Home / Current Issue / Paper 1702127
Detection Of Diabetic Retinopathy
Subject area: Science,Engineering and Technology · Area of research: Electronics and Communication Engineering
Abstract
Diabetes is the common chronic disease that most people are facing nowadays. It also leads to various other health issues. Of them, blindness is the one major issue which could be permanent, if it is not detected and nursed at the early stages. Diabetic Retinopathy is a retina disease that affects diabetes mellitus patients, and is a significant cause of blindness. It is a condition where the blood vessels of the retinal gland swell. It affects the eye retina and could lead to blindness if the diabetes level is very high. So far, early detection by routine screening test is the most effective treatment. But such screenings need too much time, effort and cost. Hence in order to overcome these problems, we employ two image processing techniques that automatically detect the presence of abnormalities in the retinal images. They are: detection of a) Vessels through OD. b)Abnormal signs (such as exudates and lesions). In the first approach, the presence of vessels which is one of the major causes for diabetic retinopathy is detected by applying histogram equalisation algorithm to the digital retinal fundus images. In this, at the start the optic disc, which is the point of exit for ganglion cell axons or optical nerves leaving the eye is determined. Later, the damaged vessels are detected by using the blood vessels. Whereas in the second approach, there are three algorithms to be followed for accurate results, namely, statistical classification, brightness adjustment procedure and local window feature space algorithms. By using these algorithms the other leading cause for blindness i.e, presence of abnormal signs (exudates and lesions) is determined. In these algorithms the majorly considered factors are luminosity and contrast which are very helpful for the exact results, even though the screenings are done in different environments. In this method the results are also verified by the local window feature space algorithm. The dataset for the project is taken from STARE database and some are taken from DRIVE database.
Keywords
Digital Retinal fundus images, Histogram equalization, statistical classification, local window feature space.
References
[1] C. Sinthanayothin, J. F. Boyce, H. L. Cook, and T. H. Williamson, “Au- tomated localisation of the optic disk, fovea, and retinal blood vessels from digital colour fundus images,” Br. J. Ophthalmol., vol. 83, no. 8, pp. 902–910, 1999.
[2] T. Teng, M. Lefley, and D. Claremont, “Progress towards automated diabetic ocular screening: A review of image analysis and intelligent systems for diabetic retinopathy,” Med. Biol. Eng. Comput., vol. 40, pp. 2–13, 2002.
[3] L. Gagnon, M. Lalonde, M. Beaulieu, and M.-C. Boucher, “Procedure to detect anatomical structures in optical fundus images,”in Proc. Conf. Med. Imag. 2001: Image Process. San Diego, CA, Feb. 19–22, 2001, pp. 1218–1225.
[4] H. Li and O. Chutatape, “Automatic location of optic disc in retinal images,” in IEEE Int. Conf. Image Process., Oct. 7–10, 2001, vol. 2, pp. 837– 840.
[5] J. Lowell, A. Hunter, D. Steel, A. Basu, R. Ryder, E. Fletcher, and L. Kennedy, “Optic nerve head segmentation,” IEEE Trans. Med. Imag., vol. 23, no. 2, pp. 256–264, Feb. 2004.
[6] H. Li and O. Chutatape, “A model-based approach for automated feature extraction in fundus images,” in 9th IEEE Int. Conf. Computer Vision (ICCV’03), 2003, vol. 1, pp. 394–399.
[7] R. A. Abdel-Ghafar, T. Morris, T.Ritchings, and I. Wood, “Detection and characterisation of the optic disk in glaucoma and diabetic retinopathy,” presented at the Med. Image Understand. Anal. Conf., London, U.K., Sep. 23–24, 2004.
[8] A. Osareh, M. Mirmehdi, B. Thomas, and R. Markham, “Classifica- tion and localisation of diabetic-related eye disease,” in 7th Eur. Conf. Computer Vision (ECCV), May 2002, vol. 2353, LNCS, pp. 502–516.
[9] STARE Project Website Clemson Univ., Clemson, SC [Online]. Avail - able: http://www.ces.clemson.edu~ahoover/stare.
[10] M. Lalonde, M. Beaulieu, and L. Gagnon, “Fast and robust optic disk detection using pyramidal decomposition and Hausdorff-based template matching,” IEEE Trans. Med. Imag., vol. 20, no. 11, pp. 1193–1200, Nov. 2001.
How to cite this paper
@article{1702127,
author = {K. Lakshmi Prasanna, K. Suswetha, M. Sahithi Priya, M. Yoga Sri, R. Tejaswini},
title = {Detection Of Diabetic Retinopathy},
journal = {Iconic Research And Engineering Journals},
year = {2020},
volume = {3},
number = {10},
pages = {29-33},
issn = {2456-8880},
url = {https://www.irejournals.com/formatedpaper/1702127.pdf},
abstract = {Diabetes is the common chronic disease that most people are facing nowadays. It also leads to various other health issues. Of them, blindness is the one major issue which could be permanent, if it is not detected and nursed at the early stages. Diabetic Retinopathy is a retina disease that affects diabetes mellitus patients, and is a significant cause of blindness. It is a condition where the blood vessels of the retinal gland swell. It affects the eye retina and could lead to blindness if the diabetes level is very high. So far, early detection by routine screening test is the most effective treatment. But such screenings need too much time, effort and cost. Hence in order to overcome these problems, we employ two image processing techniques that automatically detect the presence of abnormalities in the retinal images. They are: detection of a) Vessels through OD. b)Abnormal signs (such as exudates and lesions). In the first approach, the presence of vessels which is one of the major causes for diabetic retinopathy is detected by applying histogram equalisation algorithm to the digital retinal fundus images. In this, at the start the optic disc, which is the point of exit for ganglion cell axons or optical nerves leaving the eye is determined. Later, the damaged vessels are detected by using the blood vessels. Whereas in the second approach, there are three algorithms to be followed for accurate results, namely, statistical classification, brightness adjustment procedure and local window feature space algorithms. By using these algorithms the other leading cause for blindness i.e, presence of abnormal signs (exudates and lesions) is determined. In these algorithms the majorly considered factors are luminosity and contrast which are very helpful for the exact results, even though the screenings are done in different environments. In this method the results are also verified by the local window feature space algorithm. The dataset for the project is taken from STARE database and some are taken from DRIVE database.},
keywords = {Digital Retinal fundus images, Histogram equalization, statistical classification, local window feature space.},
month = {April},
}