Convolutional neural network for automated tooth segmentation on intraoral scans.

BACKGROUND: Tooth segmentation on intraoral scanned (IOS) data is a prerequisite for clinical applications in digital workflows. Current state-of-the-art methods lack the robustness to handle variability in dental conditions. This study aims to propose and evaluate the performance of a convolutional neural network (CNN) model for automatic tooth segmentation on IOS images. METHODS: A dataset of 761 IOS images (380 upper jaws, 381 lower jaws) was acquired using an intraoral scanner. The inclusion criteria included a full set of permanent teeth, teeth with orthodontic brackets, and partially edentulous dentition. A multi-step 3D U-Net pipeline was designed for automated tooth segmentation on IOS images. The model's performance was assessed in terms of time and accuracy. Additionally, the model was deployed on an online cloud-based platform, where a separate subsample of 18 IOS images was used to test the clinical applicability of the model by comparing three modes of segmentation: automated artificial intelligence-driven (A-AI), refined (R-AI), and semi-automatic (SA) segmentation. RESULTS: The average time for automated segmentation was 31.7 ± 8.1 s per jaw. The CNN model achieved an Intersection over Union (IoU) score of 91%, with the full set of teeth achieving the highest performance and the partially edentulous group scoring the lowest. In terms of clinical applicability, SA took an average of 860.4 s per case, whereas R-AI showed a 2.6-fold decrease in time (328.5 s). Furthermore, R-AI offered higher performance and reliability compared to SA, regardless of the dentition group. CONCLUSIONS: The 3D U-Net pipeline was accurate, efficient, and consistent for automatic tooth segmentation on IOS images. The online cloud-based platform could serve as a viable alternative for IOS segmentation.

Optimization of orofacial cleft imaging protocols using device-specific low-dose cone-beam computed tomography.

OBJECTIVE: The aim of this study was to present optimized device-specific low-dose cone-beam computed tomography (CBCT) protocols with sufficient image quality for pre-surgical diagnostics and three-dimensional (3D) modelling of cleft defects. METHODS: Six paediatric skulls were acquired, and an artificial bony cleft was created. A high-resolution CBCT scan acted as a reference standard (Accuitomo 170, Morita, Kyoto, Japan) for comparing eight low-dose protocols of Newtom VGi-evo (QR Verona, Cefla, Verona, Italy), which included Eco and Regular protocols with different field of views (FOVs). Delineation of lamina dura, cementoenamel junction (CEJ), trabecular bone and bony bridge were assessed. A 3D model of the defect was also evaluated. RESULT: The dose area product of low-dose protocols ranged from 31 to 254 mGy*cm2. Despite the dose difference of up to eight times between applied protocols, trabecular bone and CEJ exhibited appropriate image quality in all scans. However, Regular small FOV protocols (5 × 5 and 8 × 5 cm2), for both lamina dura and bony bridge, demonstrated a significant improvement in image quality compared to Eco FOV counterparts. Based on 3D defect analysis, no significant difference existed between low-dose protocols and the reference standard. CONCLUSION: The findings highlight the possibility of achieving a considerable reduction (up to eight times) in the radiation dose using low-dose CBCT protocols while maintaining sufficient image quality for assessing anatomical structures and 3D modelling in cleft cases.

Recommendations to minimize tooth root remodeling in patients undergoing maxillary osteotomies.

The purpose of this study was to report root remodeling/resorption percentages of maxillary teeth following the different maxillary osteotomies; i.e. one-piece, two-pieces, three-pieces Le Fort I, surgically assisted rapid palatal expansion (SARPE). The possibility of relationships between root remodeling and various patient- and/or treatment-related factors were further investigated. A total of 110 patients (1075 teeth) who underwent combined orthodontic and orthognathic surgery were studied retrospectively. The sample size was divided into: 30 patients in one-piece Le Fort I group, 30 patients in multi-pieces Le Fort I group, 20 patients in SARPE group and 30 patients in orthodontic group. Preoperative and 1 year postoperative cone beam computed tomography (CBCT) scans were obtained. A validated and automated method for evaluating root remodeling and resorption in three dimensions (3D) was applied. SARPE group showed the highest percentage of root remodeling. Spearman correlation coefficient revealed a positive relationship between maxillary advancement and root remodeling, with more advancement contributing to more root remodeling. On the other hand, the orthodontic group showed a negative correlation with age indicating increased root remodeling in younger patients. Based on the reported results of linear, volumetric and morphological changes of the root after 1 year, clinical recommendations were provided in the form of decision tree flowchart and tables. These recommendations can serve as a valuable resource for surgeons in estimating and managing root remodeling and resorption associated with different maxillary surgical techniques.

Reconstruction of Craniomaxillofacial Bone Defects with 3D-Printed Bioceramic Implants: Scoping Review and Clinical Case Series.

Reconstruction of craniomaxillofacial bone defects using 3D-printed hydroxyapatite (HA) bioceramic patient-specific implants (PSIs) is a new technique with great potential. This study aimed to investigate the advantages, disadvantages, and clinical outcomes of these implants in craniomaxillofacial surgeries. The PubMed and Embase databases were searched for patients with craniomaxillofacial bone defects treated with bioceramic PSIs. Clinical outcomes such as biocompatibility, biomechanical properties, and aesthetics were evaluated and compared to those of commonly used titanium or poly-ether-ether-ketone (PEEK) implants and autologous bone grafts. Two clinical cases are presented to illustrate the surgical procedure and clinical outcomes of HA bioceramic PSIs. Literature review showed better a biocompatibility of HA PSIs than titanium and PEEK. The initial biomechanical properties were inferior to those of autologous bone grafts, PEEK, and titanium but improved when integrated. Satisfactory aesthetic results were found in our two clinical cases with good stability and absence of bone resorption or infection. Radiological signs of osteogenesis were observed in the two clinical cases six months postoperatively. HA bioceramic PSIs have excellent biocompatible properties and imitate natural bone biomechanically and radiologically. They are a well-suited alternative for conventional biomaterials in the reconstruction of load-sharing bone defects in the craniomaxillofacial region.

Three-dimensional evaluation of secondary alveolar bone grafting in patients with unilateral cleft lip and palate: A 2-3 year post-operative follow-up.

OBJECTIVES: The present study aims to quantitatively assess secondary alveolar bone graft (SABG) resorption in unilateral cleft lip, alveolus and palate (UCLAP) patients in a 2-3 year longitudinal follow-up setting by using a validated 3D protocol. Furthermore, the potential relation of SABG resorption with maxillary canine position and a number of patient-related factors was investigated. METHODS: UCLAP patients who underwent SABG and had good quality CBCT images at the following timepoints were included in the study: pre-operative (T0), immediate (T1), 6 months (T2) and either 1-2 years (T3) or 2-3 years (T4) post-operative. The final bone grafted region was defined on the T1 scans and refined in the registered T0 scans. The bone graft after resorption was determined by applying threshold-based segmentation on the registered T2, T3 or T4 scans within the segmented bone graft volume. The position of the canines was determined at every timepoint at the cleft and non-cleft side. RESULTS: Forty-five UCLAP patients (mean age 9.0 ± 1.3 years) were included. In the first 6 months after SABG, 43.6% bone resorption was recorded. 2-3 years post-operative, 56% bone resorption was found if the maxillary canine was not yet erupted and 42.7% if it erupted through the graft. The vertical position of the canines was significantly higher on the cleft side at T3. CONCLUSIONS: The present study reports significant SABG resorption over time. However, no correlation was found between SABG resorption and canine position, nor between other patient-related factors.

Accuracy of surgical navigation for patient-specific reconstructions of orbital fractures: A systematic review and meta-analysis.

OBJECTIVE: This systematic review and meta-analysis aimed to review the recent literature on the technical accuracy of surgical navigation for patient-specific reconstruction of orbital fractures using a patient-specific implant, and to compare surgical navigation with conventional techniques. MATERIALS AND METHODS: A systematic literature search was conducted in PubMed (Medline), Embase, Web of Science, and Cochrane (Core Collection) databases on May 16, 2023. Literature comparing surgical navigation with a conventional method using postoperative three-dimensional computed tomography imaging was collected. Only articles that studied at least one of the following outcomes were included: technical accuracy (angular accuracy, linear accuracy, volumetric accuracy, and degree of enophthalmos), preoperative and perioperative times, need for revision, complications, and total cost of the intervention. MINORS criteria were used to evaluate the quality of the articles. RESULTS: After screening 3733 articles, 696 patients from 27 studies were included. A meta-analysis was conducted to evaluate volumetric accuracy and revision rates. Meta-analysis proved a significant better volumetric accuracy (0.93 cm3 ± 0.47 cm3) when surgical navigation was used compared with conventional surgery (2.17 cm3 ± 1.35 cm3). No meta-analysis of linear accuracy, angular accuracy, or enophthalmos was possible due to methodological heterogeneity. Surgical navigation had a revision rate of 4.9%, which was significantly lower than that of the conventional surgery (17%). Costs were increased when surgical navigation was used. CONCLUSION: Studies with higher MINORS scores demonstrated enhanced volumetric precision compared with traditional approaches. Surgical navigation has proven effective in reducing revision rates compared to conventional approaches, despite increased costs.

Augmented and Virtual Reality for Preoperative Trauma Planning, Focusing on Orbital Reconstructions: A Systematic Review.

BACKGROUND: This systematic review summarizes recent literature on the use of extended reality, including augmented reality (AR), mixed reality (MR), and virtual reality (VR), in preoperative planning for orbital fractures. METHODS: A systematic search was conducted in PubMed, Embase, Web of Science and Cochrane on 6 April 2023. The included studies compared extended reality with conventional planning techniques, focusing on computer-aided surgical simulation based on Computed Tomography data, patient-specific implants (PSIs), fracture reconstruction of the orbital complex, and the use of extended reality. Outcomes analyzed were technical accuracy, planning time, operative time, complications, total cost, and educational benefits. RESULTS: A total of 6381 articles were identified. Four articles discussed the educational use of VR, while one clinical prospective study examined AR for assisting orbital fracture management. CONCLUSION: AR was demonstrated to ameliorate the accuracy and precision of the incision and enable the better identification of deep anatomical tissues in real time. Consequently, intraoperative imaging enhancement helps to guide the orientation of the orbital reconstruction plate and better visualize the precise positioning and fixation of the PSI of the fractured orbital walls. However, the technical accuracy of 2-3 mm should be considered. VR-based educational tools provided better visualization and understanding of craniofacial trauma compared to conventional 2- or 3-dimensional images.

The impact of CBCT-head tilting on 3D condylar segmentation reproducibility.

OBJECTIVES: To investigate whether variations in head positioning may influence the reproducibility of cone-beam CT (CBCT) three-dimensional (3D) segmented models of the mandibular condyle. METHODS: Five fresh frozen cadaver heads were scanned in four different positions: reference position (RP) and a set of three tilted alternative head positions (AP) in anteroposterior direction (AP1: 2 cm anterior translation, AP2: 5° pitch rotation, AP3: 10° pitch rotation). Surface models of mandibular condyles were constructed and compared with the condylar reference position using voxel-based registration. Descriptive statistics and a linear mixed-effects model were performed to compare condylar volumetric differences and root mean square (RMS) distance between surfaces of AP vs RP. RESULTS: The mean differences in condylar volumes of AP vs RP were 14.1 mm³ (95% CI [-79.3, 107.4]) for AP1, 1.0 mm³ (95% CI [-87.2, 89.2]) for AP2 and 0.1 mm³ (95% CI [-88.3, 88.4]) for AP3. Mean and absolute volumetric differences did not exceed earlier reported intraoperator differences of 30 mm³. The RMS distance values obtained per group were 0.12 mm (95% CI [0.05,0.20]) for AP1, 0.17 mm (95% CI [0.10, 0.22]) for AP2 and 0.17 mm for AP3 (95% CI [0.10,0.22]). The confidence intervals (CI) for RMS distance remained far below the threshold for clinical acceptability (0.5 mm). CONCLUSIONS: Within the limits of the present study, it is suggested that tilted head positions may affect the reproducibility of 3D condylar segmentation, thereby influencing outcome in repeated CBCT scanning. Nevertheless, observed differences are unlikely to have a meaningful impact on clinical patient diagnosis and management.

Autoimmune diseases and orthognathic surgery: A case series of 12 patients.

Autoimmune diseases result from the immune system attacking native cells and tissues due to the recognition of "self" antigens as foreign antigens. This group of disorders is associated with an increased risk of complications after surgical interventions, as the immune system may cause tissue destruction. The study aimed to investigate the risk of surgical complications in patients with autoimmune diseases, who are at a higher risk of complications due to their condition. Among 886 patients who underwent orthognathic surgery, twelve types of autoimmune diseases with 22 patients were identified. For this case-series study, 12 patients were selected with a follow-up period of at least two years. The surgical procedures were executed by a single surgical team, which involved single or multi-piece Le Fort I osteotomy, Hunsuck/Epker modification of bilateral sagittal split osteotomy (BSSO), and/or genioplasty. The recorded outcome variables were postoperative adverse events, including respiratory or blood-related complications, wound infection, neurosensory disturbances, temporomandibular joint (TMJ) complications, and relapse. Only two patients recovered after surgery without any postoperative complications, whereas others had delayed recovery from neurosensory disturbance (5/12), infection (5/12), TMJ complications (2/12), and other complications. The findings of this study suggest that patients with autoimmune diseases undergoing orthognathic surgery are at higher risk of complications, highlighting the importance of careful consideration of patient selection and risk stratification before surgical intervention. The study also emphasizes the importance of close postoperative follow-up to detect and manage complications promptly.

Prevalence of malnutrition & anemia in preschool children; a single center study.

BACKGROUND: Malnutrition including undernutrition, overnutrition, and micronutrient deficiencies are considerable problems worldwide, with variable burdens among different communities. Its complications include physical and cognitive impairment, with the probability of irreversible lifelong consequences. We aimed to assess the prevalence of undernutrition, overweight, obesity, and anemia in preschoolers, being a risk group for developmental adverse events. METHODS: We recruited 505 healthy preschool children, with a male: female ratio of 1.05:1. Children with chronic diseases were excluded. We used anthropometry and complete blood count to screen for malnutrition and anemia. RESULTS: The mean age of the study group was 3.8 ± 1.4 years (1.02-7). The screening results were average in 228 (45.1%) children, while 277 (54.9%) children had either abnormal anthropometry, anemia, or both. We observed undernutrition in 48 (9.5%) children; among them, 33 (6.6%) were underweight, 33 (6.6%) wasted, and 15 (3%) were stunted, with no significant difference between children aged below or above five. We identified overnutrition in 125 (24.8%); 43 (8.5%) were overweight, 12 (2.4%) were obese, and 70 (13.9%) had a high body mass index Z score, not qualifying the definition of overweight. Anemia was diagnosed in 141 (27.9%) children and was significantly more frequent among older children without gender discrimination. About 10% (50 children) had both anemia and abnormal anthropometry. The frequency of abnormal anthropometry was comparable between children with anemia and those with normal hemoglobin. CONCLUSION: Malnutrition and anemia in preschoolers are still a heavy burden affecting about half of our study group, with an upward trend towards the overnutrition side. Anemia is still a moderate public health problem in preschoolers.

Trueness of cone-beam computed tomography-derived skull models fabricated by different technology-based three-dimensional printers.

BACKGROUND: Three-dimensional (3D) printing is a novel innovation in the field of craniomaxillofacial surgery, however, a lack of evidence exists related to the comparison of the trueness of skull models fabricated using different technology-based printers belonging to different cost segments. METHODS: A study was performed to investigate the trueness of cone-beam computed tomography-derived skull models fabricated using different technology based on low-, medium-, and high-cost 3D printers. Following the segmentation of a patient's skull, the model was printed by: (i) a low-cost fused filament fabrication printer; (ii) a medium-cost stereolithography printer; and (iii) a high-cost material jetting printer. The fabricated models were later scanned by industrial computed tomography and superimposed onto the original reference virtual model by applying surface-based registration. A part comparison color-coded analysis was conducted for assessing the difference between the reference and scanned models. A one-way analysis of variance (ANOVA) with Bonferroni correction was applied for statistical analysis. RESULTS: The model printed with the low-cost fused filament fabrication printer showed the highest mean absolute error ([Formula: see text]), whereas both medium-cost stereolithography-based and the high-cost material jetting models had an overall similar dimensional error of [Formula: see text] and [Formula: see text], respectively. Overall, the models printed with medium- and high-cost printers showed a significantly ([Formula: see text]) lower error compared to the low-cost printer. CONCLUSIONS: Both stereolithography and material jetting based printers, belonging to the medium- and high-cost market segment, were able to replicate the skeletal anatomy with optimal trueness, which might be suitable for patient-specific treatment planning tasks in craniomaxillofacial surgery. In contrast, the low-cost fused filament fabrication printer could serve as a cost-effective alternative for anatomical education, and/or patient communication.

Evaluating the Feasibility of Pro-Neurotensin and 25-Hydroxyvitamin D3 as Possible Indicators for Type 2 Diabetes Mellitus and Its Complications.

(1) Background: Type 2 diabetes mellitus (T2DM) and metabolic syndrome are associated with decreased vitamin D. In contrast, high pro-neurotensin (pro-NT) levels are linked with an increased risk of T2DM and cardiovascular disease. We aimed to determine the validity of pro-NT and 25-dihydroxy vitamin D3 levels as predictors for T2DM complications; (2) Methods: One hundred T2DM, and one hundred healthy volunteers participated in this case-control study. Their Pro-NT and 25-hydroxyvitamin D3 levels were evaluated using the ELISA technique; (3) Results: Pro-NT and 25 (OH) vitamin D3 have significant validity and accuracy in T2DM prediction, 84.5%, and 90.5%, respectively (p = 0.001). At a value of <29.5, 25-Hydroxy vitamin D3 showed 88% sensitivity and 93% specificity in predicting T2DM. At a value of >124 Pmol/L, Pro-NT showed 81% sensitivity and 88% specificity in predicting T2DM. At a value of 16.5, 25-Hydroxy vitamin D3 had 78.4% sensitivity and 68.3% specificity in predicting T2DM complications. At a value of >158 pmol/L, Pro-NT predicted T2DM complications with 67.6% sensitivity and 56.0% specificity; (4) Conclusions: 25 (OH) Vit D3 and Pro-NT could identify T2DM patients and predict T2DM complications. More extensive research is required to adequately validate this novel perspective with a large population study.

Anatomically and mechanically accurate scala tympani model for electrode insertion studies.

The risk of insertion trauma in cochlear implantation is determined by the interplay between individual cochlear anatomy and electrode insertion mechanics. Whereas patient anatomy cannot be changed, new surgical techniques, devices for cochlear monitoring, drugs, and electrode array designs are continuously being developed and tested, to optimize the insertion mechanics and prevent trauma. Preclinical testing of these developments is a crucial step in feasibility testing and optimization for clinical application. Human cadaveric specimens allow for the best simulation of an intraoperative setting. However, their availability is limited and it is not possible to conduct repeated, controlled experiments on the same sample. A variety of artificial cochlear models have been developed for electrode insertion studies, but none of them were both anatomically and mechanically representative for surgical insertion into an individual cochlea. In this study, we developed anatomically representative models of the scala tympani for surgical insertion through the round window, based on microCT images of individual human cochleae. The models were produced in transparent material using commonly-available 3D printing technology at a desired scale. The anatomical and mechanical accuracy of the produced models was validated by comparison with human cadaveric cochleae. Mechanical evaluation was performed by recording insertion forces, counting the number of inserted electrodes and grading tactile feedback during manual insertion of a straight electrode by experienced cochlear implant surgeons. Our results demonstrated that the developed models were highly representative for the anatomy of the original cochleae and for the insertion mechanics in human cadaveric cochleae. The individual anatomy of the produced models had a significant impact on the insertion mechanics. The described models have a promising potential to accelerate preclinical development and testing of atraumatic insertion techniques, reducing the need for human cadaveric material. In addition, realistic models of the cochlea can be used for surgical training and preoperative planning of patient-tailored cochlear implantation surgery.

Performance of novice versus experienced surgeons for dental implant placement with freehand, static guided and dynamic navigation approaches.

Lack of evidence exists related to the investigation of the accuracy and efficacy of novice versus experienced practitioners for dental implant placement. Hence, the following in vitro study was conducted to assess the accuracy of implant positioning and self-efficacy of novice compared to experienced surgeons for placing implant using freehand (FH), pilot drill-based partial guidance (PPG) and dynamic navigation (DN) approaches. The findings revealed that DN significantly improved the angular accuracy of implant placement compared with FH (P < 0.001) and PPG approaches (P < 0.001). The time required with DN was significantly longer than FH and PPG (P < 0.001), however, it was similar for both novice and experienced practitioners. The surgeon's self-confidence questionnaire suggested that novice practitioners scored higher with both guided approaches, whereas experienced practitioners achieved higher scoring with PPG and FH compared to DN. In conclusion, implant placement executed under the guidance of DN showed high accuracy irrespective of the practitioner's experience. The application of DN could be regarded as a beneficial tool for novices who offered high confidence of using the navigation system with the same level of accuracy and surgical time as that of experienced practitioners.

Three-dimensional planning accuracy and follow-up of Le Fort I osteotomy in cleft lip/palate patients.

OBJECTIVES: Our aim was to determine the accuracy of the three-dimensional (3D) virtual planning and stability of LeFort I osteotomy in cleft lip and/or palate patients (CLP) using a validated 3D method. MATERIALS AND METHODS: Eight patients with a history of cleft lip/palate treated with LeFort I osteotomy for maxillary hypoplasia between January 2016 and April 2020 were included in this retrospective study. Three-dimensional virtual planning was performed using Proplan software then transferred to the operation theater via 3D printed occlusal wafers. The accuracy of the 3D planning and the 1-year stability of the maxilla were evaluated by means of a validated semiautomatic stepwise module in Amira software resulting into 3 linear measurements: anterior/posterior, medial/lateral, superior/inferior and 3 rotational measurements: pitch, roll, yaw. RESULTS: The largest mean absolute difference (MAD) for accuracy assessment was found in the A/P direction (2.75mm±2.25 mm) and in pitch (3.23°±2.11°). For A/P translation, an error of >2 mm was observed in 5(62.5%), for S/I translation an error of >2 mm was observed in 4(50.0%) of the 8 patients, whereas for pitch 3 patients(37,5%) showed an error >4° At one year follow-up, the largest linear and rotational MAD was found in the A/P direction (1.20mm±0.92 mm) and in pitch (3.31°±2.31°). CONCLUSIONS: Findings of this study show that 3D virtual computer-assisted orthognathic surgery enables an accurate repositioning of the hypoplastic maxilla in CLP patients. However, A/P translations and pitch rotations remain challenging to achieve during surgery. These movements were also found to be least stable at one year follow-up.

Postoperative complications in asthmatic patients following orthognathic surgery: A two-year follow-up study.

BACKGROUND: Lack of evidence exists related to the incidence of postoperative complications in asthmatic patients following orthognathic surgery. The present study aimed to assess the incidence and risk factors of postoperative complications in asthmatic patients following orthognathic surgery. MATERIAL AND METHODS: A retrospective cohort study was conducted which consisted of two groups of patients i.e., asthmatic and systemically healthy patients, who underwent conventional orthognathic surgical procedures (Le Fort I osteotomy, bilateral sagittal split osteotomy, and genioplasty). The recorded postoperative complications in both groups of patients included infection, relapse, altered facial sensation, temporomandibular joint disorder, respiratory complications, and hemorrhage-related events. The association between baseline variables and complications for identifying the possible risk factors was assessed using bivariate analysis and a logistic regression model. RESULTS: A total of 886 patients underwent orthognathic surgery over a period of 6-years. Following the eligibility criteria, 16 patients were recruited in the asthmatic group and 278 patients were systemically healthy. The most common complications in the asthmatic patients were altered sensation (37.5%) followed by TMJ disorder (25.0%) and relapse (18.8%). These patients were associated with an increased risk of relapse (P = 0.048) compared to healthy patients. Following adjustment of baseline variables, increased risk of relapse was still associated with asthma (odds ratio [OR]. = 4.704, P = 0.027). CONCLUSION: Asthmatic patients suffer from a significantly higher risk of relapse and need to be closely monitored following orthognathic surgery to ensure a stable outcome. Asthma does not seem to have a significant impact on other postoperative complications.

Deep convolutional neural network-based automated segmentation and classification of teeth with orthodontic brackets on cone-beam computed-tomographic images: a validation study.

OBJECTIVE: Tooth segmentation and classification from cone-beam computed tomography (CBCT) is a prerequisite for diagnosis and treatment planning in the majority of digital dental workflows. However, an accurate and efficient segmentation of teeth in the presence of metal artefacts still remains a challenge. Therefore, the following study aimed to validate an automated deep convolutional neural network (CNN)-based tool for the segmentation and classification of teeth with orthodontic brackets on CBCT images. METHODS: A total of 215 CBCT scans (1780 teeth) were retrospectively collected, consisting of pre- and post-operative images of the patients who underwent combined orthodontic and orthognathic surgical treatment. All the scans were acquired with NewTom CBCT device. A complete dentition with orthodontic brackets and high-quality images were included. The dataset were randomly divided into three subsets with random allocation of all 32 tooth classes: training set (140 CBCT scans-400 teeth), validation set (35 CBCT scans-100 teeth), and test set (pre-operative: 25, post-operative: 15 = 40 CBCT scans-1280 teeth). A multiclass CNN-based tool was developed and its performance was assessed for automated segmentation and classification of teeth with brackets by comparison with a ground truth. RESULTS: The CNN model took 13.7 ± 1.2 s for the segmentation and classification of all the teeth on a single CBCT image. Overall, the segmentation performance was excellent with a high intersection over union (IoU) of 0.99. Anterior teeth showed a significantly lower IoU (P < 0.05) compared to premolar and molar teeth. The dice similarity coefficient score of anterior (0.99 ± 0.02) and premolar teeth (0.99 ± 0.10) in the pre-operative group was comparable to the post-operative group. The classification of teeth to the correct 32 classes had a high recall rate (99.9%) and precision (99%). CONCLUSIONS: The proposed CNN model outperformed other state-of-the-art algorithms in terms of accuracy and efficiency. It could act as a viable alternative for automatic segmentation and classification of teeth with brackets. CLINICAL SIGNIFICANCE: The proposed method could simplify the existing digital workflows of orthodontics, orthognathic surgery, restorative dentistry, and dental implantology by offering an accurate and efficient automated segmentation approach to clinicians, hence further enhancing the treatment predictability and outcomes.

The usefulness of cutting guides for resection or biopsy of mandibular lesions: A technical note and case report.

The application of three dimensional (3D) printed patient specific cutting guide for biopsy of a mandibular lesion closely positioned to the mandibular canal is presented. To prevent inferior alveolar nerve damage, the cutting site of the bone window was virtually planned and then the cutting guide was 3D printed. This guide enabled intra-operative control and resulted in absence of postoperative hypo- or dysesthesia. This case demonstrates that 3D printed patient specific guides can help reduce the risk of hypoesthesia in mandibular surgery.

Automated three-dimensional quantification of external root resorption following combined orthodontic-orthognathic surgical treatment. A validation study.

OBJECTIVE: Three-dimensional (3D) quantitative assessment of external root resorption (ERR) following combined orthodontic-orthognathic surgical treatment is vital for ensuring an optimal long-term tooth prognosis. In this era, lack of evidence exists applying automated 3D approaches for assessing ERR. Therefore, this study aimed to validate a protocol for 3D quantification of ERR on cone-beam computed tomography (CBCT) images following combined orthodontic-orthognathic surgical treatment. MATERIAL AND METHODS: Twenty patients who underwent combined orthodontic-orthognathic surgical treatment were recruited. Each patient had CBCT scans acquired with NewTom VGi evo (NewTom) at three time-points i.e., 4-weeks prior to surgery (T0), 1-week (T1) and 1-year after surgery (T2). Patients were divided into two groups, group A (surgical Le Fort I osteotomy group: 10 patients) and group B (orthodontic group without maxillary surgical intervention: 10 patients). Root resorption was assessed by measuring length and volumetric changes of maxillary premolar to premolar teeth (central and lateral incisors, canines, 1st and 2nd premolars= 10 teeth) at T0-T1 and T0-T2 time intervals in both groups. The protocol consisted of convolutional neural network based segmentation followed by surface-based superimposition and automated 3D analysis. RESULTS: The intra-observer intra-class correlation coefficient (ICC) was found to be excellent (1.0) with an average error of 0 mm and 0 mm3 for assessing root length and volume, respectively. The entire protocol took 56.8 ± 7 s for quantifying ERR. Both group of patients showed negligible changes in length and volumetric ratio at T0-T1 time-interval. Furthermore, group A had lower ERR ratio with decreased root volume and length compared to group B at T0-T2 time-interval. CONCLUSIONS: The proposed protocol was found to be time efficient, accurate and reliable for 3D quantification of ERR on CBCT images. It could act as a viable automated option for assessing ERR. CLINICAL SIGNIFICANCE: The automated protocol could provide a time efficient method to allow a reliable and accurate 3D follow up root resorption after orthognathic and orthodontic treatment procedures. These new insights could allow clinicians to implement strategies for minimizing the risk of root resorption and to further enhance treatment predictability.

Influence of experience on dental implant placement: an in vitro comparison of freehand, static guided and dynamic navigation approaches.

PURPOSE: This study aimed to investigate the performance of novice versus experienced practitioners for placing dental implant using freehand, static guided and dynamic navigation approaches. METHODS: A total of 72 implants were placed in 36 simulation models. Three experienced and three novice practitioners were recruited for performing the osteotomy and implant insertion with freehand, surgical guide (pilot-drill guidance) and navigation (X-Guide, X-Nav technologies) approaches. Each practitioner inserted 4 implants per approach randomly with a 1-week gap to avoid memory bias (4 insertion sites × 3 approaches × 6 practitioners = 72 implants). The performance of practitioners was assessed by comparing actual implant deviation to the planned position, time required for implant placement and questionnaire-based self-confidence evaluation of practitioners on a scale of 1-30. RESULTS: The navigation approach significantly improved angular deviation compared with freehand (P < 0.001) and surgical guide (P < 0.001) irrespective of the experience. Surgical time with navigation was significantly longer compared to the freehand approach (P < 0.001), where experienced practitioners performed significantly faster compared to novice practitioners (P < 0.001). Overall, self-confidence was higher in favor of novice practitioners with both guided approaches. In addition, the confidence of novice practitioners (median score = 26) was comparable to that of experienced practitioners (median score = 27) for placing implants with the navigation approach. CONCLUSIONS: Dynamic navigation system could act as a viable tool for dental implant placement. Unlike freehand and static-guided approaches, novice practitioners showed comparable accuracy and self-confidence to that of experienced practitioners with the navigation approach.