Volumetric characteristics of prognathic mandible revealed by skeletal unit analysis

Temporomandibular Joint Space in Mandibular Prognathism

This study compared the temporomandibular joint (TMJ) space between patients with normal and prognathic mandibles. The study included a total of 68 Korean individuals, and the TMJ space was measured using computed tomography. Patients with normal SNB values (normal mandible) were classified into Group 1. Patients with high SNB values (prognathic mandibles) were categorized into Group 2. The TMJ space was defined as the distance between the condylar process and the mandibular fossa, and it was significantly different between Groups 1 and 2 (1.94±0.07 mm versus 1.50±0.05 mm, P< 0.01). This study confirmed that the TMJ space in patients with prognathic mandibles is narrower than that in patients with normal mandibles.

Three-dimensional mandibular characteristics in skeletal malocclusion : A cross-sectional study

PURPOSE

We aimed to comprehensively analyse a possible correlation between skeletal malocclusions, gender and mandibular characteristics in all three dimensions in adults and to identify mandibular characteristics that are typical for extreme skeletal patterns.

METHODS

A 3D model of the skull was calculated in 111 adult patients (mean age = 27.0 ± 10.2 years; 49 women, 62 men) from available computed tomography or cone beam computed tomography scans of their heads. Based on the 3D models, the skeletal patterns were examined in (a) the transversal dimension regarding asymmetry according to menton deviation, (b) the sagittal dimension according to the Wits appraisal and (c) the vertical dimension according to the maxillomandibular plane angle. The mandibular characteristics assessed were linear (ramus height and width, body length), angular (ramus, gonial and body angle) and volumetric (ramus/mandibular volume, body/mandibular volume) parameters.

RESULTS

No correlation between transversal skeletal asymmetry and mandibular characteristics were found, while sagittal (F(16, 174) = 3.32, p < 0.001, η2 = 0.23) and vertical (F(16, 174) = 3.18, p < 0.001, η2 = 0.23) skeletal patterns were shown to have a significant effect on the mandible. Gender correlated with mandibular characteristics independently from the skeletal pattern. Discriminant analysis revealed that class II and III patients differed in ramus and body angle with class II patients showing higher angles (ramus angle: class II = 89.8 ± 3.9° vs. class III = 84.4 ± 4.8°; body angle: class II = 87.7 ± 4.8° vs. class III = 82.1 ± 5.2°). Hypo- and hyperdivergent patients were discriminated by gonial angle, body angle and body/mandibular volume with hyperdivergent patients having a greater gonial and body angle and body/mandibular volume (gonial angle: hypodivergent = 114 ± 9.3° vs. hyperdivergent = 126.4 ± 8.6°; body angle: hypodivergent = 82.9 ± 4.4° vs. hyperdivergent = 87.7 ± 6.5°; body/mandibular volume: hypodivergent = 72.4 ± 2.7% vs. hyperdivergent = 76.2 ± 2.6%).

CONCLUSION

When analysing 3D data for treatment planning of adult patients, the orthodontist should pay attention to angular and volumetric characteristics of the mandible to identify extreme skeletal sagittal or vertical malocclusions.

A rapid identification method for soft tissue markers of dentofacial deformities based on heatmap regression

OBJECTIVE

The purpose of this study was to construct a facial deformity dataset and a network model based on heatmap regression for the recognition of facial soft tissue landmarks to provide a basis for clinicians to perform cephalometric analysis of soft tissue.

MATERIALS AND METHODS

A 34-point face marker detection model, the Back High-Resolution Network (BHR-Net), was constructed based on the heatmap regression algorithm, and a custom dataset of 1780 facial detection images for orthognathic surgery was collected. The mean normalized error (MNE) and 10% failure rate (FR10%) were used to evaluate the performance of BHR-Net, and a test set of 50 patients was used to verify the accuracy of the landmarks and their measurement indicators. The test results were subsequently validated in 30 patients.

RESULTS

Both the MNE and FR10% of BHR-Net were optimal compared with other models. In the test set (50 patients), the accuracy of the markers excluding the nose root was 86%, and the accuracy of the remaining markers reached 94%. In the model validation (30 patients), using the markers detected by BHR-Net, the diagnostic accuracy of doctors was 100% for Class II and III deformities, 100% for the oral angle plane, and 70% for maxillofacial asymmetric deformities.

CONCLUSIONS

BHR-Net, a network model based on heatmap regression, can be used to effectively identify landmarks in maxillofacial multipose images, providing a reliable way for clinicians to perform cephalometric measurements of soft tissue objectively and quickly.

Three-Dimensional Postoperative Results Prediction for Orthognathic Surgery through Deep Learning-Based Alignment Network

To date, for the diagnosis of dentofacial dysmorphosis, we have relied almost entirely on reference points, planes, and angles. This is time consuming, and it is also greatly influenced by the skill level of the practitioner. To solve this problem, we wanted to know if deep neural networks could predict postoperative results of orthognathic surgery without relying on reference points, planes, and angles. We use three-dimensional point cloud data of the skull of 269 patients. The proposed method has two main stages for prediction. In step 1, the skull is divided into six parts through the segmentation network. In step 2, three-dimensional transformation parameters are predicted through the alignment network. The ground truth values of transformation parameters are calculated through the iterative closest points (ICP), which align the preoperative part of skull to the corresponding postoperative part of skull. We compare pointnet, pointnet++ and pointconv for the feature extractor of the alignment network. Moreover, we design a new loss function, which considers the distance error of transformed points for a better accuracy. The accuracy, mean intersection over union (mIoU), and dice coefficient (DC) of the first segmentation network, which divides the upper and lower part of skull, are 0.9998, 0.9994, and 0.9998, respectively. For the second segmentation network, which divides the lower part of skull into 5 parts, they were 0.9949, 0.9900, 0.9949, respectively. The mean absolute error of transverse, anterior-posterior, and vertical distance of part 2 (maxilla) are 0.765 mm, 1.455 mm, and 1.392 mm, respectively. For part 3 (mandible), they were 1.069 mm, 1.831 mm, and 1.375 mm, respectively, and for part 4 (chin), they were 1.913 mm, 2.340 mm, and 1.257 mm, respectively. From this study, postoperative results can now be easily predicted by simply entering the point cloud data of computed tomography.

Three-Dimensional Distance Mapping Method to Evaluate Mandibular Symmetry and Morphology of Adults with Unilateral Premolar Scissors Bite

(1) Objective: This study aimed to evaluate the association between unilateral premolar scissors bite and mandibular symmetry of adults via the 3D distance mapping method. (2) Methods: A total of 53 cone-beam computed tomography (CBCT) images of adults with unilateral premolar scissors bite were set as study samples. A total of 53 age- and sex-matched samples without scissors bite were in the control group. Three-dimensional mandibular models and seven mandibular functional units, including condylar process (Co), coronoid process (Cr), mandibular ramus (Ra), mandibular angle (Ma), alveolar process (Ap), mandibular body (Mb), and chin process (Ch) were constructed and mirrored. After superimposition of the original and the mirrored models, 3D distance maps and deviation analysis were performed to evaluate the mandibular symmetry and morphology. (3) Results: In the study group, the matching percentages of the entire mandible (50.79 ± 10.38%), Ap (67.00 ± 12.68%), Mb (66.62 ± 9.44%), Ra (62.52 ± 11.00%), Ch (80.75 ± 9.86%), and Co (62.78 ± 13.56) were lower than that of the entire mandible (58.60 ± 5.52) (p < 0.01), Ap (73.83 ± 8.88%) (p < 0.01), Mb (72.37 ± 8.69%) (p < 0.01), Ra (68.60 ± 7.56%) (p < 0.01), Ch (85.23 ± 6.80%) (p < 0.01), and Co (67.58 ± 10.32%) (p < 0.05) in the control group. However, Cr and Ma showed no significant difference (p > 0.05). (4) Conclusions: The 3D distance mapping method provided a qualitative and quantitative mandibular symmetry and morphology assessment. Mandibular asymmetry was found in adults with unilateral premolar scissors bites. Mandibular functional units, including the alveolar process, mandibular body, mandibular ramus, chin process, and condylar process, showed significant differences, while no significant difference was observed in the coronoid process and mandibular angle.

Volumetric Change in the Masseter and Lateral Pterygoid after Mandibular Setback

In this study, we evaluated changes in the masseter and lateral pterygoid muscles in the prognathic mandible group after a mandibular setback by comparing the volume-to-length ratios. Preoperative and postoperative 1-year computed tomography was used to calculate the volume-to-length ratio of the lateral pterygoid and masseter muscle in 60 Korean individuals. Three-dimensional images were reconstructed, the results of which showed no significant differences in the volume-to-length ratios of the masseter and lateral pterygoid muscles after a mandibular setback (p > 0.05). This result was found for both vertical ramus osteotomy and sagittal split ramus osteotomy, and for both males and females. No significant differences in the volume-to-length ratio of the masseter and lateral pterygoid muscles were found up to 1 year after a mandibular setback. Therefore, this study can contribute to the prediction of soft-tissue profiles after mandibular setback.

Diagnostic validity of different gonial angle segmentation for the assessment of mandibular growth direction: a retrospective study

BACKGROUND

The development of the mandible largely determines the sagittal and vertical lateral appearance. The gonial angle (Articulare-Gonion-Menton, Ar-Go'-Me), as a composite indicator, representes the growth direction of the mandible. We proposed a method based on the Frankfort horizontal (FH) plane and its vertical plane (VFH) to divide the gonial angle into sagittal and vertical components (Articulare-Gonion-VFH / Menton-Gonion-FH, Ar-Go'-VFH / Me-Go'-FH) and to compare the accuracy of diagnosing the development of the mandible and maxillofacial structures with other methods.

METHODS

Lateral cephalometric films from 736 volunteers aged 6-30 years were collected and analyzed for cephalometric measurements. Four groups of segmentation-based angle, including the FH-based segmentation (Ar-Go'-VFH / Me-Go'-FH), the SN-based segmentation (Articulare-Gonion- Sellion-Nasion plane' vertical plane/ Menton-Gonion- Sellion-Nasion plane, Ar-Go'-VSN / Me-Go'-SN), the Go'-S based segmentation(Articulare-Gonion-Sellion / Menton-Gonion-Sellion, Ar-Go'-S / Me-Go'-S), and the Go'-N based segmentation (Articulare-Gonion-Nasion / Menton-Gonion-Nasion, Ar-Go'-N / Me-Go'-N), as well as commonly used sagittal and vertical indices were measured. Pearson correlation analysis was used to show the representativeness of different segmentation methods on the mandibular growth direction.

RESULTS

As the gonial angle decreased with age, all the segmentation-based metrics decreased. The plane-based segmentation metrics, including Ar-Go'-VFH / Me-Go'-FH, Ar-Go'-VSN / Me-Go'-SN, were superior to the point-based segmentation metrics (Ar-Go'-S / Me-Go'-S, and Ar-Go'-N / Me-Go '-N) in evaluating vertical and sagittal development of the mandible. The sagittal indicators displayed alteration of ramus and condyle, while these vertical indicators responded to the alteration of the mandibular corpus and gonial angle.

CONCLUSIONS

The gonial angle should be clinically segmented with planes (including SN plane and FH plane) rather than points (including Go'-S and Go'-N) to assess mandibular development. The FH plane-based segmentation method facilitated chair-side diagnosis of the mandibular growth direction.

Anatomical Characteristics of the Lateral Pterygoid Muscle in Mandibular Prognathism

Mandibular prognathism is one of the most concerning subjects in the oral and maxillofacial fields. In our previous studies, we attempted to clarify the etiology of mandibular prognathism. They revealed that one of the major characteristics of mandibular prognathism was the lower volume/length ratio of the mandibular condyle and body compared to normal, and the masseter muscle showed parallelism with this. This study aimed to evaluate the relationship between mandibular prognathism and the lateral pterygoid muscle by measuring the orientation and volume/length ratio of the lateral pterygoid muscle. Computed tomography was used to calculate the volume/length ratio of the lateral pterygoid muscle in 60 Korean individuals. Mimics 10.0 and Maya version 2018 were used to reconstruct the surface area and surface planes. The results showed that the prognathic group showed smaller lateral pterygoid volume/length ratios compared to the normal group (p < 0.05). In addition, the normal group displayed a larger horizontal angle (p < 0.05) to the mandibular and palatal planes than the prognathic group. This demonstrated that the mechanical drawback of the lateral pterygoid in the prognathic group is associated with mandibular prognathism.

Deep-Learning-Based Detection of Cranio-Spinal Differences between Skeletal Classification Using Cephalometric Radiography

The aim of this study was to reveal cranio-spinal differences between skeletal classification using convolutional neural networks (CNNs). Transverse and longitudinal cephalometric images of 832 patients were used for training and testing of CNNs (365 males and 467 females). Labeling was performed such that the jawbone was sufficiently masked, while the parts other than the jawbone were minimally masked. DenseNet was used as the feature extractor. Five random sampling crossvalidations were performed for two datasets. The average and maximum accuracy of the five crossvalidations were 90.43% and 92.54% for test 1 (evaluation of the entire posterior-anterior (PA) and lateral cephalometric images) and 88.17% and 88.70% for test 2 (evaluation of the PA and lateral cephalometric images obscuring the mandible). In this study, we found that even when jawbones of class I (normal mandible), class II (retrognathism), and class III (prognathism) are masked, their identification is possible through deep learning applied only in the cranio-spinal area. This suggests that cranio-spinal differences between each class exist.

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

BACKGROUND

Posteroanterior and lateral cephalogram have been widely used for evaluating the necessity of orthognathic surgery. The purpose of this study was to develop a deep learning network to automatically predict the need for orthodontic surgery using cephalogram.

METHODS

The cephalograms of 840 patients (Class ll: 244, Class lll: 447, Facial asymmetry: 149) complaining about dentofacial dysmorphosis and/or a malocclusion were included. Patients who did not require orthognathic surgery were classified as Group I (622 patients-Class ll: 221, Class lll: 312, Facial asymmetry: 89). Group II (218 patients-Class ll: 23, Class lll: 135, Facial asymmetry: 60) was set for cases requiring surgery. A dataset was extracted using random sampling and was composed of training, validation, and test sets. The ratio of the sets was 4:1:5. PyTorch was used as the framework for the experiment.

RESULTS

Subsequently, 394 out of a total of 413 test data were properly classified. The accuracy, sensitivity, and specificity were 0.954, 0.844, and 0.993, respectively.

CONCLUSION

It was found that a convolutional neural network can determine the need for orthognathic surgery with relative accuracy when using cephalogram.

Deep learning based discrimination of soft tissue profiles requiring orthognathic surgery by facial photographs

Facial photographs of the subjects are often used in the diagnosis process of orthognathic surgery. The aim of this study was to determine whether convolutional neural networks (CNNs) can judge soft tissue profiles requiring orthognathic surgery using facial photographs alone. 822 subjects with dentofacial dysmorphosis and / or malocclusion were included. Facial photographs of front and right side were taken from all patients. Subjects who did not need orthognathic surgery were classified as Group I (411 subjects). Group II (411 subjects) was set up for cases requiring surgery. CNNs of VGG19 was used for machine learning. 366 of the total 410 data were correctly classified, yielding 89.3% accuracy. The values of accuracy, precision, recall, and F1 scores were 0.893, 0.912, 0.867, and 0.889, respectively. As a result of this study, it was found that CNNs can judge soft tissue profiles requiring orthognathic surgery relatively accurately with the photographs alone.