Explaining the Rationale of Deep Learning Glaucoma Decisions with Adversarial Examples.

Journal: Ophthalmology
Published Date: Jun 26, 2020

Abstract

PURPOSE: To illustrate what is inside the so-called black box of deep learning models (DLMs) so that clinicians can have greater confidence in the conclusions of artificial intelligence by evaluating adversarial explanation on its ability to explain the rationale of DLM decisions for glaucoma and glaucoma-related findings. Adversarial explanation generates adversarial examples (AEs), or images that have been changed to gain or lose pathologic characteristic-specific traits, to explain the DLM's rationale.

Authors

  • Jooyoung Chang
    Department of Biomedical Sciences, Seoul National University Graduate School, Seoul, South Korea.
  • Jinho Lee
    Department of Ophthalmology.
  • Ahnul Ha
    Department of Ophthalmology, Seoul National University College of Medicine, 101 Daehak-ro, Jongno-gu, Seoul, 03080, Korea.
  • Young Soo Han
    Department of Ophthalmology, Seoul National University College of Medicine, Seoul, Republic of Korea; Department of Ophthalmology, Seoul National University Hospital, Seoul, Republic of Korea.
  • Eunoo Bak
    Department of Ophthalmology, Seoul National University College of Medicine, Seoul, Republic of Korea; Department of Ophthalmology, Seoul National University Hospital, Seoul, Republic of Korea.
  • Seulggie Choi
    Department of Biomedical Sciences, Seoul National University Graduate School, Seoul, South Korea.
  • Jae Moon Yun
    Department of Family Medicine, Seoul National University Hospital, Seoul, South Korea.
  • Uk Kang
    InTheSmart Co., Ltd., Seoul, South Korea; Seoul National University Hospital Biomedical Research Institute, Seoul, Korea.
  • Il Hyung Shin
    InTheSmart Co., Ltd., Seoul, South Korea.
  • Joo Young Shin
    Department of Ophthalmology, Dongguk University Ilsan Hospital, Goyang, Korea.
  • Taehoon Ko
    Office of Hospital Information, Seoul National University Hospital, 101 Daehak-ro, Jongno-gu, Seoul, 03080, South Korea.
  • Ye Seul Bae
    Department of Family Medicine, Seoul National University Hospital, Seoul, Republic of Korea; Office of Hospital Information, Seoul National University Hospital, Seoul, Republic of Korea.
  • Baek-Lok Oh
    Department of Ophthalmology, Seoul National University Hospital, Seoul, South Korea.
  • Ki Ho Park
    Department of Ophthalmology.
  • Sang Min Park
    Spine Center and Department of Orthopaedic Surgery, Seoul National University College of Medicine, Seoul National University Bundang Hospital, Seongnam, Korea.

Keywords

External Resources

Popular Topics
Recent Journals