This AI can diagnose skin cancer as well as doctors
Posted: 26 January 2017 | By Darcie Thompson-Fields
Researchers at Stanford University have developed a deep learning algorithm that can analyse skin cancer as accurately as a human doctor.
Stanford researchers trained an existing Google image recognition algorithm using over 130,000 photos of skin lesions representing 2,000 diseases, resulting in an AI system that could detect both different cancers and benign lesions with impressive accuracy. In early tests, its performance was “at least” 91 percent that of dermatologists.
“We realised it was feasible, not just to do something well, but as well as a human dermatologist,” said Stanford Artificial Intelligence Laboratory professor and Udacity founder, Sebastian Thrun. “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.’”
One of the authors of the study, which was published in the journal Nature, wrote that this technology could “potentially provide low-cost universal access to vital diagnostic care”.