## Context

       **Glaucoma** is a prevalent condition related to an abnormal fluid balance in the eye that causes an increase of internal ocular pressure. The increase of pressure gradually damages the eye optic nerve. If undiagnosed, these damages can result in permanent vision loss. Approximately **2.86% of the global population over 40 years old** is affected by glaucoma [[1]](https://www.ncbi.nlm.nih.gov/pmc/articles/PMC1856963/). Patients affected by glaucoma usually do not present symptoms in the early stages of the disease, while an early diagnosis is critical to prevent irreversible damages. It is thus important to develop inexpensive detection methods, in order to massively and systematically control patients, before the symptoms appear.

       One way to diagnose glaucoma is to perform a visual examination of the inside back surface of the eye (fundus). The images are obtained by special cameras through a dilated pupil. The main advantage of this technique, called **"Retinal Fundus Imaging"**, is to be brief (usually a minute long) and painless to the patient, making it suited for simple routine checks. However, establishing an accurate diagnosis from these images is particularly difficult. This task is currently performed by human experts, which represents a significant financial burden. Therefore, automatic glaucoma detection methods from fundus imaging are both highly desirable and challenging.

       As most of the applications in medical imaging, this research topic essentially suffers from two limitations:
        1. **The lack of data**: such data is costly to annotate, essentially due to the human experts involved.
        2. **The disparity of data**: the data can vary a lot depending on the imaging device involved and its calibration. Therefore, one solution developed in one particular medical center may perform poorly in another medical center. It is thus crucial to design solutions that can achieve good generalization performance with few data.

## Your objective

        Your task in this challenge is to participate in the research of a machine learning solution to automatically detect glaucoma from retinal fundus images. You will be provided with a baseline method based on both a Convolutional Neural Network and some useful human experts knowledge, which you are free to use as a basis. Previous works exist in this application domain [[2]](https://arxiv.org/abs/1910.03667), and may eventually inspire you. Your goal will be to improve our baseline. As usual, model performance will not be the only evaluation criterion, and serendipity will also be taken into account.

       In the various sections we introduce some knowledge on glaucoma detection from retinal fundus images, describe the dataset, present the provided baseline method, and detail the rules of the challenge.