Decoding Diabetic Retinopathy: a Visionary Diagnosis Approach

EasyChair Preprint 11355

Abstract

This Diabetic retinopathy is a leading cause of blindness in people with diabetes. Early detection and treatment of retinopathy can help to prevent blindness. However, manual detection of retinopathy is time- consuming and requires specialized skills. Deep learning is a type of machine learning that can be used to develop automated systems for detecting retinopathy. CNN is a deep learning model that has been shown to be effective for detecting retinopathy in adults and children as it involves the processing of pixel data. This study proposes to develop a deep learning model to detect retinopathy in both children and adults by observing retina images and pre-medical history using Convolutional Neural Network (CNN). The model will be trained on a dataset of retina images and pre-medical history data from children and adults with and without retinopathy. The model will then be evaluated on a separate dataset of retina images and pre-medical history data to measure its accuracy.

Our main task will be to classify the images based on the levels of severity (i.e.)

0 – No DR, 1 – Mild, 2 – Moderate, 3 – Severe, 4 – Proliferative DR

Keyphrases: CNN, Diabetic Retinopathy, Levels of severity

@booklet{EasyChair:11355,
  author    = {S P Jagrit and Ankit Murarka and A Saranya},
  title     = {Decoding Diabetic Retinopathy: a Visionary Diagnosis Approach},
  howpublished = {EasyChair Preprint 11355},
  year      = {EasyChair, 2023}}