Automatic three-dimensional facial symmetry reference plane construction based on facial planar reflective symmetry net.

OBJECTIVES: Three-dimensional (3D) facial symmetry analysis is based on the 3D symmetry reference plane (SRP). Artificial intelligence is widely used in the dental and oral sciences. This study developed a novel deep learning model called the facial planar reflective symmetry net (FPRS-Net) to automatically construct an SRP and established a method for defining a 3D point-cloud region of interest (ROI) and high-dimensional feature computations suitable for this network model. METHODS: Overall, 240 patients were enrolled. The deep learning model was trained and predicted using 200 samples, and its clinical suitability was evaluated with 40 samples. Four FPRS-Net models were prepared, each using supervised and unsupervised learning approaches based on full facial and ROI data (FPRS-NetS, FPRS-NetSR, FPRS-NetU, and FPRS-NetUR). These models were trained on 160 3D facial datasets, validated on 20 cases, and tested on another 20 cases. The model predictions were evaluated using an additional 40 clinical 3D facial datasets by comparing the mean square error of the SRP between the parameters predicted by the four FPRS-Net models and the truth plane. The clinical suitability of FPRS-Net models was evaluated by measuring the angle error between the predicted and ground-truth planes; experts evaluated the predicted SRP of the four FPRS-Net models using the visual analogue scales (VAS) method. RESULTS: The FPRS-NetSR and FPRS-NetU models achieved an average angle error of 0.84° and 0.99° in predicting 3D facial SRP, respectively, with a VAS value of >8. Using the four FPRS-Net models to create an SRP in 40 cases of 3D facial data required <4 s. CONCLUSIONS: Our study demonstrated a new solution for automatically constructing oral clinical 3D facial SRPs. CLINICAL SIGNIFICANCE: This study proposes an innovative deep learning algorithm (FPRS-Net) to construct a symmetry reference plane that can reduce workload, shorten the time required for digital design, reduce dependence on expert experience, and improve therapeutic efficiency and effectiveness in dental clinics.

Automatic extraction of facial median sagittal plane for patients with asymmetry based on the EDMA alignment algorithm.

BACKGROUND: We aimed to establish a novel method for automatically constructing three-dimensional (3D) median sagittal plane (MSP) for mandibular deviation patients, which can increase the efficiency of aesthetic evaluating treatment progress. We developed a Euclidean weighted Procrustes analysis (EWPA) algorithm for extracting 3D facial MSP based on the Euclidean distance matrix analysis, automatically assigning weight to facial anatomical landmarks. METHODS: Forty patients with mandibular deviation were recruited, and the Procrustes analysis (PA) algorithm based on the original mirror alignment and EWPA algorithm developed in this study were used to construct the MSP of each facial model of the patient as experimental groups 1 and 2, respectively. The expert-defined regional iterative closest point algorithm was used to construct the MSP as the reference group. The angle errors of the two experimental groups were compared to those of the reference group to evaluate their clinical suitability. RESULTS: The angle errors of the MSP constructed by the two EWPA and PA algorithms for the 40 patients were 1.39 ± 0.85°, 1.39 ± 0.78°, and 1.91 ± 0.80°, respectively. The two EWPA algorithms performed best in patients with moderate facial asymmetry, and in patients with severe facial asymmetry, the angle error was below 2°, which was a significant improvement over the PA algorithm. CONCLUSIONS: The clinical application of the EWPA algorithm based on 3D facial morphological analysis for constructing a 3D facial MSP for patients with mandibular deviated facial asymmetry deformity showed a significant improvement over the conventional PA algorithm and achieved the effect of a dental clinical expert-level diagnostic strategy.

Spatial Trueness Evaluation of 3D-Printed Dental Model Made of Photopolymer Resin: Use of Special Structurized Dental Model.

(1) Background: Various 3D printers are available for dental practice; however, a comprehensive accuracy evaluation method to effectively guide practitioners is lacking. This in vitro study aimed to propose an optimized method to evaluate the spatial trueness of a 3D-printed dental model made of photopolymer resin based on a special structurized dental model, and provide the preliminary evaluation results of six 3D printers. (2) Methods: A structurized dental model comprising several geometrical configurations was designed based on dental crown and arch measurement data reported in previous studies. Ninety-six feature sizes can be directly measured on this original model with minimized manual measurement errors. Six types of photo-curing 3D printers, including Objet30 Pro using the Polyjet technique, Projet 3510 HD Plus using the Multijet technique, Perfactory DDP and DLP 800d using the DLP technique, Form2 and Form3 using the SLA technique, and each printer's respective 3D-printable dental model materials, were used to fabricate one set of physical models each. Regarding the feature sizes of the simulated dental crowns and dental arches, linear measurements were recorded. The scanned digital models were compared with the design data, and 3D form errors (including overall 3D deviation; flatness, parallelism, and perpendicularity errors) were measured. (3) Results: The lowest overall 3D deviation, flatness, parallelism, and perpendicularity errors were noted for the models printed using the Objet30 Pro (overall value: 45 µm), Form3 (0.061 ± 0.019 mm), Objet30 Pro (0.138 ± 0.068°), and Projet 3510 HD Plus (0.095 ± 0.070°), respectively. In color difference maps, different deformation patterns were observed in the printed models. The feature size proved most accurate for the Objet30 Pro fabricated models (occlusal plane error: 0.02 ± 0.36%, occlusogingival direction error: -0.06 ± 0.09%). (4) Conclusions: The authors investigated a novel evaluation approach for the spatial trueness of a 3D-printed dental model made of photopolymer resin based on a structurized dental model. This method can objectively and comprehensively evaluate the spatial trueness of 3D-printed dental models and has a good repeatability and generalizability.

Chairside digital design and manufacturing method for children's band and loop space maintainers.

OBJECTIVES: This study proposes a chairside digital design and manufacturing method for band and loop space maintainers and preliminarily validates its clinical feasibility. METHODS: Clinical cases of 10 children requiring space maintenance caused by premature loss of primary teeth were collected. Intraoral scan data of the affected children were also collected to establish digital models of the missing teeth. Using a pediatric band and loop space maintainer design software developed by our research team, a rapid personalized design of band and loop structures was achieved, and a digital model of an integrated band and loop space maintainer was ultimately generated. A chairside space maintainer was manufactured through metal computer numerical control machining for the experimental group, whereas metal 3D printing in the dental laboratory was used for the control group. A model fitting assessment was conducted for the space maintainers of both groups, and senior pediatric dental experts were invited to evaluate the clinical feasibility of the space maintainers with regard to fit and stability using the visual analogue scale scoring system. Statistical analysis was also performed. RESULTS: The time spent in designing and manufacturing the 10 space maintainers of the experimental group was all less than 1 h. Statistical analysis of expert ratings showed that the experimental group outperformed the control group with regard to fit and stability. Both types of space maintainers met clinical requirements. CONCLUSIONS: The chairside digital design and manufacturing method for pediatric band and loop space maintainers proposed in this study can achieve same-day fitting of space maintainers at the first appointment, demonstrating good clinical feasibility and significant potential for clinical application.

3D facial mask for facial asymmetry diagnosis.

Objectives: Facial asymmetry is a common problem seen in orthodontic clinics that may affect patient esthetics. In some instances, severe asymmetry that affects patient esthetics may cause psychological issues. An objective method is therefore required to help orthodontists identify asymmetry issues. Materials and methods: We used three-dimensional (3D) facial images and landmark-based anthropometric analysis to construct a 3D facial mask to evaluate asymmetry. The landmark coordinates were transformed using a symmetric 3D face model to evaluate the efficacy of this method. Patients with facial asymmetry were recruited to conduct mirror and overlap analysis to form color maps, which were used to verify the utility of the novel soft tissue landmark-based method. Results: The preliminary results demonstrated that the asymmetry evaluation method had a similar response rate compared to diagnosis using mirror and overlap 3D images, and could therefore identify 3D asymmetry problems. Conclusions: By using 3D facial scans and 3D anthropometric analysis, we developed a preliminary evaluation method that provides objective parameters to clinically evaluate patient facial asymmetry and aid in the diagnosis of asymmetric areas. Clinical relevance: This study presents a novel facial asymmetry diagnostic method that has the potential to aid clinical decisions during problem identification, treatment planning, and efficacy evaluation.

Three-Dimensional Virtual Reconstruction of External Nasal Defects Based on Facial Mesh Generation Network.

(1) Background: In digital-technology-assisted nasal defect reconstruction methods, a crucial step involves utilizing computer-aided design to virtually reconstruct the nasal defect's complete morphology. However, current digital methods for virtual nasal defect reconstruction have yet to achieve efficient, precise, and personalized outcomes. In this research paper, we propose a novel approach for reconstructing external nasal defects based on the Facial Mesh Generation Network (FMGen-Net), aiming to enhance the levels of automation and personalization in virtual reconstruction. (2) Methods: We collected data from 400 3D scans of faces with normal morphology and combined the structured 3D face template and the Meshmonk non-rigid registration algorithm to construct a structured 3D facial dataset for training FMGen-Net. Guided by defective facial data, the trained FMGen-Net automatically generated an intact 3D face that was similar to the defective face, and maintained a consistent spatial position. This intact 3D face served as the 3D target reference face (3D-TRF) for nasal defect reconstruction. The reconstructed nasal data were extracted from the 3D-TRF based on the defective area using reverse engineering software. The '3D surface deviation' between the reconstructed nose and the original nose was calculated to evaluate the effect of 3D morphological restoration of the nasal defects. (3) Results: In the simulation experiment of 20 cases involving full nasal defect reconstruction, the '3D surface deviation' between the reconstructed nasal data and the original nasal data was 1.45 ± 0.24 mm. The reconstructed nasal data, constructed from the personalized 3D-TRF, accurately reconstructed the anatomical morphology of nasal defects. (4) Conclusions: This paper proposes a novel method for the virtual reconstruction of external nasal defects based on the FMGen-Net model, achieving the automated and personalized construction of the 3D-TRF and preliminarily demonstrating promising clinical application potential.

[Preliminary evaluation of chin symmetry with three dimentional soft tissue spatial angle wireframe template].

OBJECTIVE: To develop an efficient and robust method based on three dimensional facial landmarks for evaluating chin region asymmetry at the soft tissue level and to compare it with the traditional mirror-overlap analysis method in order to test its availability. METHODS: Standard symmetrical face was used for mental tubercle coordinate transformation so as to filter soft tissue three dimensional spatial angle and construct corresponding three dimensional spatial angle wireframe template. Ten patients aged 12-32 years with clinical chin region asymmetry diagnosis at the Department of Orthodontics of Peking University Hospital of Stomatology from November 2020 to November 2021 were randomly selected. Three dimensional soft tissue face scan data of the patients were collected by three dimensional face scanner and the landmark points were automatically determined by the Meshmonk non-rigid registration algorithm program, and in this way, the asymmetric three dimensional spatial angle wireframe template and corresponding spatial angle parameters were generated. Mirror-overlap analysis of face scan data was also performed in Geomagic Studio 2015 software and deviation color maps were generated. This study took mirror-overlap analysis as the gold standard method, the response rate of chin region asymmetry was eva-luated by the outcomes of the mirror-overlap analysis and three dimensional spatial angle wireframe template analysis. RESULTS: Nine three dimensional spatial angle indicators were selected through coordinate transformation, and the response rate was calculated using mirror-overlap analysis as the gold standard method. Among these ten selected patients, the response rate of the total chin region asymmetry was 90% (9/10). Using the deviation value of mirror-overlap analysis as a reference, the response rate of chin region asymmetry in the X dimension was 86%, the response rate of chin region asymmetry in the Y dimension was 89%, and the response rate of chin region asymmetry in the Z dimension was 100%. CONCLUSION: The three dimensional soft tissue spatial angle wireframe template proposed in this study has some feasibility in evaluating chin region asymmetry at the soft tissue level, and its ability to recognize asymmetry separately in the three dimensional direction is better than the mirror-overlap analysis method, and the indicators recognition rate still needs to be further improved.

Comparison Study of Extraction Accuracy of 3D Facial Anatomical Landmarks Based on Non-Rigid Registration of Face Template.

(1) Background: Three-dimensional (3D) facial anatomical landmarks are the premise and foundation of facial morphology analysis. At present, there is no ideal automatic determination method for 3D facial anatomical landmarks. This research aims to realize the automatic determination of 3D facial anatomical landmarks based on the non-rigid registration algorithm developed by our research team and to evaluate its landmark localization accuracy. (2) Methods: A 3D facial scanner, Face Scan, was used to collect 3D facial data of 20 adult males without significant facial deformities. Using the radial basis function optimized non-rigid registration algorithm, TH-OCR, developed by our research team (experimental group: TH group) and the non-rigid registration algorithm, MeshMonk (control group: MM group), a 3D face template constructed in our previous research was deformed and registered to each participant's data. The automatic determination of 3D facial anatomical landmarks was realized according to the index of 32 facial anatomical landmarks determined on the 3D face template. Considering these 32 facial anatomical landmarks manually selected by experts on the 3D facial data as the gold standard, the distance between the automatically determined and the corresponding manually selected facial anatomical landmarks was calculated as the "landmark localization error" to evaluate the effect and feasibility of the automatic determination method (template method). (3) Results: The mean landmark localization error of all facial anatomical landmarks in the TH and MM groups was 2.34 ± 1.76 mm and 2.16 ± 1.97 mm, respectively. The automatic determination of the anatomical landmarks in the middle face was better than that in the upper and lower face in both groups. Further, the automatic determination of anatomical landmarks in the center of the face was better than in the marginal part. (4) Conclusions: In this study, the automatic determination of 3D facial anatomical landmarks was realized based on non-rigid registration algorithms. There is no significant difference in the automatic landmark localization accuracy between the TH-OCR algorithm and the MeshMonk algorithm, and both can meet the needs of oral clinical applications to a certain extent.

3D-printed titanium surgical guides for extraction of horizontally impacted lower third molars.

OBJECTIVES: This prospective study introduced a digitally designed sectioning guide and evaluated its feasibility for the extraction of horizontally impacted lower third molars. MATERIALS AND METHODS: This study included 38 horizontally impacted lower third molars, randomly divided into experimental and control groups. The teeth were extracted using a 3D-printed titanium surgical guide in the experimental group; free-hand extractions were performed in the control group. The surgical duration, tooth sectioning duration, cortical bone perforation, and postoperative complications, including pain, swelling, trismus, dry socket, infection, and hemorrhage, were evaluated. RESULTS: Although not statistically significant, guided surgery tended to reduce the number of tooth sectioning steps compared to free-hand extractions. There were no cases of cortical bone perforation in the experimental group. Although the surgical duration was greater in the experimental group (p < 0.05), there were no differences in postoperative pain, swelling, and trismus. There were no cases of postoperative infection and hemorrhage in either group. CONCLUSIONS: 3D-printed titanium surgical guides had superior accuracy and safety compared to free-hand surgery. Further studies with larger sample sizes are required to verify these findings. CLINICAL RELEVANCE: The template improved the safety of tooth sectioning during impacted lower third molar surgery and resulted in a more predictable extraction. The narrow sectioning groove could fit comfortably with hypertrophic soft tissues in the posterior mandible.

Digital versus radiographic accuracy evaluation of guided implant surgery: an in vitro study.

BACKGROUND: Cone-beam computed tomography (CBCT) is the most widely used method for postsurgical evaluation of the accuracy of guided implant surgery. However, the disadvantages of CBCT include radiation exposure, artifacts caused by metal implants, and high cost. Few studies have introduced a digital registration method to replace CBCT for evaluating the accuracy of guided surgery. The purpose of this study was to compare digital registration to conventional CBCT in terms of the capacity to evaluate the implant positioning accuracy of guided surgery. MATERIALS AND METHODS: This in vitro study included 40 acrylic resin models with posterior single mandibular tooth loss. Guided surgery software was used to determine the optimal implant position; 40 tooth-supported fully guided drilling templates were designed and milled accordingly. After the guided surgery, the accuracies of the surgical templates were evaluated by conventional CBCT and digital registration. For evaluation by conventional CBCT, postsurgical CBCT scans of the resin models were performed. The CBCT data were reconstructed and superimposed on the implant planning data. For digital registration, we constructed a virtual registration unit that consisted of an implant replica and a scan body. Next, we obtained postsurgical optical scans of resin models with the scan body. The postsurgical implant position was identified by superimposition of the registration unit and optical scan data. The implant planning data and postsurgical implant position data were superimposed; deviations were reported in terms of distance for implant entry/apex point and in terms of angle for the implant axis. Interclass correlation coefficients (ICCs) and Bland-Altman plots were used to analyze the agreement between the two evaluation methods. RESULTS: The ICCs between the two methods were 0.986, 0.993, and 0.968 for the entry point, apex point, and angle, respectively; all were significantly greater than 0.75 (p < 0.001). Bland-Altman plots showed that the 95% limits of agreement of the differences were - 0.144 to + 0.081 mm, - 0.135 to + 0.147 mm, and - 0.451° to + 0.729° for the entry point, apex point, and angle, respectively; all values were within the maximum tolerated difference. CONCLUSION: Conventional CBCT and digital registration showed good agreement in terms of evaluating the accuracy of implant positioning using tooth-supported surgical templates.

A mathematical algorithm of the facial symmetry plane: Application to mandibular deformity 3D facial data.

The three-dimensional (3D) symmetry reference plane (SRP) is the premise and basis of 3D facial symmetry analysis. Currently, most methods for extracting the SRP are based on anatomical landmarks measured manually using a digital 3D facial model. However, as different clinicians have varying definitions of landmarks, establishing common methods suitable for different types of facial asymmetry remains challenging. The present study aimed to investigate and evaluate a novel mathematical algorithm based on power function weighted Procrustes analysis (PWPA) to determine 3D facial SRPs for patients with mandibular deviation. From 30 patients with mandibular deviation, 3D facial SRPs were determined using both our PWPA algorithms (two functions) and the traditional PA algorithm (experimental groups). A reference plane, defined by experts, was considered the 'truth plane'. The 'position error' index of mirrored landmarks was created to quantitatively evaluate the difference among the PWPA SRPs and the truth plane, including overall differences and regional differences of the face (upper, middle and lower). The 'angle error' values between the SRPs and the truth plane in the experimental groups were also evaluated in this study. Statistics and measurement analyses were used to comprehensively evaluate the clinical suitability of the PWPA algorithms to construct the SRP. The average angle error values between the PWPA SRPs of the two functions and the truth plane were 1.21 ± 0.65° and 1.18 ± 0.62°, which were smaller than those between the PA SRP and the truth plane. The position error values of mirrored landmarks constructed using the PWPA algorithms for the whole face and for each facial partition were lower than those constructed using the PA algorithm. In conclusion, for patients with mandibular deviation, this novel mathematical algorithm provided a more suitable SRP for their 3D facial model, which achieved a result approaching the true effect of experts.

A novel method for 3D face symmetry reference plane based on weighted Procrustes analysis algorithm.

BACKGROUND: We aimed to establish a novel method, using the weighted Procrustes analysis (WPA) algorithm, which assigns weight to facial anatomical landmarks, to construct a three-dimensional facial symmetry reference plane (SRP) for mandibular deviation patients. METHODS: Three-dimensional facial SRPs were independently extracted from 15 mandibular deviation patients using both our WPA algorithm and the standard PA algorithm. A reference plane was defined to serve as the ground truth. To determine whether the WPA SRP or the PA SRP was closer to the ground truth, we measured the position error of mirrored landmarks, the facial asymmetry index (FAI) error, and the angle error for the global face and each facial third partition. RESULTS: The average angle error between the WPA SRP and the ground truth was 1.66 ± 0.81°, which was smaller than that between the PA SRP and the ground truth. The position error of the mirrored landmarks constructed using the WPA algorithm in the global face (3.64 ± 1.53 mm) and each facial partition was lower than that constructed using the PA algorithm. The average FAI error of the WPA SRP was - 7.77 ± 17.02 mm, which was smaller than that of the PA SRP. CONCLUSIONS: This novel automatic algorithm, based on weighted anatomic landmarks, can provide a more adaptable SRP than the standard PA algorithm when applied to severe mandibular deviation patients and can better simulate the diagnosis strategies of clinical experts.