Researchers at Moorfields Eye Hospital, which is located in London, U.K., have been working with Google’s DeepMind Health, to develop strategy to produce a platform that can assist with the diagnosis eye disease.
Initial findings suggest that an artificial intelligence program can undertake a prognosis of eye health. This was based on running thousands of eye scans, drawn from previous patients, through an artificial intelligence prototype to assess the condition of the eye. This model showed that the artificial intelligence platform could assess eye disease with 94 percent accuracy. This was in relation to over 50 different eye diseases.
The type of technology at the heart of the artificial intelligence is optical coherence tomography. This is a parallel technology to computerised tomography scanning. Optical coherence tomography is a type of imaging technique that make use of coherent light to capture micrometer-resolution, two- and three-dimensional images from within optical scattering media (like biological tissue). The technique is used for medical imaging and industrial nondestructive testing.
The downside with this technology is with the time required to undertake analysis; and the longer the time taken then the greater the chance of a patient not receiving appropriate treatment in time. This is where the artificial intelligence comes in, harnessing neural networks to identify eye patterns.
The following video reveals more:
According to Dr. Pearse Keane, who is a consultant at Moorfields Eye Hospital NHS Foundation Trust, in conversation with Laboratory Roots: “The AI technology we’re developing is designed to prioritize patients who need to be seen and treated urgently by a doctor or eye care professional.”
He adds that: “If we can diagnose and treat eye conditions early, it gives us the best chance of saving people’s sight. With further research, it could lead to greater consistency and quality of care for patients with eye problems in the future.”
The research has been published in Nature Medicine, with the paper titled “Clinically applicable deep learning for diagnosis and referral in retinal disease.”