Adaptive Eye Fundus Vessel Classification for Automatic Artery and Vein Diameter Ratio Evaluation

Stabingis, Giedrius; Bernatavičienė, Jolita; Dzemyda, Gintautas; Paunksnis, Alvydas; Stabingienė, Lijana; Treigys, Povilas; Vaičaitienė, Ramutė

doi:10.15388/Informatica.2018.191

Informatica

Adaptive Eye Fundus Vessel Classification for Automatic Artery and Vein Diameter Ratio Evaluation

Volume 29, Issue 4 (2018), pp. 757–771

Giedrius Stabingis Jolita Bernatavičienė Gintautas Dzemyda Alvydas Paunksnis Lijana Stabingienė Povilas Treigys Ramutė Vaičaitienė

https://doi.org/10.15388/Informatica.2018.191

Pub. online: 1 January 2018 Type: Research Article

Open Access

Received
1 June 2018

Accepted
1 December 2018

Published
1 January 2018

Abstract

Eye fundus imaging is a useful, non-invasive tool in disease progress tracking, in early detection of disease and other cases. Often, the disease diagnosis is made by an ophthalmologist and automatic analysis systems are used only for support. There are several commonly used features for disease detection, one of them is the artery and vein ratio measured according to the width of the main vessels. Arteries must be separated from veins automatically in order to calculate the ratio, therefore, vessel classification is a vital step. For most analysis methods high quality images are required for correct classification. This paper presents an adaptive algorithm for vessel measurements without the necessity to tune the algorithm for concrete imaging equipment or a specific situation. The main novelty of the proposed method is the extraction of blood vessel features based on vessel width measurement algorithm and vessel spatial dependency. Vessel classification accuracy rates of 0.855 and 0.859 are obtained on publicly available eye fundus image databases used for comparison with another state of the art algorithms for vessel classification in order to evaluate artery-vein ratio ($AVR$). The method is also evaluated with images that represent artery and vein size changes before and after physical load. Optomed OY digital mobile eye fundus camera Smartscope M5 PRO is used for image gathering.

References

Bankhhead, P., Scholfield, C.N., mc Geown, J.G., Curtis, T.M. (2012). Fast retinal vessel detection and measurement using wavelets and edge location refinement. PLOS ONE, 7.

Buteikienė, D., Paunksnis, A., Barzdžiukas, V., Bernatavičienė, J., Marcinkevičius, V., Treigys, P. (2012). Assessment of the optic nerve disc and excavation parameters of interactive and automated parameterization methods. Informatica, 23(3), 335–355.

Dashtbozorg, B., Mendonca, A.M., Campilho, A. (2014). An automatic graph-based approach for artery/vein classification in retinal images. IEEE Transactions on Image Processing, 23(3), 1073–1083.

Fairfield, J. (1990). Toboggan contrast enhancement for contrast segmentation. In: Proceedings of International Conference on Pattern Recognition, pp. 712–716.

Fraz, M.M., Rudnicka, A.R., Owen, C.G., Strachan, D.P., Barman, S.A. (2014). Automated arteriole and venule recognition in retinal images using ensemble classification. In: 2014 International Conference on Computer Vision Theory and Applications (VISAPP), Vol. 3, pp. 194–202.

Knudtson, M.D., Lee, K.E., Hubbard, L.D., Wong, T.Y., Klein, R., Klein, B.E.K. (2003). Revised formulas for summarizing retinal vessel diameters. Current Eye Research, 27(3), 143–149.

Li, H., Hsu, W., Lee, M.L., Wang, H. (2003). A piecewise Gaussian model for profiling and differentiating retinal vessels. In: Proceedings 2003 International Conference on Image Processing (Cat. No. 03CH37429), Vol. 1. I-1069-72.

Li, X., Wee, W.G. (2014). Retinal vessel detection and measurement for computer-aided medical diagnosis. Journal of Digital Imaging, 27, 120–132.

Mendonca, A., Dashtbozorg, B., Campilho, A. (2013). Segmentation of the vascular network of the retina. Image Analysis and Modeling in Opthalmology. CRC Press, USA.

Miri, M., Amini, Z., Rabbani, H., Kafie, R. (2017). A comprehensive study of retinal vessel classification methods in fundus images. Journal of Medical Signals & Sensors, 7(2), 59–70.

Mirsharif, Q., Tajeripour, F., Pourreza, H. (2013). Automated characterization of blood vessels as arteries and veins in retinal images. Computerized Medical Imaging and Graphics, 37, 607–617.

Morkunas, M., Treigys, P., Bernataviciene, J., Laurinavicius, A., Korvel, G. (2018). Machine learning based classification of colorectal cancer tumour tissue in whole-slide images. Informatica, 29(1), 75–90.

Muramatsu, C., Hatanaka, Y., Iwase, T., Hara, T., Fujita, H. (2011). Automated selection of major arteries and veins for measurement of arteriolar-to-venular diameter ratio on retinal fundus images. Computerized Medical Imaging and Graphics, 35, 472–480.

Niemeijer, M., Abramoff, M., van Ginneken, B. (2009). Fast detection of the optic disc and fovea in color fundus photographs. Medical Image Analysis, 13(6), 859–870.

Niemeijer, M., Xu, X., Dumitrescu, A., Gupta, P., van Ginneken, B., Folk, J., Abramoff, M. (2011). Automated measurement of the arteriolar-to-venular width ratio in digital color fundus photographs. IEEE Transactions on Medical Imaging, 30(11), 1941–1950.

Prasath, V.B.S. (2017). Quantum noise removal in X-ray images with adaptive total variation regularization. Informatica, 28(3), 505–515.

Ravishankar, S., Jain, A., Mittal, A. (2009). Automated feature extraction for early detection of diabetic retinopathy in fundus images. In: 2009 IEEE Conference on Computer Vision and Pattern Recognition, Miami, FL, pp. 210–217.

Renukalatha, S., Suresh, K.V. (2018). A review on biomedical image analysis. Biomedical Engineering: Applications, Basis and Communications, 30(4).

Soares, J.V.B., Leandro, J.J.G., Cesar, R.M., Jelinek, H.F., Cree, M.J. (2006). Retinal vessel segmentation using the 2-D Gabor wavelet and supervised classification. IEEE Transactions on Medical Imaging, 25(9), 1214–1222.

Staal, J., Abramoff, M.D., Niemeijer, M., Viergever, M.A., van Ginneken, B. (2004). Ridge based vessel segmentation in color images of the retina. IEEE Transactions on Medical Imaging, 23, 501–509.

Stabingis, G., Bernatavičienė, J., Dzemyda, G., Imbrasienė, D., Paunksnis, A. (2016). Automated classification of arteries and veins in the retinal blood vasculature. In: Proceedings of the 11th International Conference on Theoretical & Applied Stochastics, Minsk, Belarus.

Stabingis, G., Bernatavičienė, J., Dzemyda, G., Paunksnis, A., Treigys, P., Vaičaitienė, R., Stabingienė, L. (2018). Automatization of eye fundus vessel width measurements. In: VipIMAGE 2017. ECCOMAS 2017, Lecture Notes in Computational Vision and Biomechanics,: Vol. 27, pp. 787–796.

Sun, C., Wang, J.J., Mackey, D.A., Wong, T.Y. (2009). Retinal vascular caliber: systemic, environmental, and genetic associations. Survey of Ophthalmology, 54(1), 74–95.

Treigys, P., Dzemyda, G., Barzdžiukas, V. (2008). Automated positioning of overlapping eye fundus images. In: Computational Science – ICCS 2008. ICCS 2008, Lecture Notes in Computer Science, Vol. 5101, pp. 770–779.

Biographies

Stabingis Giedrius

giedrius.stabingis@ku.lt

G. Stabingis received BA in informatics in 2005 and MS in statistics in 2011 from Klaipeda University, Lithuania. He is an assistant professor in Informatics and Statistics Department of Klaipeda University. Currently he is a PhD student in Vilnius University, Institute of Data Science and Digital Technologies. His interests include image analysis methods, image processing, classification methods, spatial statistics and spatial data mining.

Bernatavičienė Jolita

jolita.bernataviciene@mii.vu.lt

J. Bernatavičienė graduated from Vilnius Pedagogical University in 2004 and received a master’s degree in informatics. In 2008, she received the doctoral degree in computer science (PhD) from Institute of Mathematics and Informatics jointly with Vilnius Gediminas Technical University. She is a researcher at Cognitive Computing Group of Vilnius University, Institute of Data Science and Digital Technologies. Her research interests include databases, data mining, neural networks, image analysis, visualization, decision support systems and internet technologies.

Dzemyda Gintautas

gintautas.dzemyda@mii.vu.lt

G. Dzemyda received the doctoral degree in technical sciences (PhD) in 1984, and he received the degree of Doctor Habilius in 1997 from Kaunas University of Technology. He was conferred the title of professor (1998) at Kaunas University of Technology. Recent employment is at Vilnius University, Institute of Data Science and Digital Technologies, as the director of the Institute, a head of Cognitive Computing Group and Principal Researcher. The research interests cover visualization of multidimensional data, optimization theory and applications, data mining in databases, multiple criteria decision support, neural networks, parallel optimization, image analysis. The author of more than 240 scientific publications, two monographs, five textbooks. Editor in chief of the international journals Informatica and Baltic Journal of Modern Computing. Member of editorial boards of seven international journals.

Paunksnis Alvydas

alvydas@stratelus.com

A. Paunksnis graduated from Kaunas University of Medicine, Lithuania. Medical doctor since June, 1969. DrSci (habil.) since 1993, professor of ophthalmology since 1997. He is the director of the Department of Ophthalmology, Institute for Biomedical Research of Kaunas University of Medicine since July, 1992. Member of the Council of European Ophthalmologist Society since 1995, a full member of the International Society of Experimental Eye Research since 1989, president of the Lithuanian Ophthalmologist Society 1993 to 1997, chairman of the Council of Kaunas University of Medicine 1997 to 2000, coordinator of the Telemedicine Project Group of Kaunas University of Medicine since June 1999, head of the Telemedicine Center of Kaunas University of Medicine since 2002. His present research areas include non-invasive ultrasound examination in ophthalmology, ophthalmooncology, epidemiology, telemedicine.

Stabingienė Lijana

lijana.stabingiene@ku.lt

L. Stabingienė graduated from Klaipeda University, Lithuania, in 2007 and received a master’s degree in system research. In 2012 she received the doctoral degree in computer science (PhD) from Vilnius University, Institute of Mathematics and Informatics. She is an associated professor in Informatics and Statistics Department of Klaipeda University. Present research interests include classification of spatially correlated data, geostatistics, image analysis and spatial data mining.

Treigys Povilas

povilas.treigys@mii.vu.lt

P. Treigys graduated from Vilnius Gediminas Technical University, Lithuania, in 2005. In 2010 he received the doctoral degree in computer science (PhD) from Institute of Mathematics and Informatics jointly with Vilnius Gediminas Technical University. Recent employment is at Vilnius University, Institute of Data Science and Digital Technologies, as senior researcher, associate professor and a head of Image and Signal Analysis Group. He is vice-dean for Information Technologies at Vilnius University, Faculty of Mathematics and Informatics. He is a member of the Lithuanian Society for biomedical engineering. His interests include image analysis, detection and object’s feature extraction in image processing, automated image objects segmentation, optimization methods, artificial neural networks and software engineering.

Vaičaitienė Ramutė

ramute.vaicaitiene@lka.lt

R. Vaičaitienė graduated from Kaunas University of Medicine, Lithuania. Medical doctor since 2000. In 2010 she received master’s degree in health psychology. From 1993 she works at Jonas Basanavičius Military Medical Service. From 2013 she works as an associated professor in General Jonas Žemaitis Military Academy of Lithuania. Her present research areas include psychological well-being, stress management, stress risk factors, military psychological resilience, peculiarities of suicide prevention in the military, health psychology, neuroimmunology, correction of psychosomatic disorders using psychological methods.

Full article Cited by

Open access article under the CC BY license.

Keywords

automatic vessel classification vessel measurement artery-vein ratio eye fundus images

Metrics

since January 2020

1293 Article info views	721 Full article views
610 PDF downloads	227 XML downloads

RSS

Authors

Abstract

References

Biographies

Export citation

Copy and paste formatted citation

Download citation in file