Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2014 Feb 12;9(2):e88061.
doi: 10.1371/journal.pone.0088061. eCollection 2014.

Automated method for identification and artery-venous classification of vessel trees in retinal vessel networks

Vinayak S Joshi  1 , Joseph M Reinhardt  1 , Mona K Garvin  2 , Michael D Abramoff  3
Affiliations

Automated method for identification and artery-venous classification of vessel trees in retinal vessel networks

Vinayak S Joshi et al. PLoS One. .

Abstract

The separation of the retinal vessel network into distinct arterial and venous vessel trees is of high interest. We propose an automated method for identification and separation of retinal vessel trees in a retinal color image by converting a vessel segmentation image into a vessel segment map and identifying the individual vessel trees by graph search. Orientation, width, and intensity of each vessel segment are utilized to find the optimal graph of vessel segments. The separated vessel trees are labeled as primary vessel or branches. We utilize the separated vessel trees for arterial-venous (AV) classification, based on the color properties of the vessels in each tree graph. We applied our approach to a dataset of 50 fundus images from 50 subjects. The proposed method resulted in an accuracy of 91.44% correctly classified vessel pixels as either artery or vein. The accuracy of correctly classified major vessel segments was 96.42%.

PubMed Disclaimer

Conflict of interest statement

Competing Interests: The authors have declared that no competing interests exist.

Figures

Figure 1
Figure 1. Overview of the steps in proposed method.
Figure 2
Figure 2
Image example: a) Two field fundus image after mosaicing b) Green channel image c) Hue channel image.
Figure 3
Figure 3
Image example: a) Vessel probability image b) Binary image.
Figure 4
Figure 4
Image example: a) Vessel network b) Vessel tree [Vessel width is enlarged for visualization].
Figure 5
Figure 5
Graph based description: a) Vessel segment map [Width is enlarged for visualization] b) Representative graph structure.
Figure 6
Figure 6
Image example: a) Vessel segment map showing the true vessel path b) True vessel path with branches.
Figure 7
Figure 7
Image example: a) Vessel probability image b) Structural mapping of vessel network.
Figure 8
Figure 8
Image example: a) Vessel segment map b) Vessel trees with AV crossing c) Vessel trees without AV crossing.
Figure 9
Figure 9
Fuzzy C-means clustering: a) Cluster formation b) Comparison of mean green channel intensity.
Figure 10
Figure 10
Image example: a) Structural mapping b) Artery-Venous Classification.
Figure 11
Figure 11
Metrics: a) Proportion of mis-classified vessel segments, b) Percentage mis-classification per image.
Figure 12
Figure 12
Image example: a) Fundus image b) Vessel probability image c) Structural mapping d) AV Classification.
Figure 13
Figure 13
Image example: a) Fundus image b) Structural mapping c) Manual AV labeling d) Automated AV Classification.
See this image and copyright information in PMC

References

    1. Sukkaew L, Makhanov B, Barman S, Panguthipong S (2008) Automatic tortuosity-based retinopathy of prematurity screening system. IEICE transactions on information and systems 12.
    1. Koreen S, Gelman R, Martinez-Perez M (2007) Evaluation of a computer-based 399 system for plus disease diagnosis in retinopathy of prematurity. Ophthalmology 114 (12) e59–e67. - PubMed
    1. Niemeijer M, Xu X, Dumitrescu A, Gupta P, Ginneken B, et al. (2011) Automated measurement of the arteriolar-to-venular width ratio in digital color fundus photographs. IEEE Transactions on Medical Imaging 30 (11) 1941–1950. - PubMed
    1. Vickerman M, Keith P, Vesgen Mckay T (2009) 2d: Automated, user-interactive software for quantification and mapping of angiogenic and lymphangiogenic trees and networks. The Anatomical record 292. - PMC - PubMed
    1. Lau Q, Lee M, Hsu W, Wong T (2013) Simultaneously identifying all true vessels from segmented retinal images. IEEE Transactions on Biomedical Engineering 60 (7) 1851–58. - PubMed

Publication types