A Novel Approach for Detection of Optic Disc and Lesion Location for Screening Diabetic Retinopathy

A Novel Approach for Detection of Optic Disc and Lesion Location for Screening Diabetic Retinopathy

Aakanksha Mahajan, Vasudha Vashisht, Rohit Bansal
DOI: 10.4018/IJHISI.20211001.oa20
Article PDF Download
Open access articles are freely available for download

Abstract

Diabetic Retinopathy is not typically perceivable in diabetic patients at the initial stage. Their first signs, like micro-aneurysms, often go unnoticed in preliminary testing by specialists. Additionally, its presence is difficult to detect as there are other pathologies that may also lead to induce similar signs and symptoms. Until the detection of the presence of exudates, a specialist cannot simply deduce the presence of diabetic retinopathy. This paper presents a method to assist in the identification and differentiation of exudates on colour retinal images based on a variety of k-nearest neighbour filters. The proposed method proved to be a rational approach to detect bright lesions with sufficient certainty, yielding a possible injury with a specificity of 99%.
Article Preview
Top

1. Introduction

Retinography, one of the most used non-invasive medical techniques in the analysis of the human visual system, refers to the clinical procedures used by highly qualified specialists to capture images that are further trained for the analysis, screening and diagnosis of specific visual diseases. The goal of a diabetes screening program is to detect and diagnose diseases before they cause vision loss. The mass screening program utilizes computer fundus images of the retina with or without mydriasis (dilated pupil) to diagnose eye diseases. Automatic retinal analysis can improve the performance of a detection program over manual imaging.

Diabetes Retinopathy (DR) is a retinal disease caused by the long standing diabetes mellitus (DM) (Niemeijer, et al., 2009; Junior, et al., 2013; Rahim, et al., 2016;). DR is the leading cause of blindness in people between the ages of 20 and 60. The likelihood of developing DR is 78% if the patient is over 30 years of age and has had diabetes for more than 15 years (Junior, et al., 2013; Marin et al., 2015). As a result of DR, the surface of the retina is severely damaged. Cotton wools, microaneurysms, exudates and haemorrhages are the primary lesions indicating the presence of DR. Microaneurysms (MAs) are lesions that appear at an early stage of the disease, and the number of MAs increases with the progression of the disease (Adal, et al., 2014; Rahim, et al., 2014). Haemorrhages are likely an injury that occurs after MAs. When the vascular tree of retina leaks blood, it forms haemorrhages (Jitpakdee, et al., 2012; Inbarathi & Karthikeyan, 2014). Thus, the diagnosis of haemorrhages and MAs is an essential part of the automatic diagnosis of retinal diseases at an early stage (Fleming, et al., 2006; Bae, et al., 2011; Rahim et al., 2016). At a later stage, a yellowish-white plasma begins to flow from the blood vessels, which is called hard exudates (Walter et al., 2002). Along with the exudates, a cotton wool appeared - a silver stain caused by the leakage of fat from the vessels. Haemorrhages, MAs, and exudates are features of non-proliferative diabetic retinopathy (NDPR) which is an early stage of DR. An advanced stage of DR, referred to as proliferative diabetic retinopathy (PDR) (Shah & Han, 2004; Danis & Davis, 2008), can have the main blood vessels of the retina entirely blocked. To supply the oxygen, new blood vessels develop, called abnormal blood vessels (DRSRG, 1981; Welikala, et al., 2014). The patient's vision has a significant impact in PDR. The main problem with DR is its asymptomatic nature as it does not affect vision until it reaches a higher level. DR can affect one or both eyes at the same time.

Fundus color images of the retina include various structures such as blood vessels, optic disc, fovea and red lesions such as haemorrhages and MAs. Haemorrhages and MAs comes under dark lesions, while cotton wools and exudates are deliberated as bright lesions. To diagnose fundus imaging lesions, the retinal morphological structure must be removed. Mathematical morphology is utilized to find the location of fovea, vascular trees, and optic disc segmentation (Dougherty & Lotufo, 2003).

Complete Article List

Search this Journal:
Reset
Volume 19: 1 Issue (2024)
Volume 18: 1 Issue (2023)
Volume 17: 2 Issues (2022)
Volume 16: 4 Issues (2021)
Volume 15: 4 Issues (2020)
Volume 14: 4 Issues (2019)
Volume 13: 4 Issues (2018)
Volume 12: 4 Issues (2017)
Volume 11: 4 Issues (2016)
Volume 10: 4 Issues (2015)
Volume 9: 4 Issues (2014)
Volume 8: 4 Issues (2013)
Volume 7: 4 Issues (2012)
Volume 6: 4 Issues (2011)
Volume 5: 4 Issues (2010)
Volume 4: 4 Issues (2009)
Volume 3: 4 Issues (2008)
Volume 2: 4 Issues (2007)
Volume 1: 4 Issues (2006)
View Complete Journal Contents Listing