Mustafa Suleyman, Deepmind’s co-founder, says this is the company’s first foray into a purely medical research. In this new collaboration with Moorfields, an algorithm will be trained using one million anonymized eye scans to train to identify early signs of degenerative eye conditions such as wet age-related macular degeneration and diabetic retinopathy.
“If you have diabetes you’re 25 times more likely to go blind. If we can detect this, and get in there as early as possible, then 98% of the most severe visual loss might be prevented,” says Suleyman.
By training a neural network to do the assessment of eye scans, it could greatly increase both the speed and accuracy of diagnosis, which can potentially save the sight of thousands of people.
Since the Moorfields collaboration involves anonymized information, Google has been given permission for access through a research collaboration agreement with the hospital, and has published a research protocol, as is standard practice for medical trials.
The scans can show details down to the cellular level, which is extremely useful. But if there are a million of these scans, it may take some time for doctors to process them manually, which is where Deepmind comes in.
It will probably take some time before any real results could be released, but if the research becomes successful, it could potentially help millions worldwide who are at risk of degenerative eye conditions.