Image Processing for the Detection of Diabetic Retinopathy and Diabetic Macular Edema

Abstract

Diabetic retinopathy (DR) and diabetic macular edema (DME) are common microvascular retinal diseases in patients with diabetes. The diabetic patients may have a sudden and devastating impact on visual acuity, in the long run leading to blindness. Advanced stages of DR are characterized by the growth of abnormal retinal blood vessels secondary to ischemia. These blood vessels grow in an attempt to supply oxygenated blood to the hypoxic retina. At any time during the progression of DR, patients with diabetes can also develop DME, which involves retinal thickening in the macular area. In the present paper, algorithms are developed to detect DR and DME. For detecting DR the abnormalities in the retina blood vessels are detected by classifying the common abnormalities namely microaneurisms, hard exudates, heammorages and cotton wool spots. DME is detected by finding the nearness of Hard exudate to macula. The macula and hard exudates are localized using image processing techniques. Severity of DME is assessed based on the nearest exudates, their area and color analysis. The algorithm is tested with 65 DR and DME images with severity index 0, 1 and 2 from MESSIDOR database.

Detection of severity level of diabetic retinopathy using Bag of features model

“…Kaggle data set provided retinal images for five severity levels of DR, which are used in a few studies including [23,28]. It is shown in the literature review that many researchers [14][15][16][17][18][19][20][21][22][23][24][25] have devoted their efforts for the detection of the stages of DR. Detection of five stages of DR was proposed in [23] using Kaggle data set and CNN and in [22] through visual features and deep NN using private data collected from a local hospital.…”

“…DR lesions can appear anywhere in the retina and this complication makes the detection of five DR-levels a difficult and tedious task for ophthalmologists and hence motivates researchers to design efficient CAD systems. Literature revealed that many researchers proposed efficient methods [8][9][10][11][12][13] for DR-lesion detection and CAD systems [14][15][16][17][18][19][20][21][22][23][24][25] for identification of severity levels of DR. Some of these studies proposed the automated methods to detect severity of DR on the basis of DR-lesions which is quite similar to the one usually practiced by ophthalmologists.…”

“…However, the accuracy of the proposed system was not demonstrated, as the authors did not show numerical results. In [20], an automated method was proposed to detect four subsets of DR grades. In this study, normal, mild NPDR, moderate and severe NPDR, and PDR were identified by reporting 85% accuracy.…”