A comprehensive patient-specific prediction model for temporomandibular joint osteoarthritis progression.

Temporomandibular joint osteoarthritis (TMJ OA) is a prevalent degenerative disease characterized by chronic pain and impaired jaw function. The complexity of TMJ OA has hindered the development of prognostic tools, posing a significant challenge in timely, patient-specific management. Addressing this gap, our research employs a comprehensive, multidimensional approach to advance TMJ OA prognostication. We conducted a prospective study with 106 subjects, 74 of whom were followed up after 2 to 3 y of conservative treatment. Central to our methodology is the development of an innovative, open-source predictive modeling framework, the Ensemble via Hierarchical Predictions through Nested cross-validation tool (EHPN). This framework synergistically integrates 18 feature selection, statistical, and machine learning methods to yield an accuracy of 0.87, with an area under the ROC curve of 0.72 and an F1 score of 0.82. Our study, beyond technical advancements, emphasizes the global impact of TMJ OA, recognizing its unique demographic occurrence. We highlight key factors influencing TMJ OA progression. Using SHAP analysis, we identified personalized prognostic predictors: lower values of headache, lower back pain, restless sleep, condyle high gray level-GL-run emphasis, articular fossa GL nonuniformity, and long-run low GL emphasis; and higher values of superior joint space, mouth opening, saliva Vascular-endothelium-growth-factor, Matrix-metalloproteinase-7, serum Epithelial-neutrophil-activating-peptide, and age indicate recovery likelihood. Our multidimensional and multimodal EHPN tool enhances clinicians' decision-making, offering a transformative translational infrastructure. The EHPN model stands as a significant contribution to precision medicine, offering a paradigm shift in the management of temporomandibular disorders and potentially influencing broader applications in personalized healthcare.

Anthropometric measures and obstructive sleep apnea in children and adolescents: a systematic review of the literature and meta-analysis.

BACKGROUND: Anthropometric measurements can be used to identify children at risk of developing obstructive sleep apnea (OSA). The study aimed to assess which anthropometric measurements (AMs) are most associated with an increased predisposition to develop OSA in healthy children and adolescents. METHODS: We performed a systematic review (PROSPERO #CRD42022310572) that searched eight databases and gray literature. RESULTS: In eight studies with low-to-high risk of bias, investigators reported the following AMs: body mass index (BMI), neck circumference, hip circumference, waist-to-hip ratio, neck-to-waist ratio, waist circumference, waist-to-height ratio, and facial AMs. The meta-analysis showed that the OSA group had an average of 1.00 cm greater for the neck circumference (p < 0.001; Cohen's d = 2.26 [0.72, 5.23]), 3.07 cm greater for the waist circumference (p = 0.030; Cohen's d = 0.28 [0.02, 0.53]), 3.96 cm greater for the hip circumference (p = 0.040; Cohen's d = 0.28 [0.02, 0.55]), 5.21° greater for the cervicomental angle (p = 0.020; Cohen's d = 0.31 [0.03, 0.59]), and 1.23° greater for maxillary-mandibular relationship angle (p < 0.001; Cohen's d = 0.47 [0.22, 0.72]) than the control group. The mandibular depth angle had a reduction of 1.86° (p = 0.001; Cohen's d = -0.36° [-0.65, -0.08]) in control than in patients with OSA. The BMI (p = 0.180), waist-to-hip ratio (p = 0.280), neck-to-waist ratio (p = 0.070), maxillary depth angle (p = 0.250), and upper/lower face height ratio (p = 0.070) showed no significant differences between groups. CONCLUSIONS: Compared to the control group, the OSA group exhibited a greater mean difference in neck circumference, the only anthropometric measurement with high certainty of evidence.

Automated artificial intelligence-based three-dimensional comparison of orthodontic treatment outcomes with and without piezocision surgery.

OBJECTIVE(S): This study aims to evaluate the influence of the piezocision surgery in the orthodontic biomechanics, as well as in the magnitude and direction of tooth movement in the mandibular arch using novel artificial intelligence (AI)-automated tools. MATERIALS AND METHODS: Nineteen patients, who had piezocision performed in the lower arch at the beginning of treatment with the goal of accelerating tooth movement, were compared to 19 patients who did not receive piezocision. Cone beam computed tomography (CBCT) and intraoral scans (IOS) were acquired before and after orthodontic treatment. AI-automated dental tools were used to segment and locate landmarks in dental crowns from IOS and root canals from CBCT scans to quantify 3D tooth movement. Differences in mesial-distal, buccolingual, intrusion and extrusion linear movements, as well as tooth long axis angulation and rotation were compared. RESULTS: The treatment time for the control and experimental groups were 13.2 ± 5.06 and 13 ± 5.52 months respectively (P = .176). Overall, anterior and posterior tooth movement presented similar 3D linear and angular changes in the groups. The piezocision group demonstrated greater (P = .01) mesial long axis angulation of lower right first premolar (4.4 ± 6°) compared with control group (0.02 ± 4.9°), while the mesial rotation was significantly smaller (P = .008) in the experimental group (0.5 ± 7.8°) than in the control (8.5 ± 9.8°) considering the same tooth. CONCLUSION: The open source-automated dental tools facilitated the clinicians' assessment of piezocision treatment outcomes. The piezocision surgery prior to the orthodontic treatment did not decrease the treatment time and did not influence in the orthodontic biomechanics, leading to similar tooth movements compared to conventional treatment.

Evaluation of condylar and mandibular movements on the upper airway during the use of mandibular advancement device for obstructive sleep apnea treatment.

OBJECTIVES: To evaluate the temporomandibular joint (TMJ), condylar and mandibular movements in obstructive sleep apnea (OSA) patients treated with mandibular advancement device (MAD) and to identify the influence of these anatomic factors on upper airway (UA) volume and polysomnographic outcomes after treatment. MATERIALS AND METHODS: Twenty OSA patients were prospectively treated with MAD. Clinical examinations, cone-beam computed tomography, and polysomnography were performed before MAD treatment and after achieving therapeutic protrusion. Polysomnographic variables and three-dimensional measurements of the TMJ, mandible, and upper airway were statistically analyzed. RESULTS: Condylar rotation, anterior translation, and anterior mandibular displacement were directly correlated with total UA volume, while vertical mandibular translation was inversely correlated with the volume of the inferior oropharynx. MAD treatment resulted in an increase in the volume and area of the superior oropharynx. There was no statistically significant correlation between condylar rotation and translation and polysomnographic variables. With MAD, there was a significant increase in vertical dimension, changes in condylar position (rotation and translation), and mandibular displacement. The central and medial lengths of the articular eminence were inversely correlated with condylar rotation and translation, respectively. The lateral length of the eminence was directly correlated with condylar translation, and the lateral height was directly correlated with condylar rotation and translation. CONCLUSION: Condylar and mandibular movements influenced UA volume. The articular eminence played a role in the amount of condylar rotation and translation. CLINICAL RELEVANCE: Individualized anatomical evaluation of the TMJ proves to be important in the therapy of OSA with MAD.

Enhancing skeletal stability and Class III correction through active orthodontist engagement in virtual surgical planning: A voxel-based 3-dimensional analysis.

INTRODUCTION: Skeletal stability after bimaxillary surgical correction of Class III malocclusion was investigated through a qualitative and quantitative analysis of the maxilla and the distal and proximal mandibular segments using a 3-dimensional voxel-based superimposition among virtual surgical predictions performed by the orthodontist in close communication with the maxillofacial surgeon and 12-18 months postoperative outcomes. METHODS: A comprehensive secondary data analysis was conducted on deidentified preoperative (1 month before surgery [T1]) and 12-18 months postoperative (midterm [T2]) cone-beam computed tomography scans, along with virtual surgical planning (VSP) data obtained by Dolphin Imaging software. The sample for the study consisted of 17 patients (mean age, 24.8 ± 3.5 years). Using 3D Slicer software, automated tools based on deep-learning approaches were used for cone-beam computed tomography orientation, registration, bone segmentation, and landmark identification. Colormaps were generated for qualitative analysis, whereas linear and angular differences between the planned (T1-VSP) and observed (T1-T2) outcomes were calculated for quantitative assessments. Statistical analysis was conducted with a significance level of α = 0.05. RESULTS: The midterm surgical outcomes revealed a slight but significantly less maxillary advancement compared with the planned position (mean difference, 1.84 ± 1.50 mm; P = 0.004). The repositioning of the mandibular distal segment was stable, with insignificant differences in linear (T1-VSP, 1.01 ± 3.66 mm; T1-T2, 0.32 ± 4.17 mm) and angular (T1-VSP, 1.53° ± 1.60°; T1-T2, 1.54° ± 1.50°) displacements (P >0.05). The proximal segments exhibited lateral displacement within 1.5° for both the mandibular right and left ramus at T1-VSP and T1-T2 (P >0.05). CONCLUSIONS: The analysis of fully digital planned and surgically repositioned maxilla and mandible revealed excellent precision. In the midterm surgical outcomes of maxillary advancement, a minor deviation from the planned anterior movement was observed.

Methodological parameters for upper airway assessment by cone-beam computed tomography in adults with obstructive sleep apnea: a systematic review of the literature and meta-analysis.

BACKGROUND: A reliable method for analyzing the upper airway (UA) remains a challenge. This study aimed to report the methods for UA assessment using cone-beam computed tomography (CBCT) in adults with obstructive sleep apnea (OSA). METHODS: We performed a systematic review (PROSPERO #CRD42021237490 and PRISMA checklist) that applied a search strategy to seven databases and grey literature. RESULTS: In 29 studies with moderate-to-high risk of bias, investigators mostly reported the body position during CBCT (upright or supine) and hard tissue references, diverging in UA delimitation and terminologies. The meta-analysis showed two subgroups (upright and supine), and no statistical differences were identified (p = 0.18) considering the UA area. The volume in the OSA group was smaller than that in the control group (p < 0.003 and Cohen's d = - 0.81) in the upright position. Patients with OSA showed smaller anteroposterior dimensions than the control group and were not affected by the position during image acquisition (p = 0.02; Cohen's d = - 0.52). The lateral measurements were also lower in the OSA group (supine) (p = 0.002; Cohen's d = - 0.6). CONCLUSIONS: Patients with OSA showed smaller UA measurements in the upright (volume) and supine (lateral dimension) positions. The anteroposterior dimension was also reduced in patients with OSA compared to the control group, regardless of the position during CBCT acquisition.

Automatic landmark identification in cone-beam computed tomography.

OBJECTIVE: To present and validate an open-source fully automated landmark placement (ALICBCT) tool for cone-beam computed tomography scans. MATERIALS AND METHODS: One hundred and forty-three large and medium field of view cone-beam computed tomography (CBCT) were used to train and test a novel approach, called ALICBCT that reformulates landmark detection as a classification problem through a virtual agent placed inside volumetric images. The landmark agents were trained to navigate in a multi-scale volumetric space to reach the estimated landmark position. The agent movements decision relies on a combination of DenseNet feature network and fully connected layers. For each CBCT, 32 ground truth landmark positions were identified by 2 clinician experts. After validation of the 32 landmarks, new models were trained to identify a total of 119 landmarks that are commonly used in clinical studies for the quantification of changes in bone morphology and tooth position. RESULTS: Our method achieved a high accuracy with an average of 1.54 ± 0.87 mm error for the 32 landmark positions with rare failures, taking an average of 4.2 second computation time to identify each landmark in one large 3D-CBCT scan using a conventional GPU. CONCLUSION: The ALICBCT algorithm is a robust automatic identification tool that has been deployed for clinical and research use as an extension in the 3D Slicer platform allowing continuous updates for increased precision.

Three-dimensional decision support system for treatment of canine impaction.

INTRODUCTION: This study aimed to develop a 3-dimensional (3D) characterization of the severity of maxillary impacted canines and to test the clinical performance of this characterization as a treatment decision support tool. METHODS: Cone-beam computed tomography images obtained from 83 patients with 120 impacted maxillary canines were included. Quantitative information on the canine 3D position and qualitative assessment of root damage of adjacent teeth were evaluated. A severity index was constructed on the basis of the quantitative findings. Clinical applicability was tested by comparing clinical diagnosis and treatment planning for conventional records vs the 3D characterization via a 2-part survey. RESULTS: The average quantitative assessments of impacted maxillary canine position were 6.4 ± 3.6 mm from the midsagittal plane, 11.6 ± 3.1 mm in height relative to the occlusal plane, 31.5° ± 18° of roll, and 48.8° ± 14.3° of pitch. The severity index ranged from 0-13 with a mean score of 4.5 ± 2.2. Overlap with adjacent teeth was the greatest contributor (33%) to the index. Bicortically impacted canines caused the most severe root damage. Cone-beam computed tomography was preferred for assessing root damage and overall severity, whereas conventional imaging was sufficient for height and angulation assessment. The 3D report was very important or important for evaluating root damage, canine position, overall severity, and overlap. The 3D report changed most of the decisions relating to biomechanics, patient education, and treatment time estimate. The decision of exposure and traction vs extraction was changed 22% of the time after the presentation of the 3D report. CONCLUSIONS: The overlap with adjacent teeth frequently contributes the most to the severity index. The 3D report provided relevant clinical information regarding the canine position, damage to adjacent teeth, and the severity index, with a profound impact on the decisions of the clinicians regarding biomechanics, patient education, and treatment time estimate.

Three-dimensional comparison between the effects of mandibular advancement device and maxillomandibular advancement surgery on upper airway.

BACKGROUND: The efficacy of mandibular advancement devices (MAD) and maxillomandibular advancement (MMA) in improving upper airway (UA) patency has been described as being comparable to continuous positive airway pressure (CPAP) outcomes. However, no previous study has compared MAD and MMA treatment outcomes for the upper airway enlargement. This study aimed to evaluate three-dimensionally the UA changes and mandibular rotation in patients after MAD compared to MMA. METHODS: The sample consisted of 17 patients with treated with MAD and 17 patients treated with MMA matched by weight, height, body mass index. Cone-beam computed tomography from before and after both treatments were used to measure total UA, superior/inferior oropharynx volume and surface area; and mandibular rotation. RESULTS: Both groups showed a significant increase in the superior oropharynx volume after the treatments (p = 0.003) and the MMA group showed greater increase (p = 0.010). No statistical difference was identified in the MAD group considering the inferior volume, while the MMA group showed a significantly gain (p = 0.010) and greater volume (p = 0.024). Both groups showed anterior mandibular displacement. However, the mandibular rotation were statistically different between the groups (p < 0.001). While the MAD group showed a clockwise rotation pattern (-3.97 ± 1.07 and - 4.08 ± 1.30), the MMA group demonstrated a counterclockwise (2.40 ± 3.43 and 3.41 ± 2.79). In the MAD group, the mandibular linear anterior displacement was correlated with superior [p = 0.002 (r=-0.697)] and inferior [p = 0.004 (r = 0.658)] oropharynx volume, suggesting that greater amounts of mandibular advancement are correlated to a decrease in the superior oropharynx and an increase in the inferior oropharynx. In the MMA group, the superior oropharynx volume was correlated to mandibular anteroposterior [p = 0.029 (r=-0.530)] and vertical displacement [p = 0.047 (r = 0.488)], indicating greater amounts of mandibular advancement may lead to a lowest gain in the superior oropharynx volume, while a great mandibular superior displacement is correlated with improvements in this region. CONCLUSIONS: The MAD therapy led to a clockwise mandibular rotation, increasing the dimensions of the superior oropharynx; while a counterclockwise rotation with greater increases in all UA regions were showed in the MMA treatment.

Three-dimensional craniofacial characteristics associated with obstructive sleep apnea severity and treatment outcomes.

OBJECTIVES: This study aims to assess craniofacial dimensions in obstructive sleep apnea (OSA) patients treated with a mandibular advancement device (MAD) and to identify anatomic influences on OSA severity and MAD therapy outcomes. MATERIALS AND METHODS: Twenty patients with OSA were prospectively treated with MAD. Clinical, cone-beam computed tomography, and polysomnography exams were performed before treatment and 4-6 months after achieving the MAD therapeutic position. Polysomnographic exams and three-dimensional maxillary, mandibular, and upper airway (UA) measurements were evaluated. Pearson's correlation and t-tests were applied. RESULTS: Before MAD treatment, the transverse width measured at the frontomaxillary suture and the angle between the mandibular ramus and Frankfurt horizontal were statistically correlated with apnea and the hypopnea index (AHI), while the gonial angle was correlated with therapeutic protrusion. After MAD treatment, all patients showed a significant AHI reduction and an improvement in minimum oxyhemoglobin saturation. The UA total volume, superior and inferior oropharynx volume, and area were statistically correlated with MAD therapeutic protrusion. The UA total area showed a statistical correlation with the improvement in AHI, and the superior oropharynx volume and area increased significantly. CONCLUSIONS: The transversal frontomaxillary suture width and the mandibular ramus facial angle may influence OSA severity. The gonial angle, volume, and area of all UA regions may indicate the amount of protrusion needed for successful MAD treatment. CLINICAL RELEVANCE: The craniofacial characteristics reported as important factors for OSA severity and MAD treatment outcomes impact therapy planning for OSA patients, considering individual anatomic characteristics, prognosis, and cost benefits.

Clinical decision support systems in orthodontics: A narrative review of data science approaches.

Advancements in technology and data collection generated immense amounts of information from various sources such as health records, clinical examination, imaging, medical devices, as well as experimental and biological data. Proper management and analysis of these data via high-end computing solutions, artificial intelligence and machine learning approaches can assist in extracting meaningful information that enhances population health and well-being. Furthermore, the extracted knowledge can provide new avenues for modern healthcare delivery via clinical decision support systems. This manuscript presents a narrative review of data science approaches for clinical decision support systems in orthodontics. We describe the fundamental components of data science approaches including (a) Data collection, storage and management; (b) Data processing; (c) In-depth data analysis; and (d) Data communication. Then, we introduce a web-based data management platform, the Data Storage for Computation and Integration, for temporomandibular joint and dental clinical decision support systems.

Decision Support Systems in Temporomandibular Joint Osteoarthritis: A review of Data Science and Artificial Intelligence Applications.

With the exponential growth of computational systems and increased patient data acquisition, dental research faces new challenges to manage a large quantity of information. For this reason, data science approaches are needed for the integrative diagnosis of multifactorial diseases, such as Temporomandibular joint (TMJ) Osteoarthritis (OA). The Data science spectrum includes data capture/acquisition, data processing with optimized web-based storage and management, data analytics involving in-depth statistical analysis, machine learning (ML) approaches, and data communication. Artificial intelligence (AI) plays a crucial role in this process. It consists of developing computational systems that can perform human intelligence tasks, such as disease diagnosis, using many features to help in the decision-making support. Patient's clinical parameters, imaging exams, and molecular data are used as the input in cross-validation tasks, and human annotation/diagnosis is also used as the gold standard to train computational learning models and automatic disease classifiers. This paper aims to review and describe AI and ML techniques to diagnose TMJ OA and data science approaches for imaging processing. We used a web-based system for multi-center data communication, algorithms integration, statistics deployment, and process the computational machine learning models. We successfully show AI and data-science applications using patients' data to improve the TMJ OA diagnosis decision-making towards personalized medicine.

ShapeAXI: Shape Analysis Explainability and Interpretability.

ShapeAXI represents a cutting-edge framework for shape analysis that leverages a multi-view approach, capturing 3D objects from diverse viewpoints and subsequently analyzing them via 2D Convolutional Neural Networks (CNNs). We implement an automatic N-fold cross-validation process and aggregate the results across all folds. This ensures insightful explainability heat-maps for each class across every shape, enhancing interpretability and contributing to a more nuanced understanding of the underlying phenomena. We demonstrate the versatility of ShapeAXI through two targeted classification experiments. The first experiment categorizes condyles into healthy and degenerative states. The second, more intricate experiment, engages with shapes extracted from CBCT scans of cleft patients, efficiently classifying them into four severity classes. This innovative application not only aligns with existing medical research but also opens new avenues for specialized cleft patient analysis, holding considerable promise for both scientific exploration and clinical practice. The rich insights derived from ShapeAXI's explainability images reinforce existing knowledge and provide a platform for fresh discovery in the fields of condyle assessment and cleft patient severity classification. As a versatile and interpretative tool, ShapeAXI sets a new benchmark in 3D object interpretation and classification, and its groundbreaking approach hopes to make significant contributions to research and practical applications across various domains. ShapeAXI is available in our GitHub repository https://github.com/DCBIA-OrthoLab/ShapeAXI.

Integrative Risk Predictors of Temporomandibular Joint Osteoarthritis Progression.

In this paper we propose feature selection and machine learning approaches to identify a combination of features for risk prediction of Temporomandibular Joint (TMJ) disease progression. In a sample of 32 TMJ osteoarthritis and 38 controls, feature selection of 5 clinical comorbidities, 43 quantitative imaging, 28 biological features and was performed using Maximum Relevance Minimum Redundancy, Chi-Square and Least Absolute Shrinkage and Selection Operator (LASSO) and Recursive Feature Elimination. We compared the performance of learning using concave and convex kernels (LUCCK), Support Vector Machine (SVM) and Random Forest (RF) approaches to predict disease cure/improvement or persistence/worsening. We show that the SVM model using LASSO achieves area under the curve (AUC), sensitivity and precision of 0.92±0.08, 0.85±0.19 and 0.76 ±0.18, respectively. Baseline levels of headaches, lower back pain, restless sleep, muscle soreness, articular fossa bone surface/bone volume and trabecular separation, condylar High Gray Level Run Emphasis and Short Run High Gray Level Emphasis, saliva levels of 6Ckine, Osteoprotegerin (OPG) and Angiogenin, and serum levels of 6ckine and Brain Derived Neurotrophic Factor (BDNF) were the most frequently occurring features to predict more severe TMJ osteoarthritis prognosis.

Condylar Position in the Treatment of Obstructive Sleep Apnea with a Mandibular Advancement Device: A Pilot Study.

Objective To evaluate, through a tomographic analysis, the positional changes of the condyle when using a mandibular advancement device (MAD) for the treatment of obstructive sleep apnea (OSA), and to assess if the condylar positions influence OSA polysomnographic patterns. Materials and Methods Ten OSA patients underwent treatment with an MAD, and polysomnographic and tomographic examinations were performed before therapy (T0) and after MAD placement (T1). Results By comparing the T0 and T1 measurements, we observed advancement and extrusion of the condyles in all patients ( p < 0.001), as well as a decrease in the apnea-hypopnea index (AHI) ( p < 0.001), increases in the mean ( p = 0.001) and minimum ( p < 0.001) oxyhemoglobin saturation, and a significant correlation between the anterior displacement of the right ( p = 0.003) and left ( p = 0.015) condyles. Discussion Condylar advancement was directly correlated with OSA improvement: the greater the advancement, the better the AHI.

Osteoarthritis Diagnosis Integrating Whole Joint Radiomics and Clinical Features for Robust Learning Models Using Biological Privileged Information.

This paper proposes a machine learning model using privileged information (LUPI) and normalized mutual information feature selection method (NMIFS) to build a robust and accurate framework to diagnose patients with Temporomandibular Joint Osteoarthritis (TMJ OA). To build such a model, we employ clinical, quantitative imaging and additional biological markers as privileged information. We show that clinical features play a leading role in the TMJ OA diagnosis and quantitative imaging features, extracted from cone-beam computerized tomography (CBCT) scans, improve the model performance. As the proposed LUPI model employs biological data in the training phase (which boosted the model performance), this data is unnecessary for the testing stage, indicating the model can be widely used even when only clinical and imaging data are collected. The model was validated using 5-fold stratified cross-validation with hyperparameter tuning to avoid the bias of data splitting. Our method achieved an AUC, specificity and precision of 0.81, 0.79 and 0.77, respectively.

DENTALMODELSEG: FULLY AUTOMATED SEGMENTATION OF UPPER AND LOWER 3D INTRA-ORAL SURFACES.

In this paper, we present a deep learning-based method for surface segmentation. This technique consists of acquiring 2D views and extracting features from the surface such as the normal vectors. The rendered images are analyzed with a 2D convolutional neural network, such as a UNET. We test our method in a dental application for the segmentation of dental crowns. The neural network is trained for multi-class segmentation, using image labels as ground truth. A 5-fold cross-validation was performed, and the segmentation task achieved an average Dice of 0.97, sensitivity of 0.98 and precision of 0.98. Our method and algorithms are available as a 3DSlicer extension.

Interpretable artificial intelligence for classification of alveolar bone defect in patients with cleft lip and palate.

Cleft lip and/or palate (CLP) is the most common congenital craniofacial anomaly and requires bone grafting of the alveolar cleft. This study aimed to develop a novel classification algorithm to assess the severity of alveolar bone defects in patients with CLP using three-dimensional (3D) surface models and to demonstrate through an interpretable artificial intelligence (AI)-based algorithm the decisions provided by the classifier. Cone-beam computed tomography scans of 194 patients with CLP were used to train and test the performance of an automatic classification of the severity of alveolar bone defect. The shape, height, and width of the alveolar bone defect were assessed in automatically segmented maxillary 3D surface models to determine the ground truth classification index of its severity. The novel classifier algorithm renders the 3D surface models from different viewpoints and captures 2D image snapshots fed into a 2D Convolutional Neural Network. An interpretable AI algorithm was developed that uses features from each view and aggregated via Attention Layers to explain the classification. The precision, recall and F-1 score were 0.823, 0.816, and 0.817, respectively, with agreement ranging from 97.4 to 100% on the severity index within 1 group difference. The new classifier and interpretable AI algorithm presented satisfactory accuracy to classify the severity of alveolar bone defect morphology using 3D surface models of patients with CLP and graphically displaying the features that were considered during the deep learning model's classification decision.

Automated Orientation and Registration of Cone-Beam Computed Tomography Scans.

Automated clinical decision support systems rely on accurate analysis of three-dimensional (3D) medical and dental images to assist clinicians in diagnosis, treatment planning, intervention, and assessment of growth and treatment effects. However, analyzing longitudinal 3D images requires standardized orientation and registration, which can be laborious and error-prone tasks dependent on structures of reference for registration. This paper proposes two novel tools to automatically perform the orientation and registration of 3D Cone-Beam Computed Tomography (CBCT) scans with high accuracy (<3° and <2mm of angular and linear errors when compared to expert clinicians). These tools have undergone rigorous testing, and are currently being evaluated by clinicians who utilize the 3D Slicer open-source platform. Our work aims to reduce the sources of error in the 3D medical image analysis workflow by automating these operations. These methods combine conventional image processing approaches and Artificial Intelligence (AI) based models trained and tested on de-identified CBCT volumetric images. Our results showed robust performance for standardized and reproducible image orientation and registration that provide a more complete understanding of individual patient facial growth and response to orthopedic treatment in less than 5 min.

Clear aligner mandibular advancement in growing patients with Class II malocclusion.

Treatment effects occurring during Class II malocclusion treatment with the clear aligner mandibular advancement protocol were evaluated in two growing patients: one male (12 years, 3 months) and one female (11 years, 9 months). Both patients presented with full cusp Class II molar and canine relationships. Intraoral scans and cone-beam computed tomography were acquired before treatment and after mandibular advancement. Three-dimensional skeletal and dental long-axis changes were quantified, in which the dental long axis was determined by registering the dental crowns obtained from intraoral scans to the root canals in cone-beam computed tomography scans obtained at the same time points. Class II correction was achieved by a combination of mandibular skeletal and dental changes. A similar direction of skeletal and dental changes was observed in both patients, with downward and forward displacement of the mandible resulting from the growth of the mandibular condyle and ramus. Dental changes in both patients included mesialization of the mandibular posterior teeth with flaring of mandibular anterior teeth. In these two patients, clear aligner mandibular advancement was an effective treatment modality for Class II malocclusion correction with skeletal and dental effects and facial profile improvement.