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.

Automatic multi-anatomical skull structure segmentation of cone-beam computed tomography scans using 3D UNETR.

The segmentation of medical and dental images is a fundamental step in automated clinical decision support systems. It supports the entire clinical workflow from diagnosis, therapy planning, intervention, and follow-up. In this paper, we propose a novel tool to accurately process a full-face segmentation in about 5 minutes that would otherwise require an average of 7h of manual work by experienced clinicians. This work focuses on the integration of the state-of-the-art UNEt TRansformers (UNETR) of the Medical Open Network for Artificial Intelligence (MONAI) framework. We trained and tested our models using 618 de-identified Cone-Beam Computed Tomography (CBCT) volumetric images of the head acquired with several parameters from different centers for a generalized clinical application. Our results on a 5-fold cross-validation showed high accuracy and robustness with a Dice score up to 0.962±0.02. Our code is available on our public GitHub repository.

Dental long axes using digital dental models compared to cone-beam computed tomography.

OBJECTIVE: Standard methods of evaluating tooth long axes are not comparable (digital dental models [DDMs], panoramic and cephalometric radiographs) or expose patients to more radiation (cone-beam computed tomography [CBCT]). This study aimed to compare angular changes in tooth long axes using DDMs vs using CBCTs. SETTINGS AND SAMPLE POPULATION: Secondary data analysis of DDMs and CBCTs, taken before and after orthodontic treatment with piezocision of 24 patients. METHODS: Angular changes in tooth long axes were evaluated using landmarks on first molars (centre of the occlusal surface and centre of the furcation), canines and incisors (cusp tip and centre of the root at the cementoenamel junction). Wilcoxon test, intraclass correlation coefficient (ICC) and Bland-Altman plots were used to test intra- and inter-rater agreement and compare DDM and CBCT measurements. RESULTS: The mesiodistal angulation and buccolingual inclination DDM measurements were reproducible. Overall mean differences between DDM and CBCT measurements of mesiodistal angulation, 1.9°±1.5°, and buccolingual inclination, 2.2 ± 2.2°, were not significant for all teeth. ICC between DDM and CBCT measurements ranged from good (0.85 molars) to excellent (0.94 canines; 0.96 incisors). The percentages of measurements outside the range of ±5 were 17.4% for molars, 13.8% for canines and 4.5% for incisors. CONCLUSIONS: DDM assessment of changes in tooth long axes has good reproducibility and yields comparable measurements to those obtained from CBCT within a 5° range. These findings lay the groundwork for machine learning approaches that synthesize crown and root canal information towards planning tooth movement without the need for ionizing radiation scans.

Automatic Segmentation of Dental Root Canal and Merging with Crown Shape.

In this paper, machine learning approaches are proposed to support dental researchers and clinicians to study the shape and position of dental crowns and roots, by implementing a Patient Specific Classification and Prediction tool that includes RootCanalSeg and DentalModelSeg algorithms and then merges the output of these tools for intraoral scanning and volumetric dental imaging. RootCanalSeg combines image processing and machine learning approaches to automatically segment the root canals of the lower and upper jaws from large datasets, providing clinical information on tooth long axis for orthodontics, endodontics, prosthodontic and restorative dentistry procedures. DentalModelSeg includes segmenting the teeth from the crown shape to provide clinical information on each individual tooth. The merging algorithm then allows users to integrate dental models for quantitative assessments. Precision in dentistry has been mainly driven by dental crown surface characteristics, but information on tooth root morphology and position is important for successful root canal preparation, pulp regeneration, planning of orthodontic movement, restorative and implant dentistry. In this paper we propose a patient specific classification and prediction of dental root canal and crown shape analysis workflow that employs image processing and machine learning methods to analyze crown surfaces, obtained by intraoral scanners, and three-dimensional volumetric images of the jaws and teeth root canals, obtained by cone beam computed tomography (CBCT).

FlyBy CNN: A 3D surface segmentation framework.

In this paper, we present FlyBy CNN, a novel deep learning based approach for 3D shape segmentation. FlyByCNN consists of sampling the surface of the 3D object from different view points and extracting surface features such as the normal vectors. The generated 2D images are then analyzed via 2D convolutional neural networks such as RUNETs. We test our framework in a dental application for segmentation of intra-oral surfaces. The RUNET is trained for the segmentation task using image pairs of surface features and image labels as ground truth. The resulting labels from each segmented image are put back into the surface thanks to our sampling approach that generates 1-1 correspondence of image pixels and triangles in the surface model. The segmentation task achieved an accuracy of 0.9.

Buccal bone defects and transversal tooth movement of mandibular lateral segments in patients after orthodontic treatment with and without piezocision: A case-control retrospective study.

INTRODUCTION: This study aimed to compare the extent of buccal bone defects (dehiscences and fenestrations) and transversal tooth movement of mandibular lateral segments in patients after orthodontic treatment with and without piezocision in cone-beam computed tomography and digital dental models. METHODS: The study sample of this study consisted of cone-beam computed tomography scans and digital dental models taken before (T0) and after (T1) orthodontic treatment of 36 patients with moderate mandibular anterior crowding. The experimental group consisted of 17 patients that had piezocision performed at the beginning of treatment with the goal of accelerating tooth movement, which was compared with 19 patients who did not receive piezocision. The measurement of bone defects, buccolingual inclination, and transversal distances of the tooth in the mandibular lateral segments (mandibular canines, premolars, and first molars) were evaluated at baseline and at the end of the orthodontic treatment. RESULTS: Overall, an increase in dehiscences, buccal inclination, and arch width from T0 to T1 was observed in both groups, but no statistically significant difference was found between groups. A significant increase in fenestrations from T0 to T1 was observed only for the canines in the experimental group. No statistically significant association was found between the increase of dehiscences and the amount of buccolingual inclination or transversal width changes. However, the changes in transversal width were statistically significantly associated with the increase in buccal inclination at the canines, first and second premolars. CONCLUSIONS: No significant differences were found in buccal dehiscences and transversal tooth movement (buccolingual inclination and arch width) of mandibular lateral segments between patients after orthodontic treatment with and without piezocision. Dehiscences, buccal inclination, and arch width significantly increased from T0 to T1 in both groups.

Comparison of linear and angular changes assessed in digital dental models and cone-beam computed tomography.

OBJECTIVE: To compare the three-dimensional (3D) linear displacements and the mesiodistal and buccolingual angulation changes after orthodontic treatment in digital dental models (DDMs) and 3D models derived from cone-beam computed tomography (CBCT). SETTINGS AND SAMPLE POPULATION: Digital dental model and CBCT scans were selected from 24 adults who had undergone orthodontic treatment for mandibular anterior crowding. MATERIAL AND METHODS: 3D linear displacements and changes in angular measurements (mesiodistal and buccolingual angulation) were assessed in pre- and post-treatment DDM and CBCT images using the software ITK-snap and 3D SlicerCMF. Intra- and inter-rater agreement of measurements in DDM and CBCT were tested using the intraclass correlation coefficient (ICC). DDM and CBCT measurements were compared using the Wilcoxon test (P < .05), ICC and Bland-Altman plots. RESULTS: Intra- and inter-rater agreement varied from good (ICC > 0.75) to excellent (ICC > 0.90) for both DDM and CBCT measurements. Although no significant difference between DDM and CBCT methods was observed for linear measurements of tooth movement, the angular assessments were different for most measurements. The agreement between measurements from both assessments varied from poor to excellent. CONCLUSIONS: Longitudinal assessments of tooth movements including 3D linear displacements and mesiodistal and buccolingual angulation are reproducible when using both DDM and CBCT. Changes in angular measurements due to orthodontic treatment are discordant when measured in the digital models (clinical crown) and in the CBCT images (whole tooth).

Patient Specific Classification of Dental Root Canal and Crown Shape.

This paper proposes machine learning approaches to support dentistry researchers in the context of integrating imaging modalities to analyze the morphology of tooth crowns and roots. One of the challenges to jointly analyze crowns and roots with precision is that two different image modalities are needed. Precision in dentistry is mainly driven by dental crown surfaces characteristics, but information on tooth root shape and position is of great value for successful root canal preparation, pulp regeneration, planning of orthodontic movement, restorative and implant dentistry. An innovative approach is to use image processing and machine learning to combine crown surfaces, obtained by intraoral scanners, with three dimensional volumetric images of the jaws and teeth root canals, obtained by cone beam computed tomography. In this paper, we propose a patient specific classification of dental root canal and crown shape analysis workflow that is widely applicable.

Shape variation analyzer: a classifier for temporomandibular joint damaged by osteoarthritis.

We developed a deep learning neural network, the Shape Variation Analyzer (SVA), that allows disease staging of bony changes in temporomandibular joint (TMJ) osteoarthritis (OA). The sample was composed of 259 TMJ CBCT scans for the training set and 34 for the testing dataset. The 3D meshes had been previously classified in 6 groups by 2 expert clinicians. We improved the robustness of the training data using data augmentation, SMOTE, to alleviate over-fitting and to balance classes. We combined geometrical features and a shape descriptor, heat kernel signature, to describe every shape. The results were compared to nine different supervised machine learning algorithms. The deep learning neural network was the most accurate for classification of TMJ OA. In conclusion, SVA is a 3D Sheer extension that classifies pathology of the temporomandibular joint osteoarthritis cases based on 3D morphology.

Challenges in measuring angles between craniofacial structures.

OBJECTIVE: Three-dimensional (3D) angular measurements between craniofacial planes pose challenges to quantify maxillary and mandibular skeletal discrepancies in surgical treatment planning. This study aims to compare the reproducibility and reliability of two modules to measure angles between planes or lines in 3D virtual surface models. METHODOLOGY: Twenty oriented 3D virtual surface models de-identified and constructed from CBCT scans were randomly selected. Three observers placed landmarks and oriented planes to determine angular measurements of pitch, roll and yaw using (1) 3D pre-existing planes, (2) 3D planes created from landmarks and (3) lines created from landmarks. Inter- and intra-observer reproducibility and repeatability were examined using the Intra-Class Correlation (ICC) test. One observer repeated the measurements with an interval of 15 days. ANOVA was applied to compare the 3 methods. RESULTS: The three methods tested provided statistically similar, reproducible and reliable angular measurements of the facial structures. A strong ICC varying from 0.92 to 1.00 was found for the intra-observer agreement. The inter-observer ICC varied from 0.84 to 1.00. CONCLUSION: Measurements of 3D angles between facial planes in a common coordinate system are reproducible and repeatable either using 3D pre-existing planes, created based on landmarks or angles between lines created from landmarks.

A web-based system for statistical shape analysis in temporomandibular joint osteoarthritis.

This study presents a web-system repository: Data Storage for Computation and Integration (DSCI) for Osteoarthritis of the temporomandibular joint (TMJ OA). This environment aims to maintain and allow contributions to the database from multi-clinical centers and compute novel statistics for disease classification. For this purpose, imaging datasets stored in the DSCI consisted of three-dimensional (3D) surface meshes of condyles from CBCT, clinical markers and biological markers in healthy and TMJ OA subjects. A clusterpost package was included in the web platform to be able to execute the jobs in remote computing grids. The DSCI application allowed runs of statistical packages, such as the Multivariate Functional Shape Data Analysis to compute global correlations between covariates and the morphological variability, as well as local p-values in the 3D condylar morphology. In conclusion, the DSCI allows interactive advanced statistical tools for non-statistical experts.

Accuracy and reliability of mandibular digital model registration with use of the mucogingival junction as the reference.

OBJECTIVE: The aim of the study was to validate a method of mandibular digital model (DM) registration, acquired from an intraoral scanner, compared with high-resolution voxel-based cone beam computed tomography (CBCT) registration with use of the mucogingival junction as the reference. STUDY DESIGN: Pre- and post-treatment CBCT and DM images from 12 adults were randomly selected from an initial sample of 40 patients who had undergone orthodontic treatment. The DM registration was performed in 6 steps: (1) construction of 3-dimensional (3-D) volumetric label maps of CBCT scans, (2) voxel-based registration of CBCT scans, (3) prelabeling of CBCT images, (4) approximation and registration of DM models to the corresponding CBCT models, (5) mucogingival-junction registration of pretreatment and post-treatment DM images, and (6) measurements. The Mann-Whitney U test was used to calculate the significance of differences between the CBCT and DM registrations. The intraclass correlation coefficient (ICC) was performed to assess reproducibility of the registration method. RESULTS: When registered CBCT models and registered DM models were compared, no statistically significant differences in the measurements were found (right-left P = .267; anterior-posterior P = .238; superior-inferior P = .384; and 3-D P = .076). ICC showed excellent intra- and inter-rater correlation (ICC > 0.90). CONCLUSIONS: The method of DM registration of the mandible with use of the mucogingival junction as the reference is accurate, reliable, and reproducible.

Challenges in measuring angles between craniofacial structures

Abstract Objective: Three-dimensional (3D) angular measurements between craniofacial planes pose challenges to quantify maxillary and mandibular skeletal discrepancies in surgical treatment planning. This study aims to compare the reproducibility and reliability of two modules to measure angles between planes or lines in 3D virtual surface models. Methodology: Twenty oriented 3D virtual surface models de-identified and constructed from CBCT scans were randomly selected. Three observers placed landmarks and oriented planes to determine angular measurements of pitch, roll and yaw using (1) 3D pre-existing planes, (2) 3D planes created from landmarks and (3) lines created from landmarks. Inter- and intra-observer reproducibility and repeatability were examined using the Intra-Class Correlation (ICC) test. One observer repeated the measurements with an interval of 15 days. ANOVA was applied to compare the 3 methods. Results: The three methods tested provided statistically similar, reproducible and reliable angular measurements of the facial structures. A strong ICC varying from 0.92 to 1.00 was found for the intra-observer agreement. The inter-observer ICC varied from 0.84 to 1.00. Conclusion: Measurements of 3D angles between facial planes in a common coordinate system are reproducible and repeatable either using 3D pre-existing planes, created based on landmarks or angles between lines created from landmarks.

Volumetric reconstruction and determination of minimum crosssectional area of the pharynx in patients with cleft lip and palate: comparison between two different softwares.

OBJECTIVE: The aim of this study was to assess the accuracy of volumetric reconstruction of the pharynx by comparing the volume and minimum crosssectional area (mCSA) determined with open-source applications (ITK-Snap, www.itksnap.org ; SlicerCMF) and commercial software (Dolphin3D, 11.8, Dolphin Imaging & Management Solutions, Chatsworth, CA, USA) previously validated in the literature. MATERIAL AND METHODS: The sample comprised of 35 cone-beam computed tomography (CBCT) scans of patients with unilateral cleft lip and palate, with mean age of 29±15. Three-dimensional volumetric models of the pharynx were reconstructed using semi-automatic segmentation using the applications ITK-Snap (G1) and Dolphin3D (G2). Volumes and minimum cross-sectional areas were determined. Inter- and intra-observer error were calculated using ICC test. Comparison between applications was calculated using the Wilcoxon test. RESULTS: Volumes and minimum crosssectional area were statistically similar between applications. ITK-Snap showed higher pharynx volumes, but lower mCSA. Visual assessment showed that 62.86% matched the region of mCSA in Dolphin3D and SPHARM-PDM. CONCLUSION: Measurements of volume and mCSA are statistically similar between applications. Therefore, open-source applications may be a viable option to assess upper airway dimensions using CBCT exams.

A web-based system for neural network based classification in temporomandibular joint osteoarthritis.

OBJECTIVE: The purpose of this study is to describe the methodological innovations of a web-based system for storage, integration and computation of biomedical data, using a training imaging dataset to remotely compute a deep neural network classifier of temporomandibular joint osteoarthritis (TMJOA). METHODS: This study imaging dataset consisted of three-dimensional (3D) surface meshes of mandibular condyles constructed from cone beam computed tomography (CBCT) scans. The training dataset consisted of 259 condyles, 105 from control subjects and 154 from patients with diagnosis of TMJ OA. For the image analysis classification, 34 right and left condyles from 17 patients (39.9 ±â€¯11.7 years), who experienced signs and symptoms of the disease for less than 5 years, were included as the testing dataset. For the integrative statistical model of clinical, biological and imaging markers, the sample consisted of the same 17 test OA subjects and 17 age and sex matched control subjects (39.4 ±â€¯15.4 years), who did not show any sign or symptom of OA. For these 34 subjects, a standardized clinical questionnaire, blood and saliva samples were also collected. The technological methodologies in this study include a deep neural network classifier of 3D condylar morphology (ShapeVariationAnalyzer, SVA), and a flexible web-based system for data storage, computation and integration (DSCI) of high dimensional imaging, clinical, and biological data. RESULTS: The DSCI system trained and tested the neural network, indicating 5 stages of structural degenerative changes in condylar morphology in the TMJ with 91% close agreement between the clinician consensus and the SVA classifier. The DSCI remotely ran with a novel application of a statistical analysis, the Multivariate Functional Shape Data Analysis, that computed high dimensional correlations between shape 3D coordinates, clinical pain levels and levels of biological markers, and then graphically displayed the computation results. CONCLUSIONS: The findings of this study demonstrate a comprehensive phenotypic characterization of TMJ health and disease at clinical, imaging and biological levels, using novel flexible and versatile open-source tools for a web-based system that provides advanced shape statistical analysis and a neural network based classification of temporomandibular joint osteoarthritis.

Volumetric reconstruction and determination of minimum crosssectional area of the pharynx in patients with cleft lip and palate: comparison between two different softwares

Abstract Objective: The aim of this study was to assess the accuracy of volumetric reconstruction of the pharynx by comparing the volume and minimum crosssectional area (mCSA) determined with open-source applications (ITK-Snap, www.itksnap.org ; SlicerCMF) and commercial software (Dolphin3D, 11.8, Dolphin Imaging & Management Solutions, Chatsworth, CA, USA) previously validated in the literature. Material and Methods: The sample comprised of 35 cone-beam computed tomography (CBCT) scans of patients with unilateral cleft lip and palate, with mean age of 29±15. Three-dimensional volumetric models of the pharynx were reconstructed using semi-automatic segmentation using the applications ITK-Snap (G1) and Dolphin3D (G2). Volumes and minimum cross-sectional areas were determined. Inter- and intra-observer error were calculated using ICC test. Comparison between applications was calculated using the Wilcoxon test. Results: Volumes and minimum crosssectional area were statistically similar between applications. ITK-Snap showed higher pharynx volumes, but lower mCSA. Visual assessment showed that 62.86% matched the region of mCSA in Dolphin3D and SPHARM-PDM. Conclusion: Measurements of volume and mCSA are statistically similar between applications. Therefore, open-source applications may be a viable option to assess upper airway dimensions using CBCT exams.