Improving Cranial Vault Remodeling for Unilateral Coronal Craniosynostosis-Introducing Automated Surgical Planning.

Study Design: Cranial vault remodeling (CVR) for unicoronal synostosis is challenging due to the asymmetric nature of the deformity. Computer-automated surgical planning has demonstrated success in reducing the subjectivity of decision making in CVR in symmetric subtypes. This proof of concept study presents a novel method using Boolean functions and image registration to automatically suggest surgical steps in asymmetric craniosynostosis. Objective: The objective of this study is to introduce automated surgical planning into a CVR virtual workflow for an asymmetric craniosynostosis subtype. Methods: Virtual workflows were developed using Geomagic Freeform Plus software. Hausdorff distances and color maps were used to compare reconstruction models to the preoperative model and a control skull. Reconstruction models were rated as high or low performing based on similarity to the normal skull and the amount of advancement of the frontal bone (FB) and supra-orbital bar (SOB). Fifteen partially and fully automated workflow iterations were carried out. Results: FB and SOB advancement ranged from 3.08 to 10.48 mm, and -1.75 to 7.78 mm, respectively. Regarding distance from a normal skull, models ranged from .85 to 5.49 mm at the FB and 5.40 to 10.84 mm at the SOB. An advancement of 8.43 mm at the FB and 7.73 mm at the SOB was achieved in the highest performing model, and it differed to a comparative normal skull by .02 mm at the FB and .48 mm at the SOB. Conclusions: This is the first known attempt at developing an automated virtual surgical workflow for CVR in asymmetric craniosynostosis. Key regions of interest were outlined using Boolean operations, and surgical steps were suggested using image registration. These techniques improved post-operative skull morphology.

Intraoperative Real-Time Image-Guided Fibular Harvest and Mandibular Reconstruction: A Feasibility Study on Cadaveric Specimens.

BACKGROUND: This study assesses the feasibility of real-time surgical navigation to plan and guide sequential steps during mandible reconstruction on a series of cadaveric specimens. METHODS: An image-guided surgical (IGS) system was designed including customized mandible and fibula fixation devices with navigation reference frames and an accompanied image-guided software. The mandibular and fibular segmental osteotomies were performed using the IGS in all five cadaveric patients. Procedural time and cephalometric measurements were recorded. RESULTS: Five real-time IGS mandibulectomy and fibular reconstruction were successfully performed. The mean Dice score and Hausdorff-95 distance between the planned and actual mandible reconstructions was 0.8 ± 0.08 and 7.29 ± 4.81 mm, respectively. Intercoronoid width, interangle width, and mandible projection differences were 1.15 ± 1.17 mm, 0.9 ± 0.56 mm, and 1.47 ± 1.62 mm, respectively. CONCLUSION: This study presents the first demonstration of a comprehensive image-guided workflow for mandibulectomy and fibular flap reconstruction on cadaveric specimens and resulted in adequate cephalometric accuracy.

Exploring the use of Virtual Surgical Planning (VSP) in Maxillofacial Reconstructions.

Background: Virtual surgical planning (VSG), also known as computer-assisted reconstruction, has started to become the norm for more complex patients in many centers in recent times. Aim: This study was conducted to evaluate the VSG in maxillofacial reconstruction surgery. Methods and Materials: This study included 20 patients who underwent surgery for maxillofacial reconstruction. The study participants were divided into two main categories: Category 1: Conventional surgical planning (CSG). Category 2: VSG. The surgical planning in both categories, including the evaluation of volume of defect, length, width, and height of graft, to be placed. Results: The gap between defect to be reconstructed and graft placed was greater in CSG as compared to VSG. The distance of graft from actual location was lesser in VSG as compared to CSG. The findings were significant statistically. Frequency of success was 93.21% and 97.47%, respectively. The frequency of success was greater in VSG as compared to CSG. Conclusion: Virtual surgical planning is more effective in maxillofacial reconstruction surgery.

Mandible-First and Maxilla-First Sequencing in Virtual Surgical Planning for Orthognathic Surgery: Comparison of Planned and Actual Outcomes.

Background: Recent studies have shown that virtual planning for orthognathic surgery is an accurate and repeatable method. It is also a fact that surgical sequence can affect the results in terms of accuracy. Various studies stated that both approaches offer comparable results when properly planned and implemented; however, further clinical studies are still needed. This study aims to evaluate the effect of virtual surgical planning (VSP) on surgical outcomes and whether it is affected by mandible-first or maxilla-first approaches. Methods: This study analyzed data from 45 patients who underwent orthognathic surgery due to dentofacial deformity. Six of these patients underwent single-jaw orthognathic surgery, and 39 underwent bimaxillary orthognathic surgery (Maxilla-first group: 21, mandible-first group: 18). The displacements of specific landmarks were assessed by comparing preoperative and postoperative conventional computed tomographies with VSP data. Results: This study showed a statistically significant relationship between the measurements made with the 2 methods (r = .944; P = .0001). The fact that the intra-class correlation coefficient value is statistically significant and relatively high and that most of the differences in the Bland-Altman chart fall between the limits of compliance indicates a correlation between the virtual plan and surgical outcomes. In addition, in vertical measurements, the absolute mean difference of the B point and the Pogonion in the Maxilla-first group were statistically significantly higher than in the Mandible-first group (P = .038, P = .011). Conclusions: Our findings corroborate the high accuracy of the VSP reported in previous studies and also demonstrate that VSP with both maxilla-first and mandible-first sequencing achieves high accuracy in the sagittal and coronal planes. Although virtual planning significantly influences accurate surgical outcomes, it is not the sole determinant. Factors like condylar positioning and fixation methods can also impact the final results.

Dura-based automated vault expansion remodelling (DAVE-R): automated planning of volume expansion in fronto-orbital advancement for trigonocephaly.

Cranial vault remodelling for craniosynostosis aims to increase intracranial volume to facilitate brain growth, avoid the development of raised intracranial pressure and address cosmesis. The extent of vault expansion is predominantly limited by scalp closure and reconstruction technique. Virtual surgical planning tools have been developed to predict post-operative changes and guide expansion. We present a validation study of a novel 'Dura-based Automated Vault Expansion-Remodeling' (DAVE-R) model to guide pre-operative planning for fronto-orbital advancement and remodelling (FOAR). METHODS: Patients with trigonocephaly who underwent FOAR with pre- and post-operative imaging from 2018 to 2020 were identified from a prospectively maintained database. Post-operative scans, normative atlas and whole brain parcellation were registered to the pre-operative images to quantify the change in intracranial volume and morphology (utilising measurement of fronto-orbital advancement and bifrontozygomatic distance) compared to that predicted by the DAVE-R model. RESULTS: Ten patients were included. The DAVE-R model predicted bifrontozygomatic distances of 92.0 + / - 5.14 mm (mean + /SD), which closely matched the post-operative results of 92.7 + / - 6.02 mm (mean + / - SD); (t(d.f. 9) = -0.306, p = 0.77). The fronto-orbital advancement predicted by the DAVE-R method was 11.5 + / - 1.96 mm (mean + / - SD) which was significantly greater than 8.6 + / - 2.94 mm (mean ± SD); (t(d.f. 9) = 3.137, p = 0.01) achieved post-operatively. CONCLUSIONS: We demonstrate that the DAVE-R model provides an objective means of extracting realistic surgical goals in patients undergoing FOAR for trigonocephaly that closely correlates with post-operative outcomes. The normative dural model warrants further study and validation for other forms of craniosynostosis correction.

Sacroiliac joint fusion guided by intraoperatively superimposed virtual surgical planning using simulated fluoroscopic images.

Introduction: Sacroiliac joint fusion (SIJF) is a minimally invasive treatment for sacroiliac (SI) dysfunction. It involves placing implants through the SI joint under fluoroscopic guidance, requiring precise implant positioning to avoid nerve injury. Preoperative virtual surgical planning (VSP) aids in optimal positioning, but replicating it accurately in the operating room is challenging. Research question: This study aims to assess the feasibility of superimposing VSP onto intraoperative fluoroscopic images to aid in optimal implant placement. Material and methods: A method for intraoperative guidance using 3D/2D registration was developed and tested during SIJF as an available and potentially efficient alternative for costly and more invasive navigation systems. Preoperatively, a VSP is performed and simulated fluoroscopic images are generated from a preoperative CT scan. During surgery, the simulated image that visually best matches the intraoperative fluoroscopic image is selected. Subsequently, the VSP is superimposed onto the intraoperative fluoroscopic image using a developed script-based workflow. The surgeon then places the implants accordingly. Postoperative implant placement accuracy was evaluated. Results: Five interventions were performed on five patients, resulting in a total of 15 placed implants. Minor complications without clinical consequences occurred in one case, primarily attributable to the patient's anatomy and pathological manifestations. Mean deviations at implant apex and 3D angle were 4.7 ± 1.6 mm and 3.5 ± 1.3°, respectively. Discussion and conclusions: The developed intraoperative workflow was feasible and resulted in implants placed with low deviations from the VSP. Further research is needed to automate and validate this method in a larger cohort.

PSI: Planner-specific, physician-specific, or patient-specific implant for orbital reconstruction?

This study aimed to identify and quantify the variations in PSI designs intended for an identical patient. Records from 10 patients with an orbital fracture involving two walls, for which a primary orbital reconstruction was indicated, were retrospectively included. Clinical engineers from two centers independently generated proposal designs for all patients. Following web meeting(s) with the surgeon from the same institute, the PSI designs were finalized by the engineer. A cross-over of the engineer with the surgeon of the other center created two new design teams. In total, 20 proposal and 40 final PSI designs were produced. A three-dimensional comparison between different PSI designs for the same patient was performed by computing a difference score. Initially, the design proposals of the two engineers showed a median difference score of 37%, which was significantly reduced to a median difference score of 26% for the final designs with different engineers. The median difference score of 22% between surgeons demonstrated that both parties introduced notable user variations to the final designs. Evidence supporting the advantages of an experienced design team was found, with significantly fewer modifications, fewer meetings, and less time required to complete the design (up to 40% time reduction). The findings of the study underline the dependency of PSI design on the surgeon and engineer, and support the need for a more evidence-based protocol for PSI design.

Virtual surgical planning in orthognathic surgery: A prospective evaluation of postoperative accuracy.

OBJECTIVES: The development of 3D computer-assisted technologies over the past years has led to vast improvements in orthognathic surgery. The aim of the present study was to evaluate differences in maxillary position between 3D virtual surgical planning (VSP) and surgical results. MATERIALS AND METHODS: We assessed data from 25 patients who underwent bimaxillary non-segmented orthognathic surgery with 3D VSP. Each patient underwent a postoperative CT scan within 40 days after surgery. We compared the STL (Standard Triangulation Language) file from the VSP with that obtained from the postoperative CT. RESULTS: According to our comparative analysis, the postoperative and VSP 3D models did not statistically differ. The Lin concordance correlation coefficient was always >0.95 for each landmark, but in 21 patients (84 % of the sample) we identified at least one point with a difference of more than 1.5 mm between the postoperative and VSP 3D model on at least one axis. The most frequently observed differences corresponded to sagittal translation and pitch rotation. CONCLUSIONS: An intraoperative clinical and aesthetic evaluation of the consequences of bone movements on patient face is strongly recommended, also when we use VSP because we may have clinically significant differences from the planning.

Three-Dimensional Heart Modeling of Hypertrophic Obstructive Cardiomyopathy for In Situ Patient-Specific Simulation to Optimize Septal Myectomy.

OBJECTIVE: Hypertrophic obstructive cardiomyopathy (HOCM) develops in at least 1 out of 715 young adults. Patients who are refractory to medical therapy qualify for septal myectomy. Due to anatomy, serious complications such as ventricular septal defect and heart block may occur. Establishing cardiovascular magnetic resonance (CMR)-based 3-dimensional (3D) models as part of preoperative planning and training has the potential to decrease procedure-related complications and improve results. METHODS: CMR images were used to segment cardiac structures. Left ventricular wall thickness was calculated and projected on top of the in silico model. A 3D model was printed with a red layer indicating a wall thickness exceeding 15 mm and used for preoperative resection planning and patient counseling. To provide preoperative patient-specific in situ simulation, the planned resection volume was replaced with silicone in a second model. For perioperative quality control, resected silicone was compared with resected myocardial tissue. The impact of the models was evaluated descriptively through consultation of both the cardiothoracic surgeon and patients and through patient outcomes. RESULTS: Three-dimensional in silico and 3D-printed heart models of 5 patients were established preoperatively. Since the introduction of the models in October 2020, the surgeon feels better prepared, more confident, and less difficulty with making decisions. In addition, patients feel better informed preoperatively. CONCLUSIONS: Using 3D heart models optimized preoperative planning and training, intraoperative quality control, and patient consultation. Reduction of procedure-related complications and clinical outcome should be studied in larger cohorts.

Reduction Cranioplasty in Cases of Hydrocephalic Macrocephaly: Pearls and Pitfalls of Computer-Assisted Surgery.

Reduction cranioplasty may be indicated to address functional or cosmetic sequelae of hydrocephalic macrocephaly. With the advent of CAD/CAM digital workflow, surgeons can design and fabricate craniotomy guides, templates, and models that allow for precise cranial reconstruction. Although there are several advantages of virtual planning, pre-determined surgical plans may limit intraoperative flexibility, requiring surgeons to troubleshoot errors in pre-operative planning or model design. The purpose of this report is to present a series of cases demonstrating our institution's technique for single-stage reduction cranioplasty using a CAD/CAM workflow. This report will highlight the benefits and challenges associated with a contemporary digital workflow for reduction cranioplasty.

Reverse Engineering Orthognathic Surgery and Orthodontics in Individuals with Cleft Lip and/or Palate: A Case Report.

This case report presents a virtual treatment simulation of the orthodontic treatment and surgery-first orthognathic surgery employed to treat a patient with a repaired unilateral cleft lip and alveolus with Class III malocclusion and lower third facial asymmetry. The patient exhibited a negative overjet of 9 mm, a missing lower right second premolar, and a 5 mm gap between the upper right central and lateral incisors with midline discrepancy. The three-dimensional virtual planning began with virtual pre-surgical orthodontics, followed by the positioning of the facial bones and teeth in their ideal aesthetic and functional positions. The sequence of steps needed to achieve this outcome was then reverse-engineered and recorded using multiplatform Nemostudio software (Nemotec, Madrid, Spain), which facilitated both surgical and orthodontic planning. The treatment included a two-piece segmental maxillary osteotomy for dental space closure, a LeFort I maxillary advancement, and a mandibular setback with bilateral sagittal split osteotomy to correct the skeletal underbite and asymmetry. A novel approach was employed by pre-treating the patient for orthognathic surgeries at age 11, seven years prior to the surgery. This early phase of orthodontic treatment aligned the patient's teeth and established the dental arch form. The positions of the teeth were maintained with retainers, eliminating the need for pre-surgical orthodontics later. This early phase of treatment significantly reduced the treatment time. The use of software to predict all the necessary steps for surgery and post-surgical orthodontic tooth movements made this approach possible. Multi-step virtual planning can be a powerful tool for analyzing complex craniofacial problems that require multidisciplinary care, such as cleft lip and/or palate.

A comparison of preoperative soft tissue contour versus bone accuracy as a predictor of quality of life outcomes in osseous free flap jaw reconstruction using occlusal-based virtual surgical planning.

OBJECTIVES: Occlusal-based virtual surgical planning (VSP) prioritises the placement of endosseous dental implants, over replicating native bone contour. This may compromise facial aesthetics. This study aimed to compare function and health-related quality of life (HRQOL) following maxillomandibular reconstruction according to the ability to replicate preoperative soft-tissue contour and virtual plan. MATERIALS AND METHODS: Patients who underwent occlusal based VSP osseous free flap reconstruction of the maxilla or mandible with high-resolution pre- and post-operative facial computerised tomography imaging and completed the FACE-Q questionnaire were retrospectively identified. Accuracy of reconstruction compared to preoperative soft tissue contour and virtual plan, was measured using 3DSlicer® and CloudCompare® in three dimensions. Random effects modelling determined the associations between bony and soft tissue accuracy and HRQOL/functional domains. RESULTS: Twenty-two patients met the inclusion criteria. For mandibular and maxillary reconstructions, better soft tissue accuracy was associated with improved appearance (p = 0.048) and appearance distress (p = 0.034). For mandibular reconstructions, better soft tissue accuracy was associated with improved smile (p = 0.039) and smile distress (p = 0.031). For maxillary reconstructions, better bony accuracy was associated with improved appearance (p = 0.023) and drooling distress (p = 0.001). Unexpectedly, better bony accuracy was associated with worse eating and drinking (p = 0.015), oral competence (p = 0.005) and eating distress (p = 0.013) in mandibular reconstructions. CONCLUSION: Whilst soft tissue accuracy was associated with better functional and HRQOL outcomes, bone accuracy was associated with worse oral function or distress in mandibular reconstruction. These results require validation but should be considered when performing occlusal-based VSP, which prioritises dental rehabilitation over replicating facial bony contour.

Mandibular reconstruction after post-traumatic complex fracture: Comparison analysis between traditional and virtually planned surgery.

BACKGROUND: Jaw reconstruction after complex post-traumatic fracture is still a challenge for surgeons using traditional surgery. Virtual surgical planning has proven to be a valid tool for managing these fractures. The aim of this study is to quantitatively evaluate the VSP effectiveness compared to traditional surgery in the management of complex mandibular fractures. METHODS: 30 patients with diagnosis of complex mandibular fracture were enrolled and divided in two groups: Group A (virtually planned surgery), The plate was pre-modeled and employed during the surgery; Group B (traditional surgery), the plate was shaped directly during the surgery. Virtually planned and post-operative Computer Tomography were after compared for both the groups to highlight discrepancies in mm. RESULTS: Fracture surgical reduction was successful without intraoperative complications. In Group A, all the mean discrepancies' values were <1 mm while in Group B the values were included between 1.36 and 1.94 mm. The mean operative time was 69 min for Group A, while 106 min for Group B. CONCLUSIONS: Fracture virtual reduction and realization of pre-modeled plate are able to guarantee a more anatomically correct reduction and a decrease in operating times. These outcomes translate into a decrease in both short and long-term complications.

In house 3-D printed surgical guide for frontal sinus osteotomy in traumatology: A technical note.

Frontal sinus surgery and particularly frontal sinus osteotomy represent historically a procedure demanding precision and careful planning. Achieving optimal results while minimizing complications requires meticulous preoperative planning and execution. Cutting guides are crucial tools in surgical procedures, particularly in complex osteotomies like could be those involving the frontal sinus. The aim of the study is to show the worflow for the in-house custom made cutting guide for secure and accurated frontal sinus approach. Given the simplicity, efficacy, rapidity, and safety of the procedure, the workflow for programming the cutting guide can be considered valid for all surgical procedures that contemplate performing an osteotomy on the anterior wall of the frontal sinus, such as trauma pathology, inflammatory naso-sinus pathology, benign or malignant neoplastic pathology, and craniofacial malformation pathology.

Evaluation of Soft Tissue Changes Following Orthognathic Surgery Using Virtual Surgical Planning Software.

CONTEXT: Orthognathic surgery brings about a harmonious relationship between jaws, resulting in improved facial aesthetics. It is key to analyze if satisfactory results can be attained by using virtual surgical planning for orthognathic procedures so as to recommend it for routine clinical practice. AIMS: The aims of this study were to evaluate the various soft tissue changes that take place following orthognathic surgery using three-dimensional (3D) imaging and virtual surgical planning software and quantify the accuracy of virtual surgical planning software on patients undergoing orthognathic surgery. SETTINGS AND DESIGN: This is an observational prospective study with a sample size of 12. METHODS AND MATERIALS: In this prospective study, 12 patients undergoing orthognathic surgery were included following the inclusion and exclusion criteria. A usual pre-surgical work-up was done and a 3D replica of the facial skeleton was formulated using the software with the DICOM data acquired from the patient i.e., CT and scans of patient's dentition. Virtual surgical planning was done and splints were manufactured according to the desired newly achieved position. Patients were operated following the virtual surgical plan guided by the computer-aided design and computer-aided manufacturing (CAD-CAM) splints. Post-operative evaluation was done. As the study is more of a descriptive study to obtain detailed knowledge of a new procedure, only one group is being studied and hence there is no statistical testing included in this study. RESULTS: The mean discrepancy noticed after superimposition of soft tissue points was 0.92 with a standard deviation of 0.3. CONCLUSIONS: 3D CT virtual surgical planning is a reliable tool to achieve predictable and reliable post-operative results in orthognathic surgical cases.

Reconstruction of Maxillary Defects Using Virtual Surgical Planning and Additive Manufacturing Technology: A Tertiary Care Centre Experience.

Introduction: Maxillary reconstruction is often a challenging task for the surgeons because of the complex anatomy. However, with the advances in virtual surgical planning (VSP) and 3D printing technology there is a new avenue for the surgeons which offers a suitable alternative to conventional flap-based reconstructions. Patients and Methods: In this article, we have described 4 case scenarios which were managed with the help of VSP and additive manufacturing technology for complex maxillary reconstruction procedures. Use of the technologies aided the clinician in achieving optimal outcomes with regards to form, function and esthetics. Discussion: Virtual surgical planning (VSP) has gained a lot of impetus in past 1 decade. These aides the surgeon in determining the extent of disease and also carry out the treatment planning. In addition to VSP, the concept of additive manufacturing provides a viable alternative to the conventional reconstruction modalities for maxillary defect rehabilitation. Increased accuracy, rehabilitation of normal anatomical configuration, appropriate dental rehabilitation, decreased intra-operative time and post-operative complications are some of the advantages. In addition, patient-specific implants eliminate the need for a separate donor site. Apart from the treatment of pathologies, they also can be used for reconstruction of post-traumatic defect, where endosteal implant placement is not possible. Conclusion: These modalities show promising results for reconstruction of complex maxillary defects.

Digitalization in Cranial Reconstruction: Revolutionizing Precision and Innovation.

Cranioplasty for cranial defects can be complex and challenging in composite defects. The intricate 3D structure of the craniofacial skeleton poses various difficulties encountered in surgical reconstruction. The continuous progress in computer-aided design and computer-aided manufacturing design, and fabrication technology has led to a growing array of applications for visual analog scale and 3D printing in craniofacial surgery, encompassing preoperative assessment, the creation of cutting guides, and the development of custom implants and stereolithographic models. Within this review, the authors detail the present and developing applications of virtual surgical planning, 3D bioprinting, augmented reality, and virtual reality in craniofacial reconstruction.

Hanna's Modified Sagittal Split Osteotomy (HSSO): An Alternative to Inverted L Osteotomy-Merging Function and Aesthetics for Enhanced Stability, Attractiveness, and Nerve Protection.

Background: The current high standards in orthognathic surgery demand surgical solutions that are both ⁠ functionally ⁠ effective and aesthetically pleasing. Our approach offers one for enhanced stability, attractiveness, and nerve protection ⁠ with improved accessibility ⁠ in the majority of orthognathic scenarios ⁠ compared to an inverted L osteotomy. Methods: A case series is presented to illustrate the application and outcomes of HSSO, an optimised approach that combines the advantages of a transoral inverted L osteotomy with specific enhancements and increased versatility, ⁠ with accessibility and exposure similar to a BSSO. Results: HSSO as a completely transoral technique, demonstrate the ability to perform significant counterclockwise rotations of the mandible, eliminating the need for trocars or skin incisions. We experinced high postoperative stability when HSSO was performed in conjunction with a three-piece LeFort 1 osteotomy on a dynamic opposing arch. In comparison to an inverted L approach, we postulated that HSSO offers advantages in stability, due to the increased segmental overlap of the proximal and distal segments of the mandible. This approach is designed to enhance the safety of the inferior alveolar nerve compared to traditional sagittal split methods. Furthermore, HSSO represents an alternative to total joint replacement in select cases of idiopathic condylar resorption and is effective for correcting mandibular asymmetries while maintaining jawline aesthetics. This is achieved through the manipulation of the mandibular angle, ramus height, and inferior border without creating a step deformity in the soft tissue. Conclusions: The outcomes of HSSO highlight its capacity to deliver predictable, functional, and aesthetically pleasing results, offering a viable alternative to more traditional orthognathic techniques.

Complex Craniofacial Cases through Augmented Reality Guidance in Surgical Oncology: A Technical Report.

Augmented reality (AR) is a promising technology to enhance image guided surgery and represents the perfect bridge to combine precise virtual planning with computer-aided execution of surgical maneuvers in the operating room. In craniofacial surgical oncology, AR brings to the surgeon's sight a digital, three-dimensional representation of the anatomy and helps to identify tumor boundaries and optimal surgical paths. Intraoperatively, real-time AR guidance provides surgeons with accurate spatial information, ensuring accurate tumor resection and preservation of critical structures. In this paper, the authors review current evidence of AR applications in craniofacial surgery, focusing on real surgical applications, and compare existing literature with their experience during an AR and navigation guided craniofacial resection, to subsequently analyze which technological trajectories will represent the future of AR and define new perspectives of application for this revolutionizing technology.

Deep Learning-Based Facial and Skeletal Transformations for Surgical Planning.

The increasing application of virtual surgical planning (VSP) in orthognathic surgery implies a critical need for accurate prediction of facial and skeletal shapes. The craniofacial relationship in patients with dentofacial deformities is still not understood, and transformations between facial and skeletal shapes remain a challenging task due to intricate anatomical structures and nonlinear relationships between the facial soft tissue and bones. In this study, a novel bidirectional 3-dimensional (3D) deep learning framework, named P2P-ConvGC, was developed and validated based on a large-scale data set for accurate subject-specific transformations between facial and skeletal shapes. Specifically, the 2-stage point-sampling strategy was used to generate multiple nonoverlapping point subsets to represent high-resolution facial and skeletal shapes. Facial and skeletal point subsets were separately input into the prediction system to predict the corresponding skeletal and facial point subsets via the skeletal prediction subnetwork and facial prediction subnetwork. For quantitative evaluation, the accuracy was calculated with shape errors and landmark errors between the predicted skeleton or face with corresponding ground truths. The shape error was calculated by comparing the predicted point sets with the ground truths, with P2P-ConvGC outperforming existing state-of-the-art algorithms including P2P-Net, P2P-ASNL, and P2P-Conv. The total landmark errors (Euclidean distances of craniomaxillofacial landmarks) of P2P-ConvGC in the upper skull, mandible, and facial soft tissues were 1.964 ± 0.904 mm, 2.398 ± 1.174 mm, and 2.226 ± 0.774 mm, respectively. Furthermore, the clinical feasibility of the bidirectional model was validated using a clinical cohort. The result demonstrated its prediction ability with average surface deviation errors of 0.895 ± 0.175 mm for facial prediction and 0.906 ± 0.082 mm for skeletal prediction. To conclude, our proposed model achieved good performance on the subject-specific prediction of facial and skeletal shapes and showed clinical application potential in postoperative facial prediction and VSP for orthognathic surgery.