REFUGE Challenge: A Unified Framework for Evaluating Automated Methods for Glaucoma Assessment from Fundus Photographs

By José Ignacio Orlando, Huan Fu, J. Breda, K. V. Keer, Deepti R. Bathula, Andres Diaz-Pinto, Ruogu Fang, P. Heng, Jeyoung Kim, Joonho Lee and 21 more. Medical Image Anal., 2019

863 citations recorded by the source corpus.

Glaucoma is one of the leading causes of irreversible but preventable blindness in working age populations. Color fundus photography (CFP) is the most cost-effective imaging modality to screen for retinal disorders. However, its application to glaucoma has been limited to the computation of a few related biomarkers such as the vertical cup-to-disc ratio. Deep learning approaches, although widely applied for medical image analysis, have not been extensively used for glaucoma assessment due to the limited size of the available data sets. Furthermore, the lack of a standardize benchmark strategy makes difficult to compare existing methods in a uniform way. In order to overcome these issues we set up the Retinal Fundus Glaucoma Challenge, REFUGE (https://refuge.grand-challenge.org), held in conjunction with MICCAI 2018. The challenge consisted of two primary tasks, namely optic disc/cup segmentation and glaucoma classification. As part of REFUGE, we have publicly released a data set of 1200 fundus images with ground truth segmentations and clinical glaucoma labels, currently the largest existing one. We have also built an evaluation framework to ease and ensure fairness in the comparison of different models, encouraging the development of novel techniques in the field. 12 teams qualified and participated in the online challenge. This paper summarizes their methods and analyzes their corresponding results. In particular, we observed that two of the top-ranked teams outperformed two human experts in the glaucoma classification task. Furthermore, the segmentation results were in general consistent with the ground truth annotations, with complementary outcomes that can be further exploited by ensembling the results.

Subfields: Ophthalmology, Radiology, Nuclear Medicine and Imaging

View Paper: https://www.semanticscholar.org/paper/b60f795c6f512ff3ebf6ee09f487aec21edbfec0

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Ophthalmology

1. Huan Fu
2. Kai Wang
3. Tao Li

In Radiology, Nuclear Medicine and Imaging

1. P. Heng
2. Qi-Yan Dou
3. Hao Chen
4. Jing Qin
5. Lequan Yu
6. Cheng Chen
7. Quande Liu
8. Chi-Wing Fu

Citations in the corpus

• Gender imbalance in medical imaging datasets produces biased classifiers for computer-aided diagnosis (2020, background): “, the recent MIMIC-CXR (24) x-ray dataset or the Retinal Fundus Glaucoma Challenge (REFUGE) database of ophtalmological images (25), just to name a few].”
• FedDG: Federated Domain Generalization on Medical Image Segmentation via Episodic Learning in Continuous Frequency Space (2021, methodology): “, the optic disc and cup segmentation on retinal fundus images [40], and the prostate segmentation on T2-weighted MRI [31].”
• Retinal Fundus Multi-Disease Image Dataset (RFMiD): A Dataset for Multi-Disease Detection Research (2021, background): “Some datasets were also developed for two other sight-threatening pathologies, Glaucoma [8–10] and Age-related Macular Degeneration (AMD) [11–14].”
• Applications of Deep Learning in Fundus Images: A Review (2021, methodology): “The REFUGE dataset (Orlando et al., 2020) was used in the REFUGE challenge.”
• Medical SAM Adapter: Adapting Segment Anything Model for Medical Image Segmentation (2023, methodology): “We refer to (Lin et al. 2020) for random sampling generation and (Mahade-van, Voigtlaender, and Leibe 2018) for simulating the iterative sampling process.”
• CNN-GCN Aggregation Enabled Boundary Regression for Biomedical Image Segmentation (2020, background): “Likewise, the size of the OD and OC in colour fundus images is of great importance for the diagnosis of glaucoma [19].”
• Transformation-Consistent Self-Ensembling Model for Semisupervised Medical Image Segmentation (2019, methodology): “The 400 training images from the REFUGE challenge [64] were randomly separated to training and test dataset with the ratio of 9:1.”