Rotation tendency of the posteriorly displaced proximal segment after vertical ramus osteotomy

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.

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.

Face the Future-Artificial Intelligence in Oral and Maxillofacial Surgery

Artificial intelligence (AI) has emerged as a versatile health-technology tool revolutionizing medical services through the implementation of predictive, preventative, individualized, and participatory approaches. AI encompasses different computational concepts such as machine learning, deep learning techniques, and neural networks. AI also presents a broad platform for improving preoperative planning, intraoperative workflow, and postoperative patient outcomes in the field of oral and maxillofacial surgery (OMFS). The purpose of this review is to present a comprehensive summary of the existing scientific knowledge. The authors thoroughly reviewed English-language PubMed/MEDLINE and Embase papers from their establishment to 1 December 2022. The search terms were (1) "OMFS" OR "oral and maxillofacial" OR "oral and maxillofacial surgery" OR "oral surgery" AND (2) "AI" OR "artificial intelligence". The search format was tailored to each database's syntax. To find pertinent material, each retrieved article and systematic review's reference list was thoroughly examined. According to the literature, AI is already being used in certain areas of OMFS, such as radiographic image quality improvement, diagnosis of cysts and tumors, and localization of cephalometric landmarks. Through additional research, it may be possible to provide practitioners in numerous disciplines with additional assistance to enhance preoperative planning, intraoperative screening, and postoperative monitoring. Overall, AI carries promising potential to advance the field of OMFS and generate novel solution possibilities for persisting clinical challenges. Herein, this review provides a comprehensive summary of AI in OMFS and sheds light on future research efforts. Further, the advanced analysis of complex medical imaging data can support surgeons in preoperative assessments, virtual surgical simulations, and individualized treatment strategies. AI also assists surgeons during intraoperative decision-making by offering immediate feedback and guidance to enhance surgical accuracy and reduce complication rates, for instance by predicting the risk of bleeding.

Surgical cutting guide and single plate fixation for intraoral vertical ramus osteotomy

With the advancement of digital technology over the last few decades, the use of virtual surgical planning and fabrication of surgical guides have tremendously improved the outcomes of various maxillofacial surgical procedures. The intraoral vertical ramus osteotomy (IVRO) is an orthognathic surgical procedure largely employed for mandibular setback in correcting dentofacial deformities. This study describes the design and application of a surgical cutting guide for IVRO. The guide can also be used to facilitate the placement of miniplate fixation. The initial experience at the authors' centre suggests that the guide has allowed the osteotomy to be performed with increased precision and confidence. Furthermore, the use of miniplate fixation decreased the period of maxillomandibular fixation. However, a larger series is required to evaluate the utility of this system more thoroughly.

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.

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.

Postoperative stability of two common ramus osteotomy procedures for the correction of mandibular prognathism: A randomized controlled trial

The aim of this randomized controlled trial was to compare the skeletal stability between sagittal split ramus osteotomy (SSRO) and intraoral vertical ramus osteotomy (IVRO) in the treatment of mandibular prognathism. Patients presenting with mandibular prognathism and scheduled for orthognathic surgery were randomized into either the SSRO group or the IVRO group. Changes at B-point were assessed by serial tracing of lateral cephalograms, which were taken preoperatively, and at 2 weeks, 6 months, 1 year, and 2 years postoperatively. Ninety-eight patients were recruited, with 49 patients in each group. Between 2 weeks and 6 months postoperatively, there was significantly more surgical relapse in the horizontal direction (anterior movement) in the SSRO group when compared with the IVRO group (1.83 mm (SD 2.91 mm) vs 0.49 mm (SD 2.32 mm); p = 0.019). At 2 years, there was more surgical relapse in the horizontal direction in the SSRO group than in the IVRO group (0.27 mm (SD 0.34 mm) vs 0.10 mm (SD 0.29 mm); p = 0.014). There were also more absolute changes (irrespective of direction) at B-point in the SSRO group than in the IVRO group at postoperative 6 months, 1 year, and 2 years (p = 0.016, 0.049, and 0.045, respectively). The amounts of change at B-point as percentages of total mandibular setback were 1.3% and 3.5% in the IVRO group and SSRO group, respectively. There were no differences in vertical changes between the two groups at any time points. In conclusion, the horizontal stability at B-point was shown to be superior in the IVRO group compared with the SSRO group in the correction of mandibular prognathism during the 2-year follow-up. Although the exact clinical importance of this difference is unknown at this time, this possible benefit may be an important key factor when deciding which osteotomy technique to employ for mandibular setback.

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.

Mandibular condyle displacements after orthognathic surgery-an overview of quantitative studies

The repositioning of bone segments during orthognathic surgeries often results in mandibular condyle positional changes and can also affect jaw muscles, soft tissues and the temporomandibular joint (TMJ). Condylar displacements are considered as one of the factors of bone remodeling and further skeletal relapse. The quantitative approach is commonly used in comparative analyses and evaluations of the relationships between examined factors. The aim of this study is the overview of the current literature including quantitative analysis in the research of mandibular condyle positional changes as a consequence of orthognathic surgeries. Thirty articles were included in the overview. Most of the articles present a comparative and evaluative analysis of treatment results concerning different surgical approaches, fixation methods or types of skeletal defects. The correlation between condylar displacements and bone remodeling, skeletal relapse and TMJ dysfunctions were considered. The most frequently repeated study variables were: short-term changes, Class III malocclusion, yaw rotation, 3D cephalometry measurements. Quantitative data might be useful in the evaluation of patterns and range of condylar displacements for specific treatment conditions. Available literature concerning the analysed topic is characterized by great heterogeneity with regards to the purpose and methodologies of the studies. More systematic approaches and long-term considerations are needed in future research.

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.

Volumetric characteristics of prognathic mandible revealed by skeletal unit analysis

The purpose of this study was to evaluate the skeletal units of a normal mandible (class I) and a prognathic mandible (class III), to compare the groups, and to investigate the key functional unit responsible for mandibular prognathism. Hemi-mandibles of 101 cases were evaluated by cone-beam computed tomography. Of these, 50 cases had Class I and 51 had Class III mandibles. The length, volume, and volume/length ratio of each skeletal unit were measured. The ratios of the condyle, body unit, and sum of the hemi-mandible between Class I and Class III showed statistically significant results (P<0.05). However, the ratios of angle, coronoid, and symphysis units did not show any statistical significance on comparison. Dependent on gender, in males the ratio of the condyle of the hemi-mandible showed statistically significant results (P<0.05). Meanwhile in females the ratio of the body and sum of the hemi-mandible showed statistically significant results (P<0.05). Accordingly, the mandibular body and condylar units are thinner in mandibular prognathism. On the basis of the functional matrix theory to determine the aetiology of mandibular prognathism, the key skeletal units are the body and condylar units.