ctmedtech/EYEPACS

EyePACS（糖尿病视网膜病变眼底图像数据集）是一个大规模的视网膜眼底图像集合，用于自动化的糖尿病视网膜病变（DR）检测。该数据集为Kaggle糖尿病视网膜病变检测挑战的基础，用于DR分类和筛查研究。数据集包括来自真实世界临床筛查的黄色中心彩色眼底图像，图像条件多样。数据集共有约88,702张图像，其中约35,000张图像用于训练，约53,000张图像用于测试，图像分辨率从640×480到5184×3456像素不等。图像被标记为0至4级，表示糖尿病视网膜病变的严重程度，由专业眼科医生使用ICDR标准进行标注。

EyePACS (Diabetic Retinopathy Fundus Image Dataset) is a large-scale collection of retinal fundus images used for automated diabetic retinopathy (DR) detection. This dataset formed the basis of the Kaggle Diabetic Retinopathy Detection challenge, enabling research into DR classification and screening. The dataset includes macula-centered color fundus images from real-world clinical screenings under varied imaging conditions. There are approximately 88,702 images in total, with about 35,000 labeled for training and 53,000 unlabeled for testing, ranging in resolution from 640×480 to 5184×3456 pixels. The images are labeled with grades from 0 to 4, indicating the severity of diabetic retinopathy, annotated by certified ophthalmologists using the ICDR grading system.