Technology fast tracks early skin cancer detection
In a possible breakthrough for the early detection and diagnosis of skin cancer, Victorian researchers are testing how artificial intelligence (AI) can become a powerful and readily accessible tool for dermatologists.
Skin experts are comparing AI detection of benign and malignant melanoma with results from doctors in a real-world setting, with evidence suggesting the technology can generate a level of accuracy close to that of a doctor’s trained eye.
The Alfred’s Victorian Melanoma Service director Associate Professor Victoria Mar, who leads the Improving Skin Cancer Management With Artificial Intelligence (SMARTI) trial, said the tool could provide significant support to skin specialists across the country.
“In our trials to-date, the system performs above 90 per cent at accurately identifying a melanoma,” A/Prof Mar said.
“There’s potential for the tool to not only be used to support a doctor’s diagnosis, but as a triage tool, which is significant for regional Australians where we know there is a chronic shortage of dermatologists and doctors.”
In the trial, AI uses a specific algorithm developed by MoleMap and the Monash University eResearch team.
“Just like a doctor might see many different melanomas and skin lesions across a career, the computer also learns that information, but much quicker so it can formulate an accurate diagnosis,” A/Prof Mar said.
A/Prof Mar said while the approach promises to be a powerful tool, it is not being considered as an alternative to seeing a doctor.
“The first port-of-call for anyone concerned about change to your skin is your GP,” A/Prof Mar said.
The ‘SMARTI’ trial was coordinated by Melanoma and Skin Cancer Trials, and conducted at the Victorian Melanoma Service at The Alfred, two Melbourne dermatology clinics, and the Skin Health Institute. The pilot study has been published in the Journal of the American Academy of Dermatology.