Machine learning-based decision support system for orthognathic diagnosis and treatment planning.

BACKGROUND: Dento-maxillofacial deformities are common problems. Orthodontic-orthognathic surgery is the primary treatment but accurate diagnosis and careful surgical planning are essential for optimum outcomes. This study aimed to establish and verify a machine learning-based decision support system for treatment of dento-maxillofacial malformations. METHODS: Patients (n = 574) with dento-maxillofacial deformities undergoing spiral CT during January 2015 to August 2020 were enrolled to train diagnostic models based on five different machine learning algorithms; the diagnostic performances were compared with expert diagnoses. Accuracy, sensitivity, specificity, and area under the curve (AUC) were calculated. The adaptive artificial bee colony algorithm was employed to formulate the orthognathic surgical plan, and subsequently evaluated by maxillofacial surgeons in a cohort of 50 patients. The objective evaluation included the difference in bone position between the artificial intelligence (AI) generated and actual surgical plans for the patient, along with discrepancies in postoperative cephalometric analysis outcomes. RESULTS: The binary relevance extreme gradient boosting model performed best, with diagnostic success rates > 90% for six different kinds of dento-maxillofacial deformities; the exception was maxillary overdevelopment (89.27%). AUC was > 0.88 for all diagnostic types. Median score for the surgical plans was 9, and was improved after human-computer interaction. There was no statistically significant difference between the actual and AI- groups. CONCLUSIONS: Machine learning algorithms are effective for diagnosis and surgical planning of dento-maxillofacial deformities and help improve diagnostic efficiency, especially in lower medical centers.

Characterization of upper airway and analysis of potential risk factor associated with OSA in patients with unilateral temporomandibular ankylosis and micrognathia deformities.

OBJECTIVE: To ascertain the airway characteristics in patients with unilateral temporomandibular joint ankylosis and maxilla-mandibular deformities (UTMAMD) and investigate the potential risk factors associated with obstructive sleep apnea (OSA) among UTMAMD patients. METHODS: Authors conducted a retrospective single-center study to assess and compare study group consisting of a cohort of 32 patients diagnosed with UTMAMD between January 2011 and July 2022 with control group including 54 participants. The study group was further divided into two subgroups based on the presence or absence of OSA in patients. Parameters related to the upper airway were measured and analyzed using three-dimensional reconstruction of computed tomographic scans. The measurements of airway parameters were compared between study group and control group and between two subgroups. Pearson correlation analysis was used to identify the factors associated with the presence of OSA, and a multiple variable regression model was used to identify risk factors for OSA. RESULTS: Airway volume (VOL), Minimum cross-section area (min CSA), mean CSA, tilt in sagittal plane (TS), and tilt in sagittal plane (TC) in velopharynx; VOL, airway length (AL), min CSA, mean CSA, TS, TC, and airway deviation (AD) in glossopharynx; min CSA, TS, and AD in hypopharynx were found difference with significance between study group and control group. Lateral dimension/anterior-posterior dimension (LAT/AP) ratio in velopharynx and min CSA, TC, and LAT/AP ratio in glossopharynx were significant different between patients with UTMAMD with OSA and without OSA. CONCLUSIONS: The upper airway of patients with UTMAMD exhibits significant narrowing and distortion, rendering them susceptible to suffer from OSA. Patients with UTMAMD and OSA demonstrate more elliptical airways, and the glossopharyngeal LAT/AP ratio is a predictive indicator for the occurrence of OSA.

Improvement of coated aluminum sheet pBRDF model based on scattering and phase function optimization.

The pBRDF model is able to relate the properties of target materials to the polarization information of incident and reflected light, and is an important basis for obtaining polarization information of targets in space. It is an important basis for obtaining target polarization information and polarization detection of space targets. P-G model is the first strictly pBRDF model officially released, but there are still deficiencies. In this paper, we first analyze the assumption framework of the P-G model, derive the imperfections in the framework through the analysis of the assumption framework, and add scattering and phase function to enhance the existing model. On the basis of the existing P-G model and parameter inversion, the output results of the model are compared with the experimental data through simulation, and the results show that the relative error of the target's linear polarizability is reduced under the improved model, which proves the accuracy and precision of the improved model.

Comparison of Effects between Total Maxillary Setback Osteotomy and Anterior Maxillary Segmental Osteotomy on Nasolabial Morphology.

BACKGROUND: The authors aimed to compare the effects of total maxillary setback osteotomy (TMSO) and anterior maxillary segmental osteotomy (AMSO) on nasolabial morphology. METHODS: This retrospective clinical trial enrolled 130 patients undergoing maxillary surgery using TMSO or AMSO. Ten nasolabial-related parameters and nasal airway volume were measured preoperatively and postoperatively. The soft-tissue digital model was reconstructed using Geomagic Studio and Dolphin image 11.0. Statistical analysis was performed using IBM SPSS Version 27.0. RESULTS: A total of 75 patients underwent TMSO, and 55 underwent AMSO. Both techniques achieved optimal repositioning of the maxilla. Except for the dorsal nasal length, the dorsal nasal height, the length of the nasal columella, and the upper lip thickness, the remaining parameters were significantly different in the TMSO group. In the AMSO group, only the nasolabial angle, the alar base width, and the greatest alar width showed significant differences. There was a significant difference in the nasal airway volume for the TMSO group. The results of matching maps are consistent with the statistical results. CONCLUSIONS: TMSO has a more significant impact on both nose and upper lip soft tissues, whereas AMSO has a more significant impact on the upper lip and less on the nasal soft tissue. There is a significant decrease in nasal airway volume after TMSO, whereas AMSO showed less decrease. This retrospective study is helpful for clinicians and patients to understand the different changes in nasolabial morphology caused by the two interventions, which is essential for effective intervention and physician-patient communication. CLINICAL QUESTION/LEVEL OF EVIDENCE: Therapeutic, III.

Artificial Intelligence Splint in Orthognathic Surgery for Skeletal Class III Malocclusion: Design and Application.

BACKGROUND: Digital splints are indispensable in orthognathic surgery. However, the present design process of splints is time-consuming and has low reproducibility. To solve these problems, an algorithm for artificial intelligent splints has been developed in this study, making the automatic design of splints accessible. METHODS: Firstly, the algorithm and program of the artificial intelligence splint were created. Then a total of 54 patients with skeletal class III malocclusion were included in this study from 2018 to 2020. Pre and postoperative radiographic examinations were performed. The cephalometric measurements were recorded and the difference between virtual simulation and postoperative images was measured. The time cost and differences between artificial intelligent splints and digital splints were analyzed through both model surgery and radiographic images. RESULTS: The results showed that the efficiency of designing splints is significantly improved. And the mean difference between artificial intelligent splints and digital splints was <0.15 mm in model surgery. Meanwhile, there was no significant difference between the artificial intelligent splints and digital splints in radiological image analysis. CONCLUSIONS: In conclusion, compared with digital splints, artificial intelligent splints could save time for preoperative design while ensuring accuracy. The authors believed that it is conducive to the presurgical design of orthognathic surgery.

Depth-based sparse bundle adjustment.

It is demonstrated in this paper that due to error model inconsistency, a certain degree of accuracy loss would be incurred to the estimated parameters when the traditional bundle adjustment method is directly applied to the scenario where a fraction of observations is implicitly error free (e.g., the reference image points in commonly used least squares matching refinement). To this end, a depth-based object point model and corresponding depth-based sparse bundle adjustment method are proposed in this paper, in which the position of an object point is represented by its 1D depth relative to its reference image. A corresponding projection model is derived, the sparse block structures of normal equations are studied depending on whether there are shared image parameters to be optimized or not, and corresponding sparse solutions of the normal equations and parameter covariance matrices are derived. Compared with the traditional sparse bundle adjustment method, simulated experiments demonstrate that our method matches the error model of the target scenario, and thus can avoid further accuracy loss. Moreover, both simulated and real data experiments demonstrate that our method can effectively improve computational efficiency.

Surgical Guides and Prebent Titanium Improve the Planning for the Treatment of Dentofacial Deformities Secondary to Condylar Osteochondroma.

PURPOSE: To investigate current Computer-Aided Design and Computer-Aided Manufacturing (CAD/CAM) technologies applied in the treatment of dentofacial deformities secondary to condylar osteochondroma and introduce a modified method with additional pre-bent titanium miniplates to improve the accuracy of operation. METHODS: Literature review about the application of CAD/CAM in the treatment of condylar osteochondroma and secondary dentofacial deformities was conducted. And 8 patients with condylar osteochondroma and secondary dentofacial deformities were treated by the CAD/CAM cutting and drilling surgical guides as well as pre-bent titanium miniplates. Pre- and post-operative 3D-cephalometric measurement were recorded and the difference between virtual simulation and postoperative modeling images was measured. Follow-up and radiographic examinations were performed. RESULTS: A total of 17 studies (including 216 patients) about the application of CAD/CAM in the treatment of dentofacial deformities secondary to condylar osteochondroma have been reported since 2010, including the 8 present patients. In our study, all patients were satisfied with the surgical outcome, without obvious relapse or evidence of temporomandibular joint disorder or other complications during follow-up; all patients avoided condylar reconstruction and sagittal split of ramus osteotomy on the ipsilateral mandible side. Comparison between simulated plans and actual postoperative outcomes showed surgical simulation plan was accurately transferred to the actual surgery. CONCLUSIONS: The application of CAD/CAM cutting and drilling guides as well as pre-bent titanium plates could achieve more accurate and favorable outcomes, improving the clinical planning and surgical execution for patients with condylar osteochondroma and secondary dentofacial deformities.

Establishment of a three-dimensional coordinate system for measuring the recurrence rate after orthognathic surgery and evaluation and analysis of the degree of recurrence / 口腔疾病防治

Objective@# To establish a three-dimensional coordinate system that can accurately measure the recurrence rate after orthognathic surgery, and evaluate and analyze the degree of recurrence.@*Methods @#Data from patients who underwent orthognathic surgery in a hospital were selected to reconstruct three-dimensional images with spiral CT. The two researchers used the multiplane assisted positioning method to fix the points three times and screened them using intra-andintreclass correlation coefficients (ICC). Reproducible and accurate landmark points were drawn to establish different coordinate systems and calculate the facial asymmetry index (AI) to determine the coordinate system with the best mid-sagittal plane symmetry. This coordinate system and lateral radiographs were used to separately measure the recurrence rate, and evaluate and analyze the three-dimensional recurrence degree of orthognathic surgery.@*Results @#Ten landmark points that may be repeatedly fixed were obtained, including N (nasion), K (K point), ANS(anterior nasal spine), PNS (posterior nasal spine), Ptm(pterygomaxillary fissure), Gn (gnathion), IZ(IZ point), MZ (MZ point), Ms (mastoideale), Cor (coronion) and and Go (gonion). Three coordinate systems were established, and the most suitable coordinate system was the upper edge point of the left infraorbital foramen. The inner upper edge of the right infraorbital foramen and both sides of the midpoint of the ear points constituted the horizontal plane (HP), which passed through the outermost point of the left zygomatic frontal suture and the outermost point of the right zygomatic frontal suture and was perpendicular to the horizontal plane to constitute the coronal plane (CP). It was perpendicular to the two planes to form a sagittal plane (SP). Two-dimensional and three-dimensional measurements of recurrence were performed on 112 patients, and new three-dimensional recurrence evaluation results were obtained. Less than 40% had low recurrence, 40% to 61% had moderate recurrence, and greater than 61% had high recurrence.@*Conclusion@#This study established a three-dimensional coordinate system suitable for measuring the recurrence rate after orthognathic surgery, obtained a new three-dimensional recurrence evaluation result, and provided a clinical experimental basis for evaluating the effect of orthognathic surgery and improving stability.

Relative pose estimation of uncooperative spacecraft using 2D-3D line correspondences.

The relative pose estimation of uncooperative spacecraft is an essential technology in space missions. However, lacking the prior knowledge of uncooperative targets brings great challenges to accurately measure their pose, which hinders their application in space. To overcome these problems, an accurate and robust pose estimation approach for uncooperative spacecraft is proposed based on a time-of-flight camera coupled with a gray-scale camera. We reconstruct the target model using our hierarchical registration strategy by the ToF camera and extract 2D lines from image sequences captured by the gray-scale camera. We attempt to establish 2D-3D line correspondences for pose estimation, which effectively associates the 2D image information with the reconstructed 3D model. Experimental results manifest that, when dealing with a completely unknown model, our method computes its relative position and attitude with significantly high accuracy.

Smart Porous Scaffold Promotes Peri-Implant Osteogenesis under the Periosteum.

Background: Adequate peri-implant bone mass and bone quality are essential factors to ensure the initial stability of the implant and success of implant operation. In clinical settings, the lack of bone mass often restricts the implant operation. In this study, we fabricated a smart porous scaffold with a shape memory function and investigated whether it could promote peri-implant osteogenesis under the periosteum. Methods: A porous shape memory polymer (SMP) scaffold was fabricated and its shape memory function, mechanical properties, and degradation rate were tested in vitro. Moreover, the scaffold was implanted in the mandible of rabbits to evaluate its efficacy to promote peri-implant osteogenesis in the periosteum and enhance the initial stability of the implant. Histological, micro-CT, and biomechanical analyses were carried out for further verification. Results: The SMP scaffold has a good shape memory function and biocompatibility in vitro. In vivo experiments demonstrated that the SMP scaffold could recover to its original shape after implantation to create a small gap in the periosteum. After 12 weeks, the scaffold was gradually replaced by a newly formed bone, and the stability of the implant increased when it implanted with the scaffold. Conclusion: The present study indicates that the SMP scaffolds have a good shape memory function and could enhance peri-implant bone formation under the periosteum. The SMP scaffold provides a clinical potential candidate for bone tissue engineering under the periosteum.

Automatic three-dimensional measurement of large-scale structure based on vision metrology.

All relevant key techniques involved in photogrammetric vision metrology for fully automatic 3D measurement of large-scale structure are studied. A new kind of coded target consisting of circular retroreflective discs is designed, and corresponding detection and recognition algorithms based on blob detection and clustering are presented. Then a three-stage strategy starting with view clustering is proposed to achieve automatic network orientation. As for matching of noncoded targets, the concept of matching path is proposed, and matches for each noncoded target are found by determination of the optimal matching path, based on a novel voting strategy, among all possible ones. Experiments on a fixed keel of airship have been conducted to verify the effectiveness and measuring accuracy of the proposed methods.