Deep Learning for Retinal Degeneration Assessment: A Comprehensive Analysis of the MARIO Challenge
Abstract
The MARIO challenge, held at MICCAI 2024, focused on advancing the automated detection and monitoring of age-related macular degeneration (AMD) through the analysis of optical coherence tomography (OCT) images. Designed to evaluate algorithmic performance in detecting neovascular activity changes within AMD, the challenge incorporated unique multi-modal datasets. The primary dataset, sourced from Brest, France, was used by participating teams to train and test their models. The final ranking was determined based on performance on this dataset. An auxiliary dataset from Algeria was used post-challenge to evaluate population and device shifts from submitted solutions. Two tasks were involved in the MARIO challenge. The first one was the classification of evolution between two consecutive 2D OCT B-scans. The second one was the prediction of future AMD evolution over three months for patients undergoing anti-vascular endothelial growth factor (VEGF) therapy. Thirty-five teams participated, with the top 12 finalists presenting their methods. This paper outlines the challenge's structure, tasks, data characteristics, and winning methodologies, setting a benchmark for AMD monitoring using OCT, infrared imaging, and clinical data (such as the number of visits, age, gender, etc.). The results of this challenge indicate that artificial intelligence (AI) performs as well as a physician in measuring AMD progression (Task 1) but is not yet able of predicting future evolution (Task 2).
Keywords
Cite
@article{arxiv.2506.02976,
title = {Deep Learning for Retinal Degeneration Assessment: A Comprehensive Analysis of the MARIO Challenge},
author = {Rachid Zeghlache and Ikram Brahim and Pierre-Henri Conze and Mathieu Lamard and Mohammed El Amine Lazouni and Zineb Aziza Elaouaber and Leila Ryma Lazouni and Christopher Nielsen and Ahmad O. Ahsan and Matthias Wilms and Nils D. Forkert and Lovre Antonio Budimir and Ivana Matovinović and Donik Vršnak and Sven Lončarić and Philippe Zhang and Weili Jiang and Yihao Li and Yiding Hao and Markus Frohmann and Patrick Binder and Marcel Huber and Taha Emre and Teresa Finisterra Araújo and Marzieh Oghbaie and Hrvoje Bogunović and Amerens A. Bekkers and Nina M. van Liebergen and Hugo J. Kuijf and Abdul Qayyum and Moona Mazher and Steven A. Niederer and Alberto J. Beltrán-Carrero and Juan J. Gómez-Valverde and Javier Torresano-Rodríquez and Álvaro Caballero-Sastre and María J. Ledesma Carbayo and Yosuke Yamagishi and Yi Ding and Robin Peretzke and Alexandra Ertl and Maximilian Fischer and Jessica Kächele and Sofiane Zehar and Karim Boukli Hacene and Thomas Monfort and Béatrice Cochener and Mostafa El Habib Daho and Anas-Alexis Benyoussef and Gwenolé Quellec},
journal= {arXiv preprint arXiv:2506.02976},
year = {2025}
}
Comments
MARIO-MICCAI-CHALLENGE 2024