Classification of Diabetic Retinopathy Disease Levels by Extracting Topological Features Using Graph Neural Networks
Summary
No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.
Summarise with VIRAT Free to try with your Science Catalogs account.Abstract
Diabetic Retinopathy (DR) is a severe complication of diabetes that can lead to irreversible blindness if not detected and treated early. This study inspects the role of deep learning in enabling scalable, automated detection of diabetic retinopathy. ResNet101 & DenseNet121 for the automated detection of DR using retinal fundus images, leveraging transfer learning to optimize performance despite the limited availability of medical data. ResNet101, a residual network, addresses the vanishing gradient problem and improves feature extraction through residual connections. DenseNet121, which connects each layer to every other layer in a feed-forward manger, enhances information flow and captures intricate retinal patterns associated with DR. The deep learning models face risks such as overfitting or underfitting, which can indicate that both models significantly reduce the time required for DR screening, enabling large-scale screening initiatives with minimal human intervention.
Fields of Study & Subjects
Retinal Imaging and Analysis
Retinal Diseases and Treatments
Ophthalmology and Visual Health Research
Publication details
- Journal / source
- Zenodo (CERN European Organization for Nuclear Research)
- Publication date
- 28 March 2026
- Language
- EN