NORMA eResearch @NCI Library

Detecting Diabetic Retinopathy from Retinal fundus images using DC-CNN

Chandel, Ananya Pratap Singh (2021) Detecting Diabetic Retinopathy from Retinal fundus images using DC-CNN. 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 (960kB) | Preview


Today one of the major causes of blindness in adults is diabetic retinopathy (DR). It is a progressive disease and can be categorized into four stages according to its severity. Early detection of DR can save individuals from developing permanent blindness. Hence, the governments run several screening programs to prevent DR. DR detection remains a problem due to the limited number of trained clinicians who can perform the diagnosis. Hence need to develop an automated DR detection system is evident. This research aims at developing a novel dual-channel convolutional network (DC-CNN) for the detection of DR using retinal fundus images. DC-CNN performs a binary classification under two labels DR and No DR. The designed DC-CNN utilizes two channels for deeper feature extraction, designed using the VGG16 transfer learning model and customized tuned CNN model. The performance of the designed DC-CNN has been evaluated using evaluation metrics like accuracy, sensitivity, specificity, and F1 score. ResNet50 and Inception v3 are trained on the same retinal fundus image dataset to perform a comparative analysis of the DC-CNN model. The Designed DC-CNN model outperforms all the models to produce an accuracy of 95.23% and sensitivity of 96.94%.

Item Type: Thesis (Masters)
Subjects: Q Science > QA Mathematics > Electronic computers. Computer science
T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science
Q Science > QA Mathematics > Computer software
T Technology > T Technology (General) > Information Technology > Computer software
R Medicine > R Medicine (General)
H Social Sciences > HM Sociology > Information Science > Communication > Medical Informatics
Divisions: School of Computing > Master of Science in Data Analytics
Depositing User: Clara Chan
Date Deposited: 15 Nov 2021 13:34
Last Modified: 06 Dec 2021 10:33

Actions (login required)

View Item View Item