RFMiD
RFMiD 2.0 是一个用于眼底图像的多标签分类数据集。作为RFMiD（1.0版本）的更新版本，该数据集曾用于ISBI 2021的RIADD挑战赛。2023年发布的这个更新版本主要对标签类别进行了修改，将原先笼统的"其他"类别细化为具体的罕见疾病，从而提升了标签质量。数据集共包含3,200个病例，目前所有病例的图像和标签均已提供。RFMiD 2.0标注了45种不同的眼部疾病，在公开可用的眼底数据集中拥有最多的疾病类别。
yanjing可视化图片
RFMiD_3.webp
RFMiD_2.webp
RFMiD_1.webp
RFMiD_0.png
数据集元信息
| 维度 | 2D |
| 模态 | fundus |
| 任务类型 | classification |
| 解剖结构 | 眼部 |
| 解剖区域 | 眼睛 |
| 类别数 | 45 |
| 数据量 | 训练集1920，验证集640，测试集640 |
| 文件格式 | png |
文件结构
Dataset
│
├── Training_Set
│ ├── Training
│ │ ├── 1.png
│ │ ├── 2.png
│ │ ├── 3.png
│ │ ├── ...
│ │ ├── 1920.png
│ └── RFMiD_Training_Labels.csv
├── Validation_Set
│ ├── Validation
│ │ ├── 1.png
│ │ ├── 2.png
│ │ ├── 3.png
│ │ ├── ...
│ │ ├── 640.png
│ └── RFMiD_Validation_Labels.csv
├── Test_Set
│ ├── Test
│ │ ├── 1.png
│ │ ├── 2.png
│ │ ├── 3.png
│ │ ├── ...
│ │ ├── 640.png
│ └── RFMiD_Test_Labels.csv引用
@article{data8020029,
AUTHOR = {Panchal, Sachin and Naik, Ankita and Kokare, Manesh and Pachade, Samiksha and Naigaonkar, Rushikesh and Phadnis, Prerana and Bhange, Archana},
TITLE = {Retinal Fundus Multi-Disease Image Dataset (RFMiD) 2.0: A Dataset of Frequently and Rarely Identified Diseases},
JOURNAL = {Data},
VOLUME = {8},
YEAR = {2023},
NUMBER = {2},
ARTICLE-NUMBER = {29},
URL = {https://www.mdpi.com/2306-5729/8/2/29},
ISSN = {2306-5729},
ABSTRACT = {Irreversible vision loss is a worldwide threat. Developing a computer-aided diagnosis system to detect retinal fundus diseases is extremely useful and serviceable to ophthalmologists. Early detection, diagnosis, and correct treatment could save the eye’s vision. Nevertheless, an eye may be afflicted with several diseases if proper care is not taken. A single retinal fundus image might be linked to one or more diseases. Age-related macular degeneration, cataracts, diabetic retinopathy, Glaucoma, and uncorrected refractive errors are the leading causes of visual impairment. Our research team at the center of excellence lab has generated a new dataset called the Retinal Fundus Multi-Disease Image Dataset 2.0 (RFMiD2.0). This dataset includes around 860 retinal fundus images, annotated by three eye specialists, and is a multiclass, multilabel dataset. We gathered images from a research facility in Jalna and Nanded, where patients across Maharashtra come for preventative and therapeutic eye care. Our dataset would be the second publicly available dataset consisting of the most frequent diseases, along with some rarely identified diseases. This dataset is auxiliary to the previously published RFMiD dataset. This dataset would be significant for the research and development of artificial intelligence in ophthalmology.},
DOI = {10.3390/data8020029}
}