Landmark-based midsagittal plane analysis in patients with facial symmetry and asymmetry based on CBCT analysis tomography

Facial surgery preview based on the orthognathic treatment prediction

BACKGROUND AND OBJECTIVE

Orthognathic surgery consultations are essential for helping patients understand how their facial appearance may change after surgery. However, current visualization methods are often inefficient and inaccurate due to limited pre- and post-treatment data and the complexity of the treatment. This study aims to develop a fully automated pipeline for generating accurate and efficient 3D previews of postsurgical facial appearances without requiring additional medical images.

METHODS

The proposed method incorporates novel aesthetic criteria, such as mouth-convexity and asymmetry, to improve prediction accuracy. To address data limitations, a robust data augmentation scheme is implemented. Performance is evaluated against state-of-the-art methods using Chamfer distance and Hausdorff distance metrics. Additionally, a user study involving medical professionals and engineers was conducted to evaluate the effectiveness of the predicted models. Participants performed blinded comparisons of machine learning-generated faces and real surgical outcomes, with McNemar's test used to analyze the robustness of their differentiation.

RESULTS

Quantitative evaluations showed high prediction accuracy for our method, with a Hausdorff Distance of 9.00 millimeters and Chamfer Distance of 2.50 millimeters, outperforming the state of the art. Even without additional synthesized data, our method achieved competitive results (Hausdorff Distance: 9.43 millimeters, Chamfer Distance: 2.94 millimeters). Qualitative results demonstrated accurate facial predictions. The analysis revealed slightly higher sensitivity (54.20% compared to 53.30%) and precision (50.20% compared to 49.40%) for engineers compared to medical professionals, though both groups had low specificity, approximately 46%. Statistical tests showed no significant difference in distinguishing Machine Learning-Generated faces from Real Surgical Outcomes, with p-values of 0.567 and 0.256, respectively. Ablation tests demonstrated the contribution of our loss functions and data augmentation in enhancing prediction accuracy.

CONCLUSION

This study provides a practical and effective solution for orthognathic surgery consultations, benefiting both doctors and patients by improving the efficiency and accuracy of 3D postsurgical facial appearance previews. The proposed method has the potential for practical application in pre-surgical visualization and aiding in decision-making.

Suboptimal patient positioning with panoramic and CBCT imaging: effects on dose

OBJECTIVE

This study examined the effects of changes in patient positioning on radiation exposure for panoramic and cone beam computed tomography (CBCT) radiographic examinations by measuring effective dose (E) and equivalent doses.

STUDY DESIGN

Simulated radiographic examinations with optimal and suboptimal positioning-anterior shift by 1 centimeter (cm), posterior shift by 1 cm, chin lowered by 10 degrees (°), chin elevated by 10°, rotation by 10°, and lateral shift by 1 cm-were conducted using a tissue-equivalent phantom and optically-stimulated luminescent dosimeters. Exposures were made with the RAYSCAN Alpha Plus 160 X-ray unit using the following exposure parameters: panoramic, 80 kVp, 14 mA, and 13.9s; CBCT (10 x 10 cm FOV), 90 kVp, 10 mA, and 14.0s; CBCT (16 x 10 cm FOV), 90 kVp, 11 mA, and 14.0 s.

RESULTS

All suboptimal panoramic conditions except rotation demonstrated significant decreases in E. Chin elevation during CBCT imaging reduced E with the 10 × 10 cm FOV (P = .0003) and 16 × 10 cm FOV (P < .0001), as well as the equivalent dose to the thyroid gland (P < .0001 for both FOVs).

CONCLUSIONS

Suboptimal positioning did not significantly increase E for either panoramic or CBCT exposures. Chin elevation decreased E in the CBCT protocols, with notable decreases in equivalent dose to the thyroid gland.

Comparison of Mirroring and Overlapping Analysis and Three-Dimensional Soft Tissue Spatial Angle Wireframe Template in Evaluating Facial Asymmetry

AIM

The purpose of this study was to evaluate the accuracy and efficacy of a new wireframe template methodology in analyzing three-dimensional facial soft tissue asymmetry.

MATERIALS AND METHODS

Three-dimensional facial soft tissue data were obtained for 24 patients. The wireframe template was established by identifying 34 facial landmarks and then forming a template on the face with the MeshLab 2020 software. The angle asymmetry index was automatically scored using the template. The mirroring and overlapping technique is accepted as the golden standard method to diagnose facial asymmetry by acquiring deviation values of one's face. Consistency rates between the two methodologies were determined through a statistical comparison of the angle asymmetry index and deviation values.

RESULTS

Overall consistency rates in the labial, mandibular angle, cheek, chin, and articular regions were 87.5%, 95.8%, 87.5%, 91.7%, and 100%, respectively. Regions with consistency rates in three dimensions of more than 85% are the x-axis and the z-axis of all regions and the y-axis of the mandibular angle, chin, and articular region.

CONCLUSIONS

Soft tissue facial asymmetry can be diagnosed accurately and effectively by using a three-dimensional soft tissue spatial angle wireframe template. Precise localization of asymmetry can be offered, and indiscernible tiny asymmetry can be identified.

Evaluation of Facial Asymmetry in Patients with Crooked Nose

BACKGROUND

This study aims to explore the correlation between facial asymmetry and a crooked nose using objective methodologies.

METHODS

The cohort of 57 patients who underwent septorhinoplasty surgery for aesthetic reasons between 2019 and 2022. Patients were categorized based on the type of nasal axis deviation. The analysis involved reviewing patients' photographs and cone beam computed tomography images. We identified various anatomical landmarks and compared measurements across the groups.

RESULTS

Among the study population, 21 (36.8%) exhibited Type-I (linear) and 15 (26.3%) demonstrated Type-C nasal axis deviation, while no deviation was detected in 21 (36.8%) patients. Upon evaluating the upper face area, significant differences were found in the glabella-lateral orbit (G-LO) and rhinion-lateral orbit (Rh-LO) parameters (p = 0.002 and p < 0.001, respectively). A statistically significant difference was discovered in all three parameters between the three groups in the middle face area [glabella-zygion (G-Zy) p = 0.04, rhinion-zygion (Rh-Zy) P < 0.001, anterior nasal spine-zygion (ANS-Zy) p < 0.001)]. Further, a statistically significant difference was noted in the soft tissue parameters gonion (Go) and LO (p = 0.008 and P = 0.005, respectively).

CONCLUSION

Patients with crooked noses, in particular, exhibit asymmetries in the upper and middle faces. The glabella in the upper face and the anterior nasal spine in the middle face are stable points, and the fact that the parameters derived from these two reference points are significant, when considered in conjunction with other significant parameters, strongly supports the aforementioned statement.

LEVEL OF EVIDENCE III

This journal requires that authors assign a level of evidence to each article. For a full description of these Evidence-Based Medicine ratings, please refer to the Table of Contents or the online Instructions to Authors www.springer.com/00266 .

3D X-ray microscope acts as an accurate and effective equipment of pathological diagnosis in craniofacial imaging

Craniofacial structure and dental hard tissue used to be researched on by traditional imaging tools such as light microscope, electron microscope and micro-CT. Due to the limitations of imaging principle, resolution and 3D rendering reconstruction technique, traditional imaging tools are constrained for presenting fine structure and precise measurements. Here a brand-new imaging equipment-3D X-ray microscope is introduced to realize a more efficient scanning by demonstrating the comparison of the craniofacial structures and dental hard tissue of diabetes and normal DBA mouse. To explore a higher resolution, more efficient imaging measurement and 3D reconstruction method on craniofacial structure and dental hard tissue. The study included 12 DBA mice which were divided into two groups (control group and diabetes group). The heads were separated and scanned by 3D X-ray microscope, after which regions of interest were selected, followed by measurement and 3D reconstruction based on microscope attached software Dragonfly pro©. Hemi-mandibles were collected for enamel mineral density assessment supported by QRM-MicroCT-HA phantom. Data was submitted to paired t-tests at a 95% confidence level. The automatic assessed enamel thickness of diabetes mice decreased on average, whereas the rest of manual measurements and automatic assessed density showed no statistical difference. We constructed HA phantom assisted enamel density procedure in Dragonfly software. Craniofacial structure and dental hard tissue were well-presented both in 2D slide and 3D reconstruction viewport by 3D X-ray microscope which can be routinely used as craniofacial structure and dental hard tissue imaging tool.

Establishment of the mid-sagittal reference plane for three-dimensional assessment of facial asymmetry: a systematic review : Establishment of the mid-sagittal reference plane: a systematic review

OBJECTIVE

To systematically review the literature for mid-sagittal plane establishment approaches to identify the most effective method for constructing the mid-sagittal plane for the evaluation of facial asymmetry.

MATERIALS AND METHODS

Six electronic databases (PubMed, Medline (via Ovid), EMBASE (via Ovid), Cochrane Library, Web of Science, and Scopus) and grey literature were searched for the studies that computed the mid-sagittal reference plane three-dimensionally, using a combination of MeSH terms and keywords. The methodological quality and the level of evidence for the included studies were analyzed using QUADAS-2 and GRADE, respectively.

RESULTS

The preliminary search yielded 6746 records, of which 42 articles that met the predefined inclusion criteria were included in the final analysis. All the included articles reported the construction of the mid-sagittal reference plane (MSP) using varied methods. The risk of bias and concerns regarding the applicability of the included studies were judged to be 'low'. The level of evidence was determined to be 'low' for the effectiveness of the technique and 'moderate' for the ease of clinical applicability.

CONCLUSION

Despite methodological heterogeneity, this review substantiates the comparable efficacy of cephalometric and morphometric MSP construction methods. A fully automated morphometric MSP holds promise as a viable option for routine clinical use. Nevertheless, future prospective studies with an emphasis on the impact, accuracy, and clinical applicability of MSP construction techniques in cases of facial asymmetry are required.

CLINICAL RELEVANCE

The present review will assist clinicians in selecting the most suitable method for MSP construction, leading to improved treatment planning and ultimately more favorable treatment outcomes.

The accuracy and reliability of different midsagittal planes in the symmetry assessment using cone-beam computed tomography

Symmetry is an essential component of esthetic assessment. Accurate assessment of facial symmetry is critical to the treatment plan of orthognathic surgery and orthodontic treatment. However, there is no internationally accepted midsagittal plane (MSP) for orthodontists and orthognathic surgeons. The purpose of this study was to explore a clinically friendly MSP, which is more accurate and reliable than what is commonly used in symmetry assessment. Forty patients with symmetric craniofacial structures were analyzed on cone-beam computed tomography (CBCT) scans. The CBCT data were exported to the Simplant Pro software to build four reference planes that were constructed by nasion (N), basion (Ba), sella (S), odontoid (Dent), or incisive foramen (IF). A total of 31 landmarks were located to determine which reference plane is the most optimal MSP by comparing the asymmetry index (AI). The mean value of AI showed a significant difference (p < 0.05) among four reference planes. Also, the mean value of AI for all landmarks showed that Plane 2 (consisting of N, Ba, and IF) and Plane 4 (consisting of N, IF, and Dent) were more accurate and stable. In conclusion, the MSP consisting of N, Dent, and IF shows more accuracy and reliability than the other planes. Further, it is more clinically friendly because of its significant advantage in landmarking.

Facial asymmetry of the hard and soft tissues in skeletal Class I, II, and III patients

To investigate and compare the facial asymmetry (hard and soft tissues) among skeletal Class I, II, and III patients. A total of 221 subjects, including skeletal Class I (n = 80), skeletal Class II (n = 75), and skeletal Class III (n = 66), were included in the study. CBCT, 22 skeletal landmarks, and 10 soft tissue landmarks were used for the measurements and the asymmetry index was calculated to assess the facial asymmetry. Statistical analyses included one-way ANOVA, Kruskal-Wallis test, and Spearman correlation analysis. The skeletal Class III patients presented greater asymmetry than Class II patients for 10 hard tissue landmarks and 3 soft tissue landmarks (p < 0.05). High correlation of asymmetry was found between four soft tissue landmarks and their corresponding skeletal landmarks (rs ≥ 0.71), as well as Me and ANS (r > 0.86). The ANS and Me in 21.3% patients deviated to contralateral sides. The skeletal Class III patients had more facial asymmetry than the Class II patients. Soft tissues showed similar asymmetry as the underlying hard tissues rather than a compensation of the hard tissue asymmetry. The inconsistency in the deviation of Me and ANS may exacerbate facial asymmetry.

Three-dimensional positioning of the maxilla using novel intermediate splints in maxilla-first orthognathic surgery for correction of skeletal class III deformity

OBJECTIVES

Successful orthognathic surgery requires accurate transfer of the intraoperative surgical plan. This study aimed to (1) evaluate the surgical error of a novel intermediate splint in positioning the maxilla during maxilla-first orthognathic surgery and (2) determine factors influencing surgical error.

MATERIALS AND METHODS

This prospective study examined 83 patients who consecutively underwent Le Fort I osteotomy for correction of skeletal class III deformity using a novel intermediate splint and a bilateral sagittal split osteotomy. Surgical error was the outcome variable, measured as the difference in postoperative translational and rotational maxillary position from the virtual plan. Measures included asymmetry, need and amount for mandibular opening during fabrication of intermediate splints, and planned and achieved skeletal movement.

RESULTS

Mean errors in translation for vertical, sagittal, and transversal dimensions were 1.0 ± 0.7 mm, 1.0 ± 0.6 mm, and 0.7 ± 0.6 mm, respectively; degrees in rotation for yaw, roll, and pitch were 0.8 ± 0.6, 0.6 ± 0.4, and 1.6 ± 1.1, respectively. The transverse error was smaller than sagittal and vertical errors; error for pitch was larger than roll and yaw (both p < 0.001). Error for sagittal, transverse, and roll positioning was affected by the achieved skeletal movement (roll, p < 0.05; pitch and yaw, p < 0.001). Surgical error of pitch positioning was affected by planned and achieved skeletal movement (both p < 0.001).

CONCLUSIONS

Using the novel intermediate splint when performing Le Fort I osteotomy allowed for accurate positioning of the maxilla.

CLINICAL RELEVANCE

The novel intermediate splint for maxillary positioning can be reliably used in clinical routines.

Automated localization of mandibular landmarks in the construction of mandibular median sagittal plane

OBJECTIVE

To use deep learning to segment the mandible and identify three-dimensional (3D) anatomical landmarks from cone-beam computed tomography (CBCT) images, the planes constructed from the mandibular midline landmarks were compared and analyzed to find the best mandibular midsagittal plane (MMSP).

METHODS

A total of 400 participants were randomly divided into a training group (n = 360) and a validation group (n = 40). Normal individuals were used as the test group (n = 50). The PointRend deep learning mechanism segmented the mandible from CBCT images and accurately identified 27 anatomic landmarks via PoseNet. 3D coordinates of 5 central landmarks and 2 pairs of side landmarks were obtained for the test group. Every 35 combinations of 3 midline landmarks were screened using the template mapping technique. The asymmetry index (AI) was calculated for each of the 35 mirror planes. The template mapping technique plane was used as the reference plane; the top four planes with the smallest AIs were compared through distance, volume difference, and similarity index to find the plane with the fewest errors.

RESULTS

The mandible was segmented automatically in 10 ± 1.5 s with a 0.98 Dice similarity coefficient. The mean landmark localization error for the 27 landmarks was 1.04 ± 0.28 mm. MMSP should use the plane made by B (supramentale), Gn (gnathion), and F (mandibular foramen). The average AI grade was 1.6 (min-max: 0.59-3.61). There was no significant difference in distance or volume (P > 0.05); however, the similarity index was significantly different (P < 0.01).

CONCLUSION

Deep learning can automatically segment the mandible, identify anatomic landmarks, and address medicinal demands in people without mandibular deformities. The most accurate MMSP was the B-Gn-F plane.

Probing real-world Central European population midfacial skeleton symmetry for maxillofacial surgery

OBJECTIVES

Symmetry is essential for computer-aided surgical (CAS) procedures in oral and maxillofacial surgery (OMFS). A critical step for successful CAS is mirroring the unaffected side to create a template for the virtual reconstruction of the injured anatomical structure. The aim was to identify specific anatomical landmarks of the midfacial skeleton, to evaluate the symmetry in a group of the real-world Central European population, and to use these landmarks to assess midfacial symmetry in CT scans.

MATERIAL AND METHODS

The retrospective cross-sectional study defined landmarks of the midface's bony contour using viscerocranial CT data. The distances of the skeletal landmarks (e.g., the frontozygomatic suture and temporozygomatic suture) of the left and right sides from the midline were measured and statistically compared. Midfacial symmetry for reference points was defined as a difference within 0 mm and their mean difference plus one standard deviation.

RESULTS

We examined a total of 101 CT scans. 75% of our population shows symmetrical proportions of the midface. The means of the differences for the left and right sides ranged from 0.8 to 1.3 mm, averaging 1.1 ± 0.2 mm for all skeletal landmarks. The standard deviations ranged from 0.6 to 1.4 mm, with a computed mean of 0.9 ± 0.3 mm.

CONCLUSION

We established a methodology to assess the symmetry of the bony midface. If the determined differences were equal to or lower than 2.5 mm in the mentioned midfacial skeletal landmarks, then the symmetry of the bony midface was considered present, and symmetry-based methods for CAS procedures are applicable.

CLINICAL RELEVANCE

Many CAS procedures require facial symmetry. We provide an easy-to-apply method to probe for symmetry of the midface. The method may be used for population-based research, to check for proper reduction of fractures after reposition or to screen for symmetry prior to CAS planning.

Subjective evaluation of facial asymmetry with three-dimensional simulated images among the orthodontists and laypersons: a cross-sectional study

OBJECTIVES

We used three-dimensional (3D) virtual images to undertake a subjective evaluation of how different factors affect the perception of facial asymmetry among orthodontists and laypersons with the aim of providing a quantitative reference for clinics.

MATERIALS AND METHODS

A 3D virtual symmetrical facial image was acquired using FaceGen Modeller software. The left chin, mandible, lip and cheek of the virtual face were simulated in the horizontal (interior/exterior), vertical (up/down), or sagittal (forward or backward) direction in 3, 5, and 7 mm respectively with Maya software to increase asymmetry for the further subjective evaluation. A pilot study was performed among ten volunteers and 30 subjects of each group were expected to be included based on 80% sensitivity in this study. The sample size was increased by 60% to exclude incomplete and unqualified questionnaires. Eventually, a total of 48 orthodontists and 40 laypersons evaluated these images with a 10-point visual analog scale (VAS). The images were presented in random order. Each image would stop for 30 s for observers with a two-second interval between images. Asymmetry ratings and recognition accuracy for asymmetric virtual faces were analyzed to explore how different factors affect the subjective evaluation of facial asymmetry. Multivariate linear regression and multivariate logistic regression models were used for statistical data analysis.

RESULTS

Orthodontists were found to be more critical of asymmetry than laypersons. Our results showed that observers progressively decreased ratings by 1.219 on the VAS scale and increased recognition rates by 2.301-fold as the degree of asymmetry increased by 2 mm; asymmetry in the sagittal direction was the least noticeable compared with the horizontal and vertical directions; and chin asymmetry turned out to be the most sensitive part among the four parts we simulated. Mandible asymmetry was easily confused with cheek asymmetry in the horizontal direction.

CONCLUSIONS

The degree, types and parts of asymmetry can affect ratings for facial deformity as well as the accuracy rate of identifying the asymmetrical part. Although orthodontists have higher accuracy in diagnosing asymmetrical faces than laypersons, they fail to correctly distinguish some specific asymmetrical areas.

An Automatic Voxel-Based Method for Optimal Symmetry Plane Generation for the Maxillofacial Region in Severe Asymmetry Cases

Symmetry is representative of aesthetics and health in all kinds of vertebrates, especially the human face. Therefore, to automatically locate the appropriate symmetry plane is crucial. The aim of this study was to develop an automatic and reliable method to determine the symmetry plane of the maxillofacial region. We compared the proposed method of determining the symmetry plane by assessing landmark-based and surface-based methods by way of quantitative symmetry assessments. Statistical analysis was applied to evaluate whether significant difference existed among these three kinds of symmetry planes. Twenty cases who had a diagnosis of severe facial asymmetry were evaluated retrospectively. The results showed that searching for the symmetry plane using a voxel-based method, named the optimal symmetry plane (OSP), achieved the most representative symmetry according to the outcomes of the trials. The OSP was significantly more symmetrical than the other two planes, as determined by other methods. The paired-voxel computation method proposed in this research is a robust and reliable method for identifying the unique symmetry plane for patients with severe facial asymmetry. Symmetry is of crucial significance for all kinds of vertebrates, including its clinical implications for surgical planning in orthognathic surgery.

Orthodontic Perspective for Face Asymmetry Correction

Facial symmetry affects the perception of facial beauty. Overall, facial harmony with an appropriate facial proportion and satisfactory midline facial symmetry are crucial factors for facial attractiveness. The role of orthodontists in correcting facial asymmetry begins with providing suitable diagnosis of the condition and identifying patients’ expectations. Through a thorough, subjective clinical evaluation of dentofacial asymmetry, the procedures for the surgical orthodontic management of facial asymmetry are discussed. The aim of this clinical review is to provide information on surgical indications for facial asymmetry, optimal treatment goals, presurgical orthodontic preparation, the surgery-first approach, three-dimensional (3D) surgical simulation, postsurgical orthodontic finishing, and treatment outcome evaluation. A comprehensive 3D diagnosis with appropriate planning, accurate transference of surgical simulation to real surgery, slight overcorrection, periodic assessment of treatment outcomes, and awareness of treatment limitations are essential to improve treatment outcomes of facial asymmetry.

Automatic Symmetry Detection From Brain MRI Based on a 2-Channel Convolutional Neural Network

Symmetry detection is a method to extract the ideal mid-sagittal plane (MSP) from brain magnetic resonance (MR) images, which can significantly improve the diagnostic accuracy of brain diseases. In this article, we propose an automatic symmetry detection method for brain MR images in 2-D slices based on a 2-channel convolutional neural network (CNN). Different from the existing detection methods that mainly rely on the local image features (gradient, edge, etc.) to determine the MSP, we use a CNN-based model to implement the brain symmetry detection, which does not require any local feature detections and feature matchings. By training to learn a wide variety of benchmarks in the brain images, we can further use a 2-channel CNN to evaluate the similarity between the pairs of brain patches, which are randomly extracted from the whole brain slice based on a Poisson sampling. Finally, a scoring and ranking scheme is used to identify the optimal symmetry axis for each input brain MR slice. Our method was evaluated in 2166 artificial synthesized brain images and 3064 collected in vivo MR images, which included both healthy and pathological cases. The experimental results display that our method achieves excellent performance for symmetry detection. Comparisons with the state-of-the-art methods also demonstrate the effectiveness and advantages for our approach in achieving higher accuracy than the previous competitors.

A Meta-analysis and Systematic Review Comparing the Effectiveness of Traditional and Virtual Surgical Planning for Orthognathic Surgery: Based on Randomized Clinical Trials

PURPOSE

To explore the advantages of virtual surgical planning (VSP) and traditional surgical planning (TSP) to determine whether the current VSP technique is superior to the TSP technique for orthognathic surgery.

METHODS

An electronic search was carried out in the CENTRAL, PubMed, and Embase databases to identify randomized clinical trials (RCTs) that compared the VSP and TSP techniques regarding their surgical accuracy for hard tissue, prediction precision for soft tissue, required time for planning and surgery, cost and patient-reported outcomes.

RESULTS

Eight articles from 5 RCTs, involving 199 patients, were identified. The findings showed that the VSP and TSP techniques were similar in surgical accuracy for hard tissue in the sagittal plane, although the VSP technique was significantly more accurate in certain reference areas, especially in the anterior area of the maxilla. Both the VSP and TSP techniques had significantly better surgical accuracy for the maxilla than for the mandible. The VSP technique showed clinically significantly greater precision for soft tissue prediction in the sagittal plane. Patients who were treated via the VSP technique presented a more symmetrical frontal view, regardless of whether hard or soft tissue was involved. The VSP technique required more time for software planning, but it showed an advantage in time savings when considering the entire preoperative process. Accompanied by the use of an accurate computer-aided splint, the VSP technique could effectively reduce the operative time. Apart from the initial financial investment of software and hardware, the total cost of the VSP technique was similar to that of the TSP technique. Patients who were treated via the VSP or TSP technique showed similar improvements in quality-of-life.

CONCLUSIONS

Currently, the VSP technique has become a good alternative to the TSP technique for orthognathic surgery, especially regarding frontal-esthetic considerations. Studies reporting indicators with good representativeness and sensitivity using an identical comparative method are recommended.

Landmark annotation and mandibular lateral deviation analysis of posteroanterior cephalograms using a convolutional neural network

Background/purpose

Facial asymmetry is relatively common in the general population. Here, we propose a fully automated annotation system that supports analysis of mandibular deviation and detection of facial asymmetry in posteroanterior (PA) cephalograms by means of a deep learning-based convolutional neural network (CNN) algorithm.

Materials and methods

In this retrospective study, 400 PA cephalograms were collected from the medical records of patients aged 4 years 2 months-80 years 3 months (mean age, 17 years 10 months; 255 female patients and 145 male patients). A deep CNN with two optimizers and a random forest algorithm were trained using 320 PA cephalograms; in these images, four PA landmarks were independently identified and manually annotated by two orthodontists.

Results

The CNN algorithms had a high coefficient of determination (R ² ), compared with the random forest algorithm (CNN-stochastic gradient descent, R ²  = 0.715; CNN-Adam, R ²  = 0.700; random forest, R ²  = 0.486). Analysis of the best and worst performances of the algorithms for each landmark demonstrated that the right latero-orbital landmark was most difficult to detect accurately by using the CNN. Based on the annotated landmarks, reference lines were defined using an algorithm coded in Python. The CNN and random forest algorithms exhibited similar accuracy for the distance between the menton and vertical reference line.

Conclusion

Our findings imply that the proposed deep CNN algorithm for detection of facial asymmetry may enable prompt assessment and reduce the effort involved in orthodontic diagnosis.

Towards an early 3D-diagnosis of craniofacial asymmetry by computing the accurate midplane: A PCA-based method

BACKGROUND AND OBJECTIVE

Craniofacial asymmetry is a common growth disorder often caused by unilateral chewing. Although an early orthodontic treatment would avoid surgical procedures later in life, the uncertainty of defining the accurate sagittal midplane potentially leads to misdiagnosis and therefore inaccurate orthodontic treatment plans. This novel study aims to 3D-diagnose craniofacial complex malformations in children with unilateral crossbite (UXB) considering a midplane which compensates the asymmetric morphology.

METHODS

The sagittal midplane of 20 children, fifteen of whom exhibited UXB, was computed by a PCA-based method which compensates the asymmetry mirroring the 3D models obtained from cone-beam computed tomography data. Once determined, one side of the data was mirrored using the computed midplane to visualize the malformations on the hard and soft tissues by 3D-computing the distances between both halves. Additionally, 31 skull's landmarks were manually placed in each model to study the principal variation modes and the significant differences in the group of subjects with and without UXB through PCA and Mann-Whitney U test analyses respectively.

RESULTS

Morphological 3D-analysis showed pronounced deformities and aesthetic implications for patients with severe asymmetry (jaw deviation > 0.8 mm) in whole craniofacial system, while initial signs of asymmetry were found indistinctly in the mandible or maxilla. We detected significant (p < 0.05) malformations for example in mandibular ramus length (0.0086), maxillary palate width (0.0481) and condylar head width (0.0408). Craniofacial malformations increased the landmarks' variability in the group of patients with UXB over the control group requiring 8 variation modes more to define 99% of the sample' variability.

CONCLUSIONS

Our findings demonstrated the viability of early diagnosis of craniofacial asymmetry through computing the accurate sagittal midplane which compensates the individual's asymmetrical morphology. Furthermore, this study provides important computational insights into the determination of craniofacial deformities which are caused by UXB, following some empirical findings of previous clinical studies. Hence, this computational approach can be useful for the development of new software in craniofacial surgery or for its use in biomedical research and clinical practice.

Assessing the Influence of Chin Asymmetry on Perceived Facial Esthetics With 3-Dimensional Images

PURPOSE

We used 3-dimensinonal (3D) images to assess the influence of chin asymmetry on perceived facial esthetics, investigate the cognitive boundaries of chin asymmetry among orthodontists, general dentists, and laypersons, and provide quantitative reference for clinical treatment.

MATERIALS AND METHODS

A 3D facial image was obtained using the 3dMD imaging system (3dMD, Atlanta, GA). The chin was altered in 2-mm increments from 0 to 12 mm and to the left and right using the software program. These images were rated by 66 orthodontists, 89 general dentists, and 66 laypersons as 1) chin symmetry; 2) slight chin asymmetry but acceptable; and 3) serious asymmetry and treatment needed. Multivariate mixed linear regression and multivariate mixed logistic regression analyses were used for statistical data analysis. Descriptive and bivariate statistics were calculated, and statistical significance was considered present at P = .05.

RESULTS

The observers progressively increased the grade ratings and the desire for surgery for greater asymmetries (P < .001). Orthodontists and general dentists could perceive a chin deviation of 4 mm to the right and 2 mm to the left, with 8-mm deviation considered to require treatment. Laypersons had a clear perception of a 4-mm chin deviation, with 8 mm to the right and 10 mm to the left considered to require treatment. The right chin deflection was more easily perceived than was the left (P < .05).

CONCLUSIONS

Chin asymmetry has a great influence on facial esthetics. We found a statistically significant difference between clinicians (orthodontists and general dentists) and laypersons in the cognition of chin asymmetry and the recommendations for treatment.