Cephalometric Landmarks Research Articles

Accuracy of web-based automated versus digital manual cephalometric landmark identification.

The purpose of this study was to assess the accuracy of two web-based automated cephalometric landmark identification and analysis programs. Manual landmark identification using Dolphin Imaging software was used as reference. 105 cephalograms were selected and divided into three groups of 35 subjects each, Class I, II and III. Radiographs were traced using Dolphin imaging software. WebCeph™ (South Korea) and Cephio™ (Poland) were used for the automated cephalometric analysis. Bland-Altman limits of agreement and the concordance correlation coefficient (CCC) were calculated. Kruskal Wallis test was used to compare the accuracy of WebCeph™ and Cephio™ measurements between the three groups. Mann-Whitney U test was used to compare the absolute difference between cephalometric measurements obtained using WebCeph™ and Cephio™. The mean difference (MD) between AI and manually-derived measurements was less than 1mm/degree and ranged from 0.01 to 0.8 except for upper lip protrusion (MD 1.35°), nasolabial angle (MD 5.01°), SN-GoGn (MD 1.41°), Ramus height (MD 1.46°), and IMPA (MD 1.94°). The mean CCC was 0.91 (range 0.60 to 0.96). No statistically significant differences were found between the three malocclusion groups for most of the measurements (P > 0.05). For most of the measurements, automated cephalometric measurements were clinically acceptable. Few differences were found between Webceph™ and Cephio™ for most measurements. Measurements including SNA, SN-PP, IMPA as well as soft tissue measurements require extra consideration and manual adjustment of respective landmarks for higher precision and improved efficiency.

Does the FARNet neural network algorithm accurately identify Posteroanterior cephalometric landmarks?

BackgroundWe explored whether the feature aggregation and refinement network (FARNet) algorithm accurately identified posteroanterior (PA) cephalometric landmarks.MethodsWe identified 47 landmarks on 1,431 PA cephalograms of which 1,177 were used for training, 117 for validation, and 137 for testing. A FARNet-based artificial intelligence (AI) algorithm automatically detected the landmarks. Model effectiveness was calculated by deriving the mean radial error (MRE) and the successful detection rates (SDRs) within 2, 2.5, 3, and 4 mm. The Mann-Whitney U test was performed on the Euclidean differences between repeated manual identifications and AI trials. The direction in differences was analyzed, and whether differences moved in the same or opposite directions relative to ground truth on both the x and y-axis.ResultsThe AI system (web-based CranioCatch annotation software (Eskişehir, Turkey)) identified 47 anatomical landmarks in PA cephalograms. The right gonion SDRs were the highest, thus 96.4, 97.8, 100, and 100% within 2, 2.5, 3, and 4 mm, respectively. The right gonion MRE was 0.94 ± 0.53 mm. The right condylon SDRs were the lowest, thus 32.8, 45.3, 54.0, and 67.9% within the same thresholds. The right condylon MRE was 3.31 ± 2.25 mm. The AI model’s reliability and accuracy were similar to a human expert’s. AI was better at four skeleton points than the expert, whereas the expert was better at one skeletal and seven dental points (P < 0.05). Most of the points exhibited significant deviations along the y-axis. Compared to ground truth, most of the points in AI and the second trial showed opposite movement on the x-axis and the same on the y-axis.ConclusionsThe FARNet algorithm streamlined orthodontic diagnosis.

Cephalometric variation of vertical dimension in patients treated with hyrax-type and McNamara-type rapid palatal expander. Study on latero-lateral teleradiography

To analyze changes in the vertical dimension of the lower third of the face studied on teleradiograph in L-L following rapid palatal expansion achieved by four-band Hyrax-type rapid palatal expander (RPE) and by acrylic-bonded McNamara RPE to identify the most appropriate therapeutic choice based on the patient's facial growth pattern. 30 patients were selected, of whom 20 (9 males and 11 females with a mean age of 8.285 ± 1.216) were treated using McNamara RPE (Group D), and 10 (6 males and 4 females with a mean age of 8.562 ± 1.152) were treated with Hyrax RPE (Group B), for an average treatment time T0-T1 of 0.96 ± 0.501 years. According to Tweed and Ricketts, Cephalometric tracings obtained from lateral cephalograms at T0 and T1 were analyzed to study changes in the vertical dimension of the lower third of the face. For this purpose, 6 cephalometric landmarks were considered: convexity (distance of point A to the NPg plane), Ricketts’ total face height (angle between the NBa plane and Xi-Pm plane), lower face height (angle between the ANS and Xi-Pm planes), facial axis (angle between the NaBa plane and PtGn plane), ANB angle, and FMA angle. No statistically significant differences were found between the measurements at T0 and T1 for any of the 6 cephalometric measurements considered, neither within the single groups nor when comparing the two. However, a greater increasing trend was found for some variables between the two groups, such as Ricketts' total facial height, lower facial height, and FMA angle, although not statistically significant. Hyrax and McNamara's RPEs have provided minimal changes in the vertical component during palatal expansion treatment, thus demonstrating their ability to preserve the vertical dimension of the face. Therefore, there are no contraindications for using either appliance for patients with dolichofacial growth patterns.

AI-based open-source software for cephalometric analysis from limited FOV radiographs

BackgroundArtificial Intelligence (AI) in dental diagnostics is evolving, offering innovative approaches for conducting cephalometric analysis with less manual input and overcoming the limitations of traditional imaging methods. To enhance the diagnostic processes in dentistry, an open-source software that utilises AI to improve the extraction of cephalometric values from limited field of view (FOV) images was created. Material and MethodsReduced FOV images lack several vital cephalometric landmarks, prompting the creation of predictive models to estimate missing values. The GridSearchCV algorithm and other algorithms were used to construct predictive models using software and to select the best models. The software was validated by comparing the predicted values with the actual measurements and calculating the mean squared error using Excel. Further validation involved a randomly selected cohort of 25 untreated orthodontic cases. ResultsEvaluation of the software showed that it was effective in accurately predicting key cephalometric measurements, suggesting that it could be a reliable tool for clinical use. However, some variations were noted in its predictive accuracy across different measurements, indicating areas that could benefit from further development. The software could align closely with the actual cephalometric measurements through detailed statistical analysis. ConclusionsThe integration of AI into cephalometric analysis with the software could represent progress, potentially leading to more efficient dental diagnostics and a reduction in the need for additional X-rays. This study aimed to advance the integration and refinement of AI in healthcare, focusing on minimising bias and understanding its impact on clinical decisions. In future studies, the application of AI in dental practice should be expanded to address these challenges. Clinical Significance StatementThis software integrates AI into clinical practice to enhance the diagnostic and therapeutic phases for patient benefit. It enables precise and comprehensive cephalometric analyses using data previously considered insufficient, thereby reducing the need for X-rays and improving patient care.

Retrospective analysis of the upper airway anatomy and Sella turcica morphology across different skeletal malocclusions: a computerized technique

ObjectiveThis study aimed to investigate the normal volumetric space and variations in the measurements of different landmarks in adults with different skeletal relations of the maxilla and the mandible based on CBCT data. The study also analyses these landmarks to locate any correlations.BackgroundNumerous studies in orthodontics have found a relationship between orthodontic treatment and changes in the anatomy and function of the airway. Severe changes in airway morphology can cause breathing difficulties, lower quality of life, and even result in life-threatening conditions such as obstructive sleep apnoea. Consequently, orthodontic diagnosis and treatment planning require a thorough understanding of the airway space and its function.MethodsThe present retrospective study was conducted using CBCT records of 120 adult patients, containing 40 samples of each skeletal class (20 males and 20 females). The boundaries were defined for the 3 major regions: the nasopharynx, the oropharynx, and the hypopharynx. Various measurements were recorded across these regions, as well as selective cephalometric landmarks. The obtained data was used to calculate average and standard deviation, while regression analysis was used to evaluate correlations and t-test was used to test statistical significance of gender differences.ResultsThe results demonstrate that skeletal Class III individuals exhibit a reduced airway volume in the nasopharynx compared to other groups, whereas skeletal Class II individuals displayed a diminished airway volume in the hypopharynx. A strong correlation was observed for Sella turcica parameters. There were no significant differences in skeletal parameters across genders. Nasopharynx cavity volume demonstrated significant differences between skeletal Class I–Class III as well as between skeletal Class II–Class III. Hypopharynx cavity volume also demonstrated significant differences between skeletal Class I–Class II and between skeletal Class II–Class III.ConclusionThe major findings are the presence of a reduced nasopharyngeal volume in skeletal Class III malocclusions while skeletal Class II individuals displayed a diminished hypopharyngeal volume, making these critical areas to consider during the diagnostic and orthodontic treatment planning stages. This study also revealed a consistent correlation between Sella turcica parameters across various facial skeletal profiles, with skeletal Class II patients exhibiting a distinct pattern and skeletal Class I and Class III demonstrating an average relationship.

Changes in the curvature of upper and lower lips following the first premolar extraction in Class I bimaxillary protrusion - A cephalometric study

Bimaxillary dentoalveolar protrusion is a condition characterized by protrusion of the maxillary and mandibular incisors with increased procumbency of the lips. The treatment of choice for these patients is fixed orthodontic treatment after extraction of four first premolars. This treatment would result in the retraction of anterior teeth with a resultant decrease in soft tissue convexity. Objective of the study is to find out how the curvature of upper and lower lip change following fixed appliance therapy in patients with class I Bimaxillary protrusion following extraction of first premolars. A total of 32 subjects, 13 males and 19 females in the age group of 13-21 years diagnosed with BMP were included in the study. Pre-treatment and post-treatment cephalograms were obtained from subjects satisfying the inclusion and exclusion criteria. Cephalometric landmarks, lines used in the study were marked and analysed. The soft tissue parameters were measured and compared using paired t test and Pearson’s correlation coefficient. The overall effect of orthodontic correction of bimaxillary protrusion from subjects were analysed by evaluating the soft tissue changes between pre-treatment and post treatment cephalometric radiographs. There is a statistically significant difference with decrease in ULST, B`-PM line, B`-LiPog`, A`-PM line, LLIT, LLVT, Pog-Pog` and no statistically significant difference in A`-NtLs and ULVT. The results showed a reduction in lip procumbency. Among the soft tissue parameter studied, there is a statistically significant decrease observed for ULST, B`-PM line, B`-LiPog`, A`-PM line, LLIT, LLVT and Pog-Pog`.

Development and validation of predictive models for skeletal malocclusion classification using airway and cephalometric landmarks

ObjectiveThis study aimed to develop a deep learning model to predict skeletal malocclusions with an acceptable level of accuracy using airway and cephalometric landmark values obtained from analyzing different CBCT images.BackgroundIn orthodontics, multitudinous studies have reported the correlation between orthodontic treatment and changes in the anatomy as well as the functioning of the airway. Typically, the values obtained from various measurements of cephalometric landmarks are used to determine skeletal class based on the interpretation an orthodontist experiences, which sometimes may not be accurate.MethodsSamples of skeletal anatomical data were retrospectively obtained and recorded in Digital Imaging and Communications in Medicine (DICOM) file format. The DICOM files were used to reconstruct 3D models using 3DSlicer (slicer.org) by thresholding airway regions to build up 3D polygon models of airway regions for each sample. The 3D models were measured for different landmarks that included measurements across the nasopharynx, the oropharynx, and the hypopharynx. Male and female subjects were combined as one data set to develop supervised learning models. These measurements were utilized to build 7 artificial intelligence-based supervised learning models.ResultsThe supervised learning model with the best accuracy was Random Forest, with a value of 0.74. All the other models were lower in terms of their accuracy. The recall scores for Class I, II, and III malocclusions were 0.71, 0.69, and 0.77, respectively, which represented the total number of actual positive cases predicted correctly, making the sensitivity of the model high.ConclusionIn this study, it is observed that the Random Forest model was the most accurate model for predicting the skeletal malocclusion based on various airway and cephalometric landmarks.

Evaluation of Sella Turcica and Maxilla Morphometry of Individuals With Cleft Lip and Palate on Lateral Cephalometric Radiographs

Objective: The objective of this study was to evaluate the dimensions and the morphology of the sella turcica, as well as maxillary cephalometric landmarks, in patients with and without clefts. Methods: Lateral cephalometric radiographs of 55 cleft patients and 55 non-cleft (control) patients were included in the study. The morphology of the sella turcica, including its shape, height, width, and diameter was evaluated. Additionally, maxillary cephalometric measurements, comprising four lengths and two angles, were assessed on the radiographs. The chi-squared test was employed to compare sella turcica shapes between the cleft and non-cleft groups. Independent samples t-tests were conducted to analyze dimensional parameters between groups and genders. Results: Significant relationship was found between groups with cleft and non-cleft for sella shapes (p=0.032). There was no statistical association for sella dimensions according to the cleft presence (p&gt;0.05). All maxillary cephalometric measurements were significantly greater in individuals of the non-cleft group compared to those in the cleft group (ANS-PNS, A-PNS, S-N-ANS , S-N-A, N-A) except R-PNS. Conclusion: Patients with clefts more frequently exhibited a flattened sella shape, whereas those without clefts tended to have a round sella shape. Maxillary cephalometric dimensions were lower in the individuals of cleft group.

A two-stage regression framework for automated cephalometric landmark detection incorporating semantically fused anatomical features and multi-head refinement loss

Accurate identification and precise localization of cephalometric landmarks provide clinicians with essential insights into craniofacial deformities, aiding in the assessment of treatment strategies for improved patient outcomes. The current methodologies heavily depend on the utilization of multiple CNNs for predicting landmark coordinates, which makes them computationally burdensome and unsuitable for translation to clinical applications. To overcome this limitation, we propose a novel, end-to-end trainable, two-stage regression framework for cephalometric landmark detection. In the initial stage, a single neural network is employed to estimate the locations of all landmarks simultaneously, enabling the identification of potential landmark regions. In the second stage, a semantic fusion block leverages the in-network multi-resolution feature hierarchy to produce high-level semantically rich features. These feature maps are then cropped based on coarsely detected landmark locations and concurrent refinement loss is used to fine-tune and refine the landmark locations. The proposed framework demonstrates the potential for enhancing clinical workflow and treatment outcomes in orthodontics. This is achieved through the utilization of a single CNN backbone augmented with multi-resolution semantically fused anatomical features, which effectively enhances representation learning in a computationally efficient manner. The performance of the proposed framework is evaluated on two publicly available anatomical landmark datasets. The experimental results demonstrate that our framework achieves a state-of-the-art detection accuracy of 87.17% within the clinically accepted range of 2 mm. The source code and the pre-trained weights are made publicly available at this https://github.com/manwaarkhd/CEPHMark-Net, promoting reproducibility and enabling further advancements.

Mystery of the Muenke midface: spheno-occipital synchondrosis fusion and craniofacial skeletal patterns.

The spheno-occipital synchondrosis (SOS) is an important site of endochondral ossification in the cranial base that closes prematurely in Apert, Crouzon, and Pfeiffer syndromes, which contributes to varying degrees of midface hypoplasia. The facial dysmorphology of Muenke syndrome, in contrast, is less severe with low rates of midface hypoplasia. We thus evaluated the timing of SOS fusion and cephalometric landmarks in patients with Muenke syndrome compared to normal controls. Patients with Muenke syndrome who had at least one fine-cut head computed tomography scan performedfrom 2000 to 2020 were retrospectively reviewed. A case-control study was performed of patient scans and age- and sex-matched control scans. SOS fusion status was evaluated as open, partially closed, or closed. We included 28 patients and compared 77 patient scans with 77 control scans. Kaplan-Meier analysis demonstrated an insignificantly earlier timeline of SOS fusion in Muenke syndrome (p = 0.300). Mean sella-orbitale (SO) distance was shorter (44.0 ± 6.6 vs. 47.7 ± 6.7 mm, p < 0.001) and mean sella-nasion-Frankfort horizontal (SN-FH) angle was greater (12.1° ± 3.8° vs. 10.1° ± 3.2°, p < 0.001)in the Muenke group, whereas mean sella-nasion-A point (SNA) angle was similar and normal (81.1° ± 5.7° vs. 81.4° ± 4.7°, p = 0.762). Muenke syndrome is characterized by mild and often absent midfacial hypoplasia, with the exception of slight retropositioning of the infraorbital rim. Interestingly, SOS fusion patterns in these patientsare not significantly different from age- and sex-matched controls despite an increased odds of fusion. It is possible that differences in timing of SOS fusion may manifest phenotypically at the infraorbital rim rather than atthe maxilla.

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

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

Analysis of Cephalometric Differences of the Midface and Upper Face in Males and Females: A Radiographic Study.

Gender affirmation facial surgery (GAFS) is an important component in treating gender dysphoria among transgender individuals by addressing gender incongruence of the face. There is a paucity of literature describing objective characterizations of the anatomic differences between male and female faces. In this study, cephalometric measurements were taken on routine CT imaging performed on cisgender patients between 2017 and 2020. Specifically defined cephalometric landmarks of the upper and midface were measured and compared between male and female cohorts. Thirty-eight patients, 19 male and 19 female, were identified for this study. Significant differences were identified in the frontal prominence, orbital size, malar height, bizygomatic width, nose, and upper lip, with moderate rates of specificity for each gender. Some important ratios are also presented. Differences in the malar region and the orbit highlight the importance of these areas as a point of focus for GAFS. These cephalometric findings provide objective evidence and parameters for perceived anatomic differences in male and female faces. In addition, they help both corroborate current surgical techniques as well as guide future approaches to GAFS.

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

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

Assessing the Accuracy of Lateral Cephalogram in Quantifying Three-Dimensional Pharyngeal Airway Morphology Compared to Cone-Beam Computed Tomography.

When it comes to orthodontic diagnosis and treatment planning, the structures of the upper and lower airway spaceare crucial because of therole they play in craniofacial development. The major objective of this study was to evaluate the accuracy of lateral cephalogram in the evaluation of upper and lower pharyngeal space by comparing it to clinical usage of cone-beam computed tomography (CBCT) in quantifying the 3D morphology of the pharyngeal airway. In total, 70 patients were included in the study. They had both a CBCT scan and a lateral cephalogram performed within a week of each other. Different cephalometric landmarks have been utilized to estimate linear and area dimensions for use in lateral cephalogram airway investigations. By superimposing the lateral cephalogram measurement of the vertical height of the pharyngeal airwayover axial CBCT slices of 0.8 to 1 mm in thickness, airway volumes were calculated. For this study, we measured the pharyngeal airway space in each patient in two dimensions (2D) using the airway area from the lateral cephalogram and in three dimensions (3D) using the airway volume from the CBCT scan over the same region of interest, using a uniform scale and magnification throughout all split 3D volumes. The mean value of the area of pharyngeal space calculated by lateral cephalograph analysis (LCA) was 336.35 ± 86.49 mm2. The maximum value was 551.234 mm2. The minimum value was 206.32 mm2. The mean value of the volume of the same area calculated using CBCT was 3409.11 ± 1237.96 mm3. The maximum value was 5887.23 mm3. When the area calculated using LCA was compared with the volume calculated using CBCT, the correlation between them was significant statistically(r=0.831, p-value =0.000). The mean values of volume evaluated in 3D CBCT in males were 4198±1008 mm3 while for females it was 2980±1134.5 mm3. During the statistical analysis,these observations were found to have a positive correlation with increased volume of pharyngeal space in males as compared to that of females (p=0.006). The values of the area of pharyngeal space calculated using LCA in males was 370.1±60.9 mm2. while it was 301.9±88 mm2 in females. The area estimated for the pharyngeal airway on LCA correlates strongly with the volume determined by a CBCT scan. Since we have considered pharyngeal space analysis using CBCT to be a reliable and standard methodology, therefore a positive correlation of area calculated using LCA with volume calculated using CBCT shows that the analysis made by LCA can be reliable.

Reliability of landmark identification for analysis of the temporomandibular joint in real-time MRI

BackgroundReal-time magnetic resonance imaging (rtMRI) is essential for diagnosing and comprehending temporomandibular joint (TMJ) movements. Current methods for tracking and analysis require manual landmark placement on each acquisition frame. Therefore, our study aimed to assess the inter- and intra-rater reliability of placing cephalometric landmarks in frames from a dynamic real-time TMJ MRI.Material and methodsFour real-time MRIs of the right TMJ were taken during mandibular movement at ten frames per second. Seven dentists identified ten landmarks on two frames (intercuspal position—ICP—and maximum mouth opening—MMO) twice at a two-week interval, yielding 112 tracings. Six typical cephalometric measurements (angles and distances) were derived from these landmarks. The reliabilities of landmarks and measurements were evaluated using distance-based (dbICC), linear mixed effect model intraclass correlation (lmeICC), and standard ICC.ResultsThe average inter-rater reliability for the landmarks stood at 0.92 (dbICC) and 0.93 (lmeICC). The intra-rater reliability scores were 0.97 and 0.98. Over 80% of the landmarks showed an ICC greater than 0.98 (inter-rater) and over 0.99 (intra-rater). The lowest landmark ICC was observed for the orbitale and the oblique ridge of the mandibular ramus. However, the cephalometric angle and distance measurements derived from these landmarks showed only moderate to good reliability, whereas the reliability in the frames with ICP was better than those with MMO. Measurements performed in the ICP frame were more reliable than measurements in the MMO frame.ConclusionWhile dentists reliably localize isolated landmarks in real-time MRIs, the cephalometric measurements derived from them remain inconsistent. The better results in ICP than MMO are probably due to a more familiar jaw position. The higher error rate of the TMJ measurements in MMO could be associated with a lack of training in real-time MRI analysis in dentistry.

Deep learning for automatic detection of cephalometric landmarks on lateral cephalometric radiographs using the Mask Region-based Convolutional Neural Network: a pilot study

ObjectiveWe examined the effectiveness and feasibility of the Mask Region-based Convolutional Neural Network (Mask R-CNN) for automatic detection of cephalometric landmarks on lateral cephalometric radiographs (LCRs). Study DesignIn total, 400 LCRs, each with 19 manually identified landmarks, were collected. Of this total, 320 images were randomly selected as the training dataset for Mask R-CNN, and the remaining 80 images were used for testing the automatic detection of the 19 cephalometric landmarks, for a total of 1520 landmarks. Detection rate, average error, and detection accuracy rate were calculated to assess Mask R-CNN performance. ResultsOf the 1520 landmarks, 1494 were detected, for a detection rate of 98.29%. The average error, or linear deviation distance between the detected points and the originally marked points of each detected landmark, ranged from 0.56 to 9.51 mm, with an average of 2.19 mm. For detection accuracy rate, 649 landmarks (43.44%) had a linear deviation distance less than 1mm, 1020 (68.27%) less than 2mm, and 1281 (85.74%) less than 4mm in deviation from the manually marked point. The average detection time was 1.48 seconds per image. ConclusionsDeep learning Mask R-CNN shows promise in enhancing cephalometric analysis by automating landmark detection on LCRs, addressing the limitations of manual analysis and demonstrating effectiveness and feasibility.

Accuracy of and dental students' preferences toward manual and digital cephalometric landmark identification: A randomized cross-over study.

To evaluate dental students' perceptions of manual and digital cephalometric landmark identification methods based on their preferences, difficulty level, and procedure time required to provide insights into the future of dental education, considering incorporating digital technology in dental schools. Fifty-five second-year dental students were randomly divided into two groups: (1) group A, students who performed manual landmark identification first, followed by digital method; and (2) group B, students who performed digital method first, followed by manual method. The duration of the procedure was recorded. Subsequently, all students completed a questionnaire regarding the difficulty they experienced using a visual analog scale and their preferences. Landmark identification accuracy was measured. Digital landmark identification was preferred by 93% of students. The mean procedure time for digital method was significantly lower than that of manual method (13.00±5.60vs. 9.70±4.60; p=0.002). Group B completed manual and digital methods in a shorter time than group A. Group A experienced less difficulty with manual procedure than group B. However, statistically significant differences were not observed in the difficulty level of digital technique. A statistically significant difference in the mean accuracy was shown in favor of the manual method. However, this difference is clinically insignificant (p=0.001). Students considered digital method to be effective for learning and preferred it over manual method. Furthermore, digital landmark identification demonstrated better performance and was faster than manual method, suggesting that this must be incorporated in undergraduate dental education.

Automated Cephalometric Landmark Detection: A Novel Software Model Compared with Manual Annotation Method

Introduction AI-based automated cephalometric landmark detection streamlines orthodontic diagnosis and treatment planning, providing accurate, efficient, and reliable results. Benefits include saving time, minimizing subjectivity, improving precision, and facilitating continuous improvement. However, they should complement clinician expertise, ensuring qualified orthodontists make the final diagnosis and treatment plan. Aim To propose a method that automatically detects cephalometric landmarks on the X-ray images and compare these values with the manual annotation method. Methodology A dataset of 600 X-ray images, each containing 19 landmarks, was collected. Two orthodontists manually marked the 19 landmarks in 300 cephalograms and their coordinates were automatically extracted. The dataset was cleaned for errors, and a pre-trained CNN model with an EfficientNetB7 backbone was used for landmark detection. The model was trained on 80% of the dataset and tested on the remaining 20%. The two-step method included ROI extraction and landmark detection. The RMSE score was used to evaluate inter-examiner reliability and the R2 score was used to compare manual and automated models. Result Model landmark locations were compared to the manual method. The mean deviation of the predicted landmarks from the actual landmarks was calculated using RMSE, and the model showed acceptable accuracy compared to manual annotation. EfficientNetB7 was found to have detection accuracies similar to the manual annotation method. For landmarks like Porion, articulare, and soft tissue pogonion, the model outperformed the human annotation method and provides a consistent better result, and for points like Point A, pogonion, gnathion, and menton, the manual methods show more accurate results. Conclusion The study introduced an automated approach using deep learning to predict landmark locations, and the results demonstrate its accuracy in comparison with the manual annotation method. This approach effectively detects cephalometric landmarks, suggesting its potential for clinical use with orthodontist’s supervision.

Evaluation of Glenoid Fossa Position in Class II Malocclusion Associated with Mandibular Retrusion and Class III Malocclusion Associated with Mandibular Protrusion

ABSTRACT Objective: This study examined the glenoid fossa in Class II and Class III malocclusions with mandibular retrusion and protrusion. Materials and Methods: A retrospective investigation examined 60 Class II and 60 Class III cephalometric radiographs. Cephalometric landmarks and glenoid fossa measurements were taken. Statistical analysis contrasted the two malocclusion groups’ glenoid fossas. Results: Class II malocclusion had a much lower mean Sella–Nasion–Condylion (SNCd) angle (glenoid fossa sagittal position) than Class III (14.6° ± 1.9). Class II malocclusion had a lower mean Sella–Nasion–Gonion (SNGo) angle (32.5° ± 4.3) than Class III (36.2° ± 3.9). The SNCd angle and SNGo angle in both groups demonstrated a negative correlation, demonstrating a relationship between the glenoid fossa and the mandibular sagittal axis. Conclusion: The glenoid fossa location differs significantly between Class II malocclusion with mandibular retrusion and Class III with protrusion. Class II malocclusion has a posterior glenoid fossa, while Class III has a less posterior one. Understanding these links may help patients receive more personalized treatment.

Precision and accuracy of craniofacial growth and orthodontic treatment evaluation by digital image correlation: a prospective cohort study.

A precise and accurate method for structural superimposition is essential for analyzing dentofacial growth and orthodontic or surgical treatment in longitudinal studies. The errors associated with different superimposition methods have not yet been assessed in high-quality studies. This study aimed to assess the precision and accuracy of digital image correlation (DIC) for structural superimposition. Two cephalometric images from 30 consecutive patients were superimposed using three DIC methods, each measured twice by two examiners. Areas including the contours of the sella, the whole cranial base (CB), and Walker's point and lamina cribrosa (WPLC) were compared using a random coefficient model. Inter-rater and intra-rater errors were assessed for each method. WPLC provided the best precision for image rotation and cephalometric landmarks. Systematic bias was observed between the WPLC and CB methods for image rotation and most landmarks. The intra-rater error in image rotation during DIC was strongly correlated with the intra-rater error in the landmarks of the anterior nasal spine, articulare, and pogonion. Structural superimposition using DIC with WPLC is a precise method for analyzing dentofacial growth and orthodontic or surgical treatment. Moreover, the best method is the measurement of longitudinal dental and craniofacial changes on structurally superimposed cephalometric radiographs with WPLC and a reference grid including the true vertical and horizontal lines from Walker's point.