Artery Research

<Previous Article In Issue
Download article (PDF)
Next Article In Issue>
Volume 24, Issue C, December 2018, Pages 119 - 119

P139 AUTOMATIC CLASSIFICATION OF ARTERIAL AND VENULAR TREES IN COLOUR FUNDUS IMAGES

Authors
M Elena Martinez-Perez1, Kim Parker2, Nick Witt2, S.A.McG. Thom3, Alun Hughes4
1Department of Computer Science, Institute of Research in Applied Mathematics and Systems, National Autonomous University of Mexico, UK
2Department of Bioengineering, Imperial College, London, UK
3Faculty of Medicine, National Heart & Lung Institute, Imperial College, London, UK
4Institute of Cardiovascular Science, University College London, London, UK
Available Online 4 December 2018.
DOI
10.1016/j.artres.2018.10.192How to use a DOI?
Abstract

Background: Quantitative imaging of retinal arterioles and venules offers unique insights into cardiovascular and microvascular diseases but is laborious. We developed and tested a method to automatically identify Arterial/Venular (A/V) vessels in digital retinal images in conjunction with a semi-automatic segmentation technique.

Methods: Segmentation of blood vessels and the Optic Disc (OD) was performed as previously described [1] using a dataset of X colour fundus images. Using the OD as a reference point a graph representation was constructed using the vessel skeletons. Vessel bifurcations and crossings were identified based on direction and local geometry, and A/V classification was carried out by fuzzy logic classification using colour information. Results were compared with expert classification.

Results: 157 arterial and 150 venular segments were classified. Preliminary Results showed sensitivity, specificity and accuracy of 42.20%, 99.21% and 97.73% for arteries and 50.89%, 98.70% and 97.54% for veins. An example is shown in Figure 1.

Conclusions: Computer-based systems can assess local and global aspects of the retinal microvascular architecture, geometry and topology. Automated A/V classification will facilitate efficient cost-effective assessment of clinical images at scale.

Figure 1

(a) Colour image, rectangle crop area in (b)-(d), (b) segmented blood vessels, red crossing, green bifurcations, blue root and yellow ambiguous points, (c) ambiguous points corrected, and (d) classified vessels, red artery and blue vein.

Open Access
This is an open access article distributed under the CC BY-NC license.

Reference

1.Martinez-Perez et al., Med Image Anal, Vol. 11, No. 1, 2007, pp. 47-61.
<Previous Article In Issue
Download article (PDF)
Next Article In Issue>
Journal
Artery Research
Volume-Issue
24 - C
Pages
119 - 119
Publication Date
2018/12/04
ISSN (Online)
1876-4401
ISSN (Print)
1872-9312
DOI
10.1016/j.artres.2018.10.192How to use a DOI?
Open Access
This is an open access article distributed under the CC BY-NC license.

Cite this article

risenwbib
TY  - JOUR
AU  - M Elena Martinez-Perez
AU  - Kim Parker
AU  - Nick Witt
AU  - S.A.McG. Thom
AU  - Alun Hughes
PY  - 2018
DA  - 2018/12/04
TI  - P139 AUTOMATIC CLASSIFICATION OF ARTERIAL AND VENULAR TREES IN COLOUR FUNDUS IMAGES
JO  - Artery Research
SP  - 119
EP  - 119
VL  - 24
IS  - C
SN  - 1876-4401
UR  - https://doi.org/10.1016/j.artres.2018.10.192
DO  - 10.1016/j.artres.2018.10.192
ID  - Martinez-Perez2018
ER  -