Corpus ID: 216562257

Addressing Artificial Intelligence Bias in Retinal Disease Diagnostics

@article{Burlina2020AddressingAI,
  title={Addressing Artificial Intelligence Bias in Retinal Disease Diagnostics},
  author={Philippe Burlina and Neil Joshi and William Paul and Katia D. Pacheco and Neil M. Bressler},
  journal={ArXiv},
  year={2020},
  volume={abs/2004.13515}
}
  • Philippe Burlina, Neil Joshi, +2 authors Neil M. Bressler
  • Published 2020
  • Computer Science, Engineering
  • ArXiv
  • This study evaluated novel AI and deep learning generative methods to address AI bias for retinal diagnostic applications when specifically applied to diabetic retinopathy (DR). Bias often results from data imbalance. We specifically considered here a strong form of data imbalance corresponding to domain shift, where AI classifiers are faced at inference time with data and concepts they were not trained on initially (here the concept of diseased black individuals). A baseline DR diagnostics DLS… CONTINUE READING

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 18 REFERENCES

    Where's Wally Now? Deep Generative and Discriminative Embeddings for Novelty Detection