BIGR[eye] consist of a small subgroup of BIGR members that work on ophthalmic imaging, performing a wide variety of tasks belonging to three main groups: image registration, image enhancement, and location and classification of biomarkers.
MERLIN: Multi-modal, multi-scale retinal imaging
The ambition of the MERLIN project is to improve in-depth diagnosis and therapeutic follow-up of diseases that impact the eye’s retina. To do so, the MERLIN partners will deliver a novel medical imaging device able to detect pathological alterations in the retina with highly enhanced sensitivity and specificity.
The medical applications of this device encompass a wide range of retinal pathologies, including age-related macular degeneration (AMD), as well as chronic vascular conditions, including diabetes. AMD and diabetic retinopathy (DR) are the leading cause of blindness worldwide in people over 55 years of age. Such diseases slowly develop at the microscopic scale in the retina. Using current imaging techniques, it is difficult to detect them at early stage, and it often takes months to assess the effects of treatments. These limitations hinders both the clinical management of patients and the investigation of new therapies.
In order to overcome these issues, the device developed in MERLIN will for the first time enable doctors to examine the retina with multiple imaging modalities at both the macroscopic and microscopic scales. Modalities will include ultrafast scanning laser ophthalmoscopy (SLO), optical coherence tomography (OCT) and OCT angiography (OCT-A), while ultrahigh resolution will be provided by adaptive optics technology. This unique combination will reveal previously invisible cellular and microvascular retinal detail in 3 dimensions. The project partners will also develop advanced image processing software for the visualization and quantitative analysis of microscopic structures, and conduct experimentations to optimize and validate performance in AMD and DR patients.
As the feasibility of this diagnostic approach has previously been demonstrated in another European R&D project (FP7 FAMOS, 2012-2017), MERLIN will translate the technology from a preexisting laboratory prototype to a nearly commercial device usable in clinical trials.
Automatic detection and classification of glaucoma disease based on multimodal retinal imaging
Glaucoma is the leading cause of irreversible blindness worldwide and its prevalence is expected to increase in the following decades. Since its damage is preventable but irreversible, an early diagnosis and close follow-up of glaucoma patients are primordial. Therefore, the aim of the project is to develop and implement a new procedure to automatically detect and classify glaucoma based on 3DOCT and OCTA retinal imaging. The project is a collaboration between Erasmus MC and KU Leuven.
Cutting-edge early detection and follow-up of uveal melanoma
Uveal melanoma is the most common cause of primary eye cancer. Despite a shift towards more conservative eye treatments, survival has not improved during the past decades. In this project, new techniques based on a recently developed imaging modality (OCTA) will be used to gain insight into structural and functional risk factors associated with uveal melanoma, contributing to an earlier and better diagnosis.
Automated segmentation and classification of drusen on SLO and OCT imaging
The presence of soft drusen (deposits of lipids under the retina) is an early sign of Age-related Macular Degeneration, a major cause of partial blindness among people aged 50 years and over. Hence, the project aims to develop new algorithms to perform segmentation and classification of drusen using SLO/OCT imaging. Both deep and machine learning techniques will be developed to segment the retinal layers and classify the type of drusen according its morphology and position.