MARIO: Monitoring Age-related Macular Degeneration Progression In Optical Coherence Tomography

This dataset was created for the MARIO challenge, held as a satellite event of the MICCAI 2024 conference.

Context

Age-related Macular Degeneration (AMD) is a progressive degeneration of the macula, the central part of the retina, affecting nearly 196 million people worldwide. It can appear from the age of 50, and more frequently from the age of 65 onwards, causing a significant weakening of visual capacities, without destroying them. It is a complex and multifactorial pathology in which genetic and environmental risk factors are intertwined. Advanced stages of the disease (atrophy and neovascularization) affect nearly 20% of patients: they are the first cause of severe visual impairment and blindness in developed countries. Since their introduction in 2007, Anti–vascular endothelial growth factor (anti-VEGF) treatments have proven their ability to slow disease progression and even improve visual function in neovascular forms of AMD. This effectiveness is optimized by ensuring a short time between the diagnosis of the pathology and the start of treatment as well as by performing regular checks and retreatment as soon as necessary. It is now widely accepted that the indication for anti-VEGF treatments is based on the presence of exudative signs (subretinal and intraretinal fluid, intraretinal hyperreflective spots, etc.) visible on optical coherence tomography (OCT), a 3-D imaging modality.The use of AI for the prediction of AMD mainly focus on the first onset of early/intermediate (iAMD), atrophic (GA), and neovascular (nAMD) stage. And there is no current work on the prediction of the development of the AMD in close monitoring for patient in anti-VEGF treatments plan. Therefore, being able to reliably detect an evolution in neovascular activity by monitoring exudative signs is crucial for the correct implementation of anti-VEGF treatment strategies, which are now individualized.

Objectives

The objective of the MARIO dataset, and of the associated challenge, is to evaluate existing and new algorithms to recognize the evolution of neovascular activity in OCT scans of patients with exudative AMD, for the purpose of improving the planning of anti-VEGF treatments.

Two tasks have been proposed:

• The first task focuses on pairs of 2D slices (B-scans) from two consecutive OCT acquisitions. The goal is to classify the evolution between these two slices (before and after), which clinicians typically examine side by side on their screens.
• The second task focuses on 2D slices level. The goal is to predict the future evolution within 3 months with close monitoring of patients that are enrolled in an anti-VEGF treatments plan.

See details on the MARIO challenge webpage.