Cephalometric Landmark Identification Research Articles

Reliability of cephalometric landmark identification on three-dimensional computed tomographic images

Our aims were to evaluate the reliability of three-dimensional (3D) cephalometric landmark identification in 3D images, and to propose an improved protocol for determining these landmarks. Computed tomographic (CT) images of 13 landmarks were obtained. One that did not show any artifacts, asymmetry in maxillofacial structures, or bony defects, was selected. Two orthodontic practitioners identified 3D cephalometric landmarks 10 times at one-week intervals. The distances of 26 landmarks were measured on the basis of three reference planes (coronal, horizontal, and sagittal). Ten mean (SD) measurements from each examiner were calculated, and the maximum and minimum values and the difference from the 10 measurements of each one were measured at a 95% confidence interval. Interexaminer differences for the three planes were found in the upper right first molar, point A, both gonions, left orbitale, and both porions. The lower right first molar, foramen magnum, gnathion, nasion, and pogonion showed interexaminer differences in two planes. Menton, basion, posterior nasal spine, upper and lower left first molar, and right mental foramen showed interexaminer differences in only one plane. With reference to intraexaminer differences, poor repeatability was observed for gonion, orbitale, condylion, and porion. Reliable 3D landmarks are the meeting point of sutures, distinct structures at converging planes, landmarks positioned in the midline, distinct anatomical structures such as the mental foramen, and teeth using multiplanar views.

Clinical applicability of automated cephalometric landmark identification: Part II - Number of images needed to re-learn various quality of images.

To estimate the number of cephalograms needed to re-learn for different quality images, when artificial intelligence (AI) systems are introduced in a clinic. A total of 2385 digital lateral cephalograms (University data [1785]; Clinic F [300]; Clinic N [300]) were used. Using data from the university and clinics F and N, and combined data from clinics F and N, 50 cephalograms were randomly selected to test the system's performance (Test-data O, F, N, FN). To examine the recognition ability of landmark positions of the AI system developed in Part I (Original System) for other clinical data, test data F, N and FN were applied to the original system, and success rates were calculated. Then, to determine the approximate number of cephalograms needed to re-learn for different quality images, 85 and 170 cephalograms were randomly selected from each group and used for the re-learning (F85, F170, N85, N170, FN85 and FN170) of the original system. To estimate the number of cephalograms needed for re-learning, we examined the changes in the success rate of the re-trained systems and compared them with the original system. Re-trained systems F85 and F170 were evaluated with test data F, N85 and N170 from test data N, and FN85 and FN170 from test data FN. For systems using F, N and FN, it was determined that 85, 170 and 85 cephalograms, respectively, were required for re-learning. The number of cephalograms needed to re-learn for images of different quality was estimated.

Accuracy of automated identification of lateral cephalometric landmarks using cascade convolutional neural networks on lateral cephalograms from nationwide multi‐centres

To investigate the accuracy of automated identification of cephalometric landmarks using the cascade convolutional neural networks (CNN) on lateral cephalograms acquired from nationwide multi-centres. A total of 3150 lateral cephalograms were acquired from 10 university hospitals in South Korea for training. We evaluated the accuracy of the developed model with independent 100 lateral cephalograms as an external validation. Two orthodontists independently identified the anatomic landmarks of the test data set using the V-ceph software (version 8.0, Osstem, Seoul, Korea). The mean positions of the landmarks identified by two orthodontists were regarded as the gold standard. The performance of the CNN model was evaluated by calculating the mean absolute distance between the gold standard and the automatically detected positions. Factors associated with the detection accuracy for landmarks were analysed using the linear regression models. The mean inter-examiner difference was 1.31±1.13mm. The overall automated detection error was 1.36±0.98mm. The mean detection error for each landmark ranged between 0.46±0.37mm (maxillary incisor crown tip) and 2.09±1.91mm (distal root tip of the mandibular first molar). A significant difference in the detection accuracy among cephalograms was noted according to hospital (P=.011), sensor type (P<.01), and cephalography machine model (P<.01). The automated cephalometric landmark detection model may aid in preliminary screening for patient diagnosis and mid-treatment assessment, independent of the type of the radiography machines tested.

Clinical applicability of automated cephalometric landmark identification: Part I-Patient-related identification errors.

To determine whether AI systems that recognize cephalometric landmarks can apply to various patient groups and to examine the patient-related factors associated with identification errors. The present retrospective cohort study analysed digital lateral cephalograms obtained from 1785 Japanese orthodontic patients. Patients were categorized into eight subgroups according to dental age, cleft lip and/or palate, orthodontic appliance use and overjet. An AI system that automatically recognizes anatomic landmarks on lateral cephalograms was used. Thirty cephalograms in each subgroup were randomly selected and used to test the system's performance. The remaining cephalograms were used for system learning. The success rates in landmark recognition were evaluated using confidence ellipses with α=0.99 for each landmark. The selection of test samples, learning of the system and evaluation of the system were repeated five times for each subgroup. The mean success rate and identification error were calculated. Factors associated with identification errors were examined using a multiple linear regression model. The success rate and error varied among subgroups, ranging from 85% to 91% and 1.32mm to 1.50mm, respectively. Cleft lip and/or palate was found to be a factor associated with greater identification errors, whereas dental age, orthodontic appliances and overjet were not significant factors (all, P<.05). Artificial intelligence systems that recognize cephalometric landmarks could be applied to various patient groups. Patient-oriented errors were found in patients with cleft lip and/or palate.

AUTOMATIC ANTHROPOLOGICAL LANDMARKS RECOGNITION AND MEASUREMENTS

Abstract. Many anthropological researches require identification and measurement of craniometric and cephalometric landmarks which provide valuable information about the shape of a head. This information is necessary for morphometric analysis, face approximation, craniafacial identification etc. Traditional techniques use special anthropological tools to perform required measurements, identification of landmarks usually being made by an expert-anthropologist. Modern techniques of optical 3D measurements such as photogrammetry, computer tomography, laser 3D scanning provide new possibilities for acquiring accurate 2D and 3D data of high resolution, thus creating new conditions for anthropological data analysis. Traditional anthropological manual point measurements can be substituted by analysis of accurate textured 3D models, which allow to retrieve more information about studied object and easily to share data for independent analysis. The paper presents the deep learning technique for anthropological landmarks identification and accurate 3D measurements. Photogrammetric methods and their practical implementation in the automatic system for accurate digital 3D reconstruction of anthropological objects are described.

Reliability and Reproducibility of Landmark Identification in Unilateral Cleft Lip and Palate Patients: Digital Lateral Vis-A-Vis CBCT-Derived 3D Cephalograms

Background: The aim of the retrospective observational study was to compare the precision of landmark identification and its reproducibility using cone beam computed tomography-derived 3D cephalograms and digital lateral cephalograms in unilateral cleft lip and palate patients. Methods: Cephalograms of thirty-one (31) North Indian children (18 boys and 13 girls) with a unilateral cleft lip and palate, who were recommended for orthodontic treatment, were selected. After a thorough analysis of peer-reviewed articles, 20 difficult-to-trace landmarks were selected, and their reliability and reproducibility were studied. These were subjected to landmark identification to evaluate interobserver variability; the coordinates for each point were traced separately by three different orthodontists (OBA, OBB, OBC). Statistical analysis was performed using descriptive and inferential statistics with paired t-tests to compare the differences measured by the two methods. Real-scale data are presented in mean ± SD. A p-value less than 0.05 was considered as significant at a 95% confidence level. Results: When comparing, the plotting of points posterior nasal spine (PNS) (p < 0.05), anterior nasal spine (ANS) (p < 0.01), upper 1 root tip (p < 0.05), lower 1 root tip (p < 0.05), malare (p < 0.05), pyriforme (p < 0.05), porion (p < 0.01), and basion (p < 0.05) was statistically significant. Conclusion: In patients with a cleft lip and palate, the interobserver identification of cephalometric landmarks was significantly more precise and reproducible with cone beam computed tomography -derived cephalograms vis-a-vis digital lateral cephalograms.

Automatic Cephalometric Landmark Identification System Based on the Multi-Stage Convolutional Neural Networks with CBCT Combination Images.

This study was designed to develop and verify a fully automated cephalometry landmark identification system, based on multi-stage convolutional neural networks (CNNs) architecture, using a combination dataset. In this research, we trained and tested multi-stage CNNs with 430 lateral and 430 MIP lateral cephalograms synthesized by cone-beam computed tomography (CBCT) to make a combination dataset. Fifteen landmarks were manually and respectively identified by experienced examiner, at the preprocessing phase. The intra-examiner reliability was high (ICC = 0.99) in manual identification. The results of prediction of the system for average mean radial error (MRE) and standard deviation (SD) were 1.03 mm and 1.29 mm, respectively. In conclusion, different types of image data might be the one of factors that affect the prediction accuracy of a fully-automated landmark identification system, based on multi-stage CNNs.

A fully deep learning model for the automatic identification of cephalometric landmarks.

PurposeThis study aimed to propose a fully automatic landmark identification model based on a deep learning algorithm using real clinical data and to verify its accuracy considering inter-examiner variability.Materials and MethodsIn total, 950 lateral cephalometric images from Yonsei Dental Hospital were used. Two calibrated examiners manually identified the 13 most important landmarks to set as references. The proposed deep learning model has a 2-step structure—a region of interest machine and a detection machine—each consisting of 8 convolution layers, 5 pooling layers, and 2 fully connected layers. The distance errors of detection between 2 examiners were used as a clinically acceptable range for performance evaluation.ResultsThe 13 landmarks were automatically detected using the proposed model. Inter-examiner agreement for all landmarks indicated excellent reliability based on the 95% confidence interval. The average clinically acceptable range for all 13 landmarks was 1.24 mm. The mean radial error between the reference values assigned by 1 expert and the proposed model was 1.84 mm, exhibiting a successful detection rate of 36.1%. The A-point, the incisal tip of the maxillary and mandibular incisors, and ANS showed lower mean radial error than the calibrated expert variability.ConclusionThis experiment demonstrated that the proposed deep learning model can perform fully automatic identification of cephalometric landmarks and achieve better results than examiners for some landmarks. It is meaningful to consider between-examiner variability for clinical applicability when evaluating the performance of deep learning methods in cephalometric landmark identification.

Efficacy of smartphone-based Mobile learning versus lecture-based learning for instruction of Cephalometric landmark identification

BackgroundConsidering the increasing popularity of electronic learning, particularly smartphone-based mobile learning, and its reportedly optimal efficacy for instruction of complicated topics, this study aimed to compare the efficacy of smartphone-based mobile learning versus lecture-based learning for instruction of cephalometric landmark identification.MethodsThis quasi-experimental interventional study evaluated 53 dental students (4th year) in two groups of intervention (n = 27; smartphone instruction using an application) and control (n = 26, traditional lecture-based instruction). Two weeks after the instructions, dental students were asked to identify four landmarks namely the posterior nasal spine (PNS), orbitale (Or), articulare (Ar) and gonion (Go) on lateral cephalograms. The mean coordinates of each landmark identified by orthodontists served as the reference point, and the mean distance from each identified point to the reference point was reported as the mean consistency while the standard deviation of this mean was reported as the precision of measurement. Data were analyzed using SPSS version 18 via independent sample t-test.ResultsNo significant difference was noted between the two groups in identification of PNS, Ar or Go (P > 0.05). However, the mean error rate in identification of Or was significantly lower in smartphone group compared with the traditional learning group (P = 0.020).ConclusionsSmartphone-based mobile learning had a comparable, and even slightly superior, efficacy to lecture-based learning for instruction of cephalometric landmark identification, and may be considered, at least as an adjunct, to enhance the instruction of complicated topics.Trial registration numberThis is not a human subject research. https://ethics.research.ac.ir/ProposalCertificateEn.php?id=33714&Print=true&NoPrintHeader=true&NoPrintFooter=true&NoPrintPageBorder=true&LetterPrint=true.

Evaluation of an automated superimposition method for computer-aided cephalometrics.

To evaluate a new superimposition method compatible with computer-aided cephalometrics and to compare superimposition error to that of the conventional Sella-Nasion (SN) superimposition method. A total of 283 lateral cephalometric radiographs were collected and cephalometric landmark identification was performed twice by the same examiner at a 3-month interval. The second tracing was superimposed on the first tracing by both the SN superimposition method and the new, proposed method. The proposed method not only relied on SN landmarks but also minimized the differences between four additional landmarks: Porion, Orbitale, Basion, and Pterygoid. The errors between the landmarks of the duplicate tracings oriented by the two superimposition methods were calculated at Anterior Nasal Spine, Point A, Point B, Pogonion, and Gonion. The paired t-test was used to find any statistical difference in the superimposition errors by the two superimposition methods and to investigate whether there existed clinically significant differences between the two methods. The proposed method demonstrated smaller superimposition errors than did the conventional SN superimposition method. When comparisons between the two superimposition methods were made with a 1-mm error range, there were clinically significant differences between them. The proposed method that was compatible with computer-aided cephalometrics might be a reliable superimposition method for superimposing serial cephalometric images.

Automated identification of cephalometric landmarks: Part 2-Might it be better than human?

To compare detection patterns of 80 cephalometric landmarks identified by an automated identification system (AI) based on a recently proposed deep-learning method, the You-Only-Look-Once version 3 (YOLOv3), with those identified by human examiners. The YOLOv3 algorithm was implemented with custom modifications and trained on 1028 cephalograms. A total of 80 landmarks comprising two vertical reference points and 46 hard tissue and 32 soft tissue landmarks were identified. On the 283 test images, the same 80 landmarks were identified by AI and human examiners twice. Statistical analyses were conducted to detect whether any significant differences between AI and human examiners existed. Influence of image factors on those differences was also investigated. Upon repeated trials, AI always detected identical positions on each landmark, while the human intraexaminer variability of repeated manual detections demonstrated a detection error of 0.97 ± 1.03 mm. The mean detection error between AI and human was 1.46 ± 2.97 mm. The mean difference between human examiners was 1.50 ± 1.48 mm. In general, comparisons in the detection errors between AI and human examiners were less than 0.9 mm, which did not seem to be clinically significant. AI showed as accurate an identification of cephalometric landmarks as did human examiners. AI might be a viable option for repeatedly identifying multiple cephalometric landmarks.

Automated identification of cephalometric landmarks: Part 1-Comparisons between the latest deep-learning methods YOLOV3 and SSD.

To compare the accuracy and computational efficiency of two of the latest deep-learning algorithms for automatic identification of cephalometric landmarks. A total of 1028 cephalometric radiographic images were selected as learning data that trained You-Only-Look-Once version 3 (YOLOv3) and Single Shot Multibox Detector (SSD) methods. The number of target labeling was 80 landmarks. After the deep-learning process, the algorithms were tested using a new test data set composed of 283 images. Accuracy was determined by measuring the point-to-point error and success detection rate and was visualized by drawing scattergrams. The computational time of both algorithms was also recorded. The YOLOv3 algorithm outperformed SSD in accuracy for 38 of 80 landmarks. The other 42 of 80 landmarks did not show a statistically significant difference between YOLOv3 and SSD. Error plots of YOLOv3 showed not only a smaller error range but also a more isotropic tendency. The mean computational time spent per image was 0.05 seconds and 2.89 seconds for YOLOv3 and SSD, respectively. YOLOv3 showed approximately 5% higher accuracy compared with the top benchmarks in the literature. Between the two latest deep-learning methods applied, YOLOv3 seemed to be more promising as a fully automated cephalometric landmark identification system for use in clinical practice.

Accuracy of Automatic Cephalometric Software on Landmark Identification

This study was to assess the accuracy of an automatic cephalometric analysis software in the identification of cephalometric landmarks. Thirty randomly selected digital lateral cephalograms of patients undergoing orthodontic treatment were used in this study. Thirteen landmarks (S, N, Or, A-point, U1T, U1A, B-point, Gn, Pog, Me, Go, L1T, and L1A) were identified on the digital image by an automatic cephalometric software and on cephalometric tracing by manual method. Superimposition of printed image and manual tracing was done by registration at the soft tissue profiles. The accuracy of landmarks located by the automatic method was compared with that of the manually identified landmarks by measuring the mean differences of distances of each landmark on the Cartesian plane where X and Y coordination axes passed through the center of ear rod. One-Sample T test was used to evaluate the mean differences. Statistically significant mean differences (p<0.05) were found in 5 landmarks (Or, A-point, Me, L1T, and L1A) in horizontal direction and 7 landmarks (Or, A-point, U1T, U1A, B-point, Me, and L1A) in vertical direction. Four landmarks (Or, A-point, Me, and L1A) showed significant (p<0.05) mean differences in both horizontal and vertical directions. Small mean differences (<0.5mm) were found for S, N, B-point, Gn, and Pog in horizontal direction and N, Gn, Me, and L1T in vertical direction. Large mean differences were found for A-point (3.0 < 3.5mm) in horizontal direction and L1A (>4mm) in vertical direction. Only 5 of 13 landmarks (38.46%; S, N, Gn, Pog, and Go) showed no significant mean difference between the automatic and manual landmarking methods. It is concluded that if this automatic cephalometric analysis software is used for orthodontic diagnosis, the orthodontist must correct or modify the position of landmarks in order to increase the accuracy of cephalometric analysis.

Cephalometric landmark identification consistency between undergraduate dental students and orthodontic residents in 3-dimensional rendered cone-beam computed tomography images: A preliminary study.

The aim of this study was to compare 3-dimensional landmark consistency and precision in skeletal structures in groups with different levels of experience with 2-dimensional cephalometrics. Sixteen observers, all undergraduate or graduate students, were divided into 4 groups with different levels of experience in 2-dimensional landmarking and no previous experience in 3 dimensions. Group 1 consisted of 4 third-year dental students with no experience in cephalometric landmarking. Groups 2, 3, and 4 consisted of first-, second-, and third-year graduate students, with increasing levels of experience. The participants located 18 landmarks in 12 surface models of cone-beam computed tomography scans of patients on 3 separate occasions. The average of all examiners locating each landmark was defined as the centroid. The mean of the distances of each located point to the centroid of that landmark was used as the mean consistency (MC), and the standard deviation (SD) was used as the precision. Analysis of variance and post hoc Tukey comparisons between groups were done. The MC andSD values across landmarks, patients, and examiners were 1.03±1.14mm. The MC and SD were 0.89±0.83mm for group 1 with no experience, 1.02±0.95mm for group 2, 1.17±1.60mm for group 3, and 1.05±1.00mm for group 4. Significant differences were found among the groups. Comparing the observer groups studied, the undergraduate dental school students without previous experience in bidimensional cephalometrics obtained the best values in volumetric landmark location. Graduate students with increasing amounts of experience did not perform as well. These results and conclusions should be interpreted with caution because the number of subjects in each group was small.

A new mandible-specific landmark reference system for three-dimensional cephalometry using cone-beam computed tomography.

To develop a novel 3D landmark reference system that is specific for mandibular midline cephalometric landmarks and to assess its repeatability and reproducibility. Cone-beam computed tomography (CBCT) scans (3D Accuitomo® 170) were performed on 26 dry human skulls. The CBCT data were exported into DICOM files and imported to Maxilim® software to create 3D surface models. Two observers identified five landmarks to create a specific mid-sagittal mandibular plane: two mandibular foramina, two molar landmarks and one interincisive landmark. On this mid-sagittal mandibular plane, four mandibular cephalometric landmarks were marked: Point B, Pogonion, Gnathion and Menton. All observations were repeated by the two observers after an interval of 4 weeks. The coordinates (x, y, z) of each landmark were exported, and statistical analyses were performed to evaluate inter- and intra-rater precision. The intra-observer median precision in locating all landmarks ranged between 0.17 and 0.61mm. The intra-observer repeatability was generally good with a precision under 1mm in more than 50 per cent. The overall median inter-observer precision was 0.26-2.30mm. The mandibular foramina showed the best inter-observer reproducibility. The general inter-observer reproducibility was moderate to good, except for Pogonion and Point B. Dry human skulls may not represent anatomical conditions found in living patients, thus the system should be validated using patients' data. The novel reference system offered good precision and generally good to moderate repeatability and reproducibility for mandibular midline cephalometric landmark identification in three dimensions. These findings will be useful for further improvement of 3D cephalometric systems.

Implementation of ultra-low-dose CBCT for routine 2D orthodontic diagnostic radiographs: Cephalometric landmark identification and image quality assessment

Since its adoption more than two decades ago in the field of dentistry, three-dimensional (3D) cone-beam computed tomography (CBCT) has rapidly gained popularity as an imaging tool for three-dimensional visualization, diagnosis, and treatment simulation. The objective of this two-part study was to assess landmark identification, as well as the diagnostic value of images obtained using an ultra-low-dose reduced projection (sparse) views algorithm Adaptive-Steepest-Descent-Projection-Onto-Convex-Sets (ASD-POCS) applied to existing dental CBCT data. ASD-POCS was developed for CBCT studies, producing multiple CBCT data files with 12.5% (39), 25% (76), and 50% (150) of the original number of projection views (which is in direct proportion with the lowering of radiation dose). Assessment of 2D landmark identification derived from CBCT data at different projection views was conducted. Assessment of diagnostic quality was studied by evaluating radiographs of various projection views on a visual analog scale by different dental specialists. In conclusion, this study found no statistically significant differences in the quality of images at 25% (76) projection views as compared to 100% (300) projection views. The implementation on ASD-POCS algorithm by the CBCT manufacturers in the future may be beneficial for clinicians in reducing the amount of patient radiation exposure when obtaining routine orthodontic diagnostic radiographs.

Cephalometric landmark variability among orthodontists and dentomaxillofacial radiologists: a comparative study.

PurposeThe aim this study was to compare the accuracy of orthodontists and dentomaxillofacial radiologists in identifying 17 commonly used cephalometric landmarks, and to determine the extent of variability associated with each of those landmarks.Materials and MethodsTwenty digital lateral cephalometric radiographs were evaluated by two groups of dental specialists, and 17 cephalometric landmarks were identified. The x and y coordinates of each landmark were recorded. The mean value for each landmark was considered the best estimate and used as the standard. Variation in measurements of the distance between landmarks and measurements of the angles associated with certain landmarks was also assessed by a subset of two observers, and intraobserver and interobserver agreement were evaluated.ResultsIntraclass correlation coefficients were excellent for intraobserver agreement, but only good for interobserver agreement. The least reliable landmark for orthodontists was the gnathion (Gn) point (standard deviation [SD], 5.92 mm), while the orbitale (Or) was the least reliable landmark (SD, 4.41 mm) for dentomaxillofacial radiologists. Furthermore, the condylion (Co)-Gn plane was the least consistent (SD, 4.43 mm).ConclusionWe established that some landmarks were not as reproducible as others, both horizontally and vertically. The most consistently identified landmark in both groups was the lower incisor border, while the least reliable points were Co, Gn, Or, and the anterior nasal spine. Overall, a lower level of reproducibility in the identification of cephalometric landmarks was observed among orthodontists.

Evaluation of cephalometric landmark identification on CBCT multiplanar and 3D reconstructions

To evaluate the reliability of three-dimensional (3D) landmark identification in cone-beam computed tomography (CBCT) using two different visualization techniques. Twelve CBCT images were randomly selected. Three observers independently repeated three times the identification of 30 landmarks using 3D reconstructions and 28 landmarks using multiplanar views. The values of the coordinates X, Y, and Z of each point were obtained and the intraclass correlation coefficient (ICC) was calculated. The ICC of the 3D visualization was rated >0.90 in 67.76% and 45.56%, and ≤0.45 in 13.33% and 14.46% of the intraobserver and interobserver assessments, respectively. The ICC of the multiplanar visualization was rated >0.90 in 82.16% and 78.56% and ≤0.45 in only 16.7% and 8.33% of the intraobserver and interobserver assessments, respectively. An individual landmark classification was done according to ICC values. The frequency of highly reliable values was greater for multiplanar than 3D reconstructions. Overall, lower reliability was found for points on the condyle and higher reliability for those on the midsagittal plane. Depending on the anatomic region, the observer must choose the most reliable type of image visualization.

Robust Cephalometric Landmark Identification on Cephalometric Downs Analysis

Cephalometric landmark identification on cephalometric analysis Downs has been developed. Here we identify a 10 point landmarks used in cephalometric Downs analysis: Gnation, Gonion, Menton, Nation, Orbital, Porion, Point A, Point B, Pogonion, and Sella. The research was conducted in three phases: preprocessing, feature extraction and identification. In the preprocessing phase, the things we do are: image size normalization, Enhance contrast, and took the ROI for each landmark. We use of PPED algorithms for image feature extraction and to measure the similarity between the template vector and vector test, euclidean distance gives good results, despite the large number of image samples do not always give the results was always good. To improve systems performance, we use a multithreading technique. The experimental results showed that the methods used can work well although still found deficiencies and inaccuracies. Accuracy of projections mainly on bilateral landmarks greatly affect the outcome of the identification.

An Approach for Efficient Detection of Cephalometric Landmarks

In this paper, a method is developed for the automated identification of cephalometric landmarks in orthodontics. The process of soft tissue edge detection is divided into two steps: detecting the sub-images that contained the required landmarks using combination of the Histograms of Oriented Gradients (HOG) descriptor with the Support Vector Machine (SVM), then utilizing Thresholding and Mathematical Morphological (TMM) algorithm to trace soft tissue profile. In addition, the mandible's edge is detected by the Active contours without edges (Chan-Vese method). Finally, the landmarks of soft tissue profile and the mandible's edge are pinned based on analyzing the contour plot of these lines. The simulation results have high accuracy.