Cancer identification AI ‘incredibly exciting’, says researchers

Researchers at Stanford University have designed an artificial intelligence (AI) system which is able to identify skin cancer in photos as accurately as specialist doctors.

The AI was redesigned from software initially developed Google. It was programmed to remember 129,450 photographs along with what type of skin condition each photograph related to. The AI then used algorithms to learn to identify distinctive characteristics of different forms of skin cancers, from carcinomas to melanomas.

Dr Andre Esteva, one of the researchers involved in the project, said: “We made a very powerful machine learning algorithm that learns from data. Instead of writing into computer code exactly what to look for, you let the algorithm figure it out.”

Postulating further, Esteva commented: “My main eureka moment was when I realized just how ubiquitous smartphones will be. Everyone will have a supercomputer in their pockets with a number of sensors in it, including a camera. What if we could use it to visually screen for skin cancer? Or other ailments?”

Dr Jana Witt, from the charity Cancer Research UK, said: "Using artificial intelligence to help diagnose skin cancer is very interesting, as it could support assessments by GPs and dermatologists."

But Witt added: "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."

Event Diary

This story was first published in digitalhealth.net

Supplier Profiles

CDC success at Victoria Infirmary, Northwich creates ideal model for future patient pathway reforms

Northwich’s Victoria Infirmary (VIN) Community Diagnostic Centre (CDC) has enabled more patients

Gain valuable insight with Adveco for gas to electric decarbonisation projects

Adveco, the commercial hot water specialist, announces the launch of live metering of domestic ho