article · Menoufia Journal of Electronic Engineering Research
Diabetic retinopathy is an eye disease associated with diabetes mellitus, and its early identification plays a critical role in condition management. Retinal fundus images are employed to examine symptoms and detect abnormalities or structural changes in the retina. To categorise these images, a convolutional neural network model was designed to distinguish between normal eyes, background retinopathy, and pre-proliferative retinopathy. The deep learning architecture is constructed with five convolutional layers, each followed by a max pooling layer, and concludes with a global average pooling layer. When tested on retinal fundus imagery, this computational model reached a classification accuracy of 95.23 per cent across the targeted diagnostic categories.
Diabetic retinopathy requires prompt detection to ensure effective disease management for people living with diabetes mellitus. Automated classification of retinal fundus images provides an objective method to identify retinal changes and differentiate disease stages, which can assist in detecting abnormalities earlier than manual observation alone might allow.
The system demonstrates potential for automated diagnostic software tools designed for clinicians examining retinal fundus images. By categorising stages from normal to pre-proliferative retinopathy with 95.23 per cent accuracy, the model could support clinical screening workflows. However, the work remains at an early computational research stage, and the abstract does not report clinical validation, deployment trials, or integration into medical device software.
AI-generated from the published abstract. Always read the original work before citing.
- Diabetes mellitus have an eye disease called diabetic retinopathy. The early discovery of the disease is a great achievement in management of diabetic retinopathy. We use Fundus images are used for identification of the nature of an illness or other problem through examination of the symptoms to check for any abnormalities or any change in the retina. In this paper, Convolutional Neural Networks (CNN) is performed to classify the retinal fundus images to normal, background and pre-proliferative retinopathy. The proposed model consists of 5 convolutional layers followed by 5 max pooling layers. Finally, a global average pooling is used. In this work we achieve accuracy reached 95.23%.
This page summarises published work. The authoritative version sits with the publisher.
DOI: 10.21608/mjeer.2019.76962
Is something wrong with this record? Report it or request removal.
Discussion
Have you built on this work, tried to replicate it, or seen it applied in practice? Share what you know. Verified researchers and MARATTO™ domain experts can open a discussion, and any member can reply. Contributions are reviewed before they appear.
No discussion yet. Open the first thread.
New to MARATTO™? Create a free account.
