Open AccessDesign of Density Clustering In Diabetic Retinopathy Based Eye Fundus Segmentation
Author(s) -
Naluguru Udaya Kumar,
Thelapolu Nikitha,
Srinivas Bangalore
Publication year - 2021
Publication title -
iop conference series. materials science and engineering
Language(s) - English
Resource type - Journals
eISSN - 1757-899X
pISSN - 1757-8981
DOI - 10.1088/1757-899x/1084/1/012006
Subject(s) - diabetic retinopathy , cluster analysis , segmentation , fundus (uterus) , artificial intelligence , retinopathy , stage (stratigraphy) , computer science , medicine , ophthalmology , pattern recognition (psychology) , diabetes mellitus , biology , paleontology , endocrinology
In order to prevent further complications, we learned in this paper that earlier diagnosis is critical in Diabetic Retinopathy (DR). The disease can be classified into one of two stages (the early stage of non-proliferative and later stage of proliferative diabetic retinopathy) of Eye Fundus Images (EFI), diagnosed on the basis of the presence and quantities of a complex series of lesions such as microaneurysms, haemorrhages or exudates. Therefore it is important to properly segment regions of potential lesions to demonstrate and classify the lesions and the degree of DR. Density clustering approaches are promising candidates for the isolation of individual lesions, and can be used along with effective methods for vascular tree elimination, extraction and classification. In this article, our approach, findings, tradeoffs and assumptions for segmenting and detecting individual lesions are reported.