A Deep Learning Based Approach for Classification of Diabetic Retinopathy

EasyChair Preprint 11196

Abstract

Diabetes Mellitus (DM) is a metabolic disorder happens because of high blood sugar
level in the body. Over the time, diabetes creates eye deficiency also called as Diabetic
Retinopathy (DR) causes major loss of vision. In recent times computer vision with Deep
Neural Networks can train a model perfectly and level of accuracy also will be higher than other
neural network models. In this study fundus images containing diabetic retinopathy has been
taken into consideration. This paper proposes an automated knowledge model to identify the
key antecedents of DR. We have tested our network on the largest publicly available Kaggle
diabetic retinopathy dataset, and achieved 0.851 quadratic weighted kappa score and 0.844
AUC score, which achieves the state-of-the-art performance on severity grading. In the earlystage
detection, we have achieved a sensitivity of 98% and specificity of above 94%, which
demonstrates the effectiveness of our proposed method. Our proposed architecture is at the
same time very simple and efficient with respect to computational time and space are
concerned. The Deep Learning models are capable of quantifying the features as blood vessels,
fluid drip, exudates, hemorrhages and micro aneurysms into different classes. The foremost
challenge of this study is the accurate verdict of each feature class thresholds. The model will
be helpful to identify the proper class of severity of diabetic retinopathy images.

Keyphrases: Computer Aided Diagnosis, Convolutional Neural Network, Deep Neural Network, Diabetic Retinopathy

@booklet{EasyChair:11196,
  author    = {Astamai Murmu and Prayag Sing and Vineeth Piyush},
  title     = {A Deep Learning Based Approach for Classification of Diabetic Retinopathy},
  howpublished = {EasyChair Preprint 11196},
  year      = {EasyChair, 2023}}