Artificial intelligence could detect skin cancer from a simple photo!

A deep learning algorithm is capable of identifying skin cancer on photographs with as much accuracy as dermatologists, show work was done at Stanford University in the United States.


Sebastian Thrun and his colleagues at Standford's artificial intelligence laboratory created a database of nearly 130,000 images of skin cancer and formed their algorithm to visually detect a potential risk.

From the first tests, the results of the tests were very accurate. The team believes that using AI will eventually turn any smartphone into a cancer scanner.

The team tested the algorithm against 21 board-certified dermatologists, and it performed just as well as its human counterparts.

Sebastian Thrun said: "We realized it was feasible, not just to do something well, but as well as a human dermatologist,” also, he said: "That's when our thinking changed. That's when we said, 'Look, this is not just a class project for students, this is an opportunity to do something great for humanity."

The tool should now be clinically tested. It could also become a very useful work tool for family physicians.

No comments:

Powered by Blogger.