Automated Diabetic Retinopathy screening with Montage Fundus Images

Sarala Kumari, Nimasha Padmakumara, Chankuka Balagalla, Waruni Palangoda, Pradeepa Samarasingha

Background: Diabetic retinopathy (DR), also known as diabetic eye disease is one of the major causes of blindness in the active population. The longer a person has diabetes, higher the chances of developing DR. DR have been found to be the global foremost cause of blindness.

Aims: This research paper is an attempt towards finding an automatic way to staging DR using montage eye images through artificial intelligence (AI).

Methods: Convolutional neural networks (CNNs) play a big role in DR detection. Using transfer learning and hyper-parameter tuning DR staging is analyzed through different models. VGG16 gave the highest classification accuracies for the stages Proliferative DR (PDR) & Non-proliferative DR (NPDR).

Results: The highest level of NPDR is severe DR which achieved 94.9% classification accuracy (CA) & at special features like cotton wool & laser treatment performed 83.3% CA for each. Moreover, by using patient’s history data such as age, right eye & left eye value accuracies & diabetic diagnosed year, system can predict the DR stages. That predictive model has achieved the best CA as 94% by using Xgboost classifier.

Conclusions: Overall, successfully built a fully functional app to detect DR stages using AI.