1. REFUGE Challenge: A unified framework for evaluating automated methods for glaucoma assessment from fundus photographs
- Author
-
Orlando, Jos�� Ignacio, Fu, Huazhu, Breda, Jo��o Barbossa, van Keer, Karel, Bathula, Deepti R., Diaz-Pinto, Andr��s, Fang, Ruogu, Heng, Pheng-Ann, Kim, Jeyoung, Lee, JoonHo, Lee, Joonseok, Li, Xiaoxiao, Liu, Peng, Lu, Shuai, Murugesan, Balamurali, Naranjo, Valery, Phaye, Sai Samarth R., Shankaranarayana, Sharath M., Sikka, Apoorva, Son, Jaemin, Hengel, Anton van den, Wang, Shujun, Wu, Junyan, Wu, Zifeng, Xu, Guanghui, Xu, Yongli, Yin, Pengshuai, Li, Fei, Zhang, Xiulan, Xu, Yanwu, and Bogunovi��, Hrvoje
- Subjects
FOS: Computer and information sciences ,genetic structures ,Computer science ,Image classification ,Fundus Oculi ,Computer Vision and Pattern Recognition (cs.CV) ,Computer Science - Computer Vision and Pattern Recognition ,Glaucoma ,Datasets as Topic ,Health Informatics ,Fundus (eye) ,Diagnostic Techniques, Ophthalmological ,Machine learning ,computer.software_genre ,030218 nuclear medicine & medical imaging ,03 medical and health sciences ,0302 clinical medicine ,Deep Learning ,TEORIA DE LA SEÑAL Y COMUNICACIONES ,medicine ,Photography ,Humans ,Radiology, Nuclear Medicine and imaging ,Segmentation ,Ground truth ,Image segmentation ,Modality (human–computer interaction) ,Radiological and Ultrasound Technology ,Contextual image classification ,medicine.diagnostic_test ,business.industry ,Fundus photography ,Deep learning ,medicine.disease ,Computer Graphics and Computer-Aided Design ,eye diseases ,Computer Vision and Pattern Recognition ,Artificial intelligence ,sense organs ,business ,computer ,030217 neurology & neurosurgery - Abstract
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 (\url{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., Comment: Accepted for publication in Medical Image Analysis
- Published
- 2019