IMAGE-R

Background

Blindness is becoming a large-scale global disorder with 285 million people visually impaired. Irreversible vision impairment caused by retinal diseases can be prevented by early detection and accurate disease management.

Detection and quantification of retinal diseases during screening and monitoring is based on the analysis and interpretation of retinal images. This is currently performed manually by certified graders and ophthalmology specialists and is a labor intensive and costly process with low intra- and interobserver reproducibility. Because of the large group of high risk individuals, it poses a major burden for the eye care health system in terms of costs and resources. By process automation, IMAGE-R will improve the diagnostic accuracy and quality of care while reducing the workload for eye care professionals and contribute to affordable eye care.

Aim

The goal of this project is to revolutionize current eye care diagnostics and disease management by providing IMAGE-R, a computer-aided detection (CAD) system for retinal diseases, which makes use of state-of-the-art machine learning techniques. IMAGE-R provides eye care professionals with a comprehensive solution for fast, accurate, and cost-saving retinal disease detection (for screening) as well as quantification (for disease management). The system will be applicable for the most frequent retinal diseases (age-related macular degeneration (AMD), diabetic retinopathy (DR) and glaucoma), be compatible with color fundus (CF) retinal images and optical coherence tomography (OCT) imaging data, and be widely accessible to eye care providers through a cloud-based platform. This project is a collaboration between Retinai Medical Ag, RadboudUMC - A-eye research group RadboudUMC, Thirona B.V., and University Of Bern - Artorg Center For Biomedical Engineering Research.

Multimodal (OCT and CF) image analysis

Funding

This project is funded by Horizon 2020: Eurostars.

People

Coen de Vente

Coen de Vente

PhD Candidate

Clarisa Sánchez

Clarisa Sánchez

Associate Professor