The EURETINA session on imaging provided a timely update on how modern imaging modalities in the field of retina have greatly enhanced our understanding of common ocular pathologies including diabetic retinopathy (DR), age-related macular degeneration (AMD), central serous chorioretinopathy (CSCR), and many rare retinal diseases which were poorly understood before.
Chaired by Tunde Peto and Sebastian Wolf, the symposium opened with a presentation by Kyoko Ohno-Matsui MD, PhD, who showed how a combination of ultra-widefield OCT and 3-D imaging can render extraordinarily detailed images of the complex structure of the posterior vitreous.
“These technologies are powerful tools that can be used to clarify the normal evolution of the vitreous, pathological changes of the vitreous and implications of vitreous changes in various vitreoretinal diseases,” she said.
Maximilian Pfau MD, PhD, then discussed predicting retinal function from OCT imaging drawing on the vast potential of machine-learning algorithms.
“Artificial intelligence-based algorithms allow us to predict retinal function from the retinal structure. This ‘inferred sensitivity’ facilitates precise functional assessment of patients with a variety of retinal diseases and could be used as a quasi-functional surrogate endpoint in trials,” he said.
The rich potential of optical coherence tomography angiography (OCTA) to image the retinal vasculature in diabetic retinopathy was outlined by Carol Y Cheung PhD.
“OCTA allows for repeated examinations and visualization of microvasculature at the retinal capillary plexuses and choriocapillaris. It enables quantification of microvascular alterations in the retinal capillary network, in addition to the detection of classical features associated with DR, including microaneurysms, intraretinal microvascular abnormalities, and neovascularization,” she said.
The utility of fluorescence lifetime imaging ophthalmoscopy (FLIO), a novel, non-invasive imaging modality able to detect early metabolic change preceding morphological changes in the retina, was highlighted by Chantal Dysli MD, PhD.
She explained that FLIO provides in-vivo autofluorescence lifetime measurements of natural retinal fluorophores upon laser excitation.
The measurements obtained by the FLIO device are very reproducible and can provide information about outcome measures for macular pigment even in the presence of macular atrophy in diseases such as age-related macular degeneration (AMD) or geographic atrophy (GA). It can also identify disease specific patterns and may provide additional parameters for outcomes in diseases such as Stargardt or choroideremia, explained Dr Dysli.
The exciting clinical applications of machine learning and Artificial Intelligence (AI) in the realm of eye diseases were discussed by Pearse Keane MD, PhD.
Dr Keane said that ophthalmology is one of the medical specialties that is at the forefront of AI-enabled healthcare, but that more profound transformations will inevitably make their way into the clinic in the near future.
Dinah Zur MD rounded off the session with a presentation on how artificial intelligence can be used to analyse real world data in AMD.
“Enhanced automated OCT segmentation may assist personalization of AMD real-world care and the detection of novel structure-function correlations. AI should augment retina specialists in their provision of care,” she said.
All registered attendees will be able to view this session via playback on the virtual platform.
