Researchers are developing an Artificial Intelligence (AI)-based system that could help detect melanoma skin cancer earlier. The technology employs machine-learning software to analyse images of skin lesions and provides doctors with objective data on telltale biomarkers of melanoma, which is deadly if detected too late, but highly treatable if caught early. The AI system – trained using tens of thousands of skin images and their corresponding eumelanin and hemoglobin levels – could initially reduce the number of unnecessary biopsies, a significant health-care cost. Changes in the concentration and distribution of eumelanin, a chemical that gives skin its colour, and hemoglobin, a protein in red blood cells, are strong indicators of melanoma. The new system gives doctors objective information on lesion characteristics to help them rule out melanoma before taking more invasive action, according to the researchers. “This could be a very powerful tool for skin cancer clinical decision support,” said Alexander Wong, Professor at University of Waterloo in Canada.
The technology, presented at the 14th International Conference on Image Analysis and Recognition in Montreal, Canada, could be available to doctors as early as next year. Currently, dermatologists largely rely on subjective visual examinations of skin lesions such as moles to decide if patients should undergo biopsies to diagnose the disease. The new system deciphers levels of biomarker substances in lesions, adding consistent, quantitative information to assessments currently based on appearance alone.
“There can be a huge lag time before doctors even figure out what is going on with the patient,” Wong said. “Our goal is to shorten that process,” Wong added.