Google DeepMind has announced a partnership with Moorfields Eye Hospital NHS Foundation in London to investigate whether computers can be trained to detect eye diseases early enough to prevent blindness.
As part of the research project, DeepMind will gain access to a million anonymous eye scans and train its computers to identify early signs of two age-related eye conditions: macular degeneration and diabetic retinopathy.
According to DeepMind, earlier detection of eye disorders related to diabetes and age-related macular degeneration could enable doctors to prevent loss of vision in many people. Together, these conditions affect over 100 million people worldwide.
“Our research with DeepMind has the potential to revolutionise the way professionals carry out eye tests and could lead to earlier detection and treatment of common eye diseases such as age-related macular degeneration,” said Director of the NIHR Moorfields Biomedical Research Centre, Prof Sir Peng Tee Khaw.
“With sight loss predicted to double by the year 2050 it is vital we explore the use of cutting-edge technology to prevent eye disease,” continued Prof Khaw.
DeepMind aims to use machine learning to give doctors a digital tool that can read an eye-scan test and recognise problems faster.
Currently eye care professionals use digital scans of the back of the eye and scans called optical coherence tomography (OCT) to diagnose and determine the correct treatment for these conditions.
These scans are highly complex and take a long time for eye doctors to analyse, which can have an impact on how quickly they can meet patients to discuss diagnosis and treatment.
Earlier this year, Google DeepMind announced its first collaboration with Royal Free London NHS Foundation Trust to create an app called Streams to enable physicians to more quickly view medical results related to kidney function.