Research suggests deep learning algorithms have become as good at image-based medical diagnosis as human doctors – and maybe even better.

“The feasibility of this approach must be considered hand-in-hand with the issue of trust,” added James Duez, CEO and co-founder of automation software vendor Rainbird.

“Any AI-powered decision must have an interpretable rationale if the technology is to be trusted and scale, a limitation to many machine-learnt approaches. That’s why in most cases, a human domain expert (in this case a radiologist) must review the AI opinion and put their name to it.”

To read the full article, see AI is matching doctors at image-based diagnosis on AI Business.