Comparison of semi and fully automated artificial intelligence driven softwares and manual system for cephalometric analysis.

BACKGROUND: Cephalometric analysis has been used as one of the main tools for orthodontic diagnosis and treatment planning. The analysis can be performed manually on acetate tracing sheets, digitally by manual selection of landmarks or by recently introduced Artificial Intelligence (AI)-driven tools or softwares that automatically detect landmarks and analyze them. The use of AI-driven tools is expected to avoid errors and make it less time consuming with effective evaluation and high reproducibility. OBJECTIVE: To conduct intra- and inter-group comparisons of the accuracy and reliability of cephalometric tracing and evaluation done manually and with AI-driven tools that is WebCeph and CephX softwares. METHODS: Digital and manual tracing of lateral cephalometric radiographs of 54 patients was done. 18 cephalometric parameters were assessed on each radiograph by 3 methods, manual method and by using semi (WebCeph) and fully automatic softwares (Ceph X). Each parameter was assessed by two investigators using these three methods. SPSS was then used to assess the differences in values of cephalometric variables between investigators, between softwares, between human investigator means and software means. ICC and paired T test were used for intra-group comparisons while ANOVA and post-hoc were used for inter-group comparisons. RESULTS: Twelve out of eighteen variables had high intra-group correlation and significant ICC p-values, 5 variables had relatively lower values and only one variable (SNO) had significantly low ICC value. Fifteen out of eighteen variables had minimal detection error using fully-automatic method of cephalometric analysis. Only three variables had lowest detection error using semi-automatic method of cephalometric analysis. Inter-group comparison revealed significant difference between three methods for eight variables; Witts, NLA, SNGoGn, Y-Axis, Jaraback, SNO, MMA and McNamara to Point A. CONCLUSION: There is a lack of significant difference among manual, semiautomatic and fully automatic methods of cephalometric tracing and analysis in terms of the variables measured by these methods. The mean detection errors were the highest for manual analysis and lowest for fully automatic method. Hence the fully automatic AI software has the most reproducible and accurate results.

Reliability and safety of miniscrew insertion planning with the use of lateral cephalograms assessed on corresponding cone-beam computer tomography images.

BACKGROUND/OBJECTIVES: Recently, lateral cephalograms have been proposed for guided miniscrew insertion planning. Therefore, the aim was to assess the reliability and safety of such planning on corresponding cone-beam computer tomography (CBCT) images. MATERIALS/METHODS: Intraoral scans, lateral cephalograms, and CBCT images of 52 subjects (even sexes distribution), aged 15.1 ±â€…2.5 years, were included. Miniscrew (n = 104) insertion planning was performed using lateral cephalograms superimposed on the maxillary intraoral scans, while the assessment of their bicortical placement, length in bone, contact with adjacent teeth, incisive canal, and nasal floor perforation was done on corresponding superimposed CBCT images. Moreover, maxillary incisor inclination, crowding, and the maxillary intercanine width were measured. RESULTS: The overall miniscrew length in bone was 7.2 ±â€…1.3mm. Bicortical placement was seen in 58.7% of the sample (38.5% of subjects). Incisive canal and nasal floor perforation was seen in 25% and 21.2% of subjects, respectively. No contact of the miniscrew with adjacent teeth was recorded. A negative significant interaction was seen between the miniscrew length in bone, the percentage of total miniscrew length and maxillary anterior teeth crowding (ß, -0.10, P = .047 and ß, -0.90, P = .006, respectively). Moreover, a positive significant interaction was seen between the incisive canal perforation and maxillary anterior teeth crowding (OR = 1.32, P = .021). LIMITATIONS: Exclusion of subjects with impacted teeth. CONCLUSIONS: Miniscrew insertion planning using lateral cephalograms, despite being safe in preventing contact with adjacent teeth, is limited in achieving bicortical placement and insufficient in completely avoiding incisive canal and nasal floor perforation.

Comparative manual and digital analysis of gonial angle in lateral cephalograms for gender determination.

Human skull has always been used for victim identification in forensic odontology. The gender-dimorphic bone of the skull is the mandible. The gonial angle has frequently been investigated for gender estimation with variable results and requires further exploration. We aim to compare the efficacy of gonial angle estimation by ancient methods of lateral cephalometric tracing compared with more recent digital analysis methods for gender estimation in the Indian population. Lateral cephalograms of 191 (96 M and 95F) cases above the age of 17 years were retrieved. Cephalometric analysis of gonial angle on radiographs was done using both manual cephalometric tracing method and digitally using Adobe Photoshop software. The results were subjected to statistical analysis for evaluation. The mean gonial angle was higher in females (125.05; 123.77 and 125.28) than in males (122.583; 121.715 and 122.008) using both manual and digital methods. On applying the logistical regression analysis (LRA), the digital method showed the highest gender estimation accuracy of 60.7% followed by Burstone's analysis (57.1%) and manual conventional analysis (56.5%). Burstone's analysis (57.9%) correctly identified increased females, whereas digital analysis (62.5%) and manual conventional analysis (59.4%) accurately recognised increased males. The present study showed a higher gender estimation accuracy using digital methods as compared to manual methods, but it still lacks the credibility to be used as a sole factor for predicting the gender of an individual. Hence, a cumulative factor must be taken into consideration for gender identification which would provide more promising results.

Prevalence of Ponticulus Posticus among Orthodontic Patients of Iranian Population by Lateral Cephalogram.

Background: The term Ponticulus Posticus (PP) refers to a complete or partial bony bridge on the vertebral artery that passes through the superior-lateral surface of the posterior arch of the atlas. This study was conducted with the aim of investigating the prevalence of ponticulus posticus in orthodontic patients referred to Mashhad Dental School. Methods: In this cross-sectional study, one thousand cephalograms were selected from the patients referred to the orthodontics department of Mashhad Dental School between 2017 and 2021. In lateral cephalogram images with appropriate quality, the type of malocclusion was determined using the AudaxCeph software (Audax d.o.o., Ljubljana, Slovenia). Then, the images were evaluated for the presence or absence of PP. For the statistical analysis, chi-square and t-test were used. Results: In this study, 861 lateral digital cephalograms were analyzed. The overall prevalence of PP in the studied population was 17.5%. The prevalence of PP was higher in males than in females (P < 0.001). The variables "presence of PP" (P = 0.056) and "type of PP" (P = 0.522) were found to be independent of age groups. Although class II subjects showed a higher prevalence of PP, skeletal malocclusion classes were not found to be correlated with the presence of PP (P = 0.104) nor with its types (P = 0.958). Conclusion: The current study is considered the primary study that provides data concerning the prevalence of PP in the East of Iran. Our study showed that PP was not rare in this region. More studies with 3D radiological examination are needed to increase the accuracy of diagnosing PP and its prevalence in Iran.

Effects of Twin-Block with an expanding device on the upper airway in growing children with skeletal class II malocclusion-a retrospective study based on the consistency of three-dimensional and two-dimensional data.

OBJECTIVES: Skeletal class II malocclusion is one of the most common malocclusions. Among the functional appliances for skeletal class II malocclusion, the Twin-Block appliance with a maxillary expander is effective in repositioning the mandible forward. In this study, we focused our efforts on investigating the effects of Twin-Block appliances with maxillary expanders on the upper airway in growing children with skeletal class II malocclusion by tracing and measuring lateral cephalograms after evaluating the consistency of three-dimensional CBCT data and two-dimensional lateral cephalogram data. MATERIALS AND METHODS: A total of 102 patients ranging from 9 to 15 years old (11.37 ± 2.80, male/female ratio = 1:1) with skeletal class II malocclusion were selected to evaluate the consistency of CBCT data and lateral cephalogram data. The strongly and moderately correlated segments were then selected to study the effects of Twin-Block with a maxillary expander on the upper airway in 66 growing children with skeletal class II malocclusion (11.31 ± 1.23 years old, male/female ratio = 1:1) by lateral cephalograms. RESULTS: The results showed a strong significant correlation in the nasopharynx (r = 0.708) and moderate significant correlations in the overall upper airway (r = 0.641), palatopharynx (r = 0.553), and glossopharynx (r = 0.575) but a weak correlation in the hypopharynx (r = 0.323). The corresponding determination coefficient (R2) was also determined by scatter plot analysis. Moreover, compared with the pretreatment data (T1), the total area of the upper airway and the areas of the nasopharynx, palatopharynx, and glossopharynx after functional treatment (T2) increased statistically and significantly. CONCLUSIONS: Lateral cephalograms can reflect the volume of the nasopharynx and oropharynx in skeletal class II children to a certain extent, while Twin-Block appliances with maxillary expanders can widen the volume of the nasopharynx and oropharynx significantly. CLINICAL RELEVANCE: The lateral cephalogram is reliable for analyzing the nasopharynx, palatopharynx, and glossopharynx in orthodontic clinical practice. Twin-Block appliances with maxillary expanders have a positive effect on skeletal class II patients with airway stenosis.

Role of the tonsil-oropharynx ratio on lateral cephalograms in assessing tonsillar hypertrophy in children seeking orthodontic treatment.

OBJECTIVES: To analyze the diagnostic value of the tonsil-oropharynx (T/O) ratio on lateral cephalograms for evaluating tonsillar hypertrophy (TH). METHODS: A cross-sectional study was performed on 185 consecutive children (101 males, 84 females; mean age 7.3 ± 1.4 years) seeking orthodontic treatment. The T/O ratios on lateral cephalograms were calculated following Baroni et al.'s method. Tonsil sizes were clinically determined according to the Brodsky grading scale. Spearman correlation coefficients between the T/O ratio and clinical tonsil size were calculated with the total sample and subgroups and then compared between subgroups. Diagnostic value was analyzed using the receiver operating characteristic (ROC) curve, sensitivity, specificity, positive and negative predictive values, and accuracy. RESULTS: There was a strong correlation between the T/O ratio and clinical tonsil size in children (ρ = 0.73; P < 0.001). A significantly higher correlation coefficient was found in the Class III children. The ROC curve revealed an area under the curve of 0.90 (95% CI, 0.86-0.94; P < 0.001). The optimal cutoff value of the T/O ratio for predicting TH was 0.58, with a sensitivity of 98.7% and specificity of 64.2%. Employing the cutoff value of 0.5, the sensitivity was 100% and the specificity was 45.9%. CONCLUSIONS: Measurement of the T/O ratio on lateral cephalograms may be helpful to initial screening in children for TH. Practitioners may combine the clinical examination of tonsil size with the cephalometric findings for a more comprehensive evaluation.

The psc-CVM assessment system: A three-stage type system for CVM assessment based on deep learning.

BACKGROUND: Many scholars have proven cervical vertebral maturation (CVM) method can predict the growth and development and assist in choosing the best time for treatment. However, assessing CVM is a complex process. The experience and seniority of the clinicians have an enormous impact on judgment. This study aims to establish a fully automated, high-accuracy CVM assessment system called the psc-CVM assessment system, based on deep learning, to provide valuable reference information for the growth period determination. METHODS: This study used 10,200 lateral cephalograms as the data set (7111 in train set, 1544 in validation set and 1545 in test set) to train the system. The psc-CVM assessment system is designed as three parts with different roles, each operating in a specific order. 1) Position Network for locating the position of cervical vertebrae; 2) Shape Recognition Network for recognizing and extracting the shapes of cervical vertebrae; and 3) CVM Assessment Network for assessing CVM according to the shapes of cervical vertebrae. Statistical analysis was conducted to detect the performance of the system and the agreement of CVM assessment between the system and the expert panel. Heat maps were analyzed to understand better what the system had learned. The area of the third (C3), fourth (C4) cervical vertebrae and the lower edge of second (C2) cervical vertebrae were activated when the system was assessing the images. RESULTS: The system has achieved good performance for CVM assessment with an average AUC (the area under the curve) of 0.94 and total accuracy of 70.42%, as evaluated on the test set. The Cohen's Kappa between the system and the expert panel is 0.645. The weighted Kappa between the system and the expert panel is 0.844. The overall ICC between the psc-CVM assessment system and the expert panel was 0.946. The F1 score rank for the psc-CVM assessment system was: CVS (cervical vertebral maturation stage) 6 > CVS1 > CVS4 > CVS5 > CVS3 > CVS2. CONCLUSIONS: The results showed that the psc-CVM assessment system achieved high accuracy in CVM assessment. The system in this study was significantly consistent with expert panels in CVM assessment, indicating that the system can be used as an efficient, accurate, and stable diagnostic aid to provide a clinical aid for determining growth and developmental stages by CVM.

Ceph-Net: automatic detection of cephalometric landmarks on scanned lateral cephalograms from children and adolescents using an attention-based stacked regression network.

BACKGROUND: The success of cephalometric analysis depends on the accurate detection of cephalometric landmarks on scanned lateral cephalograms. However, manual cephalometric analysis is time-consuming and can cause inter- and intra-observer variability. The purpose of this study was to automatically detect cephalometric landmarks on scanned lateral cephalograms with low contrast and resolution using an attention-based stacked regression network (Ceph-Net). METHODS: The main body of Ceph-Net compromised stacked fully convolutional networks (FCN) which progressively refined the detection of cephalometric landmarks on each FCN. By embedding dual attention and multi-path convolution modules in Ceph-Net, the network learned local and global context and semantic relationships between cephalometric landmarks. Additionally, the intermediate deep supervision in each FCN further boosted the training stability and the detection performance of cephalometric landmarks. RESULTS: Ceph-Net showed a superior detection performance in mean radial error and successful detection rate, including accuracy improvements in cephalometric landmark detection located in low-contrast soft tissues compared with other detection networks. Moreover, Ceph-Net presented superior detection performance on the test dataset split by age from 8 to 16 years old. CONCLUSIONS: Ceph-Net demonstrated an automatic and superior detection of cephalometric landmarks by successfully learning local and global context and semantic relationships between cephalometric landmarks in scanned lateral cephalograms with low contrast and resolutions.

Predictive Equation for Construction of Anatomic Porion with Machine Porion as Reference Point.

AIM: The aim of the study was to find a relationship between anatomic porion (PoA) and machine porion (PoM) and to construct PoA with the help of machine porion. METHODOLOGY: About 200 pretreatment lateral roentgenic cephalograms were used for the study. Perpendicular distances of PoA and PoM were measured from Sella-Nasion (SN) plane and SN perpendicular plane. The results were tabulated. With the help of statistical analysis, predictive equation was derived to construct PoA and PoM. p-value was set at p < 0.05. RESULTS: Anatomic porion distance from SN was 24.35 ± 3.96 and from SN perpendicular was 12.89 ± 4.56. Distance of PoM from SN was 22.46 ± 4.20 and from SN perpendicular was 16.76 ± 4.89. Sexual dimorphism was also seen. CONCLUSION: There is a relationship between the PoM and PoA, thus, PoA, which is more reliable, can be constructed with the help of PoM, which is easy to reproduce. CLINICAL SIGNIFICANCE: To overcome the inherent limitations of PoA and PoM, the present study aimed to find a relationship between the two so as to easily construct PoA that is more reliable while taking advantage of the ease of reproducibility of PoM.

Longitudinal Follow-Up of Facial Growth of Patients With Unilateral Cleft Lip and Palate Following Modified Veau-Wardill-Kilner Palatoplasty.

OBJECTIVE: To evaluate facial growth after modified Veau-Wardill-Kilner/pushback (PB) palatoplasty from childhood to adulthood in patients with unilateral cleft lip and palate (UCLP). DESIGN: Retrospective longitudinal study. SETTING: Single center. PATIENTS: Sixty-two (29 males and 33 females) consecutive patients with nonsyndromic UCLP. INTERVENTIONS: Pushback palatoplasty and subsequent cleft palate treatment. MAIN OUTCOME MEASURES: Lateral and posterior-anterior cephalograms were taken at 3 different phases: phase 1 (before first-stage orthodontic treatment; N = 58; average age, 4.9 ± 1.1 years), phase 2 (before second-stage orthodontic treatment; N = 58; 15.9 ± 1.1 years), and phase 3 (after orthodontic retention; N = 51; 22.1 ± 3.2 years). RESULTS: The majority of patients had skeletal class III morphology in all 3 phases due to retrognathic maxilla. Maxillary growth did not improve in phase 2 despite first-stage orthodontic treatment in phase 1. Maxillary morphology improved in phase 3 but retardation occurred, although 77.42% of patients received orthognathic surgery during second-stage orthodontic treatment. Mandibular growth was slightly reduced in phases 1 and 2 and the mandible remained retrognathic in phase 3, following mandibular setback orthognathic surgery. The horizontal occlusal cant was slightly upward and toward the cleft side with respect to the reference plane, and the upper midline was deviated to the cleft side in phases 1 and 3. CONCLUSIONS: Patients with UCLP who undergo phased PB palatoplasty, orthodontic treatment, and orthognathic surgeries do not maintain skeletal class I facial morphology.

Evaluation of fully automated cephalometric measurements obtained from web-based artificial intelligence driven platform.

BACKGROUND: Artificial Intelligence has created a huge impact in different areas of dentistry. Automated cephalometric analysis is one of the major applications of artificial intelligence in the field of orthodontics. Various automated cephalometric software have been developed which utilizes artificial intelligence and claim to be reliable. The purpose of this study was to compare the linear and angular cephalometric measurements obtained from web-based fully automated Artificial Intelligence (AI) driven platform "WebCeph"™ with that from manual tracing and evaluate the validity and reliability of automated cephalometric measurements obtained from "WebCeph"™. METHODS: Thirty pre-treatment lateral cephalograms of patients were randomly selected. For manual tracing, digital images of same cephalograms were printed using compatible X-ray printer. After calibration, a total of 18 landmarks was plotted and 12 measurements (8 angular and 4 linear) were obtained using standard protocols. The digital images of each cephalogram were uploaded to "WebCeph"™ server. After image calibration, the automated cephalometric measurements obtained through AI digitization were downloaded for each image. Intraclass correlation coefficient (ICC) was used to determine agreement between the measurements obtained from two methods. ICC value < 0.75 was considered as poor to moderate agreement while an ICC value between 0.75 and 0.90 was considered as good agreement. Agreement was rated as excellent when ICC value > 0.90 was obtained. RESULTS: All the measurements had ICC value above 0.75. A higher ICC value > 0.9 was obtained for seven parameters i.e. ANB, FMA, IMPA/L1 to MP (°), LL to E-line, L1 to NB (mm), L1 to NB (°), S-N to Go-Gn whereas five parameters i.e. UL to E-line, U1 to NA (mm), SNA, SNB, U1 to NA (°) showed ICC value between 0.75 and 0.90. CONCLUSION: A good agreement was found between the cephalometric measurements obtained from "WebCeph"™ and manual tracing.

The Link between Obstructive Sleep Apnea Syndrome and Cephalometric Assessment of Upper Airways and Hyoid Bone Position.

Background and Objectives: To determine whether there are changes in the cephalometric characteristics of the upper airways and hyoid bone, in patients diagnosed with obstructive sleep apnea syndrome (OSAS) compared to a healthy control group. Material and Methods: This retrospective case−control study included 24 patients diagnosed with OSAS (apnea−hypopnea index (AHI) > 5 obtained after polysomnography) and 24 healthy subjects as a control group that completed the STOP-Bang questionnaire to determine whether they had OSAS. Lateral cephalometric examinations were recommended for all these patients. The software used for the cephalogram interpretation was CS 3D Imaging and CS Airway imaging from Carestream Dental. Results: The subjects with OSAS had a smaller superior posterior airway space (SPAS), with an average of 10.32 mm compared to a 12.20 mm mean in the control group (p = 0.03). Patients with OSAS, had a lowered middle airway space (MAS) with a mean of 7.96 mm in the OSAS group and a 10.96 mm mean in the control group (p = 0.00). All the measurements made for the hyoid bone, such as­H-MnP, H-C3, and H-B­showed increased values (means of 26.31 mm, 39.08 mm, 60.05 mm, respectively), for the OSAS group (p = 0.00). Conclusions: Patients suffering from OSAS had reduced dimensions of the SPAS and MAS values. The hyoid bone had a more inferior position in the study group (with increased values for H-MnP, H-C3, and H-B) compared to the control group.

Aerodynamic characteristics in upper airways among orthodontic patients and its association with adenoid nasopharyngeal ratios in lateral cephalograms.

BACKGROUND: Adenoid hypertrophy among orthodontic patients may be detected in lateral cephalograms. The study investigates the aerodynamic characteristics within the upper airway (UA) by means of computational fluid dynamics (CFD) simulation. Furthermore, airflow features are compared between subgroups according to the adenoidal nasopharyngeal (AN) ratios. METHODS: This retrospective study included thirty-five patients aged 9-15 years having both lateral cephalogram and cone beam computed tomography (CBCT) imaging that covered the UA region. The cases were divided into two subgroups according to the AN ratios measured on the lateral cephalograms: Group 1 with an AN ratio < 0.6 and Group 2 with an AN ratio ≥ 0.6. Based on the CBCT images, segmented UA models were created and the aerodynamic characteristics at inspiration and expiration were simulated by the CFD method for the two groups. The studied aerodynamic parameters were pressure drop (ΔP), maximum midsagittal velocity (Vms), maximum wall shear stress (Pws), and minimum wall static pressure (Pw). RESULTS: The maximum Vms exhibits nearly 30% increases in Group 2 at both inspiration (p = 0.013) and expiration (p = 0.045) compared to Group 1. For the other aerodynamic parameters such as ΔP, the maximum Pws, and minimum Pw, no significant difference is found between the two groups. CONCLUSIONS: The maximum Vms seems to be the most sensitive aerodynamic parameter for the groups of cases. An AN ratio of more than 0.6 measured on a lateral cephalogram may associate with a noticeably increased maximum Vms, which could assist clinicians in estimating the airflow features in the UA.

Anatomical assessment by cone beam computed tomography with the use of lateral cephalograms to analyse the vertical bone height of the anterior palate for orthodontic mini-implants.

OBJECTIVE: Lateral cephalograms (LC) should be usable to evaluate the vertical bone height of the anterior maxilla for planning the placement of orthodontic mini-implants (OMI). The purpose of this study is to determine the usability of LC for examining the real vertical dimension of the anterior palate. SETTING AND SAMPLE POPULATION: Lateral cephalograms and corresponding cone beam computed tomography (CBCT) scans were employed for examining 30 fresh cadaver heads. MATERIALS & METHODS: The minimum (distance A) and maximum (distance B) vertical palatal bone heights on LCs at the level of first premolars were measured, whereas the corresponding measurements were taken via CBCTs on the median, and 2-, 4- and 6-mm paramedian planes. Additionally, the overall minimum vertical palatal height on CBCT was recorded. RESULTS: Distance A and B on LC were about 8.3 ± 2.5 mm and 9.9 ± 2.5 mm, respectively. The median palatal height on CBCT was significantly higher than both measurements on LC (P < .01). Furthermore, the bone supply on the paramedian planes was similar or higher on CBCT compared to Distance A and similar or less compared to Distance B. The strongest correlation at the level of the premolars was found in the comparison of the maximum vertical palatal height via LC with the vertical palatal height on the median plane via CBCT (r = .84, 95% CI: 0.69-0.92, P < .001). CONCLUSIONS: In order to make the best possible use of the vertical bone supply of the anterior palate and to avoid injuries to the nasal floor, Distance A should be taken into account for planning paramedian OMI placements and distance B for median OMI insertion.

Research on Panoramic Stitching Algorithm of Lateral Cranial Sequence Images in Dental Multifunctional Cone Beam Computed Tomography.

In the design of dental multifunctional Cone Beam Computed Tomography, the linear scanning strategy not only saves equipment cost, but also avoids the demand for patients to be repositioned when acquiring lateral cranial sequence images. In order to obtain panoramic images, we propose a local normalized cross-correlation stitching algorithm based on Gaussian Mixture Model. Firstly, the Block-Matching and 3D filtering algorithm is used to remove quantum and impulse noises according to the characteristics of X-ray images; Then, the segmentation of the irrelevant region and the extraction of the region of interest are performed by Gaussian Mixture Model; The locally normalized cross-relation is used to complete the registration with the multi-resolution strategy based on wavelet transform and Particle Swarm Optimization algorithm; Finally, image fusion is achieved by the weighted smoothing fusion algorithm. The experimental results show that the panoramic image obtained by this method has significant performance in both subjective vision and objective quality evaluation and can be applied to preoperative diagnosis of clinical dental deformity and postoperative effect evaluation.

Deep learning based prediction of necessity for orthognathic surgery of skeletal malocclusion using cephalogram in Korean individuals.

BACKGROUND: Posteroanterior and lateral cephalogram have been widely used for evaluating the necessity of orthognathic surgery. The purpose of this study was to develop a deep learning network to automatically predict the need for orthodontic surgery using cephalogram. METHODS: The cephalograms of 840 patients (Class ll: 244, Class lll: 447, Facial asymmetry: 149) complaining about dentofacial dysmorphosis and/or a malocclusion were included. Patients who did not require orthognathic surgery were classified as Group I (622 patients-Class ll: 221, Class lll: 312, Facial asymmetry: 89). Group II (218 patients-Class ll: 23, Class lll: 135, Facial asymmetry: 60) was set for cases requiring surgery. A dataset was extracted using random sampling and was composed of training, validation, and test sets. The ratio of the sets was 4:1:5. PyTorch was used as the framework for the experiment. RESULTS: Subsequently, 394 out of a total of 413 test data were properly classified. The accuracy, sensitivity, and specificity were 0.954, 0.844, and 0.993, respectively. CONCLUSION: It was found that a convolutional neural network can determine the need for orthognathic surgery with relative accuracy when using cephalogram.

Sella Turcica Area and Location of Point Sella in Cephalograms Acquired with Simulated Patient Head Movements.

AIM AND OBJECTIVE: This study assesses changes in the sella turcica area (STA) and location of the cephalometric point sella (S) on lateral cephalograms acquired by charge-coupled device (CCD)-based cephalostats with and without simulated patient head movements. MATERIALS AND METHODS: A real skull was placed on a robot, able to simulate four head movements (anteroposterior translation/lifting/nodding/lateral rotation) at three distances (0.75/1.5/3 mm) and two patterns (returning to 0.5 mm away from the start position/staying at maximum movement excursion). Two ProMax-2D cephalostats (Dimax-3, D-3 or Dimax-4, D-4), and an Orthophos-SL cephalostat (ORT) acquired cephalograms during the predetermined movements ("cases," 48 images/unit) and without movement ("controls," 24 images/unit). Three observers manually traced the contour of sella turcica and marked point sella using a computer mouse. STA was calculated in pixels2 by dedicated software based on the tracing. S was defined by its x and y coordinates recorded by the same software in pixels. Ten percent of the images were assessed twice. The difference between cases and controls (case minus control) for the STA and S (namely Diff-STA and Diff-S) was calculated and assessed through descriptive statistics. RESULTS: Inter- and intraobserver agreement ranged from moderate to good for STA and S. Diff-STA ranged from -42.5 to 12.9% (D-3), -15.3 to 9.6% (D-4), and -25.3 to 39.9% (ORT). Diff-S was represented up to 50% (D-3), 134% (D-4), and 103% (ORT) of the mean sella turcica diameter in control images. CONCLUSION: Simulated head movements caused significant distortion in lateral cephalograms acquired by CCD-based cephalostats, as seen from STA and S alterations, depending on the cephalostat. CLINICAL SIGNIFICANCE: Patient-related errors, including patient motion artifacts, are influential factors for the reliability of cephalometric tracing.

Assessment of Sagittal Condylar Guidance with Protrusive Inter-occlusal Method, Panoramic Radiographs, and Lateral Cephalogram: A Comparative Study.

BACKGROUND: Condylar guidance can be determined using the clinical and radiographic methods. The present study was conducted to determine condylar guidance using the protrusive interocclusal wax method, panoramic radiographs, and lateral cephalogram. AIMS: The aim of the study was to compare the correlation between sagittal condylar guidance with protrusive interocclusal method, panoramic radiographs, and lateral cephalogram. MATERIALS AND METHODS: The present study was conducted on 82 dentulous subjects (males 41, females 41). In all subjects, interocclusal registration values and condylar guidance values were measured using panoramic radiographs and lateral cephalograms. RESULTS: The mean ± SD protrusive interocclusal registration value on the left side was 34.01 ± 1.2 mm and 34.08 ± 1.4 mm on the right side. The panoramic radiographs showed 35.12 ± 1.6 mm on the left side and 35.16 ± 1.7 mm on the right side. The mean ± SD protrusive interocclusal registration values on the left side was 34.01 ± 1.2 mm on the left side and 34.08 ± 1.4 mm on the right side. Lateral cephalogram showed 34.35 ± 1.3 mm on the left side and 34.67 ± 1.6 mm on the right side. There was a significant difference between the methods (p < 0.05). CONCLUSION: Sagittal condylar guidance can be evaluated using protrusive interocclusal method. Along with it, other methods such as panoramic radiographs and lateral cephalogram may also be used for recording condylar guidance. CLINICAL SIGNIFICANCE: Lateral cephalogram and panoramic radiographs may be reliable in determining condylar guidance, which can be used in orthodontic treatment planning.

Frontal cephalometric landmarking: humans vs artificial neural networks.

Frontal cephalometric radiography (frontal ceph) is one of the important diagnostic methods in orthodontics and maxillofacial surgery. It allows one to determine occlusion anomalies in the transverse and vertical planes and to evaluate the symmetry of the facial skeleton relative to the median plane, including analysis of the position of the jawbone. AIM: The aim of this study was to develop an artificial neural network (ANN) for placing cephalometric points (CPs) on frontal cephs and to compare the accuracy of its performance against humans. MATERIALS AND METHODS: The study included 330 depersonalized frontal cephs: 300 cephs for training ANNs and 30 for research. Each image was imported into the ViSurgery software (Skolkovo, Russia) and the 45 CPs were arranged. The CPs were divided into three groups: 1) precise anatomical landmarks; 2) complex anatomical landmarks; and 3) indistinct anatomical landmarks. Two ANNs were used to improve the accuracy of CP placement. The first ANN solved the problem of multiclass image segmentation, and the second regression ANN was used to correct the predictions of the first ANN. The accuracy of CP placement was compared between the ANN and three groups of doctors: expert, regular, and inexperienced. Then, using the Wilcoxon t test, the hypothesis that an ANN makes fewer or as many errors as doctors in the three groups of points was tested. RESULTS: The deviation was estimated by the mean absolute error (MAE). The MAE for the points placed by the ANN, as compared with the control, was close to the average result for the regular doctor group: 2.87 mm (ANN) and 2.85 mm (regular group); 2.47 mm (expert group), and 3.61 mm (inexperienced group). The results for individual groups of points are presented. On average, the ANN places CPs no less accurately than the regular doctor group in each group of points. However, calculating all points in total, this hypothesis was rejected because the P value was 0.0056. A different result was observed among the inexperienced doctor group. Points from groups 2 and 3, as well as all points in total, were placed more accurately by the ANN (P = 0.9998, 0.2628, and 0.9982, respectively). The exception was group 1, where the points were more accurately placed by the inexperienced doctors (P = 0.0006). CONCLUSION: The results of the present study show that ANNs can achieve accuracy comparable to humans in placing CPs, and in some cases surpass the accuracy of inexperienced doctors (students, residents, graduate students).

Whole-genome sequencing in a pair of monozygotic twins with discordant cleft lip and palate subtypes.

OBJECTIVE: Orofacial clefts (OFCs) are common and etiologically complex birth defects. This study explored potential genetic differences in a pair of Japanese monozygotic (MZ) twins with different forms of OFC using whole-genome sequencing. SUBJECTS AND METHODS: One co-twin (MZ-1) presented with nonsyndromic bilateral cleft lip and palate; the other co-twin (MZ-2) had nonsyndromic bilateral cleft lip and unilateral left-sided cleft alveolus. Neither parent had an OFC. Craniofacial morphologic features and potential genetic differences were compared using standard cephalometry and whole-genome sequencing, respectively. RESULTS: Morphologically, MZ-1 had a smaller vertical mandibular height, compared to MZ-2. However, no discordant genetic differences were detected. Moreover, both twins and their parents harbored rare candidate gene variants (GRHL3; TPM1) considered to be associated with OFCs. CONCLUSION: The observed differences between MZ-1 and MZ-2 in craniofacial morphology assessed by cephalograms might be directly attributable to the effects of the OFC on growth and/or differences in surgical history, given the lack of any differences in genetic background. However, comparisons of discordant MZ twins should continue to identify novel candidates that might control OFC or that might partly explain the missing heritability for this common birth defect, in addition to understanding craniofacial growth and development.