DeepMind's artificial intelligence to detect over 50 eye diseases

Representative Image

Moneycontrol News

With artificial intelligence (AI) systems even diagnosing human diseases, the probability of AI's use in hospitals cannot be ignored. Moorfields Eye Hospital, along with Google’s DeepMind subsidiary UCL, have designed deep learning codes and developed a software to identify common eye diseases using 3D scans.

As per a report in The Verge, the three institutes have invested many years into developing the software, yet to be implemented for any clinical use. However, it could be made available in hospitals in a  next few years. The team has described the research as “ground-breaking”.

In a press statement, the head of DeepMind, Mustafa Suleyman, described the project as “incredibly exciting” and capable of transforming "diagnosis, treatment, and management of patients."

A consultant ophthalmologist at Moorfields, Dr Pearse Keane, also a member of the research team, said: “The number of eye scans we’re performing is growing at a pace much faster than human experts are able to interpret them. There is a risk that this may cause delays in the diagnosis and treatment of sight-threatening diseases.”

A paper published in the journal Nature Medicine describes the software as one based on the already established principles of deep learning and requiring the use of algorithms to identify common patterns seen in the data. With reference to the above-mentioned project,  the data involved  3D scans of patient’s eyes that are developed using a technique called optical coherence tomography (OCT). Taking a duration of about 10 minutes, the scans involved directing near-infrared light of the interior surface of the eye which creates a 3D image of the tissue.

Dr Keane further described the advantages of using an AI system in the hospital industry by saying, “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 care for patients with eye problems in the future.”