Artificial intelligence (AI) and 3D tongue scans showed that each human tongue is unique, according to recent discoveries, the University of Edinburgh reported on Friday.
The findings provided a unique look at the biological makeup of the tongue and how taste and touch vary from person to person.
Experts believe the findings could lead to the discovery of food preferences, developing healthy food choices, and early oral cancer diagnosis.
"We were surprised to see how unique these micron-sized features are to each individual. Imagine being able to design personalized food customized to the conditions of specific people and vulnerable populations and thus ensure they can get proper nutrition whilst enjoying their food," University of Edinburgh cited Professor Rik Sakar. "We are now planning to use this technique combining AI with geometry and topology to identify micron-sized features in other biological surfaces. This can help in early detection and diagnosis of unusual growths in human tissues."
Functions and Anatomy of the Tongue
The human tongue is a complex and sophisticated organ. It has hundreds of papillae, tiny buds that help to taste, speak, and swallow.
Of these many projections, the mushroom-shaped fungiform papillae hold our taste buds, while the crown-shaped filiform papillae provide the tongue texture and touch.
The tasting function of our fungiform papillae has been widely studied, but little is known about their shape, size, and pattern amongst individuals.
AI Contribution
Researchers at the University of Edinburgh's School of Informatics and the University of Leeds taught AI computer models to learn from three-dimensional microscopic scans of the tongue, revealing the distinctive properties of the papillae.
The AI tool received nearly two thousand comprehensive scans of papillae from silicone molds of 15 people's tongues. AI models were used to understand the characteristics of the papillae and to predict the age and gender of the volunteers.
The scientists trained the AI models on the papillae using limited amounts of data and topology, which studies how areas are formed and connected.
This allowed the AI algorithm to accurately predict papillae type, and map filiform and fungiform papillae on the tongue with 85% accuracy.
Interestingly, all 15 cases had different papillae and could be identified with 48% accuracy from a single papilla.
Researchers are interested not only in tongues, but in languages that they help people speak. Thus, scientists at the non-profit African Masakhane Research Foundation are working to develop advanced AI tools for mastering African languages, which is challenging because there's a dearth of information about them.
However, the researchers were able to overcome the problem, when they identified key stakeholders with an interest in advancing African language tools — including linguists, writers, editors, content creators, and content developers — and collected data on their backgrounds, motivations, areas of focus, and barriers, the media reported.
The next step for the research team will be to improve people's access to technology. Additionally, the outcomes of the endeavor could support the conservation of indigenous African languages.