AI in Dentistry: Designing the Future of Single-Tooth Prostheses
The use of Artificial Intelligence (AI) in healthcare is expanding at an unprecedented pace, and dentistry is no exception. While AI has already been applied in diagnostic imaging and treatment planning, its role in prosthodontics—particularly in the design of single-tooth prostheses—remains in its early stages.
A new protocol published in PLOS ONE by researchers from The University of Hong Kong and Chu Hai College of Higher Education outlines a groundbreaking approach: using AI to automate the design of single molar prostheses, potentially making treatments more efficient, precise, and patient-centered.
Why Single-Tooth Prostheses Matter
Tooth loss is among the most common oral health challenges worldwide. It not only affects appearance and chewing function but can also cause jawbone loss, shifting of neighboring teeth, and long-term bite problems.
Dental prostheses such as crowns and bridges aim to restore both function and aesthetics. However, for the best outcomes, these restorations must closely mimic the patient’s natural tooth structure and three-dimensional (3D) positioning. Existing computer-aided design (CAD) systems, while useful, still require considerable manual adjustments by dentists and technicians, making the process time-consuming.
How Can AI Help?
The research team hypothesizes that AI—trained with sufficient data from natural dentition—can learn the unique morphology and spatial relationship of a patient’s teeth, then generate a replacement tooth that is highly biomimetic.
The study will collect digitized dental models from over 250 participants. In the experimental design, one molar (the right maxillary first molar, tooth 16) is digitally “removed,” and the AI system is tasked with reconstructing it.
To achieve this, the researchers will use 3D Generative Adversarial Networks (3D-GANs), a type of deep-learning algorithm capable of handling complex 3D structures. Different GAN approaches (voxel-based, view-based, point-based, and fusion methods) will be tested to determine which is most effective.
Another critical question the study seeks to answer: does the AI need data from the opposing (antagonist) teeth to generate an accurate prosthesis? This investigation could further refine the role of AI in clinical workflows.
What Will Success Look Like?
The AI-generated teeth will be validated against natural counterparts, focusing on three key aspects:
Occlusal Morphology: Does the reconstructed tooth mirror the natural shape and cusps?
3D Positioning: Is the generated tooth aligned correctly within the dental arch?
Functional Occlusion: Can the prosthesis work harmoniously with jaw movements without interference?
If the system performs well, it could significantly reduce adjustment time for dentists and shorten chairside hours for patients.
A Step Toward Smarter Dentistry
Although this publication is a study protocol rather than a completed trial, it represents one of the first attempts to integrate AI into prosthodontics at this level. The findings, once available, may pave the way for broader use of AI in dental treatment design.
By minimizing manual labor, improving precision, and personalizing treatment, AI could become a valuable ally in modern dentistry.
DOI: 10.1371/journal.pone.0268535
Original Article: Chau, R.C.W., Chong, M., Thu, K.M., Chu, N.S.P., Koohi-Moghadam, M., Hsung, R.T.-C., McGrath, C., & Lam, W.Y.H. (2022). Artificial intelligence-designed single molar dental prostheses: A protocol of prospective experimental study. PLOS ONE, 17(6), e0268535.