Abstract: Diabetes is a disorder that causes an increase in blood glucose levels due to a lack of insulin and affects 425 million persons globally. Diabetes is the most common cause of retinopathy. The retina is the photosensitive tissue that lines the inside of the eye. Hyperglycemia (high blood sugar) can cause retinal vascular damage. Diabetic Retinopathy (DR) is a diabetic eye condition that causes the blood vessels of the retina to enlarge and leak fluids and blood. If left uncontrolled, it might cause partial or total blindness. The sustained eyesight can be treated, but it cannot be restored to its former state. The disease's prognosis worsens with age. This paper presents a detailed review of various retinopathy detection methods. A comparative study is conducted with their merits and demerits for identifying the challenges in those techniques and then this paper is concluded with suggestions of solutions for enhancing the efficiency of deep learning models.
Keywords: Diabetic Retinopathy, Principal Component Analysis, Convolutional Neural Network, Deep Learning.
|
DOI:
10.17148/IJARCCE.2023.12675
