Effective features for artery-vein classification in digital fundus images

Andrea Zamperini, Andrea Giachetti, Emanuele Trucco, Khai Sing Chin

    Research output: Chapter in Book/Report/Conference proceedingChapter

    21 Citations (Scopus)

    Abstract

    In this paper we present an analysis of image features used to discriminate arteries and veins in digital fundus images. Methods proposed in the literature to analyze the vasculature of the retina and compute diagnostic indicators like the Arteriolar to Venular ratio (AVR), use, in fact, different approaches for this classification task, extracting different color features and exploiting different additional information. We concentrate our analysis on finding optimal features for the vessel classification, considering not only simple color features, but also spatial location and vessel size and testing different supervised labeling approaches. The results obtained show that best results are obtained mixing features related with color values and contrast inside and outside the vessels and positional information. Furthermore, the discriminative power of the features changes with the image resolution and best results are not obtained at the finest one. Our experiments demonstrate that using a good set of descriptors it is possible to achieve very good classification performances even without using vascular connectivity information.
    Original languageEnglish
    Title of host publicationProceedings of CBMS 2012
    Subtitle of host publicationthe 25th IEEE International Symposium on Computer-Based Medical Systems
    PublisherIEEE
    Number of pages6
    ISBN (Print)9781467320511
    DOIs
    Publication statusPublished - 2012
    Event25th IEEE International Symposium on Computer-Based Medical Systems, CBMS 2012 - Università Campus Bio-Medico di Roma, Rome, Italy
    Duration: 20 Jun 201222 Jun 2012
    http://www.cbms2012.org/

    Conference

    Conference25th IEEE International Symposium on Computer-Based Medical Systems, CBMS 2012
    CountryItaly
    CityRome
    Period20/06/1222/06/12
    Internet address

    Fingerprint Dive into the research topics of 'Effective features for artery-vein classification in digital fundus images'. Together they form a unique fingerprint.

  • Cite this

    Zamperini, A., Giachetti, A., Trucco, E., & Chin, K. S. (2012). Effective features for artery-vein classification in digital fundus images. In Proceedings of CBMS 2012: the 25th IEEE International Symposium on Computer-Based Medical Systems IEEE. https://doi.org/10.1109/CBMS.2012.6266336