Learning to screen Glaucoma like the ophthalmologists

TL;DR

This paper discusses the GAMMA Challenge, which aims to develop AI models capable of screening glaucoma using combined 2D fundus images and 3D OCT volumes, mimicking ophthalmologists' diagnostic process.

Contribution

It introduces a challenge framework to advance AI methods for glaucoma screening with multimodal imaging data.

Findings

AI models trained on GAMMA Challenge data show promising accuracy.

Multimodal imaging improves glaucoma detection performance.

The challenge fosters progress in AI-assisted ophthalmic diagnostics.

Abstract

GAMMA Challenge is organized to encourage the AI models to screen the glaucoma from a combination of 2D fundus image and 3D optical coherence tomography volume, like the ophthalmologists.