Google DeepMind AI Harnesses Machine Learning To Conquer Blindness

Google DeepMind recently commenced a new collaboration with the United Kingdom’s National Health Service (NHS). DeepMind is working with Moorfields Eye Hospital in east London. The goal is to create a machine learning system that will be able use digital eye scans in order to recognize sight-threatening conditions.

Moorfields Eye Hospital 

DeepMind researchers will use millions of anonymous eye scans to train an algorithm to better spot the early signs of eye conditions. Professor Peng Tee Khaw, the head of Moorfields’ Ophthalmology Research Centre, remarked, “These scans are incredibly detailed, more detailed than any other scan of the body we do: we can see at the cellular level.” This algorithm could potentially improve the speed and accuracy of diagnosis.

The collaboration was organized by Dr. Pearse Keane, a consultant ophthalmologist at Moorfields. "I’d been reading about deep learning and the success that technology had had in image recognition," stated Dr. Keane. "I had the brainwave that deep learning could be really good at looking at the images of the eye. Optical Coherence Tomography is my area, and we have the largest depository of OCT images in the world."

retinal scan
An example of a retinal scan

This is the second time that DeepMind has worked with the NHS. The first time, DeepMind and its collaborator, the Royal Free hospital, were accused of not having the proper authority to share the records of patients who would be involved in the trial. The Moorfields tests are anonymous and therefore have not received the same criticism. 

Researchers are hopeful that the eye scans will be particularly useful in detecting diabetic retinopathy. They estimate that 98% of the most severe visual loss might be prevented through early detection.