June 2015
Volume 56, Issue 7
Free
ARVO Annual Meeting Abstract  |   June 2015
Evaluation of an automated detection program for diabetic retinopathy
Author Affiliations & Notes
  • Wei Xiao
    Sun Yat-sen University, Zhongshan Ophthalmic Center, Guangzhou, China
  • Canhong Wen
    Southern China Research Center of Statistical Science, Sun Yat-sen University, Guangzhou, China
  • Shan Zhu
    Southern China Research Center of Statistical Science, Sun Yat-sen University, Guangzhou, China
  • Mingguang He
    Sun Yat-sen University, Zhongshan Ophthalmic Center, Guangzhou, China
    Centre for Eye Research Australia, University of Melbourne, Melbourne, VIC, Australia
  • Footnotes
    Commercial Relationships Wei Xiao, None; Canhong Wen, None; Shan Zhu, None; Mingguang He, None
  • Footnotes
    Support None
Investigative Ophthalmology & Visual Science June 2015, Vol.56, 1431. doi:
  • Views
  • Share
  • Tools
    • Alerts
      ×
      This feature is available to authenticated users only.
      Sign In or Create an Account ×
    • Get Citation

      Wei Xiao, Canhong Wen, Shan Zhu, Mingguang He; Evaluation of an automated detection program for diabetic retinopathy. Invest. Ophthalmol. Vis. Sci. 2015;56(7 ):1431.

      Download citation file:


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

      ×
  • Supplements
Abstract
 
Purpose
 

Automated detection program has the potential to reduce the effort of image reading by raters. The purpose of this study is to evaluate the performance of an automated detection program for diabetic retinopathy (DR) and referable DR (RDR) from digital retinal photographs.

 
Methods
 

Color retinal images of both DR and normal subjects were collected from Zhongshan Ophthalmic Center. The 45-degree photographs centered on the macular were chose for the present analysis. Image gradability was assessed according to the DR screening scheme of the United Kingdom National Screening Committee. Retinal color photographs were graded independently for retinopathy severity according to the International Clinical Diabetic Retinopathy and Diabetic Macular Edema Disease Severity Scales by two trained graders and adjudicated by a retinal specialist. Gradable images were then analyzed by the automated assessment program. Referable DR was defined as severer than mild non-proliferative DR with or without macular edema.

 
Results
 

A total of 289 gradable images were assessed by the automated program. The sensitivity and specificity for DR detection was 91.6% (95%CI, 85.8% to 95.6%) and 59.6% (95%CI, 51.2% to 67.6%), respectively. In terms of RDR, the sensitivity of the program raised to 93.5% (95%CI, 88.1% to 97.0%), and specificity was 60.0% (95%CI, 51.7% to 67.9%). The program was failed to detect retinopathies in 9 of 139 DR cases (false-negative ratio: 3.10%). All the nine images met the quality criteria for manual grading but were relatively inadequate for autodetection.

 
Conclusions
 

Our automated detection program has high sensitivity and specificity to detect DR and RDR. It can be served as an assistant tool safely in DR screening projects, potentially reducing the workload of graders on image reading.  

 
The interface of the automated assessment program. (A) The original image of the right eye from a patient with moderate NPDR and macular edema. (B) A snapshot of the interface after automated analysis. Retinal hemorrhages/microaneurysms and hard exudates were marked with pink and yellow labels, respectively. Fundus anatomic landmarks (e.g. optic disc, fovea) were detected and labeled as well.
 
The interface of the automated assessment program. (A) The original image of the right eye from a patient with moderate NPDR and macular edema. (B) A snapshot of the interface after automated analysis. Retinal hemorrhages/microaneurysms and hard exudates were marked with pink and yellow labels, respectively. Fundus anatomic landmarks (e.g. optic disc, fovea) were detected and labeled as well.

 
×
×

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.

×