Profile Photograph Classification Performance of Deep Learning Algorithms Trained Using Cephalometric Measurements: A Preliminary Study.

Extraoral profile photographs are crucial for orthodontic diagnosis, documentation, and treatment planning. The purpose of this study was to evaluate classifications made on extraoral patient photographs by deep learning algorithms trained using grouped patient pictures based on cephalometric measurements. Cephalometric radiographs and profile photographs of 990 patients from the archives of Kocaeli University Faculty of Dentistry Department of Orthodontics were used for the study. FH-NA, FH-NPog, FMA and N-A-Pog measurements on patient cephalometric radiographs were carried out utilizing Webceph. 3 groups for every parameter were formed according to cephalometric values. Deep learning algorithms were trained using extraoral photographs of the patients which were grouped according to respective cephalometric measurements. 14 deep learning models were trained and tested for accuracy of prediction in classifying patient images. Accuracy rates of up to 96.67% for FH-NA groups, 97.33% for FH-NPog groups, 97.67% for FMA groups and 97.00% for N-A-Pog groups were obtained. This is a pioneering study where an attempt was made to classify clinical photographs using artificial intelligence architectures that were trained according to actual cephalometric values, thus eliminating or reducing the need for cephalometric X-rays in future applications for orthodontic diagnosis.

Association of LSMx and LIMd Angles With Cephalometric Dental and Soft Tissue Parameters of Incisor Proclination and Lip Protrusion.

BACKGROUND: Soft tissue analysis can be used to assess anatomical features but may or may not accurately correlate with underlying hard tissue morphology, leading to an incorrect perception of malocclusion. OBJECTIVE: This study aimed to assess the reliability of different soft tissue reference lines used to evaluate anteroposterior lip position and the position of incisors and malocclusion and compare it with those assessed via hard tissue angles (LSMx and LIMd) and determine if they are true indicators of underlying protrusion of incisors and malocclusion. METHOD: A total of 120 pre-treatment lateral cephalometric radiographs were selected where patients were 18-30 years old, diagnosed as Skeletal Class I, II (Division 1 and 2), and III malocclusion. The measurements taken were SN to point A angle (SNA), SN to point B angle (SNB), angle between point A and point B (ANB), upper incisor to SN plane angle (UI-SN), upper incisor to palatal plane angle (UI-PP), incisor mandibular plane angle (IMPA), Ricketts' E line, Sushner's S2 line, nasolabial (NL) angle, mentolabial (ML) angle, LSMx angle, and LIMd angle. RESULTS: In the Class I malocclusion group, when the upper lip was assessed, the distribution of UI-SN, UI-PP, E line to UL, S line to UL, NL angle, and LMax was significantly different statistically (p=0.000), though the assessment of lower variables in Class I malocclusion showed the distribution of IMPA, E line to UL, S line to UL, ML angle, and LMand angle has a statistically significant difference (p=0.007). In Class II Division 2 malocclusion, a significant difference was observed for the upper variables (p=0.000), whereas the distribution of lower values was the same across all the variables (p=0.0724). In the sample of Class III malocclusion, a significant correlation was found in the upper variables, while the distribution among lower variables did not show any significant difference (p=0.211). CONCLUSION: This study indicates that the upper and lower soft tissue correlation with hard tissue variables is reliable for some variables but not throughout for all. Soft tissue analysis (under study) can be used to assess disproportion, but it fails to correlate to the underlying hard tissue morphology and does not explain the correct malocclusion. Further studies based on 3D diagnosis to formulate a close relationship are encouraged that can help assess soft and hard tissue patterns consistent with one another.

Assessment of Upper and Lower Airway Dimensions in Skeletal Class I and Class II Subjects Having Different Growth Patterns - A Cross-Sectional Cephalometric Study.

Objectives: To compare the airway dimensions among subjects having skeletal class I and class II patterns considering their hypodivergent, normodivergent, and hyperdivergent growth patterns and to determine any variations between them. Methods and Materials: The study consisted of 156 pre-treatment lateral cephalograms of subjects aged above 18 years. The sagittal skeletal pattern was used to separate the sample into two groups. Each group was further subdivided into hypodivergent, normodivergent, and hyperdivergent growth patterns. The upper and lower airway dimensions were measured in all the subgroups. The intragroup comparison of class I and class II was performed with 1-way ANOVA and post-hoc test. Using the independent t-test, the upper and lower airways were compared between groups. Results: Comparison of subjects according to the growth pattern showed that vertical growth patterns have statically significantly reduced upper and lower airway dimensions as compared to the average and horizontal growth patterns in both skeletal class I and class II subjects. However, the subjects with skeletal class II hyperdivergent growth patterns have significantly reduced lower airway dimensions than those with skeletal class I having hyperdivergent growth patterns. Conclusion: Individuals with skeletal class I and class II patterns characterized by hyperdivergent growth exhibit reduced upper and lower pharyngeal airways. The sagittal skeletal type also plays a role in influencing the dimensions of the upper and lower airways.

A Pilot Study on the Relationship between Obstructive Sleep Apnoea-Hypopnea Syndrome, Neurodevelopment, and Ricketts' Cephalometry.

Background: The aim of this research is to achieve the early detection of facial characteristics in patients diagnosed with neurodevelopmental deficits and obstructive sleep apnoea-hypopnea syndrome (OSAHS) through the analysis of the VERT index and Ricketts' cephalometry to minimise the neurocognitive morbidity associated with these disorders. Methods: This clinical study was conducted on 44 patients aged 4 to 15 years. Participants completed an initial questionnaire about sleep disturbances, followed by a polysomnography, a radiographic study, and an oral examination. Results: The maximum variability in the data was obtained in the mandibular plane angle, where we observed that the measurement was higher in patients diagnosed with OSAHS. The relative and normalised indices of facial depth and the mandibular plane showed variations between patients with a clinical picture compatible with OSAHS and the control group without pathology. Conclusions: Our findings indicate that Ricketts' VERT index by itself is unable to provide evidence of a diagnosis compatible with OSAHS in patients with early neurodevelopmental deficits, but, after analysing the results obtained, we observed that for the cephalometric measurements of the mandibular plane angle and facial depth relative to the patient's age, there are sufficiently strong variations for creating a solid method of differential diagnosis, thus preventing complications at the neurocognitive level.

Variabilidad en la medición del ángulo ANB de Steiner entre estudiantes de odontología y ortodoncia. Medición del Angulo ANB de Steiner

Introducción: El ángulo ANB de Steiner entrega la relación entre el maxilar y la mandíbula en sentido anteroposterior y es una de las medidas cefalométricas más aplicadas en ortodoncia. Su identificación precisa podría presentar dificultades, influyendo directamente en el posterior estudio cefalométrico, diagnóstico y plan de tratamiento. El objetivo de esta investigación fue comparar la medición del ángulo ANB de Steiner entre estudiantes de pregrado de odontología y postítulo de ortodoncia de la Facultad de Odontología de la Universidad de Chile 2020. Materiales y Métodos: Por medio del programa Adobe Photoshop CS6 (Adobe System ®), se solicitó a los estudiantes la identificación de los puntos Nasion, A y B en 5 telerradiografías laterales de cráneo. Al aplicar los criterios de inclusión y exclusión se reclutaron 15 estudiantes de cada grupo. Luego se unieron los puntos mediante trazados, se midió el ángulo ANB de Steiner y se utilizó el coeficiente de correlación intraclase (ICC) para determinar el grado de acuerdo. Resultados: Se encontró un coeficiente de correlación intraclase ICC promedio de 0.97 entre ambos grupos de estudiantes. Conclusión: No hay diferencia estadística en la determinación del ángulo ANB de Steiner entre estudiantes de pregrado de odontología y postítulo de ortodoncia.

Background: The Steiner ANB angle measures the relationship between the maxilla and mandible in the anteroposterior direction and is one of the most applied cephalometric measurements in orthodontics. Its precise identification could pose difficulties, directly influencing the subsequent cephalometric study, diagnosis and treatment plan. The aim of this research was to compare the measurement of the Steiner ANB angle between dental student and postgraduate students in orthodontics from the Faculty of Dentistry of the University of Chile 2020. Materials and Methods: Using the Adobe Photoshop CS6 program (Adobe System ®), the students were asked to identify the Nasion, A and B points in 5 lateral cephalogram of the skull. By applying the inclusion and exclusion criteria, 15 students were recruited from each group. The points were then joined by tracing, the Steiner ANB angle was measured, and the intraclass correlation coefficient (ICC) was used to determine the degree of agreement. Results: An average ICC intraclass correlation coefficient of 0.97 was found between both groups of students. Conclusion: T here is no statistical difference in the determination of the Steiner ANB angle between undergraduate students of dentistry and postgraduate students of orthodontics.

Fractal analysis of mandibular trabecular pattern following protraction facemask therapy : A pilot study.

OBJECTIVE: To assess the remodeling effects of protraction facemask therapy on the trabecular pattern of the mandible and identify quantitatively the regions of the mandible undergoing maximum changes in the trabecular pattern. MATERIALS AND METHODS: The retrospective study was conducted in 30 subjects divided into two groups. The treatment group (group 1) consisted of 15 subjects with skeletal class III malocclusion treated with a facemask (mean age: 9.1 ± 2.1 years). Digital panoramic radiographs (OPG) were obtained before treatment (T0) and at the end of active facemask therapy (T1) with a mean duration of 16.1 ± 2.5 months. In all, 15 skeletal class I subjects who did not undergo any orthodontic treatment (mean age 9.1 ± 2.2 years) comprised the control group (group 2) who had two OPGs at a mean interval of 13.6 ± 2.2 months. The fractal dimensional (FD) value was calculated in three regions: angular, condylar, and corpus region. RESULTS: Intragroup comparisons revealed a significant increase in the FD values in the right condylar (T0 = 1.2 ± 0.2; T1 = 1.4 ± 0.1) and left condylar (T0 = 1.2 ± 0.1; T1 = 1.4 ± 0.1) region (p < 0.05) and in the corpus region (FD values: right T0 = 1.2 ± 0.1, T1 = 1.4 ± 0.1; left T0 = 1.2 ± 0.1, T1 = 1.4 ± 0.1; p < 0.05). The intergroup comparison demonstrated that the treatment group showed greater changes compared with the controls in the condylar process (mean difference: right = 0.19, left = 0.20; p < 0.05) and the corpus region (0.172; p < 0.05). CONCLUSION: FD analysis demonstrated that the condylar process and the corpus region underwent the most significant change in the trabecular pattern in subjects treated with protraction facemask therapy.

The Effect of Barrel-Stave Osteotomy Length in Sagittal Strip Craniectomy.

OBJECTIVE: In managing sagittal craniosynostosis, strip craniectomy of the affected suture is commonly paired with barrel-stave osteotomies to allow for additional cranial remodeling. However, the effect of these osteotomies is not well-established. This study aimed to evaluate the effect of the length of barrel-stave osteotomies on outcomes in patients with sagittal craniosynostosis. DESIGN: A retrospective review of operative records and pre-operative and one-year post-operative three-dimensional images. SETTING: Tertiary care pediatric institution. PATIENTS: Forty-five patients with sagittal craniosynostosis. INTERVENTIONS: Sagittal strip craniectomy and either long, medium, or short barrel-stave osteotomy lengths followed by helmet therapy. MAIN OUTCOME MEASURES: Operative and three-dimensional craniometric outcomes. RESULTS: Operative time, estimated blood loss, and hospital length of stay were significantly decreased in the short group (P = .003; 0.002; 0.027). The cranial index was normalized in all groups, but the long group was significantly lower (P = .007; 0.025). Head circumference was similar between groups. All indexes were within the normal percentiles in all groups. The medium group had a significantly decreased scaphocephalic index (P = .031; .035). The short group had significantly greater occipital bulleting than the medium group (P = .001). The long group had significantly greater narrowing than the short group (P = .036). CONCLUSIONS: Strip craniectomy with the addition of long, medium, or short barrel staves all resulted in clinically successful outcomes. Our findings suggest that increased barrel-stave osteotomy length may not be necessary for a successful outcome while avoiding more extensive dissection, potential risk, increased operative time, and hospital length of stay.

Accuracy of Cranial Shape Measurements Using Smartphones: A Prospective Study.

OBJECTIVE: Prospectively validate the accuracy of smartphone-based digital cranial measurements for the diagnosis and treatment of deformational plagiocephaly and/or brachycephaly (DPB), compared with calipers used in the standard of care. DESIGN/METHODS: Bird's-eye-view head photos were captured via smartphone, and their heads were measured with hand calipers by an expert user. CI/CVAI/CVA were calculated from photos and caliper measurements, and from 3D photogrammetry of the head as ground truth. Digital and caliper measurements were compared against 3D-based ground truth using mean absolute error, Spearman correlation coefficient, and Bland-Altman method. Statistical significance between methods was assessed using Wilcoxon Rank-Sum test. PARTICIPANTS: 71 infants aged 2-11 months (20 female, 51 male) with DPB. RESULTS: The mean absolute errors for CI, CVAI, CVA were 1.63 ± 1.44, 1.45 ± 1.29, 2.38 ± 1.86 mm for smartphone, and 2.60 ± 1.96, 1.43 ± 1.22, 2.04 ± 1.81 mm for calipers, respectively. The correlation coefficients for CI, CVAI, CVA between smartphone and ground truth were 0.90, 0.94, 0.80 (p < 0.001), and 0.87, 0.93, 0.84 (p < 0.001) between calipers and ground truth, respectively. Bland-Altman results were (0.08, [-4.18, 4.34]), (-0.05, [-3.85, 3.76]), (-0.82, [-6.52, 4.87]) for smartphone, and (1.41, [-4.34, 7.15]), (0.28, [-3.37, 3.94]), (0.16, [-5.18, 5.49]) for caliper measurements respectively. Digital and caliper measurements were similar (p = 0.12) except for CI, where digital measurements were more accurate (p = 0.04). CONCLUSION: Smartphone-based cranial measurements have very high correlation with 3D-based ground truth, and they are comparable or superior to caliper measurements. Digital measurements can be performed in pediatric offices or from home to help with the early detection and treatment of DPB.

Craniofacial Cephalometric Morphology in Polish Adolescents with Cleft Palate Only.

Background: Cephalometric studies indicate that craniofacial morphology in patients with cleft palate only (CPO) differs from other forms of orofacial clefts and healthy patients. Planning orthodontic treatment for patients with different craniofacial deformities requires knowledge on the craniofacial complex. The aim of the present study was to describe the cephalometric craniofacial morphology in adolescents with cleft palate only compared to generally healthy orthodontic patients. Methods: The study comprised 100 lateral cephalograms (taken in the years 2003-2020) of Polish patients with cleft palate only aged from 11.1 to 14.2 (mean age 12.43 y) and a matched control group of 100 children without orofacial clefts aged 12-14 (mean age 12.25). All digital images were analyzed in specialized cephalometric software. Results: Statistically significantly lower values of both SNA (p < 0.001) and ANB (p < 0.001) were found in the study group versus the control group. Mandibular line to cranial base angle (ML-NSL) as well as maxillary base to cranial base (NL-NSL) were significantly higher in the CPO group. Both the maxilla and mandible were rotated distally in CPO. Moreover, the intermaxillary vertical angle (ML-NL) was reduced in CPO. Mandibular angle in CPO was significantly higher (p = 0.005), reflecting posterior mandibular rotation. Conclusions: In adolescents with CPO, maxillary deficiency is found, without a severe sagittal jaw discrepancy, with a slight compensatory lingual inclination of the lower incisors. Mandibular deficiency in CPO is concurrent with posterior rotation and an increased mandibular angle.

Comparison of Three Commercially Available, AI-Driven Cephalometric Analysis Tools in Orthodontics.

Background: Cephalometric analysis (CA) is an indispensable diagnostic tool in orthodontics for treatment planning and outcome assessment. Manual CA is time-consuming and prone to variability. Methods: This study aims to compare the accuracy and repeatability of CA results among three commercial AI-driven programs: CephX, WebCeph, and AudaxCeph. This study involved a retrospective analysis of lateral cephalograms from a single orthodontic center. Automated CA was performed using the AI programs, focusing on common parameters defined by Downs, Ricketts, and Steiner. Repeatability was tested through 50 randomly reanalyzed cases by each software. Statistical analyses included intraclass correlation coefficients (ICC3) for agreement and the Friedman test for concordance. Results: One hundred twenty-four cephalograms were analyzed. High agreement between the AI systems was noted for most parameters (ICC3 > 0.9). Notable differences were found in the measurements of angle convexity and the occlusal plane, where discrepancies suggested different methodologies among the programs. Some analyses presented high variability in the results, indicating errors. Repeatability analysis revealed perfect agreement within each program. Conclusions: AI-driven cephalometric analysis tools demonstrate a high potential for reliable and efficient orthodontic assessments, with substantial agreement in repeated analyses. Despite this, the observed discrepancies and high variability in part of analyses underscore the need for standardization across AI platforms and the critical evaluation of automated results by clinicians, particularly in parameters with significant treatment implications.

Evaluation of Sella Turcica Variations in Lateral Cephalometric Radiographs and its Association with Malocclusion.

Objectives: Understanding the shape and size of the sella turcica may help predict future orthodontic treatment needs related to skeletal malocclusion. This study aims to assess different morphological types of the sella turcica in lateral cephalometric radiographs and its correlation with malocclusion, as well as the relationship between gender and linear measurements of sella turcica. Materials and Methods: The lateral cephalometric radiographs of 410 volunteers (111 men and 299 women) aged 8 to 30 years were evaluated. The patients were divided into three groups based on their skeletal growth patterns (cl I, II, and III). Then the anatomical shape and linear dimensions of sella turcica were assessed. Measurements were made using Adobe Photoshop Version: 20.0.0 software, and data analysis was performed by IBM SPSS Statistics version 25. Results: The following morphologies were observed: normal (37.8%), oblique anterior wall (9.3%), double contour of the floor (21.5%), sella turcica bridge (8.8%), irregularity (notching) in the posterior part of sella turcica (16.6%), and pyramidal shape of the dorsum sellae (6.1%). No statistically significant relationship was found between sella turcica variations and skeletal malocclusion. The correlation between female sex with the diameter (p=0.027) and depth values (p=0.035) of sella turcica was statistically significant. There was no statistically significant difference (p>0.05) in length based on gender. Conclusion: The most morphological type reported was normal sella turcica (37.8%). Anatomical variations of sella turcica had no association with malocclusion. The most considerable depth and diameter of sella turcica were found in women.

The relationship of anterior occlusion and skeletal variables with the frontal sinus index: An analytical cross-sectional study.

OBJECTIVE: To determine the relationship of anterior occlusion and skeletal variables with the frontal sinus index. METHODS: The retrospective, analytical, cross-sectional, study was conducted from July to November 2020 at Dr Ishratul- Ebad Khan Institute of Oral Health Sciences and Dow Dental College, Dow University of Health Sciences, Karachi, and comprised data from 2015 to 2018 related to pre-treatment lateral cephalograms for determining frontal sinus index and other cephalometric variables. The dental casts were observed for incisor classification. Patients with Class I incisors formed the comparison group, while the rest comprised 5 malocclusion groups. The frontal sinus was traced, and the sinus index was calculated. Data was analysed using STATA 15 and R 3.5.1. RESULTS: Of the 240 subjects, there were 40(16.66%) in each of the 6 groups; 155(64.6%) females and 85(35.4%) males. The mean age of the sample was 21.33±3.52 years (range: 16-29 years). The mean sinus index was higher in all malocclusion groups than the comparison group, but it was significantly higher only in Class II division 2 and anterior open bite groups (p<0.05). The only exception to the trend was Class II division 1 with and without contact in which the value was lower (p>0.05). The anterior cranial base length, sella-nasion mandibular plane angle, and upper incisor palatal plane angle significantly affected the frontal sinus index (p<0.05). CONCLUSIONS: The frontal sinus index could be considered an indicator of harmonious anterior occlusion.

Cephalometric evaluation of skeletal stability and pharyngeal airway changes after mandibular setback surgery: Bioabsorbable versus titanium plate and screw fixation.

Purpose: This study compared sequential changes in skeletal stability and the pharyngeal airway following mandibular setback surgery involving fixation with either a titanium or a bioabsorbable plate and screws. Materials and Methods: Twenty-eight patients with mandibular prognathism undergoing bilateral sagittal split osteotomy by titanium or bioabsorbable fixation were randomly selected in this study. Lateral cephalometric analysis was conducted preoperatively and at 1 week, 3-6 months, and 1 year postoperatively. Mandibular stability was assessed by examining horizontal (BX), vertical (BY), and angular measurements including the sella-nasion to point B angle and the mandibular plane angle (MPA). Pharyngeal airway changes were evaluated by analyzing the nasopharynx, uvula-pharynx, tongue-pharynx, and epiglottis-pharynx (EOP) distances. Mandibular and pharyngeal airway changes were examined sequentially. To evaluate postoperative changes within groups, the Wilcoxon signed-rank test was employed, while the Mann-Whitney U test was used for between-group comparisons. Immediate postoperative changes in the airway were correlated to surgical movements using the Spearman rank test. Results: Significant changes in the MPA were observed in both the titanium and bioabsorbable groups at 3-6 months post-surgery, with significance persisting in the bioabsorbable group at 1 year postoperatively (2.29°±2.28°; P<0.05). The bioabsorbable group also exhibited significant EOP changes (-1.21±1.54 mm; P<0.05) at 3-6 months, which gradually returned to non-significant levels by 1 year postoperatively. Conclusion: Osteofixation using bioabsorbable plates and screws is comparable to that achieved with titanium in long-term skeletal stability and maintaining pharyngeal airway dimensions. However, a tendency for relapse exists, especially regarding the MPA.

Changes in lateral standing posture following orthognathic surgery: a cohort study.

Altering neuromuscular and musculoskeletal relationships also affects standing body posture, particularly in the head and neck areas. This prospective cohort study assessed the effects of orthognathic surgery on head posture in the lateral standing view. Thirty-one patients who underwent single-jaw orthognathic mandibular surgery were included. The patients underwent cephalometric and photographic evaluations of their habitual posture before and 6 months after surgery. The craniovertebral angle and Frankfort angle were determined and measured using MB-Ruler software. Mandibular positional changes were also measured by superimposing lateral cephalograms and recording changes in the menton point. All data were analysed by paired t-test. The craniovertebral angle increased significantly in patients with Class II malocclusion (P = 0.001) and decreased significantly in Class III patients (P = 0.004). Furthermore, the Frankfort angle was significantly increased in both Class II (P = 0.005) and Class III (P = 0.012) patients. The tendency towards forward head posture decreased in Class II patients, and the neck posture improved. Conversely, a slight but significant tendency towards a forward head posture was observed in Class III patients after surgery. Furthermore, the natural head position changed in both study groups, leading to a more upright head posture.

Argentine and World Health Organization head circumference standards: A comparison study. / Estándares de perímetro cefálico argentinos y de la Organización Mundial de la Salud: estudio comparativo.

Introduction. Several studies have shown population differences in head circumference (HC) that question the universal validity of the World Health Organization (WHO) standard to assess head growth. Objectives. To compare the Argentine reference charts for HC from 0 to 5 years of age with the WHO standards. Population and methods. The 3rd and 97th percentiles for HC based on the Argentine reference charts were compared with the corresponding WHO standard and the percentage of children classified as having microcephaly (HC < 3rd percentile of the WHO) and macrocephaly (HC > 97th percentile of the WHO) at specific ages between 0 and 5 years were estimated. Results. The comparison of the Argentine reference charts with the WHO standards shows that, in both males and females, at the 3rd percentile, the Argentine reference charts are below the WHO standards from 1 to 6 months of age, similar from 9 to 18 months of age, and then above until 60 months old. In relation to the 97th percentile, the Argentine reference charts are above the WHO standards from birth to 60 months in both boys and girls. Conclusions. The head size of Argentine children is different from that established by the WHO standards. The adoption of the WHO standards for our population increases the percentage of macrocephaly diagnosis at all ages.

Introducción. Diversos estudios han evidenciado diferencias poblacionales en el tamaño cefálico que cuestionan la validez universal del estándar de la Organización Mundial de la Salud (OMS) para evaluar el crecimiento cefálico. Objetivos. Comparar las referencias argentinas de perímetro cefálico (PC) de 0 a 5 años con los estándares de la OMS. Población y métodos. Se compararon los percentiles 3 y 97 de PC de las referencias argentinas con los correspondientes del estándar de la OMS y se calcularon los porcentajes de niños clasificados como microcefálicos (PC < percentil 3 de la OMS) y macrocefálicos (PC > percentil 97 de la OMS) a edades específicas entre el nacimiento y los 5 años de edad. Resultados. La comparación de las referencias argentinas con los estándares de la OMS, muestra que ­en ambos sexos­ en el percentil 3, desde el primer mes y hasta los 6 meses, las referencias argentinas se encuentran por debajo de los estándares de la OMS, son similares entre los 9 y 18 meses, y luego se ubican por encima hasta los 60 meses. En relación con el percentil 97, las referencias argentinas se ubican por encima de los estándares de la OMS desde el nacimiento hasta los 60 meses en ambos sexos. Conclusiones. El tamaño cefálico de los niños y niñas argentinos difiere del de los estándares de la OMS. La adopción de los estándares de la OMS en nuestra población incrementa el porcentaje de diagnóstico de macrocefalia a todas las edades.

RadImageNet and ImageNet as Datasets for Transfer Learning in the Assessment of Dental Radiographs: A Comparative Study.

Transfer learning (TL) is an alternative approach to the full training of deep learning (DL) models from scratch and can transfer knowledge gained from large-scale data to solve different problems. ImageNet, which is a publicly available large-scale dataset, is a commonly used dataset for TL-based image analysis; many studies have applied pre-trained models from ImageNet to clinical prediction tasks and have reported promising results. However, some have questioned the effectiveness of using ImageNet, which consists solely of natural images, for medical image analysis. The aim of this study was to evaluate whether pre-trained models using RadImageNet, which is a large-scale medical image dataset, could achieve superior performance in classification tasks in dental imaging modalities compared with ImageNet pre-trained models. To evaluate the classification performance of RadImageNet and ImageNet pre-trained models for TL, two dental imaging datasets were used. The tasks were (1) classifying the presence or absence of supernumerary teeth from a dataset of panoramic radiographs and (2) classifying sex from a dataset of lateral cephalometric radiographs. Performance was evaluated by comparing the area under the curve (AUC). On the panoramic radiograph dataset, the RadImageNet models gave average AUCs of 0.68 ± 0.15 (p < 0.01), and the ImageNet models had values of 0.74 ± 0.19. In contrast, on the lateral cephalometric dataset, the RadImageNet models demonstrated average AUCs of 0.76 ± 0.09, and the ImageNet models achieved values of 0.75 ± 0.17. The difference in performance between RadImageNet and ImageNet models in TL depends on the dental image dataset used.

Cephalometry as an aid in the diagnosis of pediatric obstructive sleep apnoea: A systematic review and meta-analysis.

Background: Obstructive sleep apnoea (OSA) is part of a spectrum of sleep disorders causing snoring, gasping, and choking while sleeping. In children, OSA can also lead to behavioural issues, hyperactivity, and poor academic performance. Thus, early identification and management of OSA in children is crucial in preventing long-term health problems. The gold standard test for diagnosis is an overnight in-lab polysomnography (PSG). However, due to certain constraints associated with PSG, such as lack of accessibility, high expenses incurred, as well as the need for hospitalization, alternative diagnostic tools are needed. Cephalometry is a non-invasive, affordable diagnostic tool that may offer useful information in the evaluation of OSA. The present systematic review and meta-analysis aimed to evaluate the various cephalometric parameters associated with the diagnosis of OSA in children. Methods: A structured literature search was performed using the search engines PubMed, Scopus, Web of Science, Cochrane, and Google scholar from inception till July 2022. The weighted mean difference (z-test) was calculated using a random effects method (REM). Results: 16 studies were included in the review and meta-analysis was executed for each cephalometric parameter. The parameters of significance (p < 0.05) in Pediatric OSA with lower heterogeneity were associated with McNamara's and Linder-Aronson's analysis, the hyoid bone position, a retrognathic mandible, and an acute cranial base angle. Conclusions: Certain parameters in craniofacial morphology may be reliable diagnostic parameters. Further long-term studies are needed in order to shed more light in this area.

Craniofacial morphological variability in orthodontic patients with non-syndromic orofacial clefts: an approach using geometric morphometrics.

OBJECTIVES: Orofacial clefts are complex congenital anomalies that call for comprehensive treatment based on a thorough assessment of the anatomy. This study aims to examine the effect of cleft type on craniofacial morphology using geometric morphometrics. MATERIALS AND METHODS: We evaluated lateral cephalograms of 75 patients with bilateral cleft lip and palate, 63 patients with unilateral cleft lip and palate, and 76 patients with isolated cleft palate. Generalized Procrustes analysis was performed on 16 hard tissue landmark coordinates. Shape variability was studied with principal component analysis. In a risk model approach, the first nine principal components (PC) were used to examine the effect of cleft type. RESULTS: We found statistically significant differences in the mean shape between cleft types. The difference is greatest between bilateral cleft lip and palate and isolated cleft palate (distance of means 0.026, P = 0.0011). Differences between cleft types are most pronounced for PC4 and PC5 (P = 0.0001), which together account for 10% of the total shape variation. PC4 and PC5 show shape differences in the ratio of the upper to the lower face, the posterior mandibular height, and the mandibular angle. CONCLUSIONS: Cleft type has a statistically significant but weak effect on craniofacial morphological variability in patients with non-syndromic orofacial clefts, mainly in the vertical dimension. CLINICAL RELEVANCE: Understanding the effects of clefts on craniofacial morphology is essential to providing patients with treatment tailored to their specific needs. This study contributes to the literature particularly due to our risk model approach in lieu of a prediction model.

A case series on a new reference in mandibular angles harmonization: the Frontozygomatic-Infraorbital Line (FZ-IOL).

the aim of this paper, is to propose a new reference line: the Frontozygomatic-Infraorbital Line (FZ-IOL). This reference line can guide the surgical team planning mandibular angle harmonization, based on the patient's skeletal proportion. The Frontozygomatic-Infraorbital Line has been adopted for symmetrization surgery, masculinization surgery, and in unsatisfactory results of previous orthognathic surgery. From March 2021 to December 2022, 3 patients were treated for severe facial asymmetry affecting mainly the lower third of the face. All cases were planned with the reference FZ-IOL. Patients were treated in the same center, at the Orthognathic Surgery Department of the Instituto Portugues da Face, Lisbon, Portugal. The Frontozygomatic-Infraorbital Line is designed virtually using software to reconstruct a 3D image from a digital imaging and communications in medicine (DICOM) file obtained from a cone beam computer tomography (CBCT). , connecting the two orbital rims. Then, a vertical line, the frontozygomatic line perpendicular to the IOL and passing through the outmost lateral portion of the frontozygomatic suture is drawn. The proposed line demonstrated how establishing appropriate reference lines is crucial for the success of the surgery. The selection of reference lines should be based on the patient's anatomy, the symmetrization process's complexity, and the surgery's desired outcome. The Frontozygomatic-Infraorbital Line represents an adequate reference line for managing mandibular angle lateral projection, improving lower third of the face symmetrization.

Orthognathic surgery improves compromised natural head position and pharyngeal airway in patients with Skeletal Class II or III malocclusion.

BACKGROUND: Natural head position (NHP), pharyngeal airway and maxillofacial growth pattern are correlated. The author's previous studies proved that following surgical correction of Skeletal Class II malocclusion, the over-extended NHP returned upright, and the pharyngeal airway space (PAS) dimension expanded. OBJECTIVE: The present study compares the post-operative change in NHP and PAS after orthognathic surgery in Skeletal Class II and III malocclusion patients. METHODS: Patients receiving orthognathic procedures to correct Skeletal Class II or III malocclusions were reviewed in this retrospective study. Pre-operative and 6-week post-operative cone-beam computed tomography datasets were collected. Variables representing the craniofacial pattern, the NHP and the PAS were measured three-dimensionally. Post-operative variables were compared with their pre-operative counterparts using either repeat-measure 2-way analysis of variance or Wilcoxon matched-pairs signed rank test. RESULTS: Thirty cases of Skeletal Class II malocclusion and 13 cases of Skeletal Class III malocclusion were collected. Preoperatively, the inter-group differences were significant in craniofacial pattern (68.14 ± 3.552 degree vs. 79.63 ± 2.497 degree, p < .0001) and the NHP (68.77 ± 11.02 degree vs. 82.83 ± 7.738 degree, p = .0002) while not significant in PAS; after surgery, the intergroup differences in craniofacial pattern and the NHP between groups decreased, and the PAS increased in both groups. CONCLUSION: Orthognathic surgery may improve compromised NHP and increase PAS in Skeletal Class II and III malocclusion patients.