April 2011
Volume 52, Issue 14
Free
ARVO Annual Meeting Abstract  |   April 2011
Detection of the Presence of Irregular Shaped Abnormalities in Fundus Photographs
Author Affiliations & Notes
  • Li Tang
    Ophthal & Visual Sciences,
    University of Iowa, Iowa City, Iowa
  • Meindert Niemeijer
    Ophthal & Visual Sciences,
    University of Iowa, Iowa City, Iowa
  • James C. Folk
    Ophthal & Visual Sciences,
    University of Iowa, Iowa City, Iowa
  • Stephen R. Russell
    Ophthal & Visual Sciences,
    University of Iowa, Iowa City, Iowa
  • Joseph M. Reinhardt
    Biomedical Engineering,
    University of Iowa, Iowa City, Iowa
  • Michael D. Abràmoff
    Ophthal & Visual Sciences,
    Biomedical Engineering,
    University of Iowa, Iowa City, Iowa
  • Footnotes
    Commercial Relationships  Li Tang, None; Meindert Niemeijer, None; James C. Folk, None; Stephen R. Russell, None; Joseph M. Reinhardt, None; Michael D. Abràmoff, None
  • Footnotes
    Support  NIH Grant EY017066; U.S. Department of Veterans Affairs
Investigative Ophthalmology & Visual Science April 2011, Vol.52, 1337. doi:
  • Views
  • Share
  • Tools
    • Alerts
      ×
      This feature is available to authenticated users only.
      Sign In or Create an Account ×
    • Get Citation

      Li Tang, Meindert Niemeijer, James C. Folk, Stephen R. Russell, Joseph M. Reinhardt, Michael D. Abràmoff; Detection of the Presence of Irregular Shaped Abnormalities in Fundus Photographs. Invest. Ophthalmol. Vis. Sci. 2011;52(14):1337.

      Download citation file:


      © ARVO (1962-2015); The Authors (2016-present)

      ×
  • Supplements
Abstract
 
Purpose:
 

To automatically detect irregular shaped abnormalities, such as large retinal hemorrhages in fundus photographs, which account for one of the main causes of false negatives (FNs) in existing computer-aided detection or diagnosis (CAD) systems. Elimination of those FNs is highly desirable in developing screening systems which can be translated into practice.

 
Methods:
 

20 images from DRIVE database were used in training and 1200 images from MESSIDOR database in testing for supervised classification. Splat samples were created by segmenting the entire field of view into non-overlapping regions of homogeneous color. Splat-based feature vector, which consists of mean colors from different channels and contrasts with respect to neighboring splats, was formulated to discriminate its characteristics. A kNN classifier assigned a soft label to each splat indicating the likelihood of it being a part of a lesion. For rarely seen large retinal hemorrhages, as they share common features with blood vessels, splat labels were obtained from manually segmented vasculatures for the classifier to learn the appearance of "blood" and extract the most relevant features. Vessel splats flagged by automated vessel segmentation were removed from the output hemorrhage-likeliness map and image level decision was made by upgrading it to a single hemorrhage index.

 
Results:
 

The detector could separate blood/non-blood regions of both regular and irregular shapes. The top 20 of 1200 testing images with the highest hemorrhage index were reviewed by a retinal specialist (MDA) in masked fashion, and 18/20 were found to displayed large extensive hemorrhages, retinal membranes, extensive exudates and atrophic laser scars.

 
Conclusions:
 

Splat-based feature classification is efficient in detecting the presence of irregular shaped abnormalities in fundus images. The methodology might also be useful in eyes that show scarring or pre-retinal fibrosis. The outcome can be integrated into a comprehensive screening system to boost its overall performance and reduce the number of FNs.  

 
Keywords: image processing • imaging/image analysis: non-clinical • retina 
×
×

This PDF is available to Subscribers Only

Sign in or purchase a subscription to access this content. ×

You must be signed into an individual account to use this feature.

×