International Research Journal of Engineering and Technology (IRJET) e-ISSN: 2395-0056 Volume: 09 Issue: 05 | May 2022
www.irjet.net
p-ISSN: 2395-0072
Automated Detection of Diabetic Retinopathy Using Deep Learning Greeshma C Shekar1, Chaitanya J M Reddy2, HV Rakshitha3, Harshitha CS4, Keerthana R5 1,2,3,4,5Department
of Computer Science and Engineering, Dayananda Sagar University, Bangalore, Karnataka, India ---------------------------------------------------------------------***--------------------------------------------------------------------Abstract - Diabetic retinopathy is one of the prevalent causes of blindness among working-age adults. Diabetic retinopathy or DR is an ailment because of diabetes mellitus that can harm the patient image retina and also cause blood spills It is the fastest growing cause of blindness. We have used Deep learning classification techniques, Convolutional Neural Network (CNN), pre-trained VGG-16, ResNet to detect the severity level of Diabetic Retinopathy from the color fundus image. Fundus photography technique is used to take these
photographs. Key Words: Diabetic Retinopathy, Convolutional Neural Network, VGG-16 and ResNet
1. INTRODUCTION Diabetic retinopathy is a medical complication that is caused by the damage to the blood vessels of the light-sensitive tissue which is present at the back of the eye, retina, which can gradually lead to complete blindness and various other eye problems depending on the severity of Diabetic Retinopathy. It is observed that 40% − 45% of diabetic patients are likely to have DR in their life, but due to lack of knowledge and delayed diagnosis, the condition escalates quickly.
1.1 METHOD AND METHODOLOGY
Diabetes was once thought of as a disease of the affluent but it's now reached epidemic proportion in both developed and developing countries. Currently, a minimum of 366 million people worldwide has diabetes, and this number is probably going to extend as a results of an aging global population
We have used the data collected by the Asia-Pacific TeleOphthalmology Society (APTOS) available on the Kaggle platform.
1.2 DATA SET
The data set consists of 3,662 color fundus images. We have used the dataset of such images for the training and testing of our model. Each image in the dataset has been assigned an integral value on the scale of 0 to 4 according to the severity of the disease by a professionally trained clinician as shown in Table-1.
Globally, the quantity of individuals with DR will grow from 126.6 million in 2010 to 191.0 million by 2030, and that we estimate that the quantity with vision-threatening diabetic retinopathy (VTDR) will increase from 37.3 million to 56.3 million, if prompt action isn't taken.
Table -1
© 2022, IRJET
|
Impact Factor value: 7.529
|
ISO 9001:2008 Certified Journal
|
Page 305