NORMA eResearch @NCI Library

Optimized Deep Learning Model For Diabetic Retinopathy Screening

-, Kaushik Kalyanaraman (2022) Optimized Deep Learning Model For Diabetic Retinopathy Screening. Masters thesis, Dublin, National College of Ireland.

[thumbnail of Master of Science]
PDF (Master of Science)
Download (1MB) | Preview
[thumbnail of Configuration manual]
PDF (Configuration manual)
Download (2MB) | Preview


Diabetic retinopathy(DR) is a disorder caused by uncontrolled diabetes over an extended period of time. It is the most serious eye problem triggered by diabetes, affecting more than one-third of all diabetics. Even with the attempts of governments to expand screening, a dearth of skilled individuals for screening has made early detection even more challenging. This results in delayed treatment of this progressive disease which might lead to loss of vision, hence necessitating the use of an automated screening technique. This research seeks to implement an approach for screening using a custom optimized Convolutional Neural Network (CNN) for a binary classification of DR and No DR using retinal fundus images. This suggested implementation aims to provide an efficient model that may be used as an automated tool to screen diabetic retinopathy, allowing for early diagnosis and treatment of afflicted individuals. Sensitivity, specificity, F1 score and accuracy have been used as the evaluation metrics to measure the performance of the model. By using the same images, an analysis is done between the implemented Logistic Regression, ResNet 50 and custom optimized CNN is done where the custom optimized CNN exceeds the performance of the other two models on all metrics with a sensitivity of 92.9%, specificity of 93.4% and a test accuracy of 93.2%.

Item Type: Thesis (Masters)
Anant, Aaloka
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 May 2023 14:55
Last Modified: 19 May 2023 14:55

Actions (login required)

View Item View Item