Using a patient image archive to diagnose retinopathy

Annu Int Conf IEEE Eng Med Biol Soc. 2008:2008:5441-4. doi: 10.1109/IEMBS.2008.4650445.

Abstract

Diabetes has become an epidemic that is expected to impact 365 million people worldwide by 2025. Consequently, diabetic retinopathy is the leading cause of blindness in the industrialized world today. If detected early, treatments can preserve vision and significantly reduce debilitating blindness. Through this research we are developing and testing a method for automating the diagnosis of retinopathy in a screening environment using a patient archive and digital fundus imagery. We present an overview of our content-based image retrieval (CBIR) approach and provide performance results for a dataset of 98 images from a study in Canada when compared to an archive of 1,355 patients from a study in the Netherlands. An aggregate performance of 89% correct diagnosis is achieved, demonstrating the potential of automated, web-based diagnosis for a broad range of imagery collected under different conditions and with different cameras.

Publication types

  • Research Support, N.I.H., Extramural
  • Research Support, Non-U.S. Gov't
  • Research Support, U.S. Gov't, Non-P.H.S.

MeSH terms

  • Algorithms
  • Artificial Intelligence
  • Database Management Systems*
  • Diabetic Retinopathy / pathology*
  • Fluorescein Angiography / methods*
  • Humans
  • Image Enhancement / methods
  • Image Interpretation, Computer-Assisted / methods*
  • Mass Screening / methods
  • Pattern Recognition, Automated / methods*
  • Radiology Information Systems*
  • Reproducibility of Results
  • Retinoscopy / methods*
  • Sensitivity and Specificity