MARIO AMD Progression Challenge

completed

Organisation and analysis of the MARIO Challenge at MICCAI 2024 — a benchmark for deep learning-based AMD progression assessment.

challengebenchmarkamdmedical-imagingdeep-learningmiccai

Overview

The MARIO AMD Progression Challenge was held at MICCAI 2024 and focused on the automated assessment of Age-related Macular Degeneration (AMD) progression using deep learning.

We are pleased to announce the publication of our comprehensive analysis of the challenge results, and the corresponding dataset is now publicly available for the research community.

Research Focus

This challenge addressed two key clinical questions:

  • Progression prediction: Will a patient’s AMD progress over the next 12 months?
  • Visual acuity change: Will the patient’s visual acuity improve, stabilise, or worsen?

Dataset

The MARIO dataset provides:

  • Longitudinal OCT and fundus image sequences from AMD patients
  • Multi-centre data with diverse imaging protocols
  • Expert-graded annotations for progression labels

Challenge Results

The challenge attracted teams from leading research groups worldwide, enabling a rigorous comparative evaluation of state-of-the-art deep learning methods for AMD progression modelling. Our analysis provides insights into:

  • Effective architectures for longitudinal retinal image analysis
  • The impact of multi-modal data fusion
  • Generalisation challenges across clinical sites

Publication

A comprehensive analysis paper describing the challenge, dataset, and results is available. The dataset remains publicly accessible to support continued research in AMD progression modelling.