Researchers into AI from Stanford claim that artificial intelligence software being developed at the university can identify skin cancer in photographs with the same accuracy as trained doctors.
The major breakthrough is being described by experts on the debilitating condition as particularly exciting and revolutionary.
Already it is being suggested that AI could eventually be included within mobile technology, effectively turning everyday smartphones into cancer scanners.
Cancer Research UK has already commented on the research, suggesting that it could become a useful implement for doctors.
The AI software was repurposed from previous artificial intelligence work produced by Google, with the programme having initially been tested by comparing cats and dogs.
Following success in this relatively simple task, the AI software was later shown nearly 130,000 photographs of various skin conditions.
After this process, the software then learnt to recognise the key aspects of the most common type of skin cancer – carcinoma – and the most deadly – melanoma.
While melanoma is relatively rare, it accounts for 75% of skin cancer deaths.
Scientists then challenged the software’s ability to recognise conditions against 21 trained skin cancer doctors.
Dr Andre Esteva, involved in the research, stated that “we find, in general, that we are on par with board-certified dermatologists.”
However, the software is currently unable to make a full diagnosis, as this is typically confirmed with a tissue biopsy.
Esteva states that the next step in development is to test the AI system alongside doctors in real world settings.
“The application of AI to healthcare is, we believe, an incredibly exciting area of research that can be leveraged to achieve a great deal of societal good. One particular route that we find exciting is the use of this algorithm on a mobile device, but to achieve this we would have to build an app and test its accuracy directly from a mobile device.”
Development of AI in healthcare settings has been rapid in recent years, with London-based doctors having successfully taught an AI system to predict when the human heart will fail.
Dr Jana Witt, from the charity Cancer Research UK, is encouraged by the potential of this new AI software.
“Using artificial intelligence to help diagnose skin cancer is very interesting, as it could support assessments by GPs and dermatologists. It’s unlikely that AI will replace all of the other information your clinician would consider when making a diagnosis, but AI could help guide GP referrals to specialists in the future.”