A multi-level ensemble-based system for detecting microaneurysms in fundus images

Bálint Antal*, István Lázár, András Hajdu, Zsolt Török, Adrienne Csutak, Tünde Peto

*Corresponding author for this work

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

13 Citations (Scopus)

Abstract

In this paper, we present a complex approach to improve microaneurysm detection in color fundus images. Microaneurysms are early signs of diabetic retinopathy, so it is essential to detect these lesions accurately in an automatic screening system. The recommended detection of microaneurysms is realized through several levels. First, a specific combination of different preprocessing methods for candidate extractors is found. Then, we select candidates voted by a certain number of the candidate extractor algorithms. At all these levels, optimal adjustments are determined by corresponding simulated annealing algorithms. Finally, we classify the candidates with a machine-learning based approach considering an optimal feature vector selection determined by a feature subset selection algorithm. Our framework improves the positive likelihood ratio for the microaneurysms and outperforms both the state-of-the-art individual candidate extractors and microaneurysm detectors in these measures.

Original languageEnglish
Title of host publicationSOFA 2010 - 4th International Workshop on Soft Computing Applications, Proceedings
Pages137-142
Number of pages6
DOIs
Publication statusPublished - 29 Oct 2010
Externally publishedYes
Event4th International Workshop on Soft Computing Applications, SOFA 2010 - Arad, Romania
Duration: 15 Jul 201017 Jul 2010

Conference

Conference4th International Workshop on Soft Computing Applications, SOFA 2010
CountryRomania
CityArad
Period15/07/201017/07/2010

ASJC Scopus subject areas

  • Computer Science(all)
  • Biomedical Engineering

Fingerprint Dive into the research topics of 'A multi-level ensemble-based system for detecting microaneurysms in fundus images'. Together they form a unique fingerprint.

Cite this