The effect of JPEG compression on automated detection of microaneurysms in retinal images

  • M. J. Cree
  • , H. F. Jelinek

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

7 Scopus citations

Abstract

As JPEG compression at source is ubiquitous in retinal imaging, and the block artefacts introduced are known to be of similar size to microaneurysms (an important indicator of diabetic retinopathy) it is prudent to evaluate the effect of JPEG compression on automated detection of retinal pathology. Retinal images were acquired at high quality and then compressed to various lower qualities. An automated microaneurysm detector was run on the retinal images of various qualities of JPEG compression and the ability to predict the presence of diabetic retinopathy based on the detected presence of microaneurysms was evaluated with receiver operating characteristic (ROC) methodology. The negative effect of JPEG compression on automated detection was observed even at levels of compression sometimes used in retinal eye-screening programmes and these may have important clinical implications for deciding on acceptable levels of compression for a fully automated eye-screening programme.

Original languageBritish English
Title of host publicationImage Processing
Subtitle of host publicationMachine Vision Applications
DOIs
StatePublished - 2008
EventImage Processing: Machine Vision Applications - San Jose, CA, United States
Duration: 29 Jan 200831 Jan 2008

Publication series

NameProceedings of SPIE - The International Society for Optical Engineering
Volume6813
ISSN (Print)0277-786X

Conference

ConferenceImage Processing: Machine Vision Applications
Country/TerritoryUnited States
CitySan Jose, CA
Period29/01/0831/01/08

Keywords

  • Automated eye screening
  • JPEG compression
  • Microaneurysms
  • Retinal imaging

Fingerprint

Dive into the research topics of 'The effect of JPEG compression on automated detection of microaneurysms in retinal images'. Together they form a unique fingerprint.

Cite this