Dhoot, Amey Tarachand (2024) Enhancing Proliferative Diabetic Retinopathy Detection: Leveraging Customized CNN and Lightweight Machine Learning Models. Masters thesis, Dublin, National College of Ireland.
Preview |
PDF (Master of Science)
Download (3MB) | Preview |
Preview |
PDF (Configuration Manual)
Download (1MB) | Preview |
Abstract
Diabetic patients are often under the danger of getting an incurable eye disease called as Diabetic Retinopathy or DR which may lead to harmful effects on the eyes such as blindness. Therefore, early detection of this disease is mandatory as it may lead to permanent vision loss, if it is not treated on time. But detecting its symptoms early is not an easy task, as it involves proper medical screening along with qualified individuals, as there are limited medical practitioners available, there is a necessity of automated solution for DR detection. To facilitate early diagnosis of this problem, lightweight machine learning algorithms can be used. In this research we will do a comparative study of algorithms like Logistic Regression, Random Forest and Convolutional Neural Network (CNN). Furthermore, to evaluate the test accuracy, metrics like accuracy, sensitivity, confusion matrix, specificity and F1 score will be measured. Apart from these metrics, we will calculate another metric which studies the amount of carbon emitted by the machine when these algorithms are implemented. This will help us to understand and analyse the algorithms which are computationally less demanding but at the same time gives higher accuracy. By doing so, we will be able to provide a sustainable solution. The output shows that Random Forest gives better test accuracy of 96% which is the highest from the remaining two algorithms. This work helps us to identify the different stages of DR thus providing a reliable and quick automated solution for screening tasks.
Item Type: | Thesis (Masters) |
---|---|
Supervisors: | Name Email Byrne, Brian UNSPECIFIED |
Uncontrolled Keywords: | Diabetic Retinopathy (DR); Logistic Regression; Random Forest; Convolutional Neural Networks (CNN); Carbon Emissions |
Subjects: | Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science R Medicine > RE Ophthalmology R Medicine > Healthcare Industry Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Machine learning H Social Sciences > HM Sociology > Information Science > Communication > Medical Informatics |
Divisions: | School of Computing > Master of Science in Artificial Intelligence for Business |
Depositing User: | Ciara O'Brien |
Date Deposited: | 02 Jul 2025 13:34 |
Last Modified: | 02 Jul 2025 13:34 |
URI: | https://norma.ncirl.ie/id/eprint/7983 |
Actions (login required)
![]() |
View Item |