ramankamran/retina-age-analysis

视网膜年龄分析数据集包含来自5393名患者的9857张视网膜眼底图像，用于年龄预测任务。支持回归和分类两种任务类型，数据集按患者级别划分为训练集、验证集和测试集，以确保数据不泄露。数据集包括不同年龄段的分类，图像格式为JPEG，平均大小约1MB。数据集的预处理包括移除缺失年龄标签的图像、质量不足的图像，并进行分层划分。该数据集适用于医学图像分析研究、从视网膜图像预测年龄、眼科学任务迁移学习以及半监督学习实验。

The Retina Age Analysis Dataset contains 9,857 retinal fundus images from 5,393 patients for age prediction tasks. It supports both regression and classification tasks. The dataset is split into training, validation, and test sets at the patient level to prevent data leakage. The dataset includes age classification across different ranges, with images in JPEG format and an average size of approximately 1MB. The preprocessing of the dataset involves removing images with missing age labels and inadequate quality images, and creating stratified splits. The dataset is suitable for medical image analysis research, age prediction from retinal images, transfer learning for ophthalmology tasks, and semi-supervised learning experiments.