Exploring retinal pathology using deep learning and eye imaging
Research type
Research Study
Full title
Exploring retinal pathology using deep learning tools on 3D volumetric optical coherence tomography and digital imaging of the fundus
IRAS ID
208824
Contact name
Jeff De Fauw
Contact email
Duration of Study in the UK
2 years, 0 months, 0 days
Research summary
There are almost two million people in the UK living with sight loss, including around 360,000 people registered as blind or partially sighted. But many of these cases can be avoided (Access Economics 2009; see protocol for references). Sight threatening diseases, such as glaucoma, diabetic retinopathy and age related macular degeneration, which can be monitored and treated successfully have contributed to the 40% increase in outpatient attendances in the last decade (HES 2016).
Ophthalmic imaging provides a way to diagnose and objectively assess the progression of a number of pathologies including neovascular (“wet”) age-related macular degeneration (wet AMD) and diabetic retinopathy. Digital photographs of the fundus (the ‘back’ of the eye) and Optical Coherence Tomography (OCT, a modality that uses light waves in a similar way to how ultrasound uses sound waves) are used to provide an insight into eye health. By monitoring patients with chronic diseases that can affect the eye, and offering rapid access to imaging services for patients with concerning symptoms, permanent visual deterioration or blindness can be prevented.
Conditions such as wet AMD and diabetic retinopathy can be prevented if the disease is diagnosed efficiently and patients have rapid access to treatment. Many hospitals run rapid access clinics, which generate very large datasets of both digital fundus photographs and OCT images. They are also very busy, with average times to first treatment exceeding two weeks in busy clinics.
Cutting edge machine learning algorithms, along with this increased availability of large digital datasets, allows the creation of sophisticated image recognition tools. The work will focus on applying novel machine learning algorithms to ophthalmology imaging. Should the research be successful, implementation of the outcomes would improve patient access to treatment and ease pressures on time and resources in ophthalmology clinics and provide new insights into disease pathophysiology.
REC name
East of England - Cambridge East Research Ethics Committee
REC reference
16/EE/0253
Date of REC Opinion
3 Jun 2016
REC opinion
Favourable Opinion