Scientists at the University of Waterloo along with Sunny brook Research Institute have developed a way that uses artificial intelligence (AI) to help earlier detection of skin cancer. The technology employs machine-learning software to analyze images of skin lesions.
Scientists trained this AI system using images and their corresponding eumelanin and hemoglobin levels. It could initially reduce the number of unnecessary biopsies, a significant health-care cost.
Scientists believe that the technology to detect skin cancer earlier could also benefit user with objective information on lesion characteristics.
Alexander Wong, a professor of systems design engineering at Waterloo said, “This could be a very powerful tool for skin cancer clinical decision support. The more interpretable information there is, the better the decisions are.”
The new framework translates levels of biomarker substances in injuries, including reliable, quantitative data. Particularly, changes in the concentration and distribution of eumelanin provide strong indications of melanoma.
Wong said, “There can be a huge lag time before doctors even figure out what is going on with the patient. Our goal is to shorten that process.”