International Research Journal of Engineering and Technology (IRJET)
e-ISSN: 2395-0056
Volume: 10 Issue: 04 | Apr 2023
p-ISSN: 2395-0072
www.irjet.net
AUTOMATIC DETECTION OF SEVERITY GRADING IN DIABETIC RETINOPATHY USING CONVOLUTIONAL NEURAL NETWORK Sharan. M 1, Rithik. S2, Lakshmi Priya. S 3 1Department of computer science and Engineering, Sathyabama Institute of Science and Technology, Tamil Nadu,
Chennai
2Department of computer science and Engineering, Sathyabama Institute of Science and Technology, Tamil Nadu,
Chennai
3Assistant Professor, Department of computer science and Engineering, Sathyabama Institute of Science and
Technology, Tamil Nadu, Chennai ---------------------------------------------------------------------***--------------------------------------------------------------------identify the disease[3]. Diabetic One of the main reasons of retinal degeneration (DR) is sightlessness and there subsist valuable behaviours that hold back the development of the disease provided that it would be identified in the early stage[4]. Normal retinal assessment of the diabetic patients guarantees an early identification of DR, which considerably reduces the occurrence of blindness[5]. Due to the high prevalence of diabetes, mass screening takes a lot of time and requires a large number of qualified graders to carefully examine the fundus images looking for retinal abnormalities. Diabetes and other disorders linked to aging and society are on the rise right now[6]. The issues relating to the eyes can be divided into two main categories. The first is eye disease, such as cataract, conjunctivitis, blepharitis, and glaucoma. The second group is categorised as lifestyle-related diseases, including diabetes, hypertension, and atherosclerosis. Diabetes can harm the eyes by damaging the retinal blood vessels, which can ultimately lead to visual loss. When diabetes is treated using prosthetic retinas, Diabetic retinopathy (DR) is the name used to describe this condition [7]. One of the treatments to reduce the amount of visual mutilation processed by DR has been identified as early detection and diagnosis, with a focus on routine medical examinations for the identification and supervision of this condition. During this method, retina images, also known as fundus images (FIs), are carefully processed using a medical imaging camera and are physically checked for the presence of DR objects by screeners and ophthalmologists. Diabetic Retinopathy is an eye condition that diabetes patients experience to a great extent. If a diabetic patient's blood sugar levels are too high, the blood vessels at the back of their eye will be destroyed, which prevents the retina from getting enough nutrients to adequately retain their vision [8]. One of the main reasons for visual loss worldwide is diabetic retinopathy, also known as DR [9]. It is one of the main causes of preventable blindness and vision impairment [10].The prevalence of DR among diabetic patients globally was found to be 7.62%–47.1% based on a metaanalysis of 35 studies from 35 different countries. The second category of DR severity is non-proliferative
Abstract – The primary reason for middle-aged people's
eyesight is age is diabetic retinopathy (DR). Early identification of the development of diabetic retinopathy can be very beneficial for clinical treatment. Although several different feature extraction various strategies have been put forth, and the classification job for retinal images is still tedious and time-consuming even for those trained clinicians. Hence, primary screening of DR is to avoid vision loss, it is advised that diabetic patients have this procedure performed at least once a year. Recently, deep convolutional neural networks have manifested superior performance in image classification compared to previous handcrafted feature-based image classification methods. As a result, a Random forest classifier has been developed that can distinguish the intricate elements required for classification, such as micro-aneurysms, exudate, and hemorrhages on the retina, and then automatically deliver a diagnosis without human input. Last but not least, a CNN-based automated DR screening approach for retinal pictures is suggested. This method displays the different phases of DR (Mild, Moderate, and Severe) as well as its attention map for the region that is most affected. It also reduces the workload of ophthalmologists. Thus the proposed system of CNN classifier gives a significant improvement in terms of speed and accuracy when compared to previous methods. Key Words: Diabetic retinopathy (DR) Fundus Images (FIs),micro aneurysm (MA), Flame-shaped haemorrhages (FSHs), Convolutional Neural Network(CNN)
1. INTRODUCTION Image processing is a form of processing images those are either captured as pictures or frames for which the input is given as an image and the output of the image processing is also a picture associated with the image[1]. Image processing refers to digital image processing but the visual and analog processing is feasible as well[2]. Medical Image Processing is in which the images generated from the human body for medical purposes are subjected to processing. It helps easily to detect and
© 2023, IRJET
|
Impact Factor value: 8.226
|
ISO 9001:2008 Certified Journal
|
Page 1321