DIABETIC RETINOPATHY DETECTION USING DEEP LEARNING

DIABETIC RETINOPATHY DETECTION USING DEEP LEARNING

Prof. Sunil M Kale¹ Shubham Shivaji Lahane² Rohan Prakash Chavan³ Siddhant Popat Palde⁴ Suyash Sanjay Salmuthe⁵

Assistant Professor¹ BE Students ^2,3,4,5

^1,2,3,4,5 Department of Computer Engineering,

Sandip Institute Of Technology And Research Centre, College Of Engineering, Nashik - 422213

Abstract - Diabetic retinopathy is a disease caused by uncontrolled chronic diabetes that can result in total blindness if not diagnosed early. To avoid the severe side effects of diabetic retinopathy, the leading cause of blindness among working-age adults, early medical diagnosis and treatment are essential. We hope to detect and prevent this disease in rural areas where medical screening is difficult to conduct. Currently, technicians travel to these rural areas to capture images, which are then reviewed and diagnosed by highly trained doctors. By using technology, they hope to scale their efforts and eventually be able to automatically detect disease in images and indicate how severe it might be. Building a Convolutional neural network model that can automatically assess the degree of blindness in a patient by looking at an image of their eye will help us achieve this. Automation has the potential to drastically cut treatment times for diabetic retinopathy on a large scale.

Keywords: Diabetic Retinopathy, Artificial intelligence, Deep learning, Machine-learning, Dataset, CNN