Deep learning can generate traditional retinal fundus photographs using ultra-widefield images via generative adversarial networks.

Journal: Computer methods and programs in biomedicine
Published Date: Sep 16, 2020

Abstract

BACKGROUND AND OBJECTIVE: Retinal imaging has two major modalities, traditional fundus photography (TFP) and ultra-widefield fundus photography (UWFP). This study demonstrates the feasibility of a state-of-the-art deep learning-based domain transfer from UWFP to TFP.

Authors

  • Tae Keun Yoo
  • Ik Hee Ryu
    B&VIIt Eye Center, Seoul, South Korea.
  • Jin Kuk Kim
    B&VIIt Eye Center, Seoul, South Korea.
  • In Sik Lee
    B&VIIt Eye Center, Seoul, South Korea.
  • Jung Sub Kim
    B&VIIt Eye Center, Seoul, South Korea.
  • Hong Kyu Kim
    Department of Ophthalmology, Dankook University Hospital, Dankook University College of Medicine, Cheonan, South Korea.
  • Joon Yul Choi
    Department of Electrical and Computer Engineering, Seoul National University, Seoul, South Korea.

Keywords

External Resources

Popular Topics
Recent Journals