Three-dimensional analysis of palatal morphology and PAS in patients with cleft lip and palate prior to orthodontic treatment.

BACKGROUND: Since many different conclusions of craniofacial anomalies and their relation to the posterior airway space coexist, this comparative clinical study investigated the palatal morphology concerning volumetric size, posterior airway space dimension and the adenoids of patients with and without a cleft before orthodontic treatment. METHODS: Three-dimensional intraoral scans and cephalometric radiographs of n = 38 patients were used for data acquisition. The patients were divided into three groups: unilateral cleft lip and palate (n = 15, 4 female, 11 male; mean age 8.57 ± 1.79 years), bilateral cleft lip and palate (n = 8, 0 female, 8 male; mean age 8.46 ± 1.37 years) and non-cleft control (n = 15, 7 female, 8 male; mean age 9.03 ± 1.02 years). The evaluation included established procedures for measurements of the palatal morphology and posterior airway space. Statistics included Shapiro-Wilk-Test and simple ANOVA (Bonferroni) for the three-dimensional intraoral scans and cephalometric radiographs. The level of significance was set at p < 0.05. RESULTS: The palatal volume and cephalometric analysis showed differences between the three groups. The palatal volume, the superior posterior face height and the depth of the bony nasopharynx of patients with cleft lip and palate were significantly smaller than for non-cleft control patients. The superior posterior face height of bilateral cleft lip and palate patients was significantly smaller than in unilateral cleft lip and palate patients (BCLP: 35.50 ± 2.08 mm; UCLP: 36.04 ± 2.95 mm; p < 0.001). The percentage of the adenoids in relation to the entire nasopharynx and the angle NL/SN were significantly bigger in patients with cleft lip and palate than in the non-cleft control. In particular, the palatal volume was 32.43% smaller in patients with unilateral cleft lip and palate and 48.69% smaller in patients with bilateral cleft lip and palate compared to the non-cleft control. CONCLUSIONS: Skeletal anomalies relate to the dimension of the posterior airway space. There were differences among the subjects with cleft lip and palate and these without a cleft. This study showed that the morphology of the palate and especially transverse deficiency of the maxilla resulting in smaller palatal volume relates to the posterior airway space. Even the adenoids seem to be affected, especially for cleft lip and palate patients.

Automated diagnosis of adenoid hypertrophy with lateral cephalogram in children based on multi-scale local attention.

Adenoid hypertrophy can lead to adenoidal mouth breathing, which can result in "adenoid face" and, in severe cases, can even lead to respiratory tract obstruction. The Fujioka ratio method, which calculates the ratio of adenoid (A) to nasopharyngeal (N) space in an adenoidal-cephalogram (A/N), is a well-recognized and effective technique for detecting adenoid hypertrophy. However, this process is time-consuming and relies on personal experience, so a fully automated and standardized method needs to be designed. Most of the current deep learning-based methods for automatic diagnosis of adenoids are CNN-based methods, which are more sensitive to features similar to adenoids in lateral views and can affect the final localization results. In this study, we designed a local attention-based method for automatic diagnosis of adenoids, which takes AdeBlock as the basic module, fuses the spatial and channel information of adenoids through two-branch local attention computation, and combines the downsampling method without losing spatial information. Our method achieved mean squared error (MSE) 0.0023, mean radial error (MRE) 1.91, and SD (standard deviation) 7.64 on the three hospital datasets, outperforming other comparative methods.

Comparative analysis of deep-learning-based bone age estimation between whole lateral cephalometric and the cervical vertebral region in children.

Bone age determination in individuals is important for the diagnosis and treatment of growing children. This study aimed to develop a deep-learning model for bone age estimation using lateral cephalometric radiographs (LCRs) and regions of interest (ROIs) in growing children and evaluate its performance. This retrospective study included 1050 patients aged 4-18 years who underwent LCR and hand-wrist radiography on the same day at Pusan National University Dental Hospital and Ulsan University Hospital between January 2014 and June 2023. Two pretrained convolutional neural networks, InceptionResNet-v2 and NasNet-Large, were employed to develop a deep-learning model for bone age estimation. The LCRs and ROIs, which were designated as the cervical vertebrae areas, were labeled according to the patient's bone age. Bone age was collected from the same patient's hand-wrist radiograph. Deep-learning models trained with five-fold cross-validation were tested using internal and external validations. The LCR-trained model outperformed the ROI-trained models. In addition, visualization of each deep learning model using the gradient-weighted regression activation mapping technique revealed a difference in focus in bone age estimation. The findings of this comparative study are significant because they demonstrate the feasibility of bone age estimation via deep learning with craniofacial bones and dentition, in addition to the cervical vertebrae on the LCR of growing children.

In-office distalizer as Motion Carriere versus Herbst appliance: a comparative study by superimpositions on 156 cases / Distaliseur in-office façon Motion Carriere versus les bielles de Herbst : une étude comparative par superposition sur 156 cas.

Introduction: Among the class II dental supported therapeutic devices, the Carriere Motion Appliance (Henri Schein) was introduced in 2004 followed by in-office adjustments. The objective of this study was to evaluate, by superimpositions, the dento-skeletal effects of the in-office distalizer (D) close to the Carriere Motion Appliance compared to the reference treatment: the Herbst appliance (B). Material and Method: A retrospective intention-to-treat study was conducted. Patients had to be in class II, 1 bilateral, have growth potential, two successive lateral cephalograms. The criteria evaluated were cephalometric, mainly from the Pancherz analysis. Statistical tests were performed with a threshold of 5%. Results: Overall, 116 patients treated with D and multi-attachment appliance (MA) and 40 patients treated with B and MA were included. D and B slow maxillary advance, stimulate mandibular advance and correct the skeletal Class II. They normalize the molar class by distalizing the maxillary arch (palato-position of the maxillary incisors, retreat of the maxillary first molar) and by mesializing the mandibular arch (vestibulo-position and vestibulo-version of the mandibular incisors by 5 to 6°, advance of the mandibular first molar). They provide good control of facial divergence, but with a clockwise tilt of the occlusal plane. Discussion: Randomized trials are needed to confirm our results. Conclusion: With similar adverse effects, the in-office distalizer may be an interesting alternative because of its smaller volume, comfort and easy manufacture.

Introduction: Parmi les dispositifs thérapeutiques de classe II à appui dentaire, le Carriere Motion Appliance (Henri Schein) a été proposé en 2004 puis des adaptations in-office. L'objectif de cette étude était d'évaluer, par superpositions, les effets dento-squelettiques du distaliseur in-office (D) proche du Carriere Motion Appliance par rapport au traitement de référence, les bielles de Herbst (B). Matériel et méthode: Une étude rétrospective en intention de traiter a été menée. Les patients devaient être en classe II, division 1 bilatérale, avoir du potentiel de croissance, deux téléradiographies de profil successives. Les critères évalués étaient céphalométriques, essentiellement issus de l'analyse de Pancherz. Des tests statistiques ont été réalisés avec un seuil de 5 %. Résultats: Au total, 116 patients traités par D et appareil multi-attache (MA) et 40 patients traités par B et MA ont été inclus. D et B permettent de freiner l'avancée maxillaire, favoriser l'avancée mandibulaire et corriger le décalage squelettique de classe II. Ils normalisent la classe molaire en distalant l'arcade maxillaire (palato-position des incisives maxillaires, recul de la première molaire maxillaire) et en mésialant l'arcade mandibulaire (vestibulo-position et vestibulo-version des incisives mandibulaires de 5 à 6°, avancée de la première molaire mandibulaire). Ils permettent un bon contrôle de la divergence faciale avec néanmoins une bascule horaire du plan d'occlusion. Discussion: Des essais randomisés sont nécessaires pour confirmer nos résultats. Conclusion: À effets indésirables proches, le distaliseur in-office peut constituer une alternative intéressante par son volume moindre, son confort et sa facilité de conception.

[Transverse characteristics of normodivergent patients in different sagittal skeletal patterns].

PURPOSE: This study aimed to measure and analyze the transverse indicators of normodivergent patients with different sagittal skeletal malocclusions, to explore the transverse characteristics of different sagittal skeletal malocclusions. METHODS: Lateral cephalograms and CBCT of 90 normodivergent patients with skeletal Class Ⅰ, Ⅱ and Ⅲ in their permanent dentition were collected. Dolphin software was applied to measure the widths of the basal bone, alveolar bone, dental arch and buccolingual inclination angle of the corresponding teeth in the maxillary and mandibular canine, premolar and molar areas. SPSS 22.0 software package was applied for statistical analysis of the data. RESULTS: The widths of the mandibular basal bone in canine, premolar and molar areas of skeletal Class Ⅲ were (27.15±2.74), (39.30±2.82) and (59.97±2.93) mm, respectively. The widths of the mandibular alveolar bone of skeletal Class Ⅲ were (25.38±1.78), (34.51±2.28) and (47.72±2.73) mm, respectively. The dental arch widths of the maxillary premolar and mandibular canine areas of skeletal Class Ⅲ were (48.70±2.35) and (30.69±2.31)mm, respectively. The above data of skeletal Class Ⅲ were significantly larger than those of skeletal Class Ⅰ and Ⅱ(P＜0.01). The dental arch widths of the maxillary canine, maxillary molar and mandibular molar areas of skeletal Class Ⅲ were (38.88±1.90), (59.51±3.40) and (56.01±2.86)mm, respectively, which were significantly larger than those of skeletal Class Ⅱ(P＜0.05). The maxillomandibular width difference of basal bone in the canine, premolar and molar areas of skeletal Class Ⅲ were (4.69±2.84), (2.31±2.39) and (3.27±2.05) mm, respectively, which were significantly less than that of skeletal Class Ⅰ and Ⅱ(P＜0.01). Compared with skeletal Class Ⅰ, the maxillary canines and first molars of skeletal Class Ⅱ had larger lingual inclination level, while the maxillary first premolars and first molars of skeletal Class Ⅲ had larger buccal inclination level, the mandibular canines and the mandibular first premolars of skeletal Class Ⅲ had larger lingual inclination level(P＜0.01). CONCLUSIONS: For normodivergent patients, the width of the mandibular base bone, alveolar bone, and maxillary and mandibular dental arch in skeletal Class Ⅲ is the widest, which is more likely to have width discrepancy in basal bone. In skeletal Class Ⅲ, the maxillary teeth are buccally inclined, and the mandibular teeth are ingually inclined. In skeletal Class Ⅱ, the maxillary teeth are lingually inclined, and the mandibular teeth are compensatory upright.

Friction versus frictionless mechanics during maxillary en-masse retraction in adult patients with Class I bimaxillary dentoalveolar protrusion: a randomized clinical trial.

BACKGROUND: Extraction space closure is a challenging phase during orthodontic treatment that affects not only the total treatment duration but also the whole treatment outcome. OBJECTIVE: To compare the efficiency of friction and frictionless mechanics during en-masse retraction of maxillary anterior teeth in adult patients with bimaxillary dentoalveolar protrusion. TRIAL DESIGN: Two-arm parallel group, single-center randomized clinical trial. MATERIALS AND METHODS: Thirty-two adult patients with bimaxillary protrusion were recruited and randomly allocated to two different retraction mechanics. A friction group, using NiTi coil springs and a frictionless group using closing T-loops for en-masse retraction. Randomization in a 1:1 ratio was generated by Microsoft Excel. The randomization numbers were secured in opaque sealed envelopes for allocation concealment. Retraction started in all patients following first premolars extraction using miniscrews as a source of indirect anchorage. Activation was done on a monthly basis until complete retraction of anterior segment. The rate of retraction, amount of anchorage loss, the dental, and soft tissue changes were analyzed on digital models and lateral cephalograms taken before retraction and after space closure. BLINDING: The outcome assessor was blinded through data concealment during assessment. RESULTS: Two patients were lost to follow up, so 30 patients completed the trial. The rate of anterior segment retraction was 0.88 ±â€…0.66 mm/month in the frictionless group compared to 0.72 ±â€…0.36 mm/month in the friction group which was statistically significant. Anchorage loss of 1.18 ±â€…0.72 mm in the friction group compared to 1.29 ±â€…0.55 mm in the frictionless group with no significant difference. Comparable dental and soft tissue changes following en-masse retraction were reported in both groups, with no statistically significant difference. HARM: one patient complained of soft tissue swelling following miniscrew insertion, but the swelling disappeared after one week of using mouth wash. LIMITATION: The study focused only on the maxillary arch. CONCLUSION: Both mechanics have successfully achieved the required treatment objectives in patients with bimaxillary dentoalveolar protrusion. Frictionless group showed a faster rate of retraction than the friction group, which was statistically but not clinically significant. TRIAL REGISTRATION: Clinicaltrials.gov with the identifier NCT03261024.

Radiologic study of the distance between the maxillary central incisor root and the incisive canal according to skeletal malocclusion classification.

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.

Developing an eyeball positioning method in the eye orbit for craniofacial identification in Korean population.

We analysed the skulls and faces of Korean subjects using anthropometric methods to understand the anatomical characteristics of the eyeball and eye orbit region of Korean population and to determine the correlations between the hard and soft tissues around the eyeball and eye orbit region. In total, 82 sections in the region were measured to determine the correlations; among them, 34 showed significant differences by sex, and 6 showed significant differences by age. As the distance from the centre of the eye lens to the eye orbit is calculated as a ratio, we determined that the centre of the eye lens is located relatively on the lateral and superior position in each eye orbit in front view. Fourteen sections that could be used for craniofacial reconstruction/approximation in men and women were selected. Regression equations were derived according to the correlation of each section, and their reliabilities were verified by out of sample validation tests. Therefore, our results increase the accuracy of eyeball position determination, which would be useful for more efficient craniofacial reconstruction/approximation of the Korean population and should improve the efficiency of facial recognition.

Comparative evaluation of transverse width indices for diagnosing maxillary transverse deficiency.

OBJECTIVES: This study aimed to compare and evaluate different transverse width indices for diagnosing maxillary transverse deficiency (MTD), a common malocclusion characterized by uncoordinated dental arches, crossbites, and tooth crowding. MATERIALS AND METHODS: Sixty patients aged 7-12 years were included in the study, with 20 patients diagnosed with MTD and 40 normal controls. Transverse width indices, including maxillary width at the buccal alveolar crest and lingual midroot level, as well as at the jugal process width, were measured. Differences between these indices and their corresponding mandibular indices were used as standardized transverse width indices. The reference range of these indices was determined and evaluated. Receiver operating characteristic (ROC) analysis was performed to evaluate their diagnostic ability. RESULTS: The transverse width indices and standardized transverse width indices of the MTD group were significantly smaller than those of the control group, except for the jugal process width. The evaluation of the reference range and ROC analysis revealed that the difference of the maxillomandibular width at buccal alveolar crest was the most accurate diagnostic method. CONCLUSIONS: The jugal point analysis method may not be suitable for diagnosing MTD. Instead, measuring the difference in maxillomandibular width at the buccal alveolar crest proves to be a more reliable and accurate diagnostic method for MTD.

Predictability of expansion movements performed by clear aligners in mixed dentition in both arches: a retrospective study on digital casts.

BACKGROUND: to evaluate the predictability of expansion achieved in patients in early mixed dentition treated with Clear Aligners (CA), analyzing the efficiency of the expansion at the end of the first set of aligners and at the end of the therapy in the upper and lower arch. METHODS: 36 patients (20 F, 16 M; mean age 8.3 ± 1.5 years) were selected retrospectively from the Department of Orthodontics of the Hospital of Rome "Tor Vergata". All subjects were treated with CA with no other auxiliaries than attachments. For each patient a standardized sequential expansion protocol was planned for both arches. Digital dental casts were created at three observation periods from an intraoral scanner: prior to treatment (T0), at the end of the first set of aligners (T1), at the end of treatment (T2). The 3D models in planned position determined by the first Clincheck (CC) were obtained for comparison with T1 and T2. Six linear transversal measurements were used to evaluate the dimensional changes and the predictability of expansion movements, comparing T1-CC and T2-CC. RESULTS: a statistically significant increase within the pre-treatment and the final outcomes for all the variables examined was found. In the upper arch, the greatest level of predictability was detected at the level of the first (46.44%) and second deciduous molar width (44.95%) at T1. The analysis of T2-CC changes showed a significant increase in the percentage of predictability of expansion at the level of the first permanent molars, at mesial (54.86%) and distal (58.92%) width. In the lower arch, a higher percentage of predictability than the upper arch was reported at T1-CC and T2-CC, with the greatest values at the level of second (T1-CC: 48.70%; T2-CC: 75.32%) and first deciduous molar width (T1-CC: 45.71%; T2-CC: 72.75%). CONCLUSIONS: CA can induce significant transversal increments. The predictability of expansion is variable, but it did not exceed the 50% during the first set of aligners. It was necessary to apply refinement set to achieve a good predictability for expansion of about 70%. The expansion in the lower arch was observed to be more predictable than in the upper arch.

Estimating mandibular growth stage based on cervical vertebral maturation in lateral cephalometric radiographs using artificial intelligence.

INTRODUCTION: Determining the right time for orthodontic treatment is one of the most important factors affecting the treatment plan and its outcome. The aim of this study is to estimate the mandibular growth stage based on cervical vertebral maturation (CVM) in lateral cephalometric radiographs using artificial intelligence. Unlike previous studies, which use conventional CVM stage naming, our proposed method directly correlates cervical vertebrae with mandibular growth slope. METHODS AND MATERIALS: To conduct this study, first, information of people achieved in American Association of Orthodontics Foundation (AAOF) growth centers was assessed and after considering the entry and exit criteria, a total of 200 people, 108 women and 92 men, were included in the study. Then, the length of the mandible in the lateral cephalometric radiographs that were taken serially from the patients was calculated. The corresponding graphs were labeled based on the growth rate of the mandible in 3 stages; before the growth peak of puberty (pre-pubertal), during the growth peak of puberty (pubertal) and after the growth peak of puberty (post-pubertal). A total of 663 images were selected for evaluation using artificial intelligence. These images were evaluated with different deep learning-based artificial intelligence models considering the diagnostic measures of sensitivity, specificity, accuracy, positive predictive value (PPV), and negative predictive value (NPV). We also employed weighted kappa statistics. RESULTS: In the diagnosis of pre-pubertal stage, the convolutional neural network (CNN) designed for this study has the higher sensitivity and NPV (0.84, 0.91 respectively) compared to ResNet-18 model. The ResNet-18 model had better performance in other diagnostic measures of the pre-pubertal stage and all measures in the pubertal and post-pubertal stages. The highest overall diagnostic accuracy was also obtained using ResNet-18 model with the amount of 87.5% compared to 81% in designed CNN. CONCLUSION: The artificial intelligence model trained in this study can receive images of cervical vertebrae and predict mandibular growth status by classifying it into one of three groups; before the growth spurt (pre-pubertal), during the growth spurt (pubertal), and after the growth spurt (post-pubertal). The highest accuracy is in post-pubertal stage with the designed networks.

The Frequency of Occipital Spurs in Relation to the Cephalic Index: An Anatomorphometric Cone Beam CT Study.

BACKGROUND: The occipital spur (OS) can be described as an abnormal elongation of the external occipital protuberance (EOP). The cephalic index (CI) refers to the ratio of width to length in any skull. AIM: The aim of the present study was to evaluate the frequency and types of OS. It also aimed to determine the mean CI and the distribution of skull types using cone beam computed tomography (CBCT). And to determine if there was a relationship between the cephalic index and the presence and types of OS. METHODS: CBCT scans from 523 patients were included in the study. OSs were classified as type 1 (flat), type 2 (crest), and type 3 (spine). Skull length and width were measured on axial sections and the CI was calculated. Based on the cephalic index (CI), skull types were classified as dolichocephalic (CI < 75), mesocephalic (75 < CI < 80), brachycephalic (80 < CI < 85), and hyperbrachycephalic (CI > 85). RESULTS: The most common cranial types in the study group were brachycephalic (44.7%), mesocephalic (28.3%), hyperbrachycephalic (21.2%), and dolichocephalic (5.7%). Regarding the presence of OS, 54.3% of the participants had no OS, 23.1% had flat type, 15.3% had crest type, and 7.2% had spin type OS. There was a statistically significant difference (P < 0.05) in the frequency of OS according to skull type. CONCLUSION: This study, the first to evaluate CI and OS using CBCT, concludes that brachycephaly is the most common cranial type. OS is more common in mesocephalic and dolichocephalic skulls, at older ages, and in males.

Facial soft-tissue shape changes after fixed edgewise treatment with premolar extraction in individual artificial-intelligence-classified facial profile patterns.

OBJECTIVE: To examine the patterns of pretreatment facial soft tissue shape in orthodontic cases with premolar extraction using artificial intelligence (AI) and to investigate the corresponding changes. METHODS: One hundred and fifty-two patients who underwent orthodontic treatment with premolar extraction were enrolled. Lateral cephalograms were obtained before and after the treatment. For each record, the outlines of the nose-lip-chin profile and corresponding 21 cephalometric variables were extracted. The AI method classified pretreatment records into three subject groups based on the feature variables extracted from the outline. Dentoskeletal and soft tissue facial form changes observed after treatment were compared statistically (P < 0.05) between the groups using ANOVA. Multivariate regression models were used for each group. RESULTS: Group 1 (n = 59) was characterized by Class II high-angle retrognathic mandible with an incompetent lip, group 2 (n = 55) by Class I malocclusion with retruded and thin lips, and group 3 (n = 38) by Class I malocclusion with an everted superior lip before treatment. The ratios of anteroposterior soft tissue to hard tissue movements in Group 1 were 56% (r = 0.64) and 83% (r = 0.75) for the superior and inferior lips, respectively, whereas those in Group 2 were 49% (r = 0.78) and 91% (r = 0.80), and 40% (r = 0.54) and 79% (r = 0.70), respectively, in Group 3. CONCLUSIONS: The modes of facial form changes differed depending on the pre-treatment profile patterns classified by the AI. This indicates that the determination of the pre-treatment profile pattern can help in the selection of soft tissue to hard tissue movement ratios, which helps estimate the post-treatment facial profile with a moderate to high correlation.

Three-Dimensional Anthropometric Facial Analysis and Fitting Discrepancies Between Stereophotogrammetry and CT.

BACKGROUND: The reliability and repeatability of stereophotogrammetry and CT in 3-dimensional anthropometric facial analysis were investigated in this study, which also explored the clinical application of supine CT. METHOD: In this study, 3D CT and 3dMD stereophotogrammetry were used on 20 healthy volunteers. The fitting distance between stereophotogrammetry and CT scans at landmark points was measured, along with facial feature measurements (Al-Al) face width (Go-Go, Zy-Zy, Ex-Ex), and hemi-face height (Sn-Gn). The intraclass correlation coefficient (ICC) was employed to assess interrater agreement and to verify the reliability of the measurement methods. Paired t -analysis was utilized for analyzing intramethod displacement. RESULTS: The alare, nasion, and pronasale points were found to be minimally influenced by different positions and are more recommended as landmark points for registration. CT demonstrated good interrater reliability on all indicators. In stereophotogrammetry, measurements for Go-Go and Zy-Zy displayed an interclass correlation coefficient (ICC) of less than 0.75. Significant differences between the 2 methods were observed for En-En, Ex-Ex, and Go-Go ( P < 0.05). Specifically, CT analysis for Go-Go showed a measurement 2.34 mm larger than that obtained with the 3dMD method. CONCLUSION: Both CT and stereophotogrammetry were found to be reliable methods for evaluating facial soft tissue. It is speculated that Go-Go measurement is primarily influenced by factors such as different positions, facial expressions, and gravity. These variables should be carefully considered during the evaluation of the mandibular angle region.

Comparison Between an Expert Operator an Inexperienced Operator, and Artificial Intelligence Software: A Brief Clinical Study of Cephalometric Diagnostic.

INTRODUCTION: Artificial intelligence (AI) is constantly developing in several medical areas and has become useful to assist with treatment planning. Orthodontics and maxillofacial surgery use AI-based technology to identify and select cephalometric points for diagnostics. Although some studies have shown promising results from the use of AI, the evidence is still limited. Hence, additional investigation is justified. MATERIALS AND METHODS: In this retrospective study, 2 human operators (1 expert and 1 inexperienced) and 1 software analyzed 30 lateral cephalograms of individuals with orthodontic treatment indications. They measured 10 cephalometric variables and then 2 weeks later, repeated measurements on 30% of the sample. We evaluated the reliability of the measurements between the 2-time points and the differences in the means between the expert operator and the AI software and between the expert and inexperienced operators. RESULTS: There was high reliability for the expert operator and AI measurements, and moderate reliability for the inexperienced operator measurements. There were some significant differences in the means produced by the AI software and the inexperienced operator compared with the expert operator. CONCLUSION: Although AI is useful for cephalometric analysis, it should be used with caution because there are differences compared with analysis by humans.

Comparative Evaluation of Digital Cephalometric Tracing Applications on Mobile Devices and Manual Tracing.

BACKGROUND Cephalometric radiography evaluates facial skeleton development and aids in diagnosis and treatment phases (pre and post) in orthodontics. This study aimed to compare digital cephalometric tracing using a smartphone application (App), a tablet-based platform, and manual tracing in 30 orthodontic patients. MATERIAL AND METHODS Thirty orthodontic pretreatment, criteria based, lateral cephalometric radiographs were analyzed/grouped for Steiner analysis parameters (5 skeletal, 3 dentals, 1 soft tissue) by 3 tracing methods [manual - group (Gp M), smartphone (Android - OS9) - Gp S, tablet (Apple - IOS13) - Gp T) after mandatory standardization/calibration. Measurements include 5 angular (SNA, SNB, ANB, SNMPA, SNOP), 3 linear U1NA, L1NB, U1L1, and 1 soft tissue (S line) (millimeters and degrees). Inter-examiner rating was determined using Dahlberg's test. After normality distribution testing (Shapiro-Wilk), data were analyzed using one-way analysis of variance (ANOVA) for group differences. Homogeneity of variance was verified using the Levene test. Differences were determined on probability value of (p≤0.05). RESULTS The results showed that Steiner's analysis parameters were similar in all groups with homogenous variances. Highest differences in mean values were found for L1NB, U1L1, and S line measurement, with higher values being observed in Gp S tracings. However, these differences were not statistically significant (p≤0.05). All parameters, irrespective of being measured in either degrees or millimeters, had means comparable to each other. CONCLUSIONS Smartphone and tablet-based applications produced tracings that were comparable and reliable when compared to conventional manual tracings. Standardization of images, processing, printing, and calibration of devices is important to achieve good results.

Can artificial intelligence-driven cephalometric analysis replace manual tracing? A systematic review and meta-analysis.

OBJECTIVES: This systematic review and meta-analysis aimed to investigate the accuracy and efficiency of artificial intelligence (AI)-driven automated landmark detection for cephalometric analysis on two-dimensional (2D) lateral cephalograms and three-dimensional (3D) cone-beam computed tomographic (CBCT) images. SEARCH METHODS: An electronic search was conducted in the following databases: PubMed, Web of Science, Embase, and grey literature with search timeline extending up to January 2024. SELECTION CRITERIA: Studies that employed AI for 2D or 3D cephalometric landmark detection were included. DATA COLLECTION AND ANALYSIS: The selection of studies, data extraction, and quality assessment of the included studies were performed independently by two reviewers. The risk of bias was assessed using the Quality Assessment of Diagnostic Accuracy Studies-2 tool. A meta-analysis was conducted to evaluate the accuracy of the 2D landmarks identification based on both mean radial error and standard error. RESULTS: Following the removal of duplicates, title and abstract screening, and full-text reading, 34 publications were selected. Amongst these, 27 studies evaluated the accuracy of AI-driven automated landmarking on 2D lateral cephalograms, while 7 studies involved 3D-CBCT images. A meta-analysis, based on the success detection rate of landmark placement on 2D images, revealed that the error was below the clinically acceptable threshold of 2 mm (1.39 mm; 95% confidence interval: 0.85-1.92 mm). For 3D images, meta-analysis could not be conducted due to significant heterogeneity amongst the study designs. However, qualitative synthesis indicated that the mean error of landmark detection on 3D images ranged from 1.0 to 5.8 mm. Both automated 2D and 3D landmarking proved to be time-efficient, taking less than 1 min. Most studies exhibited a high risk of bias in data selection (n = 27) and reference standard (n = 29). CONCLUSION: The performance of AI-driven cephalometric landmark detection on both 2D cephalograms and 3D-CBCT images showed potential in terms of accuracy and time efficiency. However, the generalizability and robustness of these AI systems could benefit from further improvement. REGISTRATION: PROSPERO: CRD42022328800.

Deep learning for 3D cephalometric landmarking with heterogeneous multi-center CBCT dataset.

Cephalometric analysis is critically important and common procedure prior to orthodontic treatment and orthognathic surgery. Recently, deep learning approaches have been proposed for automatic 3D cephalometric analysis based on landmarking from CBCT scans. However, these approaches have relied on uniform datasets from a single center or imaging device but without considering patient ethnicity. In addition, previous works have considered a limited number of clinically relevant cephalometric landmarks and the approaches were computationally infeasible, both impairing integration into clinical workflow. Here our aim is to analyze the clinical applicability of a light-weight deep learning neural network for fast localization of 46 clinically significant cephalometric landmarks with multi-center, multi-ethnic, and multi-device data consisting of 309 CBCT scans from Finnish and Thai patients. The localization performance of our approach resulted in the mean distance of 1.99 ± 1.55 mm for the Finnish cohort and 1.96 ± 1.25 mm for the Thai cohort. This performance turned out to be clinically significant i.e., ≤ 2 mm with 61.7% and 64.3% of the landmarks with Finnish and Thai cohorts, respectively. Furthermore, the estimated landmarks were used to measure cephalometric characteristics successfully i.e., with ≤ 2 mm or ≤ 2° error, on 85.9% of the Finnish and 74.4% of the Thai cases. Between the two patient cohorts, 33 of the landmarks and all cephalometric characteristics had no statistically significant difference (p < 0.05) measured by the Mann-Whitney U test with Benjamini-Hochberg correction. Moreover, our method is found to be computationally light, i.e., providing the predictions with the mean duration of 0.77 s and 2.27 s with single machine GPU and CPU computing, respectively. Our findings advocate for the inclusion of this method into clinical settings based on its technical feasibility and robustness across varied clinical datasets.

Automatic extraction of facial median sagittal plane for patients with asymmetry based on the EDMA alignment algorithm.

BACKGROUND: We aimed to establish a novel method for automatically constructing three-dimensional (3D) median sagittal plane (MSP) for mandibular deviation patients, which can increase the efficiency of aesthetic evaluating treatment progress. We developed a Euclidean weighted Procrustes analysis (EWPA) algorithm for extracting 3D facial MSP based on the Euclidean distance matrix analysis, automatically assigning weight to facial anatomical landmarks. METHODS: Forty patients with mandibular deviation were recruited, and the Procrustes analysis (PA) algorithm based on the original mirror alignment and EWPA algorithm developed in this study were used to construct the MSP of each facial model of the patient as experimental groups 1 and 2, respectively. The expert-defined regional iterative closest point algorithm was used to construct the MSP as the reference group. The angle errors of the two experimental groups were compared to those of the reference group to evaluate their clinical suitability. RESULTS: The angle errors of the MSP constructed by the two EWPA and PA algorithms for the 40 patients were 1.39 ± 0.85°, 1.39 ± 0.78°, and 1.91 ± 0.80°, respectively. The two EWPA algorithms performed best in patients with moderate facial asymmetry, and in patients with severe facial asymmetry, the angle error was below 2°, which was a significant improvement over the PA algorithm. CONCLUSIONS: The clinical application of the EWPA algorithm based on 3D facial morphological analysis for constructing a 3D facial MSP for patients with mandibular deviated facial asymmetry deformity showed a significant improvement over the conventional PA algorithm and achieved the effect of a dental clinical expert-level diagnostic strategy.

Effects of Removable Functional Appliances on the Dentoalveolar Unit in Growing Patients.

Background and Objectives: The objective of this retrospective controlled study is to compare class II growing patients who underwent treatment with two different functional appliances: the Fraenkel regulator (FR-2), utilized as the control group, and the elastodontic device "Cranium Occluded Postural Multifunctional Harmonizers" (AMCOP), utilized as the test group. Materials and Methods: The study sample consisted of 52 patients with class II division I malocclusion (30 males, 22 females, mean age 8.6 ± 1.4 years) who were treated with the two different types of appliances: Group 1 (n = 27, mean age 8 [7.00, 9.00] years, 12 females, 15 males) received treatment with AMCOP, while Group 2 (n = 25, mean age 9.2 years [8.20, 10.00], 10 females, 15 males) received treatment with FR-2. The mean treatment duration for Group 1 was 28.00 [21.50, 38.00] months, while for Group 2 it was 23.70 [17.80, 27.40] months. Cephalometric analyses were performed on lateral cephalograms taken before treatment (T1) and after treatment (T2). Results: Significant intragroup differences were observed over time in Group 1 for 1^/PP. Similarly, significant intragroup differences were observed over time in Group 2 for SNB, ANB, and IMPA. Conclusions: Both treatment modalities resulted in the correction of class II malocclusion with dentoalveolar compensation, although the treatment duration with AMCOP tended to be longer on average.