May 2007
Volume 48, Issue 13
ARVO Annual Meeting Abstract  |   May 2007
Plus Disease in Retinopathy of Prematurity: Comparison of Computer-Based and Expert Diagnosis
Author Affiliations & Notes
  • R. Gelman
    Columbia University, New York, New York
  • L. Jiang
    Columbia University, New York, New York
  • Y. E. Du
    Epidemiology and Public Health, Albert Einstein College of Medicine, New York, New York
  • M. E. Martinez-Perez
    Computer Science, National Autonomous University of Mexico, Mexico City, Mexico
  • J. T. Flynn
    Columbia University, New York, New York
  • M. F. Chiang
    Columbia University, New York, New York
    Biomedical Informatics,
  • Footnotes
    Commercial Relationships R. Gelman, None; L. Jiang, None; Y.E. Du, None; M.E. Martinez-Perez, None; J.T. Flynn, None; M.F. Chiang, None.
  • Footnotes
    Support Research to Prevent Blindness Career Development Award (MFC), NIH Grant EY13972 (MFC).
Investigative Ophthalmology & Visual Science May 2007, Vol.48, 3100. doi:
  • Views
  • Share
  • Tools
    • Alerts
      This feature is available to authenticated users only.
      Sign In or Create an Account ×
    • Get Citation

      R. Gelman, L. Jiang, Y. E. Du, M. E. Martinez-Perez, J. T. Flynn, M. F. Chiang; Plus Disease in Retinopathy of Prematurity: Comparison of Computer-Based and Expert Diagnosis. Invest. Ophthalmol. Vis. Sci. 2007;48(13):3100.

      Download citation file:

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

  • Supplements

Purpose:: To compare accuracy of plus disease diagnosis by retinopathy of prematurity (ROP) experts to that of a computer-based image analysis system, Retinal Image multiScale Analysis (RISA).

Methods:: Twenty-two recognized ROP experts independently interpreted a set of 34 wide-angle retinal photographs for presence of plus disease. A reference standard was defined based on majority vote of experts. Images were analyzed using individual and linear combinations of computer-based system parameters for arterioles and venules: integrated curvature (IC), diameter, and tortuosity index (TI). Sensitivity, specificity, and receiver operating characteristic areas under the curve (AUC) for plus disease diagnosis compared to the reference standard were determined for each expert, and for the computer-based system.

Results:: Among the 22 experts, sensitivity ranged from 0.308-1.000, specificity ranged from 0.571-1.000, and AUC ranged from 0.784-1.000. Among individual computer system parameters, venular IC had highest AUC (0.821). Among linear combinations of computer system parameters, the combination of arteriolar IC, arteriolar TI, venular IC, venular diameter, and venular TI had highest AUC (0.967).

Conclusions:: Accuracy of recognized ROP experts for plus disease diagnosis is imperfect. A computer-based image analysis system can be modeled to diagnose plus disease with comparable or better accuracy than that of human experts.

Keywords: retinopathy of prematurity • imaging/image analysis: clinical • clinical (human) or epidemiologic studies: systems/equipment/techniques 

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.