Computer Aided Approach for Detection of Age Related Macular Degeneration from Retinal Fundus Images

Computer Aided Approach for Detection of Age Related Macular Degeneration from Retinal Fundus Images

 Abstract:

Age Related Macular Degeneration (ARMD) is a retinal disorder usually found in old people, which affects the central vision, but not the peripheral vision. The objective of this work is to develop an automated system for the classification of ARMD using digital fundus images, so that an intelligent computer aided system can be developed for the diagnosis of ARMD. from ARMD. Diagnosis and treatment of ARMD in the earlier stages helps to cure the disease and According to American Society of Retinal Specialists, about fifteen million people around the globe are suffering will save many from vision loss. ARMD may result from the ageing and thinning of macular tissues, depositing of pigment in the macula, growth of abnormal blood vessels or a combination of the these processes. So it is possible to detect and diagnosis the disease by analyzing such abnormalities present in the retinal images. The abnormalities should have significant difference with the neighboring tissues and by properly segmenting such regions, as a result macular degeneration is predicted whether it is present or not. Here the abnormalities are segmented from the fundus images after multi stage segmentation processes. Threshold based segmentation is used along with Canny edge detection algorithm to efficiently identify the abnormality region. Threshold based binary classification of the analyzed image is evaluated by finding the extent of abnormalities present in the image. The abnormal area are shown white pixels as a result the classifier the classifier checks whether the number of pixels in the result is more or less than the threshold value. If more it is considered as an ARMD affected image or else it is predicted as a normal one.

Comments are closed.