Online citations, reference lists, and bibliographies.
← Back to Search

Combining ODR And Blood Vessel Tracking For Artery–Vein Classification And Analysis In Color Fundus Images

Minha Alam, T. Son, Devrim Toslak, Jennifer I. Lim, Xincheng Yao
Published 2018 · Medicine

Save to my Library
Download PDF
Analyze on Scholarcy Visualize in Litmaps
Share
Reduce the time it takes to create your bibliography by a factor of 10 by using the world’s favourite reference manager
Time to take this seriously.
Get Citationsy
Purpose This study aims to develop a fully automated algorithm for artery–vein (A-V) and arteriole-venule classification and to quantify the effect of hypertension on A-V caliber and tortuosity ratios of nonproliferative diabetic retinopathy (NPDR) patients. Methods We combine an optical density ratio (ODR) analysis and blood vessel tracking (BVT) algorithm to classify arteries and veins and arterioles and venules. An enhanced blood vessel map and ODR analysis are used to determine the blood vessel source nodes. The whole vessel map is then tracked beginning from the source nodes and classified as vein (venule) or artery (arteriole) using vessel curvature and angle information. Fifty color fundus images from NPDR patients are used to test the algorithm. Sensitivity, specificity, and accuracy metrics are measured to validate the classification method compared to ground truths. Results The combined ODR-BVT method demonstrates 97.06% accuracy in identifying blood vessels as vein or artery. Sensitivity and specificity of A-V identification are 97.58%, 97.81%, and 95.89%, 96.68%, respectively. Comparative analysis revealed that the average A-V caliber and tortuosity ratios of NPDR patients with hypertension have 48% and 15.5% decreases, respectively, compared to that of NPDR patients without hypertension. Conclusions Automated A-V classification has been achieved by combined ODR-BVT analysis. Quantitative analysis of color fundus images verified robust performance of the A-V classification. Comparative quantification of A-V caliber and tortuosity ratios provided objective biomarkers to differentiate NPDR groups with and without hypertension. Translational Relevance Automated A-V classification can facilitate quantitative analysis of retinal vascular distortions due to diabetic retinopathy and other eye conditions and provide increased sensitivity for early detection of eye diseases.
This paper references
10.1001/archopht.1933.00830010582006
Pigmentation of the Optic Nerve.
A. Reese (1932)
10.1016/0002-9394(78)90013-2
Retinal depression sign indicating a small retinal infarct.
M. Goldbaum (1978)
10.1118/1.596131
Analysis of vessel absorption profiles in retinal oximetry.
D. Roberts (1987)
10.1016/S0065-2458(08)60261-2
Computer Vision
A. Rosenfeld (1988)
10.1109/42.34715
Detection of blood vessels in retinal images using two-dimensional matched filters.
S. Chaudhuri (1989)
10.1109/78.80892
A class of fast Gaussian binomial filters for speech and image processing
R. Haddad (1991)
10.1109/34.161346
Thinning Methodologies - A Comprehensive Survey
L. Lam (1992)
10.1016/s0923-0459(96)x8001-7
Topological Algorithms for Digital Image Processing
T. Y. Kong (1996)
10.1016/S1386-5056(98)00163-4
Measurement and classification of retinal vascular tortuosity
W. Hart (1999)
10.1016/S0161-6420(99)90525-0
Methods for evaluation of retinal microvascular abnormalities associated with hypertension/sclerosis in the Atherosclerosis Risk in Communities Study.
L. Hubbard (1999)
10.1109/ICIP.2001.958635
A method of vessel tracking for vessel diameter measurement on retinal images
X. Gao (2001)
10.1016/S0039-6257(01)00234-X
Retinal microvascular abnormalities and their relationship with hypertension, cardiovascular disease, and mortality.
T. Wong (2001)
10.1016/S0031-3203(00)00032-7
Segmentation of macular fluorescein angiographies. A statistical approach
A. Simó (2001)
Automated Calculation of Retinal Arteriovenous Ratio for Detection and Monitoring of Cerebrovascular Disease Based on Assessment of Morphological Changes of Retinal Vascular System
R. Chrástek (2002)
10.1109/IEMBS.2003.1279908
A divide et impera strategy for automatic classification of retinal vessels into arteries and veins
E. Grisan (2003)
10.1109/ICIP.2003.1247151
A piecewise Gaussian model for profiling and differentiating retinal vessels
Huiqi Li (2003)
10.1016/J.OPHTHA.2003.09.039
Computer-assisted measurement of retinal vessel diameters in the Beaver Dam Eye Study: methodology, correlation between eyes, and effect of refractive errors.
T. Wong (2004)
10.1002/0471721581.CH2
Color as a Science
William R. Mathew (2005)
10.1007/0-306-48606-7_7
Automatic Analysis of Color Fundus Photographs and Its Application to the Diagnosis of Diabetic Retinopathy
Thomas Walter (2005)
10.1109/TBME.2005.847402
Automatic grading of retinal vessel caliber
Huiqi Li (2005)
Towards vessel characterisation in the vicinity of the optic disc in digital retinal images
H. Jelinek (2005)
10.1016/j.preteyeres.2005.07.001
Retinal image analysis: Concepts, applications and potential
N. Patton (2006)
10.1136/hrt.2006.090522
Retinal vascular calibre and the risk of coronary heart disease-related death
J. Wang (2006)
10.1063/1.2812298
Automatic retinal oximetry.
S. Hardarson (2006)
10.1001/ARCHINTE.166.21.2388
Quantitative retinal venular caliber and risk of cardiovascular disease in older persons: the cardiovascular health study.
T. Wong (2006)
10.1007/11866565_79
A Region Based Algorithm for Vessel Detection in Retinal Images
K. Huang (2006)
10.1161/01.HYP.0000199104.61945.33
Retinal Vessel Diameters and Risk of Hypertension: The Rotterdam Study
M. Ikram (2006)
10.1117/12.708469
Blood vessel classification into arteries and veins in retinal images
Claudia Kondermann (2007)
10.1117/1.2772655
Spectral oximetry assessed with high-speed ultra-high-resolution optical coherence tomography.
L. Kagemann (2007)
10.1109/TBME.2007.900804
Automatic Identification of Retinal Arteries and Veins From Dual-Wavelength Images Using Structural and Functional Features
H. Narasimha-Iyer (2007)
10.1007/978-3-540-72903-7_3
Graph-Based Methods for Retinal Mosaicing and Vascular Characterization
W. Aguilar (2007)
10.1016/j.media.2007.05.001
Automatic detection of microaneurysms in color fundus images
T. Walter (2007)
10.1136/hrt.2008.146670
Retinopathy predicts coronary heart disease mortality
G. Liew (2008)
10.1117/12.813826
Automatic classification of retinal vessels into arteries and veins
M. Niemeijer (2009)
10.1097/HJH.0b013e3283310f7e
Retinal vessel diameters and risk of hypertension: the Multiethnic Study of Atherosclerosis
R. Kawasaki (2009)
10.1016/j.imavis.2008.02.013
Separation of the retinal vascular graph in arteries and veins based upon structural knowledge
K. Rothaus (2009)
10.2316/J.2010.216.680-0094
AUTOMATIC CLASSIFICATION OF RETINAL VESSELS INTO ARTERIES AND VEINS
S. G. Vázquez (2010)
10.1364/boe.1.000310/
Assessing hemoglobin concentration using spectroscopic optical coherence tomography for feasibility of tissue diagnostics
F. Robles (2010)
10.1109/DICTA.2010.106
On the Automatic Computation of the Arterio-Venous Ratio in Retinal Images: Using Minimal Paths for the Artery/Vein Classification
S. G. Vázquez (2010)
10.1109/RBME.2010.2084567
Retinal Imaging and Image Analysis.
M. Abràmoff (2010)
10.1109/TMI.2011.2159619
Automated Measurement of the Arteriolar-to-Venular Width Ratio in Digital Color Fundus Photographs
M. Niemeijer (2011)
10.1016/c2011-0-06935-1
Feature extraction & image processing for computer vision
M. Nixon (2012)
10.1007/s00138-012-0442-4
Improving retinal artery and vein classification by means of a minimal path approach
S. G. Vázquez (2012)
10.1117/12.911490
Automated artery-venous classification of retinal blood vessels based on structural mapping method
Vinayak S. Joshi (2012)
10.1007/s10278-012-9501-7
Retinal Image Registration Using Geometrical Features
Sara Gharabaghi (2012)
10.1109/EMBC.2013.6611267
Retinal vessel classification: Sorting arteries and veins
D. Relan (2013)
10.1111/aos.12598
Reproducibility of retinal oximetry measurements in healthy and diseased retinas
C. Tuerksever (2015)
10.1016/J.IJLEO.2015.05.027
Optimum green plane masking for the contrast enhancement of retinal images using enhanced genetic algorithm
E. Daniel (2015)
10.1117/1.JBO.21.6.066008
Quantitative assessment of the retinal microvasculature using optical coherence tomography angiography
Zhongdi Chu (2016)
10.1364/BOE.8.001741
Quantitative characteristics of sickle cell retinopathy in optical coherence tomography angiography.
M. Alam (2017)



This paper is referenced by
10.1007/s12652-020-02294-3
Prediction of atherosclerosis pathology in retinal fundal images with machine learning approaches
C. Parameswari (2021)
10.1364/boe.399514
AV-Net: deep learning for fully automated artery-vein classification in optical coherence tomography angiography.
Minha Alam (2020)
Joint Learning of Vessel Segmentation and Artery/Vein Classification with Post-processing
Liangzhi Li (2020)
10.3390/diagnostics10121026
Scattering of Light from the Systemic Circulatory System
S. Batool (2020)
10.1117/12.2510213
Quantitative artery-vein analysis in optical coherence tomography angiography of diabetic retinopathy
M. Alam (2019)
10.1117/12.2508918
Optical coherence tomography guided artery-vein classification in retinal OCT angiography of macular region
Taeyoon Son (2019)
10.1364/BOE.10.002055
OCT feature analysis guided artery-vein differentiation in OCTA.
M. Alam (2019)
10.1177/1535370219850791
Highlight article: Near infrared oximetry-guided artery–vein classification in optical coherence tomography angiography
Taeyoon Son (2019)
10.1088/1755-1315/243/1/012021
Semantic segmentation of artery-venous retinal vessel using simple convolutional neural network
Wahyudi Budi Setiawan (2019)
10.1167/tvst.8.2.3
Differential Artery–Vein Analysis Improves the Performance of OCTA Staging of Sickle Cell Retinopathy
M. Alam (2019)
10.1093/neuros/nyx351
Contrast Time‐Density Time on Digital Subtraction Angiography Correlates With Cerebral Arteriovenous Malformation Flow Measured by Quantitative Magnetic Resonance Angiography, Angioarchitecture, and Hemorrhage
D. Brunozzi (2018)
Semantic Scholar Logo Some data provided by SemanticScholar