Researchers from the University of Waterloo and the Sunnybrook Research Institute are developing a new technology that uses artificial intelligence (AI) to help detect melanoma earlier than current methods.
The technology uses machine-learning software to analyze images of skin lesions to provide doctors with objective data on telltale biomarkers of melanoma. Melanoma can be deadly if found too late but is highly treatable if caught early enough.
Source: Joe Raedle/Getty Images
Researchers trained the AI system using tens of thousands of skin images and the corresponding eumelanin and hemoglobin levels. The system could initially reduce the number of costly unnecessary biopsies. It gives doctors objective information on lesion characteristics to help them rule out melanoma before taking more invasive action.
The researchers say that this new technology could be available to doctors as early as next year.
"This could be a very powerful tool for skin cancer clinical decision support," said Alexander Wong, a professor of systems design engineering at Waterloo. "The more interpretable information there is, the better the decisions are."
Dermatologists currently rely on subjective visual examinations of skin lesions, like moles, to decide if a patient needs to undergo biopsies to diagnose the disease.
The new system deciphers levels of biomarker substances in lesions, adding consistent, quantitative information to assessments that are currently based on appearance alone. The technology pays attention to changes in concentration and distribution of eumelanin and hemoglobin, both strong indicators of melanoma.
"There can be a huge lag time before doctors even figure out what is going on with the patient," said Wong, who is also the Canada Research Chair in Medical Imaging Systems. "Our goal is to shorten that process."
Wong developed the technology with Daniel Cho, a former Ph.D. student at Waterloo, David Clausi, a professor of a systems design engineering professor at Waterloo, and Farzad Khalviti, an adjunct professor at Waterloo and scientist at Sunnybrook.
The research was presented at the 14th International Conference on Image Analysis and Recognition in Montreal.
