Automated diagnosis of Age-related macular degeneration from color retinal fundus images

Author

Priya, R. ; Aruna, P.

Author_Institution

Comput. Sci. & Eng. Dept., Annamalai Univ., Chidambaram, India

Volume

2

fYear

2011

fDate

8-10 April 2011

Firstpage

227

Lastpage

230

Abstract

Automated image processing has the potential to assist in the early detection of Age-related macular degeneration, by detecting changes in blood vessel and patterns in the retina. Age-related macular degeneration (ARMD) is gradual loss of vision by oxidation of macula and most common cause of irreversible vision loss. The ARMD can be classified into 1. Dry macular degeneration 2. Wet macular degeneration. The purpose of this paper is to diagnose the retinal disease ARMD and to classify the two types. The extent of the disease spread in the retina can be identified by extracting the features of the retina. Detection of ARMD disease is done using Probabilistic Neural Network (PNN) method and the two types are classified and diagnosed successfully. The results showed a sensitivity of 94.00% for the classifier and specificity of 95.00%.

Keywords

eye; medical image processing; neural nets; ARMD disease; age-related macular degeneration; automated diagnosis; automated image processing; blood vessel; color retinal fundus images; dry macular degeneration; irreversible vision loss; probabilistic neural network; retina patterns; retinal disease; wet macular degeneration; Artificial neural networks; Biomedical imaging; Blood vessels; Diseases; Feature extraction; Probabilistic logic; Retina; Fundus Images; Probabilistic neural network; Retina; Sensitivity; Specificity;

fLanguage

English

Publisher

ieee

Conference_Titel

Electronics Computer Technology (ICECT), 2011 3rd International Conference on

Conference_Location

Kanyakumari

Print_ISBN

978-1-4244-8678-6

Electronic_ISBN

978-1-4244-8679-3

Type

conf

DOI

10.1109/ICECTECH.2011.5941690

Filename

5941690