Automated Detection of Retinal Detachment Using Deep Learning-Based Segmentation on Ocular Ultrasonography Images.

Journal: Translational vision science & technology
Published Date:

Abstract

PURPOSE: This study aims to develop an automated pipeline to detect retinal detachment from B-scan ocular ultrasonography (USG) images by using deep learning-based segmentation.

Authors

  • Onur Caki
    Department of Computer Engineering, Koç University, Istanbul, Turkey.
  • Umit Yasar Guleser
    Department of Ophthalmology, Acıbadem Maslak Hospital, Istanbul, Turkey.
  • Dilek Ozkan
    KUIS AI Center, Koç University, Istanbul, Turkey.
  • Mehmet Harmanli
    Department of Computer Engineering, Koç University, Istanbul, Turkey.
  • Selahattin Cansiz
    Department of Computer Engineering, Koç University, Istanbul, Turkey.
  • Cem Kesim
    Department of Ophthalmology, School of Medicine, Koç University, Istanbul, Turkey.
  • Rustu Emre Akcan
    Department of Ophthalmology, School of Medicine, Koç University, Istanbul, Turkey.
  • Ivan Merdzo
    Department of Ophthalmology, University Hospital Mostar, Mostar, Bosnia and Herzegovina.
  • Murat Hasanreisoglu
    Department of Ophthalmology, School of Medicine, Koç University, Istanbul, Turkey.
  • Cigdem Gunduz-Demir