Tools
Tools
Chandak, Shivani (2022) Classification of Severity Levels in Diabetic Retinopathy in Ultra-wide Field Colour Fundus Images using Hybrid Deep Learning Models. Masters thesis, Dublin, National College of Ireland.
Preview |
PDF (Master of Science)
Download (15MB) | Preview |
Preview |
PDF (Configuration manual)
Download (2MB) | Preview |
Abstract
Diabetic Retinopathy (DR) is one of the leading causes for permanent vision loss. Blindness can impact the economic growth of a country as well as the quality of life of an individual. Early diagnosis and treatment can prevent individuals from permanent loss of eye-sight. DR is detected through a fundus imaging technique during eye examination. While the traditional fundus images of the retina provide only up to 60◦ view of the retina, ultra-wide field color fundus (UWF-CF)images provides up to 200◦ view of the surface of retina which makes it more promising and reliable. This research aims to compare and contrast the ability of deep learning models: VGG-19, VGG19-RF and VGG19 SVM to classify the severity levels in Diabetic Retinopathy using UWF-CF images. The performance of the models have been evaluated using accuracy, sensitivity, specificity and Cohen’s kappa. All the models were trained on same dataset under default settings to perform comparative analysis. The results depicted that VGG-19 outperformed the hybrid models by achieving an accuracy, sensitivity, specificity and Cohen’s kappa score of 80% , 95%, 80% and 0.75 respectively.
| Item Type: | Thesis (Masters) |
|---|---|
| Uncontrolled Keywords: | Diabetic Retinopathy; Ultra-wide field fundus; VGG-19; VGG19- SVM; VGG19-RF |
| Subjects: | Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science 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: | 19 Jan 2023 15:56 |
| Last Modified: | 06 Mar 2023 15:41 |
| URI: | https://norma.ncirl.ie/id/eprint/6097 |
Actions (login required)
 |
View Item |