OCT-Angiography to determine remodelling in common Retinal conditions
Research type
Research Study
Full title
Using OCT-Angiography as a disease indicator and treatment efficacy predictor for common retinal conditions
IRAS ID
319954
Contact name
Riaz Asaria
Contact email
Sponsor organisation
University College London
Clinicaltrials.gov Identifier
2834172, UCL Data protection registration number
Duration of Study in the UK
1 years, 0 months, 1 days
Research summary
Optical Coherence Tomography Angiography (OCTA) is a non-invasive imaging modality for analysing blood vessels in the retina (the light-sensing tissue at the back of the eye). As a clinical tool, OCTA has demonstrated superior capabilities in detecting early changes to blood vessels in common retinal conditions like retinal vein occlusions (RVO) and diabetic macular oedema (DMO) compared to other imaging techniques. The data about retinal blood vessels contained in OCTA images makes it possible to train an artificial intelligence (AI) decision support system capable of automatically diagnosing and monitoring DMO or RVO.
We propose to conduct a multi-centre observational study to prospectively investigate which microvascular OCTA imaging parameters reliably predict clinical outcomes and treatment response in patients with DMO and RVOs. We aim to develop and validate an artificial intelligence algorithm that automatically identifies early markers of disease and treatment response in these conditions.
Following fully informed consent, the research team will collect OCTA images taken as part of the routine care for patients attending Royal Free and Whittington Hospitals retina service with a new diagnosis of RVO or DMO. We aim to collect imaging data at diagnosis, during treatment with anti-VEGF injections and after a completed series of anti-VEGF injections. Established disease markers, such as best-corrected visual acuity, will be collected alongside OCTA images, allowing timely correlation between imaging data and clinical outcomes. OCTA images for healthy control eyes will also be acquired, generating a sample of participants.Next, the University College London WEISS/Surgical Robot Vision Research Group and UCL Institute of Ophthalmology will conduct data analysis and algorithm development using feature-based and deep-learning techniques. The project uses classical feature-based and deep learning-based techniques to create an AI algorithm.
REC name
London - Riverside Research Ethics Committee
REC reference
23/LO/0980
Date of REC Opinion
25 Jan 2024
REC opinion
Further Information Favourable Opinion