Author: Andrea Park
Computer scientists have secured funding to develop artificial intelligence that can automatically identify signs of early-stage oral cancer using an existing screening app.
The project will build upon Cancer Research Malaysia’s Mobile Mouth Screening Anywhere (MeMoSA) app, which is currently used to capture images of the oral cavity for remote interpretation by oral medicine and surgical specialists. Researchers from the U.K.’s Kingston University and Malaysia’s University of Malaya will train a deep learning system to distinguish between thousands of photos with and without signs of oral cancer, then integrate that system into the app.
“Our challenge is to develop deep learning models that demonstrate a high accuracy and prediction of disease,” said lead researcher Sarah Barman, PhD, a professor of computer vision at Kingston. “If we find this approach is reliable enough, artificial intelligence could be used for other forms of disease screening with a wide range of possible applications in the field of medical diagnostics.”