A platform which allows an AI model to recognise abnormalities in anatomical structures has been developed by King’s College London and the University of Surrey in collaboration with Royal Surrey NHS Foundation Trust and Oral Health Foundation, with the project aiming to “provide a one-stop solution to both collect and annotate dental radiographs and assist with disease diagnoses.”
The project was made possible by £1.55 million in grant funding from the National Institute for Health and Care Research (NIHR), with KCL stating that the platform “is allowing dentists and dental students to read radiograms with higher accuracy, helping them to better detect tooth decay and gum diseases.”
“This next phase of the project is incredibly exciting,” said Dr Yunpeng Li, senior lecturer in artificial intelligence and the project lead at the University of Surrey, adding that “as we work collaboratively to build a working prototype suitable for real-life clinical settings.”
Professor Owen Addison, Professor of oral rehabilitation and the joint project lead at King’s College London, said: “AI systems that support more accurate diagnosis and clinical decision-making will help patients, but they must be trustworthy. We look forward to supporting this project by providing dental expertise and consideration of the needs of end-users.”
In our recent deep dive we explored dentistry with a focus on digital, examining how technology is being used in the delivery of dental care across the UK and exploring the relationship between AI and dentistry through recent research.
In other news from KCL, we took a look at King’s College London’s latest psychiatry, psychology and neuroscience report which identified 19 “pockets of value” in data for transformative mental health research. The aim was to provide a resource for researchers to identify longitudinal data to inform greater insight into mental health.
Earlier in the year, we highlighted how a researcher from KCL received a £1.5 million grant to explore the technical development of a digital twin for the heart, aiming to track and forecast how patients respond to medications and surgeries and improving heart health monitoring.
