Retinal Abnormality Risk Prediction Model: A Hybrid Approach Based on Vessel Characteristics and Exudates

  • M. Aiswarya Raj
  • Shinu Acca Mani
Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 394)


A few systemic diseases, for example, hypertension, diabetes, and vascular disorders will first affect the retinal vessels. When affected with these diseases, the retinal vessels show some sort of vascular changes according to the severity of the conditions. So, in order to diagnose this kind of diseases an efficient system that can detect the retinal abnormalities is required. This paper presents a hybrid approach for the automatic retinal vessel classification, vascular caliber estimation, and exudate detection in retinal images. The retinal vessel classification and caliber estimation is done by exploiting both visual and geometric features that enable discrimination between vein and arteries. Exudates are identified by extracting the yellow pixel level in the retinal image. Based on these three parameters, the retinal abnormality risk prediction model predicts whether the input retinal image is normal or abnormal.


Retina Dick 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.



Authors would like to thank the authors of DRIVE, DERIVA, and HRIS datasets for making their image databases publicly available.


  1. 1.
    Li H, Hsu W, Lee M, Wang H. A piecewise Gaussian model for profiling and differentiating retinal vessels. Proc Int Conf Image Process. 2003;1:1069–72.Google Scholar
  2. 2.
    Vazquez S, Cancela B, Barreira N, Penedo M, Saez M. On the automatic computation of the arterio-venous ratio in retinal images: using minimal paths for the artery/vein classification. Proc Int Conf Digital Image Comput Tech Appl. 2010;599–604.Google Scholar
  3. 3.
    Kaba AD, Li Y, Liu X. Segmentation of blood vessels and optic dick in retinal images. IEEE J Biomed Health Inf. 2013.Google Scholar
  4. 4.
    Joshi VS, Reinhardt JM, Garvin MK, Abramoff MD. Automated method for identification and artery-venous classification of vessel trees in retinal vessel networks. Plos One. 2012.Google Scholar
  5. 5.
    Mendonça AM, Campilho A. Segmentation of retinal blood vessels by combining the detection of centerlines and morphological reconstruction. IEEE Trans Med Imaging 25(9). 2006.Google Scholar
  6. 6.
    El Abbadi NK, Al-Saadi EH. Automatic detection of exudates in retinal images. IJCSI Int J Comput Sci Issues 10(2). 2013.Google Scholar
  7. 7.
    Dashtbozorg B, Mendonca AM, Campilho A. An automatic graph-based approach for artery/vein classification in retinal images. IEEE Trans Image Process. 23(3). 2014.Google Scholar
  8. 8.
    Foracchia M, Grisan E, Ruggeri A. Detection of optic disk in retinal images by means of a geometrical model of vessel structure. IEEE Trans Med Imaging. 2004;23(10):1189–95.CrossRefGoogle Scholar
  9. 9.
    Li H, Chutatape O. Automated feature extraction in color retinal images by a model based approach. IEEE Trans Med Eng. 2004;51:246–54.CrossRefGoogle Scholar

Copyright information

© Springer India 2016

Authors and Affiliations

  1. 1.Department of Computer Science and EngineeringNehru College of Engineering and Research CentreThrissurIndia

Personalised recommendations