Automatic segmentation of corneal deposits from corneal stromal dystrophy images via deep learning.

Journal: Computers in biology and medicine
Published Date: Oct 1, 2021

Abstract

BACKGROUND: Granular dystrophy is the most common stromal dystrophy. To perform automated segmentation of corneal stromal deposits, we trained and tested a deep learning (DL) algorithm from patients with corneal stromal dystrophy and compared its performance with human segmentation.

Authors

  • Mihir Deshmukh
    Singapore Eye Research Institute, Singapore National Eye Centre, Singapore.
  • Yu-Chi Liu
    Singapore Eye Research Institute, Singapore; Singapore National Eye Centre, Singapore; Duke-NUS Medical School, National University of Singapore, Singapore.
  • Tyler Hyungtaek Rim
    Department of Ocular Epidemiology, Singapore Eye Research Institute, Singapore, Singapore.
  • Anandalakshmi Venkatraman
    Singapore Eye Research Institute, Singapore.
  • Matthew Davidson
    Singapore Eye Research Institute, Singapore.
  • Marco Yu
    Singapore Eye Research Institute, Singapore National Eye Centre, Singapore.
  • Hong Seok Kim
    Siloam Eye Hospital, Seoul, South Korea.
  • Geunyoung Lee
    MediWhale, Seoul, South Korea.
  • Ikhyun Jun
    Department of Ophthalmology, Severance Hospital, Institute of Vision Research, Corneal Dystrophy Research Institute, Yonsei University College of Medicine, Seoul, South Korea; Corneal Dystrophy Research Institute, Yonsei University College of Medicine, Seoul, Republic of Korea.
  • Jodhbir S Mehta
    Singapore National Eye Centre, Singapore, Singapore.
  • Eung Kweon Kim
    Corneal Dystrophy Research Institute, Yonsei University College of Medicine, Seoul, Republic of Korea; Saevit Eye Hospital, Goyang-Si, Gyeonggi-Do, South Korea. Electronic address: eungkkim@yuhs.ac.

Keywords

External Resources

Popular Topics
Recent Journals