Volume 3, Issue 1, May 2013, Pages 116–120
Anitha Somasundaram1 and Janardhana Prabhu2
1 Regional Centre, Anna University, Madurai, Tamilnadu, India
2 Department of Electronics and Communication Engineering, Regional Centre, Anna University, Madurai, Tamilnadu, India
Original language: English
Copyright © 2013 ISSR Journals. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
Diabetes is a group of metabolic diseases in which a person has high blood sugar. Diabetic Retinopathy (DR) is caused by the abnormalities in the retina due to insufficient insulin in the body. Diabetic Retinopathy affects 80% of all patients who had diabetes for 10 years or more, which can also lead to vision loss. The most primitive sign of Diabetic Retinopathy is Exudates. Exudates in the retina are opacities that result from the escape of plasma and white blood cells from defective blood vessels. Detecting the exudates in an earlier stage can prevent the vision loss. In this paper, an automated algorithm has demonstrated to detect and localize the presence of exudates from low-contrast digital images of retinopathy patients with non-dilated pupils. In this method, first the retinal fundus image is pre-processed. Then, Mask Technique and Score Computation technique is used for segmenting the exudates in the retinal fundus images. This method does not require supervised learning which requires labeled set, may cause human error and it is time consuming process. It can effectively identify the lesions because exudates were clearly distinguished from optic disc and blood vessels. It helps the ophthalmologists apply proper treatments that might eliminate the disease or decrease the severity of it.
Author Keywords: Diabetic Retinopathy, Exudates, Kirsch Edge detector, Mask Technique, Optic Disc, Score Computation.
Anitha Somasundaram1 and Janardhana Prabhu2
1 Regional Centre, Anna University, Madurai, Tamilnadu, India
2 Department of Electronics and Communication Engineering, Regional Centre, Anna University, Madurai, Tamilnadu, India
Original language: English
Copyright © 2013 ISSR Journals. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
Abstract
Diabetes is a group of metabolic diseases in which a person has high blood sugar. Diabetic Retinopathy (DR) is caused by the abnormalities in the retina due to insufficient insulin in the body. Diabetic Retinopathy affects 80% of all patients who had diabetes for 10 years or more, which can also lead to vision loss. The most primitive sign of Diabetic Retinopathy is Exudates. Exudates in the retina are opacities that result from the escape of plasma and white blood cells from defective blood vessels. Detecting the exudates in an earlier stage can prevent the vision loss. In this paper, an automated algorithm has demonstrated to detect and localize the presence of exudates from low-contrast digital images of retinopathy patients with non-dilated pupils. In this method, first the retinal fundus image is pre-processed. Then, Mask Technique and Score Computation technique is used for segmenting the exudates in the retinal fundus images. This method does not require supervised learning which requires labeled set, may cause human error and it is time consuming process. It can effectively identify the lesions because exudates were clearly distinguished from optic disc and blood vessels. It helps the ophthalmologists apply proper treatments that might eliminate the disease or decrease the severity of it.
Author Keywords: Diabetic Retinopathy, Exudates, Kirsch Edge detector, Mask Technique, Optic Disc, Score Computation.
How to Cite this Article
Anitha Somasundaram and Janardhana Prabhu, “Detection of Exudates for the diagnosis of Diabetic Retinopathy,” International Journal of Innovation and Applied Studies, vol. 3, no. 1, pp. 116–120, May 2013.
