April 2014
Volume 55, Issue 13
Free
ARVO Annual Meeting Abstract  |   April 2014
Accurate Retinal Artery and Vein Classification using Local Binary Patterns
Author Affiliations & Notes
  • Michael Henry Goldbaum
    Ophthalmology, University of California at San Diego, La Jolla, CA
  • Nima Hatami
    Ophthalmology, University of California at San Diego, La Jolla, CA
  • Footnotes
    Commercial Relationships Michael Goldbaum, None; Nima Hatami, None
  • Footnotes
    Support None
Investigative Ophthalmology & Visual Science April 2014, Vol.55, 232. doi:
  • Views
  • Share
  • Tools
    • Alerts
      ×
      This feature is available to authenticated users only.
      Sign In or Create an Account ×
    • Get Citation

      Michael Henry Goldbaum, Nima Hatami; Accurate Retinal Artery and Vein Classification using Local Binary Patterns. Invest. Ophthalmol. Vis. Sci. 2014;55(13):232.

      Download citation file:


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

      ×
  • Supplements
Abstract
 
Purpose
 

This paper proposes a new Local Binary Pattern (LBP)-based method to generate features for automatic artery and vein (AV) classification of retinal fundus images.

 
Methods
 

Ten retinal fundus images were selected from the STARE dataset for validating the proposed method. Each image was digitized to produce a 1400x1200 pixel image, 24-bits per pixel (standard RGB). All ten images contained abnormalities that obscured or confused the blood vessel appearance. Segmented vessels were divided into pieces. LBP windows were applied along each point on a vessel centerline in a gray scale image. Generated features were classified by Random Forest Trees (RFT).

 
Results
 

Figure 1 shows the LBP operation feature generation on a fundus image. Figure 2 shows the step-by-step pre-processing (Matched Filter Response and morphological operation) for vessel center-line extraction and the final AV classification results obtained using the LBP features for RFT classifiers. The result of the automatic AV classifier matches well the hand-labeled image by two medical experts. Area under the ROC curve was 0.95 over all vessel pieces in all images.

 
Conclusions
 

LBP classified by RFT is a fast and accurate method for AV classification of color fundus images. The proposed method performs well in the image margins compared to existing methods and is also illumination- and scale-invariant. This simple method is robust, even when applied to low contrast and quality fundus images. LBP accuracy compares favorably to previous AV classification methods. Accurate AV classification enables future applications, such as AV diameter ratio (AVR) and artery and venous tortuosity measurements.

 
 
Figure 1: A 2-level LBP-based feature extraction for AV classification. Top left: an instance fundus image; top-right: two LBP windows on a vessel centerline point; bottom: LBP operation on the gray-scale values.
 
Figure 1: A 2-level LBP-based feature extraction for AV classification. Top left: an instance fundus image; top-right: two LBP windows on a vessel centerline point; bottom: LBP operation on the gray-scale values.
 
 
Figure 2: Top left: hand-labeled image by the gold standard, right: after vessel segmentation. Bottom left: hand-labeled image by the gold standard; right: results of the proposed automatic system.
 
Figure 2: Top left: hand-labeled image by the gold standard, right: after vessel segmentation. Bottom left: hand-labeled image by the gold standard; right: results of the proposed automatic system.
 
Keywords: 551 imaging/image analysis: non-clinical • 549 image processing • 688 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.

×