May 2003
Volume 44, Issue 13
ARVO Annual Meeting Abstract  |   May 2003
Computer Automated Quantification of Plus Disease in RetCam Images of Retinopathy of Prematurity
Author Affiliations & Notes
  • D.K. Wallace
    University of North Carolina, Chapel Hill, NC, United States
  • A. Capone, Jr.
    Royal Oak, MI, United States
  • J. Jomier
    Royal Oak, MI, United States
  • S.R. Aylward
    Royal Oak, MI, United States
  • M.B. Landers, III
    Royal Oak, MI, United States
  • M.T. Trese
    Royal Oak, MI, United States
  • PHOTO-ROP Study Group
    Royal Oak, MI, United States
  • Footnotes
    Commercial Relationships  D.K. Wallace, None; A. Capone, Jr., None; J. Jomier, None; S.R. Aylward, None; M.B. Landers, III, None; M.T. Trese, None.
Investigative Ophthalmology & Visual Science May 2003, Vol.44, 588. doi:
  • Views
  • Share
  • Tools
    • Alerts
      This feature is available to authenticated users only.
      Sign In or Create an Account ×
    • Get Citation

      D.K. Wallace, A. Capone, Jr., J. Jomier, S.R. Aylward, M.B. Landers, III, M.T. Trese, PHOTO-ROP Study Group; Computer Automated Quantification of Plus Disease in RetCam Images of Retinopathy of Prematurity . Invest. Ophthalmol. Vis. Sci. 2003;44(13):588.

      Download citation file:

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

  • Supplements

Abstract: : Purpose: In some cases of retinopathy of prematurity, it difficult to determine with certainty whether the abnormality of the posterior pole blood vessels exceeds the minimum requirement for plus disease. We have developed a computer program that captures digital images using a video indirect ophthalmoscope, identifies and traces the major posterior pole blood vessels, measures the dilation and tortuosity of each vessel, and calculates whether an eye has plus disease or not. Our purpose was to apply this program to images captured instead by a RetCam to determine its accuracy in comparison to two masked examiners. Methods: RetCam images from 22 eyes of premature infants in the PHOTO-ROP study were analyzed by both the computer program and by two masked examiners experienced in the diagnosis of ROP. The standard photograph from the CRYO-ROP study representing the minimum degree of dilation and tortuosity required for plus disease had previously been digitized and analyzed by our program, and it was again used as a numeric threshold for the automated determination of plus disease. Results: Of the 6 images determined to have plus disease by 2 masked examiners, 5 were calculated to have plus disease by the computer program. (83% sensitivity). Of the 13 images without plus disease, 9 were calculated to not have plus disease by the computer program (69% specificity). Conclusions: Automated computer analysis of RetCam images has very good sensitivity but less specificity in detecting plus disease in comparison to masked examiners. Refinements of this technology in the future has the potential to remove subjectivity from the determination of plus disease. References: (1) Cryotherapy for Retinopathy of Prematurity Cooperative Group. Multicenter trial of cryotherapy for retinopathy of prematurity: Preliminary results. Arch Ophthalmol 1988;106:471-9. (2) Wallace DK, Jomier J, Aylward S, Landers MB. Computer Automated Quantification of Plus Disease in Retinopathy of Prematurity. Journal of AAPOS (in press).

Keywords: retinopathy of prematurity 

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.