NIHR | August 2018 | Artificial intelligence can detect eye disease as accurately as expert doctors
Researchers from Moorfields Hospital , DeepMind Health and University College London, used artificial intelligence (AI) to create a system that is capable of recognising signs of eye disease as accurately as expert doctors. The AI system was trained so it was able to learn how to identify features of over 50 eye diseases and decide how patients should be referred for treatment. In the study doctors also reviewed the eye scans, showing that the AI was able to make the right referral more than 94% of the time. The system offers benefits to patient care as it could help make sure serious eye problems are treated as early as possible.
Dr Pearse Keane, consultant ophthalmologist at Moorfields Eye Hospital NHS Foundation Trust and NIHR Clinician Scientist at the UCL Institute of Ophthalmology 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, which can be devastating for patients.”
“The AI technology we’re developing is designed to prioritise patients who need to be seen and treated urgently by a doctor or eye care professional. 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.” (Source: NIHR)
Visit NIHR for the full news story
Moorfields Hospital Breakthrough in AI technology to improve care for patients
The research has now been published in Nature
The volume and complexity of diagnostic imaging is increasing at a pace faster than the availability of human expertise to interpret it. Artificial intelligence has shown great promise in classifying two-dimensional photographs of some common diseases and typically relies on databases of millions of annotated images. Until now, the challenge of reaching the performance of expert clinicians in a real-world clinical pathway with three-dimensional diagnostic scans has remained unsolved. Here, we apply a novel deep learning architecture to a clinically heterogeneous set of three-dimensional optical coherence tomography scans from patients referred to a major eye hospital. We demonstrate performance in making a referral recommendation that reaches or exceeds that of experts on a range of sight-threatening retinal diseases after training on only 14,884 scans. Moreover, we demonstrate that the tissue segmentations produced by our architecture act as a device-independent representation; referral accuracy is maintained when using tissue segmentations from a different type of device. Our work removes previous barriers to wider clinical use without prohibitive training data requirements across multiple pathologies in a real-world setting.
Full reference: , J. R., Romera-Paredes, B., Nikolov, S., Tomasev, N., Blackwell, S., … & van den Driessche, G. |2018 | Clinically applicable deep learning for diagnosis and referral in retinal disease| Nature Medicine| 1.
Rotherham NHS staff are able to request a copy of the article here