Artificial Intelligence in Orthodontics

“Predicting the future isn’t miracle, it’s artificial intelligence.”

Orthodontics is one of the top specialties of dentistry that mainly deals with the diagnosis of malocclusion, its prevention and correction. It is mainly concerned with the craniofacial skeleton, with more emphasis on modifying the dentoalveolar structures. Accurate diagnosis and treatment planning are considered as a key to the success of orthodontic treatment. Orthodontic diagnosis is mainly based on the patient’s dental and medical history, clinical examination, study models, and cephalometric radiographs.

The use of information technology (IT) in the dental field has increased significantly over the past 25 years and has helped reduce cost, time, dependence on human expertise, and medical errors. As a subfield of computer science, artificial intelligence (AI) encompasses both hardware and software that can perceive its environment and take action that maximizes its chances of successfully achieving its goals.

In the last few decades the field of dentistry has widely revolutionized. Newer technologies have been developed that are based on the principles of mimicking the functioning of the human brain. These are mainly based on the artificial intelligence (AI) technologies that have made a significant contribution.

Artificial intelligence (AI) refers to a system's ability to mimic human-like intelligence making effective and right decisions according to a gold standard. It is predominant nowadays in everyday technology, for example, in internet search engines, mail spam filtering and even image recognition on social media platforms.

In the beginning, people tried to build hand crafted AI, which means they tried to incorporate all the possible problems and their corresponding solutions into computer programs.

Under certain circumstances, it worked pretty well, but hand crafted AI by no means could surpass human brain because it couldn’t “learn” anything by itself.

In the modern AI, the creators endowed the machine with learning ability. Machine learning, briefly speaking, is the process finding a function from given data.

One of the main subcategories of AI, i.e., machine learning is characterized by mathematical and statistical techniques enabling machines to improve their abilities by using self-adapting algorithms. Based on sample data (training data), machine learning algorithms generate mathematical models that generalize specific patterns to predict decisions. The architecture of machine learning algorithms is inspired by biological neural networks of the human brain.

A variety of artificial neurons are connected to each other forming a net, which is organized in layers. Between the first (input) and the last (output) layer, there are a certain number of (atleast one) so-called hidden layers that are responsible for decision making of the AI. Such multilayered networks exist in different configurations. One type is a “convolutional neural network” (CNN) which especially has established itself in analysis of image content.

Artificial intelligence technology has been used in a wide spectrum from differential diagnosis and radiographic interpretation to restorative treatment in dental field. Dental management software, which uses AI to gather and store the patient data, is available in the market.

It can be used to generate complete detailed virtual databases which are easily accessible. With its unique learning ability, it can be integrated into dental imaging systems to identify even the smallest deviations which human eye cannot recognize. With this outstanding ability, it can easily be used to make accurate diagnosis of cephalometric landmarks.

Despite advances and successful integration of AI in human medicine, application of AI has been limited in dentistry until now. The first promising attempts were made in automated caries detection on intraoral X-rays.

 Likewise, the analysis of cephalometric X-rays appears to be a suitable diagnostic application of CNN algorithms.

Cephalometric X-ray analysis is based on identification of radiological landmarks to subsequently measure various angles, distances and ratios for the interpretation of craniofacial structures. While nowadays software is commonly used for cephalometric measurements, tracing of the landmarks remains a manual task that must be performed by an orthodontic expert.

The quality level of this analysis depends mainly on the expert’s experience and expertise. Inaccurate identification of cephalometric landmarks may lead to incorrect decision-making for orthodontic therapy. A fully automated and reliable identification of the cephalometric landmarks is desired and this is where AI algorithms present new opportunities to support orthodontic experts.

Artificial intelligence-based software systems have a significant role in the field of orthodontics and are considered as the future of orthodontics. Artificial intelligence is used in every area of orthodontics from patient communication and diagnosis to treatment processes. The AI software programs can analyze diagnostic dental radiographs, photos, and 3D intraoral scans to give guidance to clinicians.

Orthodontic treatments for malocclusion can be categorized as either extraction or non-extraction treatments. This decision is traditionally made on the basis of clinical experience gained over time; therefore, it is hard for new practitioners to make these decisions. AI deep learning methods could help to resolve this problem.

Deciding if a patient requires orthognathic surgery can also be challenging for practitioners. AI has shown potential in this field to help clinicians determine whether surgical intervention is necessary.

Automatized technologies of artificial intelligence have been used as powerful tools in predicting the diagnosis and helping the clinicians in treatment planning. These AI based systems have been used as tools for assisting orthodontists in providing standard patient care and maximizing the chances of achieving the set goals. The clinician can apply the AI technology for better clinical decision making.