@article{nokey,

title = {A semi-automated assessment tool for craniofacial landmarks in CBCT: InVivo7 software},

author = {Luísa Schubach da Costa Barreto and Bruno Moreira das Neves and Jonas Bianchi and Heesoo Oh and Klaus Barretto dos Santos Lopes Batista and Jose Augusto Mendes Miguel},

url = {https://www.sciencedirect.com/science/article/pii/S0300571225007353?pes=vor&utm_source=scopus&getft_integrator=scopus},

doi = {https://doi.org/10.1016/j.jdent.2025.106292},

year  = {2026},

date = {2026-02-01},

urldate = {2026-02-01},

journal = {Journal of Dentistry},

volume = {165},

abstract = {Objectives: This study describes and evaluates the functionality of the InVivo7 3D imaging software as a semiautomated tool for identifying craniofacial landmarks in CBCT scans. Methods: AI-assisted landmark tracing in InVivo7 was used to automatically identify anatomical points in CBCT images. Each landmark was manually verified by a skilled evaluator to ensure accurate and reliable results, particularly for soft tissue markers and dental measurements, which often presented challenges for AI detection. The study utilized a standardized cephalometric analysis to compare the software’s performance. The evaluation included assessing the software’s ability to recognize skeletal, dental, and soft tissue structures accurately. Results: The semi-automated AI-assisted algorithm showed high precision in landmark identification. Manual verification confirmed its reliability and allowed the creation of a customized automated configuration for orthodontic diagnosis and treatment outcome evaluation. Specific clinical measures, such as the facial plane angle and molar relationships, were calculated using established formulas, allowing the software to categorize molar relationship classes (Angle Class I, II, III). Conclusions: InVivo7 presents a reliable and efficient tool for craniofacial landmark analysis, enhancing diagnostic accuracy while reducing manual labor. However, ongoing validation and software updates are essential to fully optimize its clinical applicability and ensure consistent performance across diverse patient populations. Future developments should focus on refining AI algorithms to improve soft tissue landmark detection and expanding datasets to enhance the robustness of automated analyses. Clinical Relevance: Rule-based automated algorithm CBCT craniofacial landmark detection using InVivo7 provides accurate, reproducible measurements, reducing manual workload and enhancing orthodontic diagnostic efficiency. Its integration into clinical practice supports standardized assessments, streamlining treatment planning.},

keywords = {3d, anatomic landmarks, artificial intelligence, CBCT, orthodontics},

pubstate = {published},

tppubtype = {article}

}

@article{nokey,

title = {Explainable artificial intelligence to quantify adenoid hypertrophy-related upper airway obstruction using 3D Shape Analysis},

author = {Claudia Trindade Mattos and Lucie Dole and Sergio Luiz Mota-Júnior and Adriana de Alcantara Cury-Saramago and Jonas Bianchi and Heesoo Oh and Karine Evangelista and José Valladares-Neto and Antonio Carlos de Oliveira Ruellas and Juan Carlos Prieto and Lucia Helena Soares Cevidanes },

url = {https://www.sciencedirect.com/science/article/pii/S0300571225001344},

doi = {https://doi.org/10.1016/j.jdent.2025.105689},

issn = {0300-5712},

year  = {2025},

date = {2025-05-01},

journal = {Journal of Dentistry},

volume = {156},

abstract = {Objectives: To develop and validate an explainable Artificial Intelligence (AI) model for classifying and quantifying upper airway obstruction related to adenoid hypertrophy using three-dimensional (3D) shape analysis of cone-beam computed tomography (CBCT) scans. Methods: 400 CBCT scans of patients aged 5–18 years were analyzed. Nasopharyngeal airway obstruction (NAO) ratio was calculated to label scans into four grades of obstruction severity, used as the ground truth. Upper airway surface meshes were used to train a deep learning model combining multiview and point-cloud approaches for 3D shape analysis and obstruction severity classification and quantification. Surface Gradient weighted Class Activation Mapping (SurfGradCAM) generated explainability heatmaps. Performance was evaluated using area under the curve (AUC), precision, recall, F1-score, mean absolute error, root mean squared error, and correlation coefficients. Results: The explainable AI model demonstrated strong performance in both classification and quantification tasks. The AUC values for the classification task ranged from 0.77 to 0.94, with the highest values of 0.88 and 0.94 for Grades 3 and 4, respectively, indicating excellent discriminative ability for identifying more severe cases of obstruction. The SurfGradCAM-generated heatmaps consistently highlighted the most relevant regions of the upper airway influencing the AI’s decision-making process. In the quantification task, the regression model successfully predicted the NAO ratio, with a strong correlation coefficient of 0.854 (p < 0.001) and R2 = 0.728, explaining a substantial proportion of the variance in NAO ratios. Conclusions: The proposed explainable AI model, using 3D shape analysis, demonstrated strong performance in classifying and quantifying adenoid hypertrophy-related upper airway obstruction in CBCT scans. Clinical significance: This AI model provides clinicians with a reliable, automated tool for standardized adenoid hypertrophy assessment. The model’s explainable nature enhances clinical confidence and patient communication, potentially improving diagnostic workflow and treatment planning.},

keywords = {3D shape analysis, Adenoid hypertrophy, artificial intelligence, CBCT, Upper Airway obstruction},

pubstate = {published},

tppubtype = {article}

}

@article{Jung2025,

title = {Accuracy and reliability of automated landmark identification and cephalometric measurements on cone beam computed tomography using Invivo software},

author = {Young-Eun Jung and Heeyeon Suh and Joorok Park and Heesoo Oh },

url = {https://angle-orthodontist.kglmeridian.com/view/journals/angl/95/4/article-p362.xml},

doi = {10.2319/122324-1049.1},

year  = {2025},

date = {2025-04-10},

urldate = {2025-04-10},

journal = {The Angle Orthodontist},

volume = {95},

issue = {4},

pages = {362-370},

abstract = {Objectives: To evaluate the accuracy and reliability of an automated landmark identification (ALI) system and the impact of ALI errors on cephalometric measurements on cone-beam computed tomography (CBCT) images. Materials and Methods: Thirty-one landmarks were identified on 76 CBCT images using Invivo7 software (Anatomage, San Jose, Calif). Ground truth was established by averaging landmark coordinates from two calibrated human examiners. The accuracy of the ALI system was assessed by the mean absolute error (MAE, mm) across coordinate axes, the mean error distance (mm), and the successful detection rate (SDR) for each landmark. Interexaminer reliability between the ALI and manual landmark location was evaluated. Eighteen cephalometric measurements were computed from 25 landmarks. Accuracy of measurements from the ALI system was assessed with the MAE and successful measurement rates (SMR). Results: The ALI system closely matched human examiners in landmark identification, with an average MAE of 0.94 +/- 0.99 mm. Across all three coordinate axes, 87% of the landmarks had <2 mm MAE. ALI average MAE for conventional linear and angular cephalometric measurements were 1.35 +/- 1.33 mm and 0.89 +/- 0.89 degrees, respectively. Only one measurement, Intercondylar Width, showed MAE >3 mm. Conclusions: The ALI system showed clinically acceptable accuracy and reliability for the majority of cephalometric landmarks and measurements. Clinicians are advised to critically evaluate ALI landmarks with substantial errors, to fully utilize the capabilities of commercial software effectively. (Angle Orthod. 2025;95:362–370.)},

keywords = {Automated, CBCT, Cephalometric analysis, Landmark Identification},

pubstate = {published},

tppubtype = {article}

}

@article{Leroux2024,

title = {Novel CBCT-MRI Registration Approach for Enhanced Analysis of Temporomandibular Degenerative Joint Disease},

author = {Gaelle Leroux and Claudia Mattos and Jeanne Claret and Eduardo Caleme and Selene Barone and Marcela Gurgel and Felicia Miranda and Joao Goncalves and Paulo Zupelari Goncalves and marina Morettin Zupelari and Larry Wolford and Nina Hsu and Antonio Ruellas and Jonas Bianchi and Juan Prieto and Lucia Cevidanes},

url = {https://doi.org/10.1007/978-3-031-73083-2_7},

doi = {10.1007/978-3-031-73083-2_7},

isbn = {978-3-031-73083-2},

year  = {2024},

date = {2024-09-29},

urldate = {2024-09-29},

journal = {Clinical Image-Based Procedures. CLIP},

volume = {15196},

pages = {63-72},

abstract = {Temporomandibular Degenerative Joint Disease (TM DJD) is characterized by chronic and progressive degeneration of the joint, leading to functional limitations. Converging on enhancing TM DJD diagnosis, prognosis, and personalized patient care, multimodal Cone Beam Computed Tomography (CBCT) and Magnetic Resonance Imaging (MRI) registration aims to allow comprehensive understanding of the articular disc and subchondral bone alterations towards elucidating the onset, advancement, and progression of TM DJDs. This study proposes a novel multimodal image registration (fusion) approach that combines image processing techniques with mutual information to register MRI to CBCT images, enhancing TMJ complex visualization and analysis. The algorithm leverages automated image orientation, resampling, MRI inversion, normalization and rigid mutual information registration methods to align and overlay multimodal images while preserving anatomical details. Evaluation on 70 CBCT and 70 MRI scans acquired at the same time points for 70 TM DJD patients demonstrates robustness to variations in image quality, anatomical morphology, and acquisition protocols. By integrating MRI soft tissue information with CBCT bony details, this novel open-source tool available in the 3D Slicer platform provides a more comprehensive patient-specific TM DJD model. The current 98.75% success rate, with mean absolute rotation differences of 1.53 degrees ± 1.75 degrees, 1.69 degrees ± 1.54 degrees, and 2.70 degrees ± 2.89 degrees in Pitch, Roll and Yaw respectively; and translation differences of 0.92mm ± 1.64mm, 0.98mm ± 0.85mm, and 0.5mm ± 0.43mm in respectively the Left-Right, Antero-Posterior and Supero-Inferior axes. The proposed approach has potential to enhance care for TM DJD and other conditions requiring multimodal images.

},

keywords = {3D Slicer, CBCT, MRI, TMJ complex visualization},

pubstate = {published},

tppubtype = {article}

}

@article{Prieto2024,

title = {ShapeAXI: shape analysis explainability and interpretability},

author = {Juan Carlos Prieto and Felicia Miranda and Marcela Gurgel and Luc Anchling and Nathan Hutin and Selene Barone and Najla Al Turkestani and Aron Aliaga Del Castillo and Marilia Yatabe and Jonas Bianchi and Lucia Cevidanes},

url = {https://doi.org/10.1117/12.3007053},

doi = {10.1117/12.3007053},

year  = {2024},

date = {2024-04-02},

journal = {Medical Imaging 2024: Imaging Informatics for Healthcare, Research, and Applications},

volume = {12931},

abstract = {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.},

keywords = {CBCT, cleft patients, Convolutional Neural Networks, ShapeAXI},

pubstate = {published},

tppubtype = {article}

}

@article{Bianchi2022b,

title = {Automatic multi-anatomical skull structure segmentation of cone-beam computed tomography scans during 3D UNETR},

author = {Gillot M and Baquero B and Le C and R Deleat-Besson and Bianchi J and Gurgel M and Yatabe M and Al Turkestani N and Najarian K},

url = {https://pubmed.ncbi.nlm.nih.gov/36223330/},

doi = {10.1371/journal.pone.0275033},

year  = {2022},

date = {2022-10-12},

journal = {PLoS One},

volume = {17},

issue = {10},

abstract = {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.},

keywords = {3d, CBCT, Cone-beam computed tomography (CBCT), multi-anatomical skull structure, structure segmentation},

pubstate = {published},

tppubtype = {article}

}

@article{Oh2022b,

title = {Automated landmark identification on one cone beam computed tomography: Accuracy and reliability},

author = {A Ghowsi and D Hatcher and H Suh and D Wiled and W Castro and J Krueger and J Park and H Oh},

url = {https://pubmed.ncbi.nlm.nih.gov/35653226/},

doi = {10.2319/122121-928.1},

year  = {2022},

date = {2022-06-02},

urldate = {2022-06-02},

journal = {Angle Orthodontist},

volume = {92},

pages = {642-654},

abstract = {Objectives: To evaluate the accuracy and reliability of a fully automated landmark identification (ALI) system as a tool for automatic landmark location compared with human judges.



Materials and methods: A total of 100 cone-beam computed tomography (CBCT) images were collected. After the calibration procedure, two human judges identified 53 landmarks in the x, y, and z coordinate planes on CBCTs using Checkpoint Software (Stratovan Corporation, Davis, Calif). The ground truth was created by averaging landmark coordinates identified by two human judges for each landmark. To evaluate the accuracy of ALI, the mean absolute error (mm) at the x, y, and z coordinates and mean error distance (mm) between the human landmark identification and the ALI were determined, and a successful detection rate was calculated.



Results: Overall, the ALI system was as successful at landmarking as the human judges. The ALI's mean absolute error for all coordinates was 1.57 mm on average. Across all three coordinate planes, 94% of the landmarks had a mean absolute error of less than 3 mm. The mean error distance for all 53 landmarks was 3.19 ± 2.6 mm. When applied to 53 landmarks on 100 CBCTs, the ALI system showed a 75% success rate in detecting landmarks within a 4-mm error distance range.



Conclusions: Overall, ALI showed clinically acceptable mean error distances except for a few landmarks. The ALI was more precise than humans when identifying landmarks on the same image at different times. This study demonstrates the promise of ALI in aiding orthodontists with landmark identifications on CBCTs.},

keywords = {3D landmark identification, AAOF, accuracy, Automated, CBCT, Landmark error, Reliability},

pubstate = {published},

tppubtype = {article}

}

@article{Oh2022g,

title = {Condylar degeneration in anterior open bite patients: A cone-beam computed tomography (CBCT) study.},

author = {L Phi and B Albertson and D Hatcher and S Rathi and J Park and H Oh },

url = {https://pubmed.ncbi.nlm.nih.gov/34503937/},

doi = {10.1016/j.oooo.2021.07.019},

year  = {2022},

date = {2022-02-01},

journal = {Oral Surgery Oral Med Oral Path Oral Radiology },

volume = {133},

issue = {2},

pages = {221-228},

abstract = {Objectives: The purpose of this study was to investigate the prevalence of condylar degeneration in patients with anterior open bites (AOB).



Study design: Cone beam computed tomography (CBCT) scans of 194 patients with AOB (108 with skeletal open bites and 86 with dental open bites) and 100 patients serving as controls were included in this retrospective study. Two oral and maxillofacial radiologists categorized each of the 588 condyles as normal, degenerative-active, or degenerative-repair. The χ2 analysis with Bonferroni adjustment was used to evaluate the relationship of condylar status (normal vs degenerative) to anterior open bites.



Results: Of the 103 degenerative condyles, there were 59 in the group with skeletal open bites, 14 in the group with dental open bites, and 30 in the control group. Condylar degeneration occurred twice as frequently in patients with skeletal open bites as it did in the control group (P < .0001). Conversely, a greater frequency of normal condyles was found in the group of patients with dental open bites (P = .0002). The group with skeletal open bites also showed a significantly higher frequency of bilateral degenerative condyles (P = .0001). The frequency of condylar degeneration did not differ significantly between female and male individuals.



Conclusions: Degenerative condylar change was significantly more likely in patients with skeletal open bites and less likely in patients with dental open bites.},

keywords = {anterior openbite, CBCT, condylar degeneration, Cone-beam computed tomography},

pubstate = {published},

tppubtype = {article}

}

@article{Bianchi2022f,

title = {Dental long axes using digital dental models compared to cone-beam computed tomography},

author = {Cong A and Massaro C and Ruellas A.C and de O and Barkley M and Yatabe M and Bianchi J and Ioshida M and Alvarez M.A and Aristizabal J.F and Rey D},

url = {https://pubmed.ncbi.nlm.nih.gov/33966340/},

doi = {10.1111/ocr.12489},

year  = {2022},

date = {2022-02-01},

journal = {Orthod Craniofac Res},

volume = {25},

issue = {1},

pages = {64-72},

abstract = {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.},

keywords = {CBCT, Dental long axis, digital dental models},

pubstate = {published},

tppubtype = {article}

}