Could AI Help You Straighten Your Teeth?

Many of us remember the feeling of regularly adjusting and retightening our nails at the orthodontist’s office. And every year, about 30 percent of Danish youth up to the age of 15 wear braces to straighten crooked teeth. Orthodontists use the knowledge gained from their training and experience to perform their tasks, but without the capabilities that a computer can provide to predict the end results.

A new tool, developed in collaboration between the University of Copenhagen’s Department of Computer Science and the company 3Shape, makes it possible to simulate how braces should be applied to give the best result without too much unnecessary discomfort.

The tool has been developed using scanned images of teeth and bone structures from human jaws, which AI then uses to predict how brace sets should be designed to best straighten a patient’s teeth.

“Our simulation can inform an orthodontist where braces should and shouldn’t apply pressure to straighten teeth. Currently, these interventions are entirely at the discretion of orthodontists and involve a lot of trial and error. This can lead to many adjustments and visits to the orthodontist’s office, which our simulation can help reduce in the long term,” says Professor Kenny Erleben, head of IMAGE (Image Analysis, Computational Modeling and Geometry), a research division in the Department of Computer Science of UCPH.

Helps predict tooth movement

It’s no wonder that it can be difficult to predict exactly how braces will move teeth because teeth continue to change slightly throughout a person’s life. And, these movements are very different from mouth to mouth.

“The fact that tooth movements vary from one patient to another makes it even more difficult to accurately predict how teeth will move for different people. That’s why we’ve developed a new tool and a dataset of different models to to help address these challenges,” explains Torkan Gholamalizadeh, from 3Shape and PhD from the Department of Computer Science.

As an alternative to the classic brace and braces, a new generation of transparent braces, known as aligners, has gained ground. Aligners are designed as a clear plastic mold of teeth that patients fit over their teeth.

Patients must wear aligners for at least 22 hours a day and must be replaced with new, tighter sets every two weeks. Because aligners are made of plastic, a person’s teeth also change the contours of the aligner itself, which the new tool also takes into account.

“As clear aligners are softer than metal braces, calculating the force required to move the teeth becomes even more complicated. But it’s a factor we’ve taught our model to take into account so that one can predict the tooth movements when using aligners as well,” says Torkan Gholamalizadeh.

Digital twins can improve therapy

Researchers have created a computer model that creates accurate 3D simulations of a patient’s jaw that dentists and technicians can use to plan the best possible treatment.

To create these simulations, the researchers mapped sets of human teeth using detailed CT scans of teeth and the small, thin structures between the jawbone and teeth known as periodontal ligaments—a type of fiber-rich connective tissue that holds teeth in place in the jaw. .

This type of exact digital imitation is referred to as a digital twin – and in this context, the researchers created a database of ‘digital dental patients’.

But they didn’t stop there. The researchers’ database also contains other digital patient types that could one day be used elsewhere in healthcare:

“Right now, we have a digital patient database that, in addition to simulating alignment plans, can be used for hip implants, among other things. In the long run, this could make patients’ lives easier and save resources for society,” says Kenny Erleben.

The field of research using digital twins is relatively new, and currently Professor Erleben’s database of virtual patients is a world leader. However, the database will need to become even larger if digital twins are to truly take root and benefit the healthcare sector and society.

“More data will allow us to simulate treatments and tailor medical devices to more precisely target patients across entire populations,” says Professor Erleben.

In addition, the tool must overcome several regulatory hurdles before it can be released to orthodontists. This is something researchers hope to see in the near future.

Digital twins

A digital twin is a virtual model that lives in the cloud and is designed to accurately reflect a real-world person, physical object, system, or process.

“The virtual model can answer what’s happening in the real world and do it instantly. For example, one can ask what would happen if you pushed on a tooth and get answers about where it would move and how it would affect other teeth. This can to be done quickly so you know what’s going on. Today, it takes weeks to know if the desired effect has been achieved,” says Professor Kenny Erleben.

Digital twins can be used to plan, design and optimize – and therefore can be used to run companies, robots, factories and much more in energy, health and other sectors.

One of the goals of the work with digital twins in the Department of Computer Science is to be able to create simulations of populations, for example, in the field of health care. If you are working with a medical product, virtual people need to be exposed and tested for their reactions to various situations. A simulation provides a picture of what would happen to an individual – and eventually, to an entire population.

Report: P. Xu, T. Gholamalizadeh, F. Moshfeghifar, S. Darkner, K. Erleben. Deep learning-based segmentation of individual teeth and bones with periodontal ligament interface details for simulation purposes. Access IEEE. 2023? 11:102460-102470. doi: 10.1109/ACCESS.2023.3317512

This article has been republished from the following materials. Note: material may have been edited for length and content. For more information, please contact the cited source.