Canadian researchers from the University of Waterloo and the Sunnybrook Research Institute have developed an artificial intelligence (AI) technology to aid early detection of melanoma skin cancer.
The new AI tool uses machine-learning software to analyse skin lesion images and deliver objective data on common biomarkers of melanoma.
The cancer is reported to be deadly if detected too late, but can be treated more successfully when detected early.
Intended to decrease healthcare costs by minimising the number of unnecessary biopsies, the researchers trained the tool with numerous skin images and their corresponding eumelanin and haemoglobin levels.
Changes in the concentration and distribution of eumelanin, which is a chemical that imparts its colour to skin, and haemoglobin protein in red blood cells are considered as crucial indicators of the disease.
See Also:
The tool will also provide objective information on lesion characteristics to assist doctors in ruling out melanoma prior to any invasive action.
How well do you really know your competitors?
Access the most comprehensive Company Profiles on the market, powered by GlobalData. Save hours of research. Gain competitive edge.
Thank you!
Your download email will arrive shortly
Not ready to buy yet? Download a free sample
We are confident about the unique quality of our Company Profiles. However, we want you to make the most beneficial decision for your business, so we offer a free sample that you can download by submitting the below form
By GlobalDataUniversity of Waterloo systems design engineering professor Alexander Wong 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 AI system is designed to add consistent, quantitative information to current appearance-based assessments by decoding levels of biomarker substances in lesions.
Developed by professor Wong in collaboration with his colleagues, the technology is expected to be available for doctors next year.
Image: Histopathologic image of malignant melanoma. Photo: courtesy of KGH/Wikipedia.