We’ve all heard it: “If you’re worried about that new mole on your back, it might be a good idea to have a doctor check it out”, but what happens if you’re in a situation where the nearest doctor is really far away, or you simply don’t have the money to cover the cost of the visit? In a situation like this, receiving a diagnosis through your smartphone could be lifesaving.
That’s the idea behind a recent project created by Stanford University computer scientists, who, wishing to offer people universal access to health care, have created an artificially intelligent diagnosis algorithm for skin cancer.
Using a database of close to 130,000 images of skin diseases, the scientists created a deep learning algorithm capable to diagnose skin lesions with a performance level that matches dermatologists. “We made a very powerful machine learning algorithm that learns from data,” said said Andre Esteva, co-lead author of the paper. “Instead of writing into computer code exactly what to look for, you let the algorithm figure it out.”
This smart algorithm can classify keratinocyte carcinomas (which are the most common cancers among humans), melanoma (which is the deadliest skin cancer), and melanoma when viewed using dermoscopy just as well as experts.
Currently, the algorithm exists only on a computer, but the team plans to make it smartphone compatible in the near future.
Stanford University (http://news.stanford.edu/2017/01/25/artificial-intelligence-used-identify-skin-cancer/)
Digital Trends (http://www.digitaltrends.com/cool-tech/deep-learning-algorithm-cancer/)