Tools
Tools
Chava, Abhilash (2023) Deep Learning-Based Detection of Diabetic Retinopathy in Retinal Images. Masters thesis, Dublin, National College of Ireland.
Preview |
PDF (Master of Science)
Download (2MB) | Preview |
Preview |
PDF (Configuration manual)
Download (2MB) | Preview |
Abstract
Diabetic retinopathy (DR) is an eye ailment that is progressive in nature and is caused by high blood glucose levels. It is the major cause of blindness among diabetics, particularly in less developed nations. The early identification of DR is essential for the preservation of vision; yet the present practise of having ophthalmologists review photographs of the retinal fundus is time-consuming and expensive. This is especially true in the early stages of the illness, when disease symptoms are less apparent in the photographs. The research suggests using deep learning methods, such as supervised, self-supervised, and Vision Transformer configurations, for classifying and detecting DR in photographs of the retinal fundus. Several models were evaluated and compared; based on the Kappa values, DenseNet was found to have the greatest performance, followed by MobileNet and VGG-19. Various models' Kappa scores are shown to be 77.0% for VGG19, 77.6% for ResNet-50, 82.0% for DenseNet, 80.0% for MobileNet, and 73.2% for Vision transformer. Additionally, current retinal fundus datasets are investigated for DR detection, classification, and segmentation, and research gaps and potential topics for additional exploration are identified. The long-term objective is to devise a method that can diagnose DR in a speedy and accurate manner using only a smartphone.
| Item Type: | Thesis (Masters) |
|---|---|
| Supervisors: | Name Email Milosavljevic, Vladimir UNSPECIFIED |
| Uncontrolled Keywords: | Diabetic retinopathy; Transfer learning; Staged Networks; Artificial Neural Networks |
| Subjects: | Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science R Medicine > RB Pathology R Medicine > RE Ophthalmology Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Machine learning |
| Divisions: | School of Computing > Master of Science in Data Analytics |
| Depositing User: | Tamara Malone |
| Date Deposited: | 08 Nov 2024 13:11 |
| Last Modified: | 08 Nov 2024 13:11 |
| URI: | https://norma.ncirl.ie/id/eprint/7175 |
Actions (login required)
 |
View Item |