DR-GAN: Conditional Generative Adversarial Network for Fine-Grained Lesion Synthesis on Diabetic Retinopathy Images

@article{Zhou2020DRGANCG,
  title={DR-GAN: Conditional Generative Adversarial Network for Fine-Grained Lesion Synthesis on Diabetic Retinopathy Images},
  author={Y. Zhou and Boyang Wang and X. He and Shanshan Cui and Fan Zhu and Li Liu and Ling Shao},
  journal={IEEE journal of biomedical and health informatics},
  year={2020},
  volume={PP}
}
  • Y. Zhou, Boyang Wang, +4 authors Ling Shao
  • Published 2020
  • Computer Science, Medicine, Engineering
  • IEEE journal of biomedical and health informatics
  • Diabetic retinopathy (DR) is a complication of diabetes that severely affects eyes. It can be graded into five levels of severity according to international protocol. However, optimizing a grading model to have strong generalizability requires a large amount of balanced training data, which is difficult to collect, particularly for the high severity levels. Typical data augmentation methods, including random flipping and rotation, cannot generate data with high diversity. In this paper, we… CONTINUE READING
    1 Citations

    Figures and Tables from this paper

    Analysis of Adversarial based Augmentation for Diabetic Retinopathy Disease Grading

    References

    SHOWING 1-10 OF 52 REFERENCES
    A Benchmark for Studying Diabetic Retinopathy: Segmentation, Grading, and Transferability
    • 1
    • PDF
    Synthesizing retinal and neuronal images with generative adversarial nets
    • 57
    • Highly Influential
    • PDF
    A Framework for Identifying Diabetic Retinopathy Based on Anti-noise Detection and Attention-Based Fusion
    • 15
    • Highly Influential
    Towards Adversarial Retinal Image Synthesis
    • 74
    • PDF
    High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANs
    • 1,351
    • PDF
    Generative Adversarial Network in Medical Imaging: A Review
    • 289
    • PDF
    Medical Image Synthesis with Context-Aware Generative Adversarial Networks
    • 357
    • PDF
    Large Scale GAN Training for High Fidelity Natural Image Synthesis
    • 1,500
    • PDF