Article Text

Download PDFPDF
Original article
Comparison of expert graders to computer-assisted image analysis of the retina in retinopathy of prematurity
  1. Deepika N Shah1,2,
  2. Clare M Wilson3,
  3. Gui-shuang Ying2,
  4. Karen A Karp1,
  5. Kenneth D Cocker4,
  6. Jeffrey Ng4,
  7. Ed Schulenburg5,
  8. Alistair R Fielder4,
  9. Monte D Mills1,2,
  10. Graham E Quinn1,2
  1. 1Division of Pediatric Ophthalmology at Children's Hospital of Philadelphia, Philadelphia, Pennsylvania, USA
  2. 2Department of Ophthalmology at University of Pennsylvania School of Medicine, Scheie Eye Institute, Philadelphia, Pennsylvania, USA
  3. 3UCL Institute of Ophthalmology, London, UK
  4. 4Department of Optometry and Vision Sciences at City University, London, UK
  5. 5Western Eye Hospital, London, UK
  1. Correspondence to Dr Graham Quinn, Children's Hospital of Philadelphia, Pediatric Ophthalmology, Wood Center, 1st Floor, 34 and Civic Center Blvd, Philadelphia, PA 19104-6087, USA


Aims To determine correlation of width and tortuosity between expert graders and computer-assisted image analysis of the retina in narrow-field images of eyes with retinopathy of prematurity.

Methods 11 digital images were selected based on severity of retinopathy of prematurity (ROP). Narrow field images were analysed for width and tortuosity of vessels using computer-aided image analysis of the retina (CAIAR), an image analysis software, and by four ROP experts. Spearman correlation coefficients (ρ) assessed the correlation of CAIAR grading with expert grading. Intra-class correlations assessed agreement among graders. Width and tortuosity were compared among severity of ROP and treatment status using analysis of variance and generalised estimating equations.

Results Expert measurements correlated well with measures from CAIAR for venule width (ρ=0.57–0.66) and arteriole tortuosity (ρ=0.71–0.81). Measurements from four graders agreed moderately well (intra-class correlations were 0.49 and 0.69 for venule width and arteriole tortuosity, respectively). Increased severity of ROP (no pre-plus/plus, pre-plus, plus) was associated with larger width (linear trend p=0.02 in two graders) and tortuosity (linear trend p<0.03 in all graders). Tortuosity measurements by CAIAR and graders were statistically different between treated and untreated eyes (p<0.002).

Conclusions We found moderate correlation between expert graders' assessment of vessel tortuosity and width and CAIAR using narrow-field images.

  • Digital image analysis
  • retinopathy of prematurity
  • retina
  • diagnostic tests/investigation
  • telemedicine
  • child health (paediatrics)

Statistics from

Request Permissions

If you wish to reuse any or all of this article please use the link below which will take you to the Copyright Clearance Center’s RightsLink service. You will be able to get a quick price and instant permission to reuse the content in many different ways.


  • Funding DNS was supported by the Doris Duke Clinical Research Fellowship New York, USA; CMW was supported by the Action Medical Research (UK); MDM was supported by The Mabel Leslie Endowed Chair of the Children's Hospital of Philadelphia; and GY was supported by a grant from the Paul & Evanina Bell Mackall Foundation Trust, New York, USA.

  • Competing interests None to declare.

  • Ethics approval This study was approved by our institution's Institutional Review Board and conformed with the United States Health Insurance Portability and Accountability Act. Voluntary informed consent for subject participation in the study, as was approved by the Children's Hospital of Philadelphia Institutional Review Board, was obtained in our imaging study under IRB # 2004-10-4000.

  • Provenance and peer review Not commissioned; externally peer reviewed.

Linked Articles

  • At a glance
    Harminder S Dua Arun D Singh