September 2016
Volume 57, Issue 12
Open Access
ARVO Annual Meeting Abstract  |   September 2016
Efficacy of Automated Computer-Aided Diagnosis of Retinal Nerve Fiber Layer Defects in Healthcare Screening
Author Affiliations & Notes
  • Changwon Kee
    Ophthalmology, Samsung Medical Center, Seoul, Korea (the Republic of)
    School of Medicine Sungkyunkwan University, Seoul, Korea (the Republic of)
  • Jeong-Min Hwang
    Ophthalmology, Seoul National University Bundang Hospital, Seongnam, Korea (the Republic of)
    College of Medicine, Seoul National University, Seoul, Korea (the Republic of)
  • Sang Beom Han
    Ophthalmology, Kangwon National University Hospital, Chuncheon, Korea (the Republic of)
  • Hee Kyung Yang
    Ophthalmology, Seoul National University Bundang Hospital, Seongnam, Korea (the Republic of)
  • Ji Eun Oh
    Biomedical Engineering Branch, Division of Convergence Technology, National Cancer Center, Goyang, Korea (the Republic of)
  • Kwang Gi Kim
    Biomedical Engineering Branch, Division of Convergence Technology, National Cancer Center, Goyang, Korea (the Republic of)
  • Footnotes
    Commercial Relationships   Changwon Kee, None; Jeong-Min Hwang, None; Sang Beom Han, None; Hee Kyung Yang, None; Ji Eun Oh, None; Kwang Gi Kim, None
  • Footnotes
    Support  None
Investigative Ophthalmology & Visual Science September 2016, Vol.57, 854. doi:
  • Views
  • Share
  • Tools
    • Alerts
      ×
      This feature is available to authenticated users only.
      Sign In or Create an Account ×
    • Get Citation

      Changwon Kee, Jeong-Min Hwang, Sang Beom Han, Hee Kyung Yang, Ji Eun Oh, Kwang Gi Kim; Efficacy of Automated Computer-Aided Diagnosis of Retinal Nerve Fiber Layer Defects in Healthcare Screening. Invest. Ophthalmol. Vis. Sci. 2016;57(12):854.

      Download citation file:


      © ARVO (1962-2015); The Authors (2016-present)

      ×
  • Supplements
Abstract

Purpose : Development of techniques for automatic detection of RNFL defect is important for the screening of glaucomatous change using fundus photographs in large population, and researches have been performed for the development of the techniques. This cross-sectional study was conducted to evaluate the efficacy of a new automatic computer-aided detection (CAD) system for mass screening of retinal nerve fiber layer (RNFL) defects in a large population using fundus photographs.

Methods : Among the fundus photographs of 1200 consecutive subjects who visited a healthcare center, a total of 2270 photographs appropriate for the analysis were tested. The photographs were first reviewed by two expert ophthalmologists for detection of RNFL defects (gold standard). The images were also analyzed using an automatic detection method of RNFL defects using the CAD system on fundus photographs in various cases of glaucomatous and non-glaucomatous optic neuropathy. A free-response receiver operating characteristics curve was generated for the evaluation of efficacy of the CAD system. The results of the automatic detection were compared to those of manual detection, and sensitivity and specificity of the CAD system were calculated.

Results : In manual detection of 2270 photographs, 41 RNFL defects from 36 photographs (1.6%) were detected, and no RNFL defects were found in 2234 photographs (98.4%). The sensitivity of the CAD system was 90.2% (37/41 RNFL defects) and the specificity was 72.5% (1620/2234 photographs with no RNFL defects) at a false positive rate of 0.36 per image for detecting RNFL defects.

Conclusions : The new CAD system successfully detected RNFL defects in mass screening of fundus photographs in a large population who visited a healthcare center. The proposed algorithm can be useful for clinicians in screening RNFL defects in healthcare centers.

This is an abstract that was submitted for the 2016 ARVO Annual Meeting, held in Seattle, Wash., May 1-5, 2016.

×
×

This PDF is available to Subscribers Only

Sign in or purchase a subscription to access this content. ×

You must be signed into an individual account to use this feature.

×