Eyepacs数据集包含35,126张糖尿病视网膜病变眼底图像,按0到4级分级。这些开源图像来自Kaggle 2019糖尿病视网膜病变检测竞赛,由印度阿拉文眼科医院的技术人员在医疗资源匮乏的农村地区拍摄,后经经验丰富的眼科医生检查和分类。图像分辨率从433x289像素到5184x3456像素不等。该数据集为糖尿病视网膜病变的研究和诊断提供了宝贵资源。
yanjing
| 维度 | 2D |
| 模态 | fundus |
| 任务类型 | classification |
| 解剖结构 | 眼部 |
| 解剖区域 | 眼 |
| 类别数 | 5 |
| 数据量 | 35126 |
| 文件格式 | JPEG |
eyepacs
├── images
│ ├── xxx.jpeg
│ ├── xxx.jpeg
│ │ ...
├── train.txt
├── val.txt
| 统计类型 | 间距 (mm) | 尺寸 |
|---|---|---|
| 最小值 | - |
(433, 289, 3) |
| 中位值 | - |
(3644, 2477, 3) |
| 最大值 | - |
(5184, 3456, 3) |
@article{gulshan2016development,
title={Development and validation of a deep learning algorithm for detection of diabetic retinopathy in retinal fundus photographs},
author={Gulshan, Varun and Peng, Lily and Coram, Marc and Stumpe, Martin C and Wu, Derek and Narayanaswamy, Arunachalam and Venugopalan, Subhashini and Widner, Kasumi and Madams, Tom and Cuadros, Jorge and others},
journal={jama},
volume={316},
number={22},
pages={2402--2410},
year={2016},
publisher={American Medical Association}
}