Automated measurement of the arteriolar-to-venular width ratio in digital color fundus photographs
- PMID: 21690008
- DOI: 10.1109/TMI.2011.2159619
Automated measurement of the arteriolar-to-venular width ratio in digital color fundus photographs
Abstract
A decreased ratio of the width of retinal arteries to veins [arteriolar-to-venular diameter ratio (AVR)], is well established as predictive of cerebral atrophy, stroke and other cardiovascular events in adults. Tortuous and dilated arteries and veins, as well as decreased AVR are also markers for plus disease in retinopathy of prematurity. This work presents an automated method to estimate the AVR in retinal color images by detecting the location of the optic disc, determining an appropriate region of interest (ROI), classifying vessels as arteries or veins, estimating vessel widths, and calculating the AVR. After vessel segmentation and vessel width determination, the optic disc is located and the system eliminates all vessels outside the AVR measurement ROI. A skeletonization operation is applied to the remaining vessels after which vessel crossings and bifurcation points are removed, leaving a set of vessel segments consisting of only vessel centerline pixels. Features are extracted from each centerline pixel in order to assign these a soft label indicating the likelihood that the pixel is part of a vein. As all centerline pixels in a connected vessel segment should be the same type, the median soft label is assigned to each centerline pixel in the segment. Next, artery vein pairs are matched using an iterative algorithm, and the widths of the vessels are used to calculate the AVR. We trained and tested the algorithm on a set of 65 high resolution digital color fundus photographs using a reference standard that indicates for each major vessel in the image whether it is an artery or vein. We compared the AVR values produced by our system with those determined by a semi-automated reference system. We obtained a mean unsigned error of 0.06 (SD 0.04) in 40 images with a mean AVR of 0.67. A second observer using the semi-automated system obtained the same mean unsigned error of 0.06 (SD 0.05) on the set of images with a mean AVR of 0.66. The testing data and reference standard used in this study has been made publicly available.
Similar articles
-
Color Fundus Image Guided Artery-Vein Differentiation in Optical Coherence Tomography Angiography.Invest Ophthalmol Vis Sci. 2018 Oct 1;59(12):4953-4962. doi: 10.1167/iovs.18-24831. Invest Ophthalmol Vis Sci. 2018. PMID: 30326063 Free PMC article.
-
Automated selection of major arteries and veins for measurement of arteriolar-to-venular diameter ratio on retinal fundus images.Comput Med Imaging Graph. 2011 Sep;35(6):472-80. doi: 10.1016/j.compmedimag.2011.03.002. Epub 2011 Apr 13. Comput Med Imaging Graph. 2011. PMID: 21489750
-
An improved system for the automatic estimation of the Arteriolar-to-Venular diameter Ratio (AVR) in retinal images.Annu Int Conf IEEE Eng Med Biol Soc. 2008;2008:3550-3. doi: 10.1109/IEMBS.2008.4649972. Annu Int Conf IEEE Eng Med Biol Soc. 2008. PMID: 19163475
-
[A new approach for studying the retinal and choroidal circulation].Nippon Ganka Gakkai Zasshi. 2004 Dec;108(12):836-61; discussion 862. Nippon Ganka Gakkai Zasshi. 2004. PMID: 15656089 Review. Japanese.
-
Optic disc size and retinal vessel characteristics in healthy children.Acta Ophthalmol Scand. 1998 Jun;76(3):260-7. doi: 10.1034/j.1600-0420.1998.760302.x. Acta Ophthalmol Scand. 1998. PMID: 9686834 Review.
Cited by
-
Non-Invasive Retinal Vessel Analysis as a Predictor for Cardiovascular Disease.J Pers Med. 2024 May 9;14(5):501. doi: 10.3390/jpm14050501. J Pers Med. 2024. PMID: 38793083 Free PMC article. Review.
-
Multi-Task Segmentation and Classification Network for Artery/Vein Classification in Retina Fundus.Entropy (Basel). 2023 Jul 31;25(8):1148. doi: 10.3390/e25081148. Entropy (Basel). 2023. PMID: 37628178 Free PMC article.
-
A Global Review of Publicly Available Datasets Containing Fundus Images: Characteristics, Barriers to Access, Usability, and Generalizability.J Clin Med. 2023 May 21;12(10):3587. doi: 10.3390/jcm12103587. J Clin Med. 2023. PMID: 37240693 Free PMC article.
-
Recent developments on computer aided systems for diagnosis of diabetic retinopathy: a review.Multimed Tools Appl. 2023;82(10):14471-14525. doi: 10.1007/s11042-022-13841-9. Epub 2022 Sep 24. Multimed Tools Appl. 2023. PMID: 36185322 Free PMC article.
-
Deep learning for ultra-widefield imaging: a scoping review.Graefes Arch Clin Exp Ophthalmol. 2022 Dec;260(12):3737-3778. doi: 10.1007/s00417-022-05741-3. Epub 2022 Jul 20. Graefes Arch Clin Exp Ophthalmol. 2022. PMID: 35857087 Review.
Publication types
MeSH terms
Grants and funding
LinkOut - more resources
Full Text Sources
Research Materials