Deep learning-enabled ultra-widefield retinal vessel segmentation with an automated quality-optimized angiographic phase selection tool.

Journal: Eye (London, England)
Published Date:

Abstract

OBJECTIVES: To demonstrate the feasibility of a deep learning-based vascular segmentation tool for UWFA and evaluate its ability to automatically identify quality-optimized phase-specific images.

Authors

  • Duriye Damla Sevgi
    The Tony and Leona Campane Center for Excellence in Image-Guided Surgery and Advanced Imaging Research, Cole Eye Institute, Cleveland Clinic, Cleveland, Ohio.
  • Sunil K Srivastava
    The Tony and Leona Campane Center for Excellence in Image-Guided Surgery and Advanced Imaging Research, Cole Eye Institute, Cleveland Clinic, Cleveland, Ohio.
  • Charles Wykoff
    Retina Consultants of America, Houston, Texas; Blanton Eye Institute, Houston Methodist Hospital & Weill Cornell Medical College, Houston, TX, USA.
  • Adrienne W Scott
    Retina Division, Wilmer Eye Institute, The Johns Hopkins University School of Medicine and Hospital, Baltimore, Maryland.
  • Jenna Hach
    The Tony and Leona Campane Center for Excellence in Image-Guided Surgery and Advanced Imaging Research, Cole Eye Institute, Cleveland Clinic, Cleveland, OH, USA.
  • Margaret O'Connell
    The Tony and Leona Campane Center for Excellence in Image-Guided Surgery and Advanced Imaging Research, Cole Eye Institute, Cleveland Clinic, Cleveland, Ohio.
  • Jon Whitney
    The Tony and Leona Campane Center for Excellence in Image-Guided Surgery and Advanced Imaging Research, Cole Eye Institute, Cleveland Clinic, Cleveland, Ohio.
  • Amit Vasanji
    ERT, Cleveland, OH, USA.
  • Jamie L Reese
    The Tony and Leona Campane Center for Excellence in Image-Guided Surgery and Advanced Imaging Research, Cole Eye Institute, Cleveland Clinic, Cleveland, OH, USA.
  • Justis P Ehlers
    The Tony and Leona Campane Center for Excellence in Image-Guided Surgery and Advanced Imaging Research, Cole Eye Institute, Cleveland Clinic, Cleveland, Ohio.