The use of datasets of bad quality images to define fundus image quality

Matteo Menolotto, Mario E. Giardini

Research output: Chapter in Book/Report/Conference proceedingConference contribution book

16 Downloads (Pure)

Abstract

Abstract—Screening programs for sight-threatening diseases rely on the grading of a large number of digital retinal images. As automatic image grading technology evolves, there emerges a need to provide a rigorous definition of image quality with reference to the grading task. In this work, on two subsets of the CORD database of clinically gradable and matching non-gradable digital retinal images, a feature set based on statistical and on task-specific morphological features has been identified. A machine learning technique has then been demonstrated to classify the images as per their clinical gradeability, offering a proxy for a rigorous definition of image quality.

Clinical Relevance— This work offers a novel strategy to define fundus image quality, to contribute to the development of automatic fundus image graders for retinal screening.
Original languageEnglish
Title of host publication2022 44th IEEE Engineering in Medicine and Biology Conference (EMBC)
Place of PublicationPiscataway, NJ
PublisherIEEE
Pages504-507
Number of pages4
ISBN (Electronic)9781728127828
DOIs
Publication statusE-pub ahead of print - 15 Jul 2022
Event44th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC'22) - Scottish Event Campus (SEC) , Glasgow, United Kingdom
Duration: 11 Jul 202215 Jul 2022
https://embc.embs.org/2022/#:~:text=About%20the%20Conference&text=The%20IEEE%20Engineering%20in%20Medicine,from%2011%2D15%20July%202022.

Publication series

NameInternational Conference of the IEEE Engineering in Medicine & Biology Society (EMBC)
PublisherIEEE
ISSN (Print)2375-7477
ISSN (Electronic)2694-0604

Conference

Conference44th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC'22)
Country/TerritoryUnited Kingdom
CityGlasgow
Period11/07/2215/07/22
Internet address

Keywords

  • image processing
  • image de-noising
  • retinal imaging
  • fundus imaging

Fingerprint

Dive into the research topics of 'The use of datasets of bad quality images to define fundus image quality'. Together they form a unique fingerprint.

Cite this