DETEKSI PENYAKIT DIABETIC RETINOPATHY PADA CITRA RETINA MENGGUNAKAN RETINANET DENGAN BACKBONE RESNET-50

PRATAMA, MUHAMMAD ZIYAN and Erwin, Erwin (2023) DETEKSI PENYAKIT DIABETIC RETINOPATHY PADA CITRA RETINA MENGGUNAKAN RETINANET DENGAN BACKBONE RESNET-50. Undergraduate thesis, Sriwijaya University.

	Text RAMA_56201_09011281722045.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (2MB) | Request a copy
	Text RAMA_56201_09011281722045_TURNITIN.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (2MB) | Request a copy
	Text RAMA_56201_09011281722045_0029017101_01_front_ref.pdf - Accepted Version Available under License Creative Commons Public Domain Dedication. Download (1MB)
	Text RAMA_56201_09011281722045_0029017101_02.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (708kB) | Request a copy
	Text RAMA_56201_09011281722045_0029017101_03.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (780kB) | Request a copy
	Text RAMA_56201_09011281722045_0029017101_04.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (1MB) | Request a copy
	Text RAMA_56201_09011281722045_0029017101_05.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (174kB) | Request a copy
	Text RAMA_56201_09011281722045_0029017101_06_ref.pdf - Bibliography Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (399kB) | Request a copy
	Text RAMA_56201_09011281722045_0029017101_07_lamp.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (478kB) | Request a copy

Abstract

This research aims to develop a method for detecting Diabetic Retinopathy (DR) in retinal images using the RETINANET architecture with a ResNet-50 backbone. DR is a serious complication in individuals with diabetes mellitus, leading to damage to the blood vessels in the retina and, in severe cases, blindness. ResNet (Residual Network) is chosen as the neural network architecture to deepen the model and enhance detection accuracy. The approach utilizes the STARE dataset and involves data annotation processes using labeling applications and Roboflow to identify disease characteristics in retinal images. The proposed method achieves satisfactory results, with an precision value of 84.7% for Diabetic Retinopathy, an average precision of 74.4%, and an intersection over union value of 84.7%. Regular monitoring and early detection of DR are crucial in preventing permanent eye damage, and this approach significantly contributes to these efforts through the application of image processing technology and artificial neural networks.

Item Type:	Thesis (Undergraduate)
Uncontrolled Keywords:	Diabetic Retinopathy (DR), RETINANET, Resnet-50, retinal image and detection
Subjects:	Q Science > Q Science (General) > Q334-342 Computer science. Artificial intelligence. Algorithms. Robotics. Automation.
Divisions:	09-Faculty of Computer Science > 56201-Computer Systems (S1)
Depositing User:	Muhammad Ziyan Pratama
Date Deposited:	18 Jan 2024 05:08
Last Modified:	18 Jan 2024 05:08
URI:	http://repository.unsri.ac.id/id/eprint/138497

Actions (login required)

View Item