Disease Severity Based On Areas of Exudates, Blood Vessels and Micro-Aneurysms in Retinal Fundus Images Using K-Means Clustering

Journal Title: International Journal of Engineering and Science Invention - Year 2018, Vol 7, Issue 2

Abstract

Diabetic retinopathy (DR) is a kind of disease that attacks retina of human eye occurs mainly due to diabetes because of diabetes there is elaboration of sugar levels in body. Due to DR Patient losses his vision; earlier exposure can diminish the complication of visual detoriation. Existence of micro-aneurysms, cotton-wool spots, hemorrahages and exudates are indication of DR. Micro aneurysms and exudates are foremost signs of DR and can be blocked with a recent diagnosis. Digital fundus image collected from fundus camera helps in analyzing the exudates and micro-aneurysms in prior way. This thesis proposes a method which has two essential steps they are coarse segmentation executed by k-means clustering and fine segmentation executed by morphological image processing for disclosure of required features such as exudates, micro-aneurysms and blood vessels on retinal images of very low contrast. Initially pre-processing of retinal images are performed. Later segmentation of the processed images is done through K-Means clustering. In order to specify these segmented regions into Non-Exudates (blood vessels and micro aneurysms) and Exudates a special set of features which are based on colour and texture are derived from Morphological operations are done to acquire the perfect classification. As disclosure of exudates, and micro aneurysms existing in limited areas can easily identified using this technique hence this technique appears encouraging. Depending upon the area of exudates, blood vessels and micro aneurysms disease severity can be explained whether it is mild or in severe stage.

Authors and Affiliations

Dr. P. V. Ramaraju, I. H. S. Manisree

Keywords

Related Articles

Generation of Good Quality Direct Input Data for Mathematical Models of Pulsatile Flow of Blood in Animal CVS

The aim of the paper is to investigate a good quality direct input data for mathematical models of pulsatile flow of blood in animal cardio-vascular system (CVS). It is first shown that the input data used in the literat...

Eco-Friendly Solar Energy Conversion end Storage In Electrical Energy

Photo sensitizer used for solar energy conversion and storage: The conversion of solar energy on the basis of photo galvanic effect in solar cell. Photo galvanic effect has been studied in system that contains photo sens...

A Real-Time Design Model for Monitoring Electrical Power Transformers from Substations to the Consumers

Widely used in industry for Supervisory Control and Data Acquisition of industrial processes, SCADA systems are now also penetrating the experimental physics laboratories for the controls of ancillary systems such as coo...

Compressive Strength and Thickening Time of Cement in Oil Well

Proper slurry design is critical to the success of a cementing job. The best method to obtain a good slurry design with desired compressive strength is by laboratory experiments which involve experimenting different form...

Fixed-Bed Column Studies on Adsorption of 4-Nitroaniline from Aqueous Solution by Bagasse Fly Ash

Sorptive removal of 4-nitroaniline from aqueous solutions by bagasse fly ash (BFA) was investigated at 303 K under dynamic conditions in a packed bed. The effects of sorbent bed height (Z = 5 - 15 cm), flow rate (Q = 10...

Download PDF file
  • EP ID EP396384
  • DOI -
  • Views 126
  • Downloads 0

How To Cite

Dr. P. V. Ramaraju, I. H. S. Manisree (2018). Disease Severity Based On Areas of Exudates, Blood Vessels and Micro-Aneurysms in Retinal Fundus Images Using K-Means Clustering. International Journal of Engineering and Science Invention, 7(2), 69-77. https://europub.co.uk/articles/-A-396384