• angle
• cephalometric
• diagnosis
• malar bone
• relationship
• vector

• Deep learning
• Diagnosis
• Imaging
• Omics
• Pathomics
• Radiomics
• Stomatology

• Humans
• Mouth Diseases/diagnostic imaging
• Mouth Diseases/diagnosis
• Genomics
• Deep Learning
• Image Processing, Computer-Assisted/methods
• Oral Medicine
• Multiomics

• cephalometric analysis
• icc
• nemoceph
• oneceph
• reliability
• tracing
• webceph

• Artificial intelligence
• Cephalometry
• Software

• Humans
• Cephalometry/methods
• Software
• Artificial Intelligence
• Reproducibility of Results
• Anatomic Landmarks/diagnostic imaging
• Female
• Male
• Image Processing, Computer-Assisted/methods
• Adolescent
• Child

• Artificial Intelligence
• CephX
• Cephalometric analyses
• Lateral cephalogram
• WebCeph

• Humans
• Cephalometry/methods
• Artificial Intelligence
• Software
• Reproducibility of Results
• Adolescent
• Male
• Female

• Artificial intelligence
• Automatic cephalometry
• Cone-beam computed tomography
• Deep learning
• Systematic review

• Humans
• Cephalometry/methods
• Artificial Intelligence
• Anatomic Landmarks/diagnostic imaging
• Systematic Reviews as Topic
• Imaging, Three-Dimensional/methods
• Machine Learning

• Cephalometric analysis
• Cephalometry
• Lateral cephalogram
• Orthodontic education
• Radiograph
• Tablet computer
• iPad

• Humans
• Prospective Studies
• Reproducibility of Results
• Image Processing, Computer-Assisted
• Cephalometry
• Computers, Handheld

• Open Access Publication Fund of the University of Münster
• Universität Münster (1056)

• Humans
• Artificial Intelligence
• Cross-Sectional Studies
• Orthodontists
• Students
• Surveys and Questionnaires
• Health Knowledge, Attitudes, Practice

• artificial intelligence
• automatic
• cephalometrics
• digital
• manual
• tracing

The purpose of this study was to investigate the accuracy of one-step automated orthodontic diagnosis of skeletodental discrepancies using a convolutional neural network (CNN) and lateral cephalogram images with different qualities from nationwide multi-hospitals.

Among 2,174 lateral cephalograms, 1,993 cephalograms from two hospitals were used for training and internal test sets and 181 cephalograms from eight other hospitals were used for an external test set. They were divided into three classification groups according to anteroposterior skeletal discrepancies (Class I, II, and III), vertical skeletal discrepancies (normodivergent, hypodivergent, and hyperdivergent patterns), and vertical dental discrepancies (normal overbite, deep bite, and open bite) as a gold standard. Pre-trained DenseNet-169 was used as a CNN classifier model. Diagnostic performance was evaluated by receiver operating characteristic (ROC) analysis, t-stochastic neighbor embedding (t-SNE), and gradient-weighted class activation mapping (Grad-CAM).

In the ROC analysis, the mean area under the curve and the mean accuracy of all classifications were high with both internal and external test sets (all, > 0.89 and > 0.80). In the t-SNE analysis, our model succeeded in creating good separation between three classification groups. Grad-CAM figures showed differences in the location and size of the focus areas between three classification groups in each diagnosis.

Since the accuracy of our model was validated with both internal and external test sets, it shows the possible usefulness of a one-step automated orthodontic diagnosis tool using a CNN model. However, it still needs technical improvement in terms of classifying vertical dental discrepancies.

• Convolutional neural networks
• Lateral cephalogram
• Multi-center study
• One-step automated orthodontic diagnosis

This study compares the accuracy and reliability of WebCeph (web-based program for cephalometric analysis) with the AutoCAD computer software.

A sample of pretreatment digital lateral cephalograms of 50 orthodontic patients was analysed with WebCeph and AutoCAD software (as a standard measure). On each cephalogram, 17 landmarks and 11 measurements were marked and performed as skeletal, dental, and soft–tissue parameters. We used six angular and five linear measurements. A paired t-test was used to assess the systematic bias. The intraclass correlation coefficient (ICC) and Bland–Altman plot with linear regression analysis were used to assess the agreement between the two methods.

There was adequate reproducibility for the measurements with both WebCeph and AutoCAD. The paired t-test showed statistically significant differences for five angular and two linear measurements (P < 0.05). The ICC test between WebCeph and AutoCAD revealed very good to excellent agreement for all measurements, except for the lower incisor to mandibular plane angle. The Bland–Altman plot visually showed a relatively acceptable limit of agreement for three angular and two linear measurements only, and the linear regression analysis revealed a significant proportional bias between the two methods for four angles and the upper lip-Esthetic line (U Lip-E Line). The systematic bias and level of agreement improved with the use of the semi-automatic WebCeph.

Different problems, such as poor landmark identification/soft tissue tracing and inconsistency of measurements, are inherent to the automatic WebCeph. The semi-automatic WebCeph can overcome some limitations of the automatic WebCeph; however, it should be used for cephalometric analysis with a great deal of caution.

Lateral cephalometric analysis continues to be one of the gold standard diagnostic aids in orthodontics, with various software available to enhance this.

This study was done to evaluate the accuracy and reliability of linear and angular measurements obtained from OneCeph digital cephalometric tracing and manual tracings in lateral cephalometry.

This is a cross-sectional study done on twenty pre-treatment lateral cephalometric radiographs of subjects who reported to the postgraduate orthodontic clinic for orthodontic treatment over one month. Cephalometric tracings were done using OneCeph digital software and manual tracing method to evaluate nine parameters of Steiner’s cephalometric analysis. An Independent T-sample test was done between the mean values of manual and OneCeph tracing. Intra operator reliability was evaluated by paired T-test after a week.

No significant statistical difference was observed as the p-value was greater than 0.05 for all the parameters in the two groups.

The reliability and accuracy of OneCeph software application was found to be at par with manual cephalometric tracing

The rapid development of artificial intelligence technologies for medical imaging has recently enabled automatic identification of anatomical landmarks on radiographs. The purpose of this study was to compare the results of an automatic cephalometric analysis using convolutional neural network with those obtained by a conventional cephalometric approach.

Cephalometric measurements of lateral cephalograms from 35 patients were obtained using an automatic program and a conventional program. Fifteen skeletal cephalometric measurements, nine dental cephalometric measurements, and two soft tissue cephalometric measurements obtained by the two methods were compared using paired t test and Bland-Altman plots.

A comparison between the measurements from the automatic and conventional cephalometric analyses in terms of the paired t test confirmed that the saddle angle, linear measurements of maxillary incisor to NA line, and mandibular incisor to NB line showed statistically significant differences. All measurements were within the limits of agreement based on the Bland-Altman plots. The widths of limits of agreement were wider in dental measurements than those in the skeletal measurements.

Automatic cephalometric analyses based on convolutional neural network may offer clinically acceptable diagnostic performance. Careful consideration and additional manual adjustment are needed for dental measurements regarding tooth structures for higher accuracy and better performance.

• Artificial intelligence
• Cephalometric analysis
• Convolutional neural network
• Machine learning

• Cephalometric analysis
• OneCeph
• Reliability
• Reproducibility
• Smartphone application

• Cephalometry
• Image Processing, Computer-Assisted
• Mandible
• Maxilla
• Nasal Bone
• Reproducibility of Results
• Smartphone

• Cephalometry
• Chirurgies orthognathiques
• Computer Simulation
• Céphalométrie
• Orthognathic Surgical Procedures
• Résultat thérapeutique
• Simulation par ordinateur
• Treatment Outcome

• Cephalometrics
• computerized cephalometric program
• manual tracing
• onyxceph
• reliability

• CephX
• Cephalometry
• FACAD
• Reproducibility

The association between maxillary development and vector relationships is used in the field of plastic surgery, but the validity of this principle has not been tested yet.

The aim of this study is to determine whether visual classification of anterior malar projection using vector relationships is supported by cephalometric analysis.

Normal, healthy 40 subjects aged 10–15 years with no history of orthodontic treatment, craniofacial syndromes, or trauma formed the study group. These subjects based on the visual assessment of vector relationship (positive and negative) were divided into 2 groups (Group A and Group B), consisting of 20 subjects each. Vectors were drawn on the profile photographs. Sella–Nasion–Orbitale (SNO) angle were traced using the Nemoceph software. The relationship of anterior malar projection obtained from profile photograph and lateral cephalogram were compared. The data obtained were subjected to statistical analysis.

Skeletal differences between the positive and negative vector groups based on SNO angles were statistically significant (P < 0.001). SNO angulations in the negative vector group were smaller than the positive vector group by an average of 5.9°.

Visual assessment of vector relationship can be effectively used to classify anterior malar projection. This also helps in diagnosing maxillary hypoplasia and executes different treatment modalities.

• Malar projection
• midface esthetics
• nemoceph
• soft tissue diagnosis

Cephalometric analysis and measurements of skull parameters using X-Ray images plays an important role in predicating and monitoring orthodontic treatment. Manual analysis and measurements of cephalometric is considered tedious, time consuming, and subjected to human errors. Several cephalometric systems have been developed to automate the cephalometric procedure; however, no clear insights have been reported about reliability, performance, and usability of those systems. This study utilizes some techniques to evaluate reliability, performance, and usability metric using SUS methods of the developed cephalometric system which has not been reported in previous studies.

In this study a novel system named Ceph-X is developed to computerize the manual tasks of orthodontics during cephalometric measurements. Ceph-X is developed by using image processing techniques with three main models: enhancements X-ray image model, locating landmark model, and computation model. Ceph-X was then evaluated by using X-ray images of 30 subjects (male and female) obtained from University of Malaya hospital. Three orthodontics specialists were involved in the evaluation of accuracy to avoid intra examiner error, and performance for Ceph-X, and 20 orthodontics specialists were involved in the evaluation of the usability, and user satisfaction for Ceph-X by using the SUS approach.

Statistical analysis for the comparison between the manual and automatic cephalometric approaches showed that Ceph-X achieved a great accuracy approximately 96.6%, with an acceptable errors variation approximately less than 0.5 mm, and 1°. Results showed that Ceph-X increased the specialist performance, and minimized the processing time to obtain cephalometric measurements of human skull. Furthermore, SUS analysis approach showed that Ceph-X has an excellent usability user’s feedback.

The Ceph-X has proved its reliability, performance, and usability to be used by orthodontists for the analysis, diagnosis, and treatment of cephalometric.

• Automated cephalometric
• Computer-aided biomedical image
• Digital image processing
• Evaluation cephalometric system

The Wits values for various ethnic groups are different and the applicability of the norms described in these analyses to different populations is difficult. The objectives of this study were to establish the normal values of Wits appraisal in a sample from the western region of Saudi Arabia and to evaluate the existence of gender dimorphism. Also, to compare the results with previously published Wits values.

A total of 66 lateral cephalometric digital radiographs of Saudi patients from the western region (25 males and 41 females, mean age 19.32±8.16 years and 20.88±8.77 years, respectively). All subjects had angle class-I occlusion, well-balanced faces, all premolars had erupted and in occlusion, and no history of orthodontic treatment. Tracing was performed using the VistadentOC^® software.

Wits mean values were greater in males (−0.73±2.48) than females (1.79±2.06), with significant gender difference (P<0.001). Comparisons with previously published showed that there is a significant differences between ethnic groups, especially in females’ data.

Wits appraisal appears to be gender-specific and ethnicity-specific for female values.

• Cephalometric
• Saudi norms
• Wits appraisal