Diabetic retinopathy detection and comparison of several CNN models

Shekhar, Sanjeet (2024) Diabetic retinopathy detection and comparison of several CNN models. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (698kB) | Preview
Preview	PDF (Configuration Manual) Download (728kB) | Preview

Abstract

Diabetic retinopathy is a type of medical condition that stems from diabetes and leads to partial or full loss of sight and is a leading contributor to blindness in most of the developed countries in the world. Early detection of the condition is not only effective by is crucial for the treatment of people suffering from diabetic retinopathy. In this study, a convolutional neural network (CNN) – based framework for classification of several stages of diabetic retinopathy has been proposed. The study uses images from actual cases of several stages of the retinal disease and compares several models in order to find out the best-performing model in predicting the stage of the disease. The study compares the ResNet model with EfficientNet and MobileNet to get a better understanding of the model suitable for the task study also compares how different optimizers compare with each other and concludes EfficientNet model with an accuracy of 82% trained using Adam optimizer to be the best choice for the use case.

Item Type:	Thesis (Masters)
Supervisors:	Name Email Subhnil, Shubham 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 R Medicine > Healthcare Industry Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Machine learning
Divisions:	School of Computing > Master of Science in Data Analytics
Depositing User:	Ciara O'Brien
Date Deposited:	05 Sep 2025 10:14
Last Modified:	05 Sep 2025 10:14
URI:	https://norma.ncirl.ie/id/eprint/8810

Actions (login required)

View Item