糖尿病视网膜病变眼底彩照人工智能研究标准数据库的建立规范

Procedures of Establishing a Well-annotated Database of Color Fundus Photography of Diabetic Retinopathy for Artificial Intelligence Research

摘要: 近年来，随着人工智能技术的兴起，世界范围内对于眼底病尤其是糖尿病视网膜病变的人工智能识别研究越来越多，但不同人工智能识别软件准确度的验证与比较问题尚未解决。本文对北京协和医院眼科在建立1.5万张糖尿病视网膜病变眼底彩照人工智能研究标准数据库的过程中所遵循的规范进行阐述，以期为后续眼科以及其他相关学科建立更多的相关数据库提供参考。

Abstract: With the development of artificial intelligence technology, explosive research on the recognition of retina diseases with artificial intelligence was published worldwide, among which, diabetic retinopathy attracted most attention. However, evaluation of different artificial intelligence software remains a problem. The Department of Ophthalmology, Peking Union Medical College Hospital published the first standard well-annotated color photo database of diabetic retinopathy for artificial intelligence research in China. We herein present the procedures for the establishment of the database and aim to provide reference for the future development of similar databases.