Accurate Identification of the Trabecular Meshwork under Gonioscopic View in Real Time Using Deep Learning.

Journal: Ophthalmology. Glaucoma
PMID: 34798322

Abstract

PURPOSE: Accurate identification of iridocorneal structures on gonioscopy is difficult to master, and errors can lead to grave surgical complications. This study aimed to develop and train convolutional neural networks (CNNs) to accurately identify the trabecular meshwork (TM) in gonioscopic videos in real time for eventual clinical integrations.

Authors

  • Ken Y Lin
    Gavin Herbert Eye Institute, Department of Ophthalmology, UC Irvine School of Medicine, Irvine, California; Department of Biomedical Engineering, University of California, Irvine, California. Electronic address: linky@hs.uci.edu.
  • Gregor Urban
    Department of Computer Science, University of California, Irvine , Irvine, California 92697, United States.
  • Michael C Yang
    Gavin Herbert Eye Institute, Department of Ophthalmology, University of California, Irvine, California.
  • Lung-Chi Lee
    Department of Ophthalmology, Tri-Service General Hospital, National Defense Medical Center, Taipei, Taiwan.
  • Da-Wen Lu
    Department of Ophthalmology, Tri-Service General Hospital, National Defense Medical Center, Taipei, Taiwan.
  • Wallace L M Alward
    Department of Ophthalmology and Visual Sciences, University of Iowa, Iowa City, Iowa.
  • Pierre Baldi
    Department of Computer Science, Department of Biological Chemistry, University of California-Irvine, Irvine, CA 92697, USA.

Keywords

External Resources

Popular Topics
Recent Journals