# EURECOM AML 2021:: Challenge 2 — Data

来源：https://www.kaggle.com/competitions/eurecom-aml-2021-challenge-2/data

采集时间：2026-10-19T06:30:59Z

 This challenge has been adapted from the first edition of the “Retinal Fundus Glaucoma Challenge” (a.k.a. REFUGE) which was included in the MICCAI conference of 2018. A report describing the original challenge and the top performing solutions for this edition is available [[2]](https://arxiv.org/abs/1910.03667). The dataset at your disposal consists of 1200 retinal fundus images (400 for training, 400 for validation, 400 for testing), issued from different cameras, and annotated by human experts. The annotations are only provided for the train and validation splits, and are described below. Among the provided samples, 10% represent positive diagnosis of glaucoma, therefore the dataset is unbalanced.

The annotations in `index.json` contain for each sample :

1. **The Glaucoma diagnosis:** a `1` for a glaucomatous eye, `0` for a healthy eye.

2. **A segmentation map for the OD and OC:** its size is the same as the input image.

3. **Fovea localization coordinates:** (X,Y) coordinates. The fovea is the sharp central vision point. 

To give you an idea of the Optic Disc and the Optic Cup area you can find illustrations like Figures 2 and 3 in **Overview/Retinal Fundus Images** for training samples in the illustration folder.