Classification of Artery and Vein in Retinal Fundus Images Based on the Context-Dependent Features
In this paper, we present an automatic method based on context-dependent characteristics for the detection and classification of arterial vessels and venous vessels in retinal fundus images. It provides a non-invasive opportunity and effective foundation for the diagnosis of several medical pathologies. In the proposed method, a combination of shifted filter responses is used, which can selectively respond to vessels. It achieves orientation selectivity by computing the weighted geometric mean of the output of a pool of Difference-of-Gaussian filters, whose supports are aligned in a collinear manner. We then configure two combinations of shifted filters, namely symmetric and asymmetric, that are selective for bars and bar-endings, respectively. We achieve vessel detection by summing up the responses of the two filters. Then we extract the morphology and topological characteristics based on the vessel segmentation, and specifically present context-dependent features of blood vessels, including the shape, structure, relative position, context information and other important features. Based on these features, we use JointBoost classifier to construct potential function for conditional random fields (CRFs) model, and train the labeled samples to classify arteriovenous blood vessels in retinal images. The training and testing data sets were prepared according to the results based on DRIVE dataset provided by Estrada et al. The experimental results show that the accuracy of the proposed method for vein and artery detection is 91.1% and 94.5%, respectively, which is superior to that of the state-of-the-art methods. It can be used as a clinical reference for computer-assisted quantitative analysis of fundus images.
KeywordsRetinal image analysis Vessel segmentation Classification of artery and vein Combination of shifted filter responses Context-dependent features Conditional random fields
This research is funded by Natural Science Foundation of Changchun Normal University in 2015 (contract number: CCNU Natural Science Co-words  No. 005) and Scientific Research Planning Project of the Education Department of Jilin Province in 2016 (contract number: Ji Edu & Sci Co-words  No. 001). It is also supported by China scholarship Council under the State Scholarship Fund.
- 4.Macgillivray, T.J., Patton, N., Doubal, F.N., et al.: Fractal analysis of the retinal vascular network in fundus images. In: The IEEE 29th Annual International Conference of Engineering in Medicine and Biology Society, pp. 6455–6458 (2007)Google Scholar
- 6.Grisan, E., Ruggeri, A.: A divide et impera strategy for automatic classification of retinal vessels into arteries and veins. In: Proceedings of the IEEE 25th Annual International Conference of Engineering in Medicine and Biology Society, vol. 1, pp. 890–893 (2003)Google Scholar
- 7.Jelinek, H.F., Depardieu, C., Lucas, C., et al.: Towards vessel characterisation in the vicinity of the optic disc in digital retinal images. In: Image and Vision Computing Conference, pp. 2–7 (2005)Google Scholar
- 8.Kondermann, C., Kondermann, D., Yan, M.: Blood vessel classification into arteries and veins in retinal images. In: Medical Imaging. International Society for Optics and Photonics, pp. 651247–651247-9 (2007)Google Scholar
- 10.Niemeijer, M., van Ginneken, B., Abràmoff, M.D.: Automatic classification of retinal vessels into arteries and veins. In: SPIE Medical Imaging, pp. 72601F–72601F-8 (2009)Google Scholar
- 12.Vázquez, S.G., Barreira, N., Penedo, M.G., Saez, M., Pose-Reino, A.: Using retinex image enhancement to improve the artery/vein classification in retinal images. In: Campilho, A., Kamel, M. (eds.) ICIAR 2010. LNCS, vol. 6112, pp. 50–59. Springer, Heidelberg (2010). doi: 10.1007/978-3-642-13775-4_6 CrossRefGoogle Scholar
- 13.Relan, D., MacGillivray, T., Ballerini, L., et al.: Retinal vessel classification: sorting arteries and veins. In: 35th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), pp. 7396–7399. IEEE (2013)Google Scholar
- 20.Yao, C., Chen, H.: Measurement of retinal vessel widths based on prior knowledge. Sci. Pap. 4(1), 64–68 (2009)Google Scholar
- 22.Shotton, J., Winn, J., Rother, C., Criminisi, A.: TextonBoost: joint appearance, shape and context modeling for multi-class object recognition and segmentation. In: Leonardis, A., Bischof, H., Pinz, A. (eds.) ECCV 2006. LNCS, vol. 3951, pp. 1–15. Springer, Heidelberg (2006). doi: 10.1007/11744023_1 CrossRefGoogle Scholar
- 23.Torralba, A., Murphy, K.P., Freeman, W.T.: Sharing features: efficient boosting procedures for multiclass object detection. In: IEEE Computer Vision and Pattern Recognition (CVPR), vol. 2, pp. II-762–II-769 (2004)Google Scholar
- 31.Muramatsu, C., Hatanaka, Y., Iwase, T., et al.: Automated detection and classification of major retinal vessels for determination of diameter ratio of arteries and veins. In: SPIE Medical Imaging. International Society for Optics and Photonics, pp. 76240J–76240J-8 (2010)Google Scholar