Artificial Intelligence Designed Single Tooth Dental Prostheses

Artificial Intelligence in Prosthodontics - Design of Maxillary Single-tooth Dental Prostheses

Tooth loss is common and as consequence deteriorate patient's health and quality-of-life. Dental prostheses aim to restore patients' appearance and functions by replacement of missing teeth. The occlusal morphology and 3D position of the healthy natural teeth should be adopted by the dental prostheses (biomimetic). Despite computer-assisted design (CAD) software are available for designing dental prostheses, considerable clinical time are still required to fit the dental prostheses into patients' occlusion (teeth-to-teeth relationship). Teeth of an individual subjects are genetically controlled and exposed to mostly identical oral environment, therefore the occlusal morphology and 3D position of teeth are inter-related. It is hypothesized that artificial intelligence (AI) can automated designing the single-tooth dental prostheses from the features of remaining dentition.

Study Overview

• Status: Completed
• Conditions: Dental Prosthesis
• Intervention / Treatment: Other: artificial intelligence (AI) computer assisted design (CAD)

Detailed Description

Objectives:

1. To compare four deep-learning methods/algorithms in interpreting and learning of the features of 3D models;
2. To compare the AI system with maxillary tooth model alone to maxillary and mandibular (antagonist) models;
3. To compare the occlusal morphology and 3D position of the single-tooth dental prostheses designed by trained AI and by dental technicians.

Methods:

First, investigators will collect 200 maxillary dentate teeth models as training models. AI will learn the relationship between individual teeth and rest of the dentition using the 3D Generative Adversarial Network (GAN) by following deep-learning methods/algorithms:

Group 1) Voxel-based; Group 2) View-based; Group 3) Point-based; and Group 4) Fusion methods. Investigators will collect another 100 maxillary models that serve as validation models. Investigators will remove a tooth (act as control) in each model. Then investigators will evaluate these deep learning algorithms in predicting the occlusal morphology and 3D position of single-missing tooth.

Second, investigators will evaluate the need of antagonist model in predicting the occlusal morphology and 3D position of single-missing tooth in 100 validation models:

Group i) maxillary model only and Group ii) with antagonist model using the tested deep-learning algorithm in objective (1).

Third, investigators will analyze the geometric morphometric and 3D position of dental prostheses designed by:

Group a) the trained AI system; Group b) dental technicians on the physical models; and Group c) dental technicians using CAD software. Investigators will compare these teeth to the corresponding natural teeth (control) in 100 validation models.

Furthermore, investigators will analyze the time required for tooth design in these groups as secondary outcome.

• Study Type: Observational
• Enrollment (Actual): 250

Contacts and Locations

Study Locations

• Hong Kong
  • Sai Ying Pun, Hong Kong
    • Prince Philip Dental Hospital

Participation Criteria

Eligibility Criteria

• Ages Eligible for Study: 18 years and older (Adult, Older Adult)
• Accepts Healthy Volunteers: Yes

• Sampling Method: Non-Probability Sample

Study Population

• Patients attended/attending Prince Philip Dental Hospital
• Dental undergraduate students from the Faculty of Dentistry, The University of Hong Kong

Description

Inclusion Criteria:

• Subjects with sufficient dentition present for the determination of the upper occlusal plane
• Subjects with more than 12 occluding pairs and stable intercuspal position
• Subjects with teeth restorations that did not grossly alter its morphology
• Subjects who did not undergo orthodontic treatment and/or did not have teeth that rotated more than 45 degrees and/or displaced more than 1.5 mm
• Subjects who are of Cantonese descent.

Exclusion Criteria:

• Subjects with periodontal disease whereby there is pathological tooth migration and alteration of occlusal plane.
• Subjects who are under the age of 18 and unable to give consent.
• Subjects with extensive teeth restorations that affect the morphology.

Study Plan

How is the study designed?

Design Details

• Observational Models: Case-Control
• Time Perspectives: Cross-Sectional

Number of groups / cohorts

2

Cohorts and Interventions

Group / Cohort	Intervention / Treatment
Control; Original 3D maxillary teeth model from subjects who fulfill inclusion/exclusion criteria
Test; 3D maxillary teeth model from subjects who fulfill inclusion/exclusion criteria. The right first molar (FDI number 16) will be removed in the computer and then designed by artificial intelligence (AI) system AI system will be trained by; different algorithms such as Group 1) Voxel-based; Group 2) View-based; Group 3) Point-based; and Group 4) Fusion methods; Group i) maxillary model only and Group ii) with antagonist model	Other: artificial intelligence (AI) computer assisted design (CAD); Maxillary right first molar will be removed in the computer and will be designed by artificial intelligence system

What is the study measuring?

Primary Outcome Measures

Outcome Measure	Measure Description	Time Frame
3D position of tooth	The center of a tooth automatically determined by computer	Outcome will be measured when 25% of training models were studied by AI, up to 6 months
3D position of tooth	The center of a tooth automatically determined by computer	Outcome will be measured when 50% of training models were studied by AI, up to 12 months
3D position of tooth	The center of a tooth automatically determined by computer	Outcome will be measured when 75% of training models were studied by AI, up to 18 months
3D position of tooth	The center of a tooth automatically determined by computer	Outcome will be measured after the whole training, which AI was trained of 100% of all models, up to 24 months
Occlusal morphology of tooth	The cusps (highest point) and the fossa (lowest point) of the occlusal surface	Outcome will be measured when 25% of training models were studied by AI, up to 6 months
Occlusal morphology of tooth	The cusps (highest point) and the fossa (lowest point) of the occlusal surface	Outcome will be measured when 50% of training models were studied by AI, up to 12 months
Occlusal morphology of tooth	The cusps (highest point) and the fossa (lowest point) of the occlusal surface	Outcome will be measured when 75% of training models were studied by AI, upto 18 months
Occlusal morphology of tooth	The cusps (highest point) and the fossa (lowest point) of the occlusal surface	Outcome will be measured after the whole training, which AI was trained of 100% of all models, upto 24 months
Time spent in laboratory design and in clinical deliver of denture prostheses	Time (in minutes) spend in a) design and b) deliver of dental prostheses	Outcome will be measured after the whole training, which AI was trained of 100% of all models, upto 24 months

Collaborators and Investigators

• Sponsor: The University of Hong Kong
• Collaborators: University Grants Committee, Hong Kong
• Investigators: Principal Investigator: Walter Lam, BDS, MDS, The University of Hong Kong

Publications and helpful links

General Publications

• Chow TW, Clark RK, Cooke MS. The orientation of the occlusal plane in Cantonese patients. J Dent. 1986 Dec;14(6):262-5. doi: 10.1016/0300-5712(86)90034-5. No abstract available.
• Chow TW, Clark RK, Cooke MS. Errors in mounting maxillary casts using face-bow records as a result of an anatomical variation. J Dent. 1985 Dec;13(4):277-82. doi: 10.1016/0300-5712(85)90021-1. No abstract available.
• Lam WY, Hsung RT, Choi WW, Luk HW, Pow EH. A 2-part facebow for CAD-CAM dentistry. J Prosthet Dent. 2016 Dec;116(6):843-847. doi: 10.1016/j.prosdent.2016.05.013. Epub 2016 Jul 28.
• Lam WYH, Hsung RTC, Choi WWS, Luk HWK, Cheng LYY, Pow EHN. A clinical technique for virtual articulator mounting with natural head position by using calibrated stereophotogrammetry. J Prosthet Dent. 2018 Jun;119(6):902-908. doi: 10.1016/j.prosdent.2017.07.026. Epub 2017 Sep 29.

Study record dates

Study Major Dates

• Study Start (Actual): September 1, 2021
• Primary Completion (Actual): September 1, 2024
• Study Completion (Actual): May 30, 2025

Study Registration Dates

• First Submitted: September 9, 2021
• First Submitted That Met QC Criteria: September 22, 2021
• First Posted (Actual): September 27, 2021

Study Record Updates

• Last Update Posted (Estimated): October 3, 2025
• Last Update Submitted That Met QC Criteria: September 29, 2025
• Last Verified: September 1, 2025

More Information

Terms related to this study

• Keywords: Artificial Intelligence; Machine Learning; Deep Neural Network; Generative Adversarial Network (GAN); Biomimetics; Dental Prostheses; Prosthodontic Treatment
• Additional Relevant MeSH Terms: Algorithms; Mathematical Concepts; Artificial Intelligence
• Other Study ID Numbers: UW 20-848

Plan for Individual participant data (IPD)

• Plan to Share Individual Participant Data (IPD)?: NO
• IPD Plan Description: There is no IPD sharing plan yet

Drug and device information, study documents

• Studies a U.S. FDA-regulated drug product: No
• Studies a U.S. FDA-regulated device product: No
• product manufactured in and exported from the U.S.: No