This website requires JavaScript.

GAMMA Challenge:Glaucoma grAding from Multi-Modality imAges

Junde WuHuihui FangFei Li ...+25 Yanwu Xu
Color fundus photography and Optical Coherence Tomography (OCT) are the twomost cost-effective tools for glaucoma screening. Both two modalities of imageshave prominent biomarkers to indicate glaucoma suspected. Clinically, it isoften recommended to take both of the screenings for a more accurate andreliable diagnosis. However, although numerous algorithms are proposed based onfundus images or OCT volumes in computer-aided diagnosis, there are still fewmethods leveraging both of the modalities for the glaucoma assessment. Inspiredby the success of Retinal Fundus Glaucoma Challenge (REFUGE) we heldpreviously, we set up the Glaucoma grAding from Multi-Modality imAges (GAMMA)Challenge to encourage the development of fundus \& OCT-based glaucoma grading.The primary task of the challenge is to grade glaucoma from both the 2D fundusimages and 3D OCT scanning volumes. As part of GAMMA, we have publicly releaseda glaucoma annotated dataset with both 2D fundus color photography and 3D OCTvolumes, which is the first multi-modality dataset for glaucoma grading. Inaddition, an evaluation framework is also established to evaluate theperformance of the submitted methods. During the challenge, 1272 results weresubmitted, and finally, top-10 teams were selected to the final stage. Weanalysis their results and summarize their methods in the paper. Since allthese teams submitted their source code in the challenge, a detailed ablationstudy is also conducted to verify the effectiveness of the particular modulesproposed. We find many of the proposed techniques are practical for theclinical diagnosis of glaucoma. As the first in-depth study of fundus \& OCTmulti-modality glaucoma grading, we believe the GAMMA Challenge will be anessential starting point for future research.