FGADR Dataset - Look Deeper into Eyes.

Yi Zhou, Boyang Wang, Lei Huang, Shanshan Cui, and Ling Shao

A large-scale Fine-Grained Annotated Diabetic Retinopathy (FGADR) dataset consists of two subsets: Seg-set (1842 images) and Grade-set (1000 images).

People with diabetes are at risk of having an eye disease called diabetic retinopathy (DR). This disease is when high blood glucose level cause damage to blood vessels in the retina. Computer-aided DR diagnosis is a promising choice for early detection of DR and severity grading due to the great successes of deep learning. However, most of the previous works proposed DR diagnosis systems without satisfied performance or interpretability for ophthalmologists, due to the lack of training data with consistent and fine-grained annotations. To address this problem, we construct a large-scale Fine-Grained Annotated DR dataset containing 2,842 images (FGADR). This dataset has 1,842 images with pixel-level DR-related lesion annotations, and 1,000 images with image-level labels graded by 6 board-certified ophthalmologists with intra-rater consistency. The proposed dataset enables the extensive studies of DR diagnosis.

Statistics

FGADR consists of two sets. The first set, named Seg-set, contains 1,842 images with both pixel-level lesion annotations and image-level grading labels. The lesions include microaneurysms (MA), hemorrhages (HE), hard exudates (EX), soft exudates (SE), intra-retinal microvascular abnormalities (IRMA), and neovascularization (NV). The grading labels are annotated by three ophthalmologists. The second set, named Grade-set, is a set of 1,000 images with grading labels annotated by six ophthalmologists. This set is particularly used for evaluating grading performance due to its high annotation confidence. In addition to the six pixel-level lesions annotated in Seg-set, we also annotate the laser mark (LM) and proliferate membrane (PM) lesions with image-level labels.

Dataset Access

Note:

  1. The FGADR database is available for non-commercial research purposes only.
  2. Most images of the FGADR database are obtained from the UAE hospitals which are the property of Inception Institute of Artificial Intelligence, Abu Dhabi, UAE.
  3. You agree not to reproduce, duplicate, copy, sell, trade, resell or exploit for any commercial purposes, any portion of the images and any portion of derived data.
  4. You agree not to further copy, publish or distribute any portion of the FGADR database. Except, for internal use at a single site within the same organization it is allowed to make copies of the database.
  5. The IIAI reserves the right to terminate your access to the database at any time.
  6. All submitted papers or any publicly available text using the FGADR database must cite the following paper: A Benchmark for Studying Diabetic Retinopathy: Segmentation, Grading, and Transferability
    @ARTICLE{9257400,
    author={Y. {Zhou} and B. {Wang} and L. {Huang} and S. {Cui} and L. {Shao}},
    journal={IEEE Transactions on Medical Imaging},
    title={A Benchmark for Studying Diabetic Retinopathy: Segmentation, Grading, and Transferability},
    year={2021},
    volume={40},
    number={3},
    pages={818-828},
    doi={10.1109/TMI.2020.3037771}}

Download Instructions:

Please read the IIAI FGADR Dataset Research Use Agreement Link.

Once you agree to register to download the FGADR dataset, please sign the form and email to yizhou.szcn@gmail.com. You will receive a link to the download over email. Note that you may not share the link to download the dataset with others.

Contact

yizhou.szcn@gmail.com