DRAC 2022: A public benchmark for diabetic retinopathy analysis on ultra-wide optical coherence tomography angiography images
Year: 2024
Type: article
Abstract: Computer-assisted automatic analysis of diabetic retinopathy (DR) is of great importance in improving the efficiency of DR management. As a novel, non-invasive imaging modality, ultra-wide optical coherence tomography angiography (UW-OCTA) could enable precise assessment of microvascular changes in all retinal layers, but there is a scarcity of publicly available benchmarks for model development and evaluation in this domain. To promote further research and scientific benchmarking for DR evaluation and monitoring using UW-OCTA images, we organized a challenge called "DRAC - Diabetic Retinopathy Analysis Challenge" in conjunction with the 25th International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI 2022). Within this challenge, we made available a UW-OCTA dataset (1103 images) addressing three primary clinical tasks: DR lesion segmentation, image quality assessment, and DR grading. The scientific community responded positively to the challenge, with 11, 12, and 13 teams from 8 different countries submitting different solutions in these three tasks, respectively. This paper presents a concise summary and analysis of the top-performing solutions and results across all challenge tasks. In addition to providing practical guidance for developing accurate classification and segmentation models for image quality assessment and DR diagnosis, these solutions have the potential to provide valuable feedback on image quality during the imaging process, enhance the diagnostic capabilities of healthcare professionals and yield more accurate diagnostic results. The dataset has been released to support the development of computer-aided diagnostic systems for DR evaluation and monitoring.
Source: Patterns
Authors: Bo Qian, Hao Chen, Xiangning Wang, Zhouyu Guan, Tingyao Li, Yixiao Jin, Yilan Wu, Yang Wen, Haoxuan Che, Gitaek Kwon, Jaeyoung Kim, Sungjin Choi, Seoyoung Shin, Felix Krause, Markus Unterdechler, Junlin Hou, Rui Feng, Yihao Li, Mostafa El Habib Daho, Dawei Yang, Qiang Wu, Ping Zhang, Xiaokang Yang, Yiyu Cai, Gavin Siew Wei Tan, Carol Y. Cheung, Weiping Jia, Huating Li, Yih Chung Tham, Tien Yin Wong, Bin Sheng
Institutions: Shanghai Jiao Tong University, Shanghai Sixth People's Hospital, Hong Kong University of Science and Technology, Tsinghua University, Shenzhen University, Korea Telecom (South Korea), Johannes Kepler University of Linz, Fudan University, Inserm, Université de Bretagne Occidentale, Laboratoire de Traitement de l'Information Médicale, Chinese University of Hong Kong, The Ohio State University, Nanyang Technological University, Singapore National Eye Center, Singapore Eye Research Institute, National University of Singapore, Duke-NUS Medical School, Beijing Tsinghua Chang Gung Hospital
Language: English
Topic: Retinal Imaging and Analysis
Subfield: Radiology, Nuclear Medicine and Imaging
Field: Medicine
Domain: Health Sciences
Open Access status: gold
Estimated APC paid: $4,900
OpenAlex ID: W4391643750