0), posterior movement of the proximal segment (T1 - T0), counterclockwise rotation of symphysis (T2 - T1), and the resolution of VBS (T2 - T1). CONCLUSIONS: The development and resolution of VBS were correlated with the relapse of mandibular setback. Minimizing VBS is recommended to reduce the relapse of mandibular setback.
Asunto(s)
Mandíbula , Osteotomía Sagital de Rama Mandibular , Cefalometría/métodos , Tomografía Computarizada de Haz Cónico/métodos , Humanos , Mandíbula/diagnóstico por imagen , Mandíbula/cirugía , Osteotomía Sagital de Rama Mandibular/métodos , RecurrenciaRESUMEN
Crowdsourcing has become an important tool for gathering knowledge for urban planning problems. The questions posted to the crowd for urban planning problems are quite different from the traditional crowdsourcing models. Unlike the traditional crowdsourcing models, due to the constraints among the multiple components (e.g., multiple locations of facilities) in a single question and non-availability of the defined option sets, aggregating of multiple diverse opinions that satisfy the constraints as well as finding the ranking of the crowd workers becomes challenging. Moreover, owing to the presence of the conflicting nature of features, the traditional ranking methods such as the Technique for Order of Preference by Similarity to Ideal Solution (TOPSIS) cannot always be feasible as the optimal solutions in terms of multiple objectives cannot occur simultaneously for the conflicting cases (e.g., benefit and cost criteria) for urban planning problems. Therefore, in this work, a multi-objective approach is proposed to produce better compromised solutions in terms of conflicting features from the general crowd. In addition, the solutions are employed to obtain a proper ideal solution for ranking the crowd. The experimental results are validated using two constrained crowd opinion datasets for real-world urban planning problems and compared with the state-of-the-art TOPSIS models.
RESUMEN
OBJECTIVE: To investigate the accuracy of automated identification of cephalometric landmarks using the cascade convolutional neural networks (CNN) on lateral cephalograms acquired from nationwide multi-centres. SETTINGS AND SAMPLE POPULATION: A total of 3150 lateral cephalograms were acquired from 10 university hospitals in South Korea for training. MATERIALS AND METHODS: We evaluated the accuracy of the developed model with independent 100 lateral cephalograms as an external validation. Two orthodontists independently identified the anatomic landmarks of the test data set using the V-ceph software (version 8.0, Osstem, Seoul, Korea). The mean positions of the landmarks identified by two orthodontists were regarded as the gold standard. The performance of the CNN model was evaluated by calculating the mean absolute distance between the gold standard and the automatically detected positions. Factors associated with the detection accuracy for landmarks were analysed using the linear regression models. RESULTS: The mean inter-examiner difference was 1.31 ± 1.13 mm. The overall automated detection error was 1.36 ± 0.98 mm. The mean detection error for each landmark ranged between 0.46 ± 0.37 mm (maxillary incisor crown tip) and 2.09 ± 1.91 mm (distal root tip of the mandibular first molar). A significant difference in the detection accuracy among cephalograms was noted according to hospital (P = .011), sensor type (P < .01), and cephalography machine model (P < .01). CONCLUSION: The automated cephalometric landmark detection model may aid in preliminary screening for patient diagnosis and mid-treatment assessment, independent of the type of the radiography machines tested.
Asunto(s)
Puntos Anatómicos de Referencia , Redes Neurales de la Computación , Cefalometría , Humanos , Radiografía , Reproducibilidad de los ResultadosRESUMEN
For the treatment of low-angle mandibular prognathism, rotational mandibular setback surgery is usually performed with Le Fort I maxillary osteotomy to rotate the maxillomandibular complex simultaneously. However, this maxillary surgery can be replaced with the orthodontic intrusion of maxillary posterior teeth. Single-jaw rotational mandibular setback surgery can be done with a surgery-first approach by planning orthodontic rotation of the maxillary occlusal plane with the simulation of the postsurgical forward mandibular rotation. This case report describes this approach applied to a 19-year-old female patient with low-angle mandibular prognathism but without maxillary deficiency. A Class II open bite was formed by the rotational setback surgery. During postsurgical orthodontic treatment, the maxillary total arch was distalized with maxillary molar intrusion using palatal mini-implants and lever. This case report demonstrates that orthodontic rotation of the maxillary occlusal plane and simulation of mandibular rotation can replace maxillary surgery and enable single-jaw rotational mandibular setback surgery with a surgery-first approach.
Asunto(s)
Maloclusión de Angle Clase III , Procedimientos Quirúrgicos Ortognáticos , Prognatismo , Adulto , Cefalometría , Femenino , Humanos , Maloclusión de Angle Clase III/diagnóstico por imagen , Maloclusión de Angle Clase III/cirugía , Mandíbula/diagnóstico por imagen , Mandíbula/cirugía , Maxilar , Osteotomía Le Fort , Prognatismo/diagnóstico por imagen , Prognatismo/cirugía , Dimensión Vertical , Adulto JovenRESUMEN
When performing single-jaw surgery for mandibular setback, the distal segment of the mandible is brought distally along the occlusal plane, leaving the relationship of the B-point and pogonion unchanged. Double-jaw surgery for rotation of the maxillomandibular complex can be considered for solving this problem. However, maxillary surgery for rotational setback of the mandible can be replaced with orthodontic intrusion of the maxillary molars. Correcting the mandibular asymmetry that frequently accompanies mandibular prognathism often requires corrections of roll, yaw, and transverse shift of the mandible. Performing these corrections in mandibular single-jaw setback surgery requires transverse decompensation and orthodontic correction of maxillary occlusal-plane canting. This case report describes the simultaneous achievement of maxillary molar intrusion, transverse decompensation, and canting correction using a palatal lever supported by 2 midpalatal mini-implants. After creating a lateral open bite, mandibular setback surgery was performed with a 13.5° clockwise rotation, 2.9° roll correction, 3.5° yaw correction, and 3.5-mm transverse shift. The application of rotational setback significantly improved the facial esthetics. This case report demonstrates that orthodontic intrusion of the maxillary molars and transverse decompensation can replace maxillary surgery in the treatment of mandibular prognathism with asymmetry.
Asunto(s)
Procedimientos Quirúrgicos Ortognáticos , Prognatismo , Cefalometría , Estética Dental , Humanos , Mandíbula , Maxilar , Diente MolarRESUMEN
INTRODUCTION: The authors of this work propose an unsupervised machine learning model that has the ability to identify real-world latent infectious diseases by mining social media data. In this study, a latent infectious disease is defined as a communicable disease that has not yet been formalized by national public health institutes and explicitly communicated to the general public. Most existing approaches to modeling infectious-disease-related knowledge discovery through social media networks are top-down approaches that are based on already known information, such as the names of diseases and their symptoms. In existing top-down approaches, necessary but unknown information, such as disease names and symptoms, is mostly unidentified in social media data until national public health institutes have formalized that disease. Most of the formalizing processes for latent infectious diseases are time consuming. Therefore, this study presents a bottom-up approach for latent infectious disease discovery in a given location without prior information, such as disease names and related symptoms. METHODS: Social media messages with user and temporal information are extracted during the data preprocessing stage. An unsupervised sentiment analysis model is then presented. Users' expressions about symptoms, body parts, and pain locations are also identified from social media data. Then, symptom weighting vectors for each individual and time period are created, based on their sentiment and social media expressions. Finally, latent-infectious-disease-related information is retrieved from individuals' symptom weighting vectors. DATASETS AND RESULTS: Twitter data from August 2012 to May 2013 are used to validate this study. Real electronic medical records for 104 individuals, who were diagnosed with influenza in the same period, are used to serve as ground truth validation. The results are promising, with the highest precision, recall, and F1 score values of 0.773, 0.680, and 0.724, respectively. CONCLUSION: This work uses individuals' social media messages to identify latent infectious diseases, without prior information, quicker than when the disease(s) is formalized by national public health institutes. In particular, the unsupervised machine learning model using user, textual, and temporal information in social media data, along with sentiment analysis, identifies latent infectious diseases in a given location.
Asunto(s)
Enfermedades Transmisibles , Minería de Datos , Medios de Comunicación Sociales/estadística & datos numéricos , Aprendizaje Automático no Supervisado , Humanos , Salud Pública , Red SocialRESUMEN
INTRODUCTION: The purpose of this study was to determine the relationships between cephalometric measurements and cone-beam computed tomography-based measurements of the palatal bone thickness. METHODS: Thirty sets of cone-beam computed tomography images and lateral cephalograms were used. Palatal bone thicknesses were measured anteroposteriorly from between the first and second premolars to between the first and second molars using both imaging methods, and also laterally from 1.5 mm off-center to 10 mm off-center in the cone-beam computed tomography images. Repeated-measures analysis of variance was used to examine the differences between the measurements. RESULTS: Bland-Altman plots showed that the 95% limits of agreement were smallest at 5 mm off-center (-0.2 ± 1.7 mm). The 5-mm off-center measurements were the only ones for which there were no statistically significant differences compared with the cephalometric measurements in all anteroposterior areas. The measurements at 1.5 mm off-center were significantly thicker than the cephalometric measurements only from the area between the second premolar and the first molar to the area between the first and second molars. CONCLUSIONS: Among the areas measured, the bone at 5 mm off-center is most likely to be depicted in cephalograms as palatal bone contours.
Asunto(s)
Cefalometría/métodos , Tomografía Computarizada de Haz Cónico/métodos , Paladar Duro/diagnóstico por imagen , Diente Premolar/diagnóstico por imagen , Cefalometría/estadística & datos numéricos , Tomografía Computarizada de Haz Cónico/estadística & datos numéricos , Femenino , Humanos , Procesamiento de Imagen Asistido por Computador/métodos , Procesamiento de Imagen Asistido por Computador/estadística & datos numéricos , Incisivo/diagnóstico por imagen , Masculino , Maxilar/diagnóstico por imagen , Seno Maxilar/diagnóstico por imagen , Diente Molar/diagnóstico por imagen , Cavidad Nasal/diagnóstico por imagen , Adulto JovenRESUMEN
Analyzing the correlation between cephalometric measurements is important for improving our understanding of the anatomy in the oral and maxillofacial region. To minimize bias resulting from the design of the input data and to establish a reference for malocclusion research, the aims of this study were to construct the input set by integrating nine cephalometric analyses and to study the correlation structure of cephalometric variables in Korean adults with normal occlusion. To analyze the complex correlation structure among 65 cephalometric variables, which were based on nine classical cephalometric analyses, network analysis was applied to data obtained from 735 adults (368 males, 367 females) aged 18-25 years with normal occlusion. The structure was better revealed through weighted network analysis and minimum spanning tree. Network analysis revealed cephalometric variable clusters and the inter- and intra-correlation structure. Some metrics were divided based on their geometric interpretation rather than their clinical significance. It was confirmed that various classical cephalometric analyses primarily focus on investigating nine anatomical features. Investigating the correlation between cephalometric variables through network analysis can significantly enhance our understanding of the anatomical characteristics in the oral and maxillofacial region, which is a crucial step in studying malocclusion using artificial intelligence.
Asunto(s)
Cefalometría , Humanos , Cefalometría/métodos , Masculino , Femenino , Adulto , Adolescente , República de Corea , Adulto Joven , Oclusión Dental , Pueblos del Este de AsiaRESUMEN
The aim of this study was to evaluate the distance between the maxillary central incisor root and the incisive canal based on skeletal malocclusion classification and to analyze the morphology of the incisive canal using cone-beam computed tomography (CBCT). Skeletal malocclusion was categorized into Class I, II, and III using lateral cephalometric analysis. Measurements of the distance between the maxillary central incisor root and the incisive canal were taken at two levels: 2 mm (L1) and 4 mm (L2) superior to the labial cementoenamel junction of the maxillary central incisor. At L1, the distance was found to be closer in the Class II group compared to the Class I or Class III groups. Similarly, at L2, the Class II group exhibited a closer distance than the Class III group. Interestingly, females showed a closer distance compared to males at both L1 and L2. Further analysis revealed a significant gender difference in the Class I and III groups, but not in the Class II group. These findings emphasize the significance of evaluating the distance between the maxillary central incisor root and the incisive canal in patients with skeletal Class II malocclusion, regardless of gender.
Asunto(s)
Cefalometría , Tomografía Computarizada de Haz Cónico , Incisivo , Maloclusión , Maxilar , Raíz del Diente , Humanos , Incisivo/diagnóstico por imagen , Masculino , Femenino , Tomografía Computarizada de Haz Cónico/métodos , Maxilar/diagnóstico por imagen , Raíz del Diente/diagnóstico por imagen , Raíz del Diente/anatomía & histología , Maloclusión/diagnóstico por imagen , Maloclusión/clasificación , Cefalometría/métodos , Adulto , Adulto Joven , AdolescenteRESUMEN
Orthodontic uprighting or traction of an impacted mandibular second molar often necessitates invasive interventions. This report aims to illustrate the utilization of nickel-titanium wire segments inserted into small, simple tubes for uprighting mesially impacted mandibular second molars and also for scissor bite correction. The term "simple tube" refers to a tube without a bonding base attached to a tooth surface by covering it with flowable composite resin. Due to the absence of a bonding base, the simple tube is characterized by its diminutive size and minimal profile height, facilitating placement on partially exposed second molars and unconventional positioning to adjust the force geometry. In this case study, mesially-impacted mandibular second molars with scissor bite were uprighted in a 21-year-old male utilizing simple tubes. Simple tubes can be used for molar uprighting and scissor bite correction buccally and lingually.
Asunto(s)
Mandíbula , Diente Molar , Níquel , Alambres para Ortodoncia , Técnicas de Movimiento Dental , Diente Impactado , Humanos , Masculino , Adulto Joven , Técnicas de Movimiento Dental/instrumentación , Técnicas de Movimiento Dental/métodos , Diente Impactado/terapia , Diseño de Aparato Ortodóncico , Titanio , Aleaciones Dentales , Resinas CompuestasRESUMEN
Objective: : To quantify the effects of midline-related landmark identification on midline deviation measurements in posteroanterior (PA) cephalograms using a cascaded convolutional neural network (CNN). Methods: : A total of 2,903 PA cephalogram images obtained from 9 university hospitals were divided into training, internal validation, and test sets (n = 2,150, 376, and 377). As the gold standard, 2 orthodontic professors marked the bilateral landmarks, including the frontozygomatic suture point and latero-orbitale (LO), and the midline landmarks, including the crista galli, anterior nasal spine (ANS), upper dental midpoint (UDM), lower dental midpoint (LDM), and menton (Me). For the test, Examiner-1 and Examiner-2 (3-year and 1-year orthodontic residents) and the Cascaded-CNN models marked the landmarks. After point-to-point errors of landmark identification, the successful detection rate (SDR) and distance and direction of the midline landmark deviation from the midsagittal line (ANS-mid, UDM-mid, LDM-mid, and Me-mid) were measured, and statistical analysis was performed. Results: : The cascaded-CNN algorithm showed a clinically acceptable level of point-to-point error (1.26 mm vs. 1.57 mm in Examiner-1 and 1.75 mm in Examiner-2). The average SDR within the 2 mm range was 83.2%, with high accuracy at the LO (right, 96.9%; left, 97.1%), and UDM (96.9%). The absolute measurement errors were less than 1 mm for ANS-mid, UDM-mid, and LDM-mid compared with the gold standard. Conclusions: : The cascaded-CNN model may be considered an effective tool for the auto-identification of midline landmarks and quantification of midline deviation in PA cephalograms of adult patients, regardless of variations in the image acquisition method.
RESUMEN
BACKGROUND AND OBJECTIVE: Despite recent development of AI, prediction of the surgical movement in the maxilla and mandible by OGS might be more difficult than that of tooth movement by orthodontic treatment. To evaluate the prediction accuracy of the surgical movement using pairs of pre-(T0) and post-surgical (T1) lateral cephalograms (lat-ceph) of orthognathic surgery (OGS) patients and dual embedding module-graph convolution neural network (DEM-GCNN) model. METHODS: 599 pairs from 3 institutions were used as training, internal validation, and internal test sets and 201 pairs from other 6 institutions were used as external test set. DEM-GCNN model (IEM, learning the lat-ceph images; LTEM, learning the landmarks) was developed to predict the amount and direction of surgical movement of ANS and PNS in the maxilla and B-point and Md1crown in the mandible. The distance between T1 landmark coordinates actually moved by OGS (ground truth) and predicted by DEM-GCNN model and pre-existed CNN-based Model-C (learning the lat-ceph images) was compared. RESULTS: In both internal and external tests, DEM-GCNN did not exhibit significant difference from ground truth in all landmarks (ANS, PNS, B-point, Md1crown, all P > 0.05). When the accumulated successful detection rate for each landmark was compared, DEM-GCNN showed higher values than Model-C in both the internal and external tests. In violin plots exhibiting the error distribution of the prediction results, both internal and external tests showed that DEM-GCNN had significant performance improvement in PNS, ANS, B-point, Md1crown than Model-C. DEM-GCNN showed significantly lower prediction error values than Model-C (one-jaw surgery, B-point, Md1crown, all P < 0.005; two-jaw surgery, PNS, ANS, all P < 0.05; B point, Md1crown, all P < 0.005). CONCLUSION: We developed a robust OGS planning model with maximized generalizability despite diverse qualities of lat-cephs from 9 institutions.
Asunto(s)
Mandíbula , Procedimientos Quirúrgicos Ortognáticos , Humanos , Cefalometría/métodos , Mandíbula/diagnóstico por imagen , Mandíbula/cirugía , Procedimientos Quirúrgicos Ortognáticos/métodos , Maxilar/diagnóstico por imagen , Maxilar/cirugíaRESUMEN
The study aimed to identify critical factors associated with the surgical stability of pogonion (Pog) by applying machine learning (ML) to predict relapse following two-jaw orthognathic surgery (2 J-OGJ). The sample set comprised 227 patients (110 males and 117 females, 207 training and 20 test sets). Using lateral cephalograms taken at the initial evaluation (T0), pretreatment (T1), after (T2) 2 J-OGS, and post treatment (T3), 55 linear and angular skeletal and dental surgical movements (T2-T1) were measured. Six ML modes were utilized, including classification and regression trees (CART), conditional inference tree (CTREE), and random forest (RF). The training samples were classified into three groups; highly significant (HS) (≥ 4), significant (S) (≥ 2 and < 4), and insignificant (N), depending on Pog relapse. RF indicated that the most important variable that affected relapse rank prediction was ramus inclination (RI), CTREE and CART revealed that a clockwise rotation of more than 3.7 and 1.8 degrees of RI was a risk factor for HS and S groups, respectively. RF, CTREE, and CART were practical tools for predicting surgical stability. More than 1.8 degrees of CW rotation of the ramus during surgery would lead to significant Pog relapse.
Asunto(s)
Maloclusión de Angle Clase III , Procedimientos Quirúrgicos Ortognáticos , Masculino , Femenino , Humanos , Mentón/cirugía , Maloclusión de Angle Clase III/cirugía , Mandíbula/diagnóstico por imagen , Mandíbula/cirugía , Recurrencia , Cefalometría , Estudios de Seguimiento , Estudios Retrospectivos , Maxilar/cirugíaRESUMEN
OBJECTIVE: To investigate demographic and skeletodental characteristics of one-jaw (1J-OGS) and two-jaw orthognathic surgery (2J-OGS) in patients with skeletal Class III malocclusion. METHODS: 750 skeletal Class III patients who underwent OGS at 10 university hospitals in Korea between 2015 and 2019 were investigated; after dividing them into the 1J-OGS (n = 186) and 2J-OGS groups (n = 564), demographic and skeletodental characteristics were statistically analyzed. RESULTS: 2J-OGS was more frequently performed than 1J-OGS (75.2 vs. 24.8%), despite regional differences (capital area vs. provinces, 86.6 vs. 30.7%, p < 0.001). Males outnumbered females, and their mean operation age was older in both groups. Regarding dental patterns, the most frequent maxillary arch length discrepancy (ALD) was crowding in the 1J-OGS group (52.7%, p < 0.001) and spacing in the 2J-OGS group (40.4%, p < 0.001). However, the distribution of skeletal pattern was not significantly different between the two groups (all p > 0.05). The most prevalent skeletal patterns in both groups were hyper-divergent pattern (50.0 and 54.4%, respectively) and left-side chin point deviation (both 49.5%). Maxillary spacing (odds ratio [OR], 3.645; p < 0.001) increased the probability of 2J-OGS, while maxillary crowding (OR, 0.672; p < 0.05) and normo-divergent pattern (OR, 0.615; p < 0.05) decreased the probability of 2J-OGS. CONCLUSIONS: In both groups, males outnumbered females, and their mean operation age was older. The most frequent ALD was crowding in the 1J-OGS group, and spacing in the 2J-OGS group, while skeletal characteristics were not significantly different between the two groups.
RESUMEN
Objective: To investigate the pattern of accuracy change in artificial intelligence-assisted landmark identification (LI) using a convolutional neural network (CNN) algorithm in serial lateral cephalograms (Lat-cephs) of Class III (C-III) patients who underwent two-jaw orthognathic surgery. Methods: A total of 3,188 Lat-cephs of C-III patients were allocated into the training and validation sets (3,004 Lat-cephs of 751 patients) and test set (184 Lat-cephs of 46 patients; subdivided into the genioplasty and non-genioplasty groups, n = 23 per group) for LI. Each C-III patient in the test set had four Lat-cephs: initial (T0), pre-surgery (T1, presence of orthodontic brackets [OBs]), post-surgery (T2, presence of OBs and surgical plates and screws [S-PS]), and debonding (T3, presence of S-PS and fixed retainers [FR]). After mean errors of 20 landmarks between human gold standard and the CNN model were calculated, statistical analysis was performed. Results: The total mean error was 1.17 mm without significant difference among the four time-points (T0, 1.20 mm; T1, 1.14 mm; T2, 1.18 mm; T3, 1.15 mm). In comparison of two time-points ([T0, T1] vs. [T2, T3]), ANS, A point, and B point showed an increase in error (p < 0.01, 0.05, 0.01, respectively), while Mx6D and Md6D showeda decrease in error (all p < 0.01). No difference in errors existed at B point, Pogonion, Menton, Md1C, and Md1R between the genioplasty and non-genioplasty groups. Conclusions: The CNN model can be used for LI in serial Lat-cephs despite the presence of OB, S-PS, FR, genioplasty, and bone remodeling.
RESUMEN
OBJECTIVE: The purpose of this study was to investigate the accuracy of one-step automated orthodontic diagnosis of skeletodental discrepancies using a convolutional neural network (CNN) and lateral cephalogram images with different qualities from nationwide multi-hospitals. METHODS: Among 2,174 lateral cephalograms, 1,993 cephalograms from two hospitals were used for training and internal test sets and 181 cephalograms from eight other hospitals were used for an external test set. They were divided into three classification groups according to anteroposterior skeletal discrepancies (Class I, II, and III), vertical skeletal discrepancies (normodivergent, hypodivergent, and hyperdivergent patterns), and vertical dental discrepancies (normal overbite, deep bite, and open bite) as a gold standard. Pre-trained DenseNet-169 was used as a CNN classifier model. Diagnostic performance was evaluated by receiver operating characteristic (ROC) analysis, t-stochastic neighbor embedding (t-SNE), and gradientweighted class activation mapping (Grad-CAM). RESULTS: In the ROC analysis, the mean area under the curve and the mean accuracy of all classifications were high with both internal and external test sets (all, > 0.89 and > 0.80). In the t-SNE analysis, our model succeeded in creating good separation between three classification groups. Grad-CAM figures showed differences in the location and size of the focus areas between three classification groups in each diagnosis. CONCLUSIONS: Since the accuracy of our model was validated with both internal and external test sets, it shows the possible usefulness of a one-step automated orthodontic diagnosis tool using a CNN model. However, it still needs technical improvement in terms of classifying vertical dental discrepancies.
RESUMEN
PURPOSE: The purpose of the present study was to evaluate the clinical application of resorbable and nonresorbable plates for correction of facial asymmetry. PATIENTS AND METHODS: A total of 272 patients who had undergone orthognathic surgery were enrolled. The site of osteotomy was fixed using a nonresorbable plate in group I (n = 152) and using a resorbable plate in group II (n = 120). The postoperative complications included postoperative anterior open bite, infection, temporomandibular joint dysfunction, and postoperative relapse. The incidence of all complications was examined. RESULTS: The surgical outcome was successful in 269 patients (98.89%). Of the 152 patients with a titanium plate, 13 (8.6%) developed complications. Of the 120 patients with a resorbable plate, 22 (18.3%) developed complications. A greater degree of postoperative open bite and a trend toward relapse were observed in patients' cases in which an absorbable fixation plate was used. Postoperative infection occurred in patients with an absorbable fixation plate. CONCLUSION: On the basis of these data, we have concluded that an absorbable fixation plate should be used instead of a titanium fixation plate in indicated patients.