Tools
Tools
Tarade, Namrata Shrishail (2024) A Novel Deep Learning Framework for Diabetic Retinopathy Detection Integrating Ben Graham and CLAHE Preprocessing. Masters thesis, Dublin, National College of Ireland.
Preview |
PDF (Master of Science)
Download (1MB) | Preview |
Preview |
PDF (Configuration Manual)
Download (811kB) | Preview |
Abstract
Diabetic retinopathy (DR) is a severe complication of diabetes that can lead to blindness if not detected and managed appropriately. The disease progresses through various stages from the initial mild non-proliferative abnormalities to advanced proliferative retinopathy, where new blood vessels develop on the retina. Early detection and treatment of DR are critical to preventing vision loss and improving patient outcomes. Traditional approaches to DR detection have relied on manual examination by ophthalmologists, which has been criticized for being time- consuming and vulnerable to human error. Automated detection has been attempted using machine learning approaches, such as Support Vector Machines (SVMs) and Random Forests, but these approaches often find difficulty with large and complex datasets. This study brings forth a new deep learning-based approach to DR detection, which utilizes three advanced models, Custom CNN (Convolutional Neural Network), EfficientNetB7, and NasNet. The research applied sophisticated image preprocessing techniques such as Ben Graham and CLAHE (Contrast Limited Adaptive Histogram Equalization) to improve image quality. While all models produced the same accuracy, NasNet produced higher precision, recall, and F1-score measures, an advance in the quality of detection. The novelty in this research is in the evaluation and comparison of the models’ performance using various metrics and advanced image preprocessing, offering a more reliable and accurate detection framework for diabetic retinopathy.
| Item Type: | Thesis (Masters) |
|---|---|
| Supervisors: | Name Email Tomer, Vikas UNSPECIFIED |
| 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 Q Science > Life sciences > Medical sciences |
| Divisions: | School of Computing > Master of Science in Data Analytics |
| Depositing User: | Ciara O'Brien |
| Date Deposited: | 26 Aug 2025 11:45 |
| Last Modified: | 26 Aug 2025 11:45 |
| URI: | https://norma.ncirl.ie/id/eprint/8643 |
Actions (login required)
 |
View Item |