SEGMENTASI INFEKSI PARU-PARU PENDERITA COVID-19 MENGGUNAKAN SEGNET

ROMADHON, ARIZLI and Fachrurrozi, Muhammad and Rizqie, M. Qurhanul (2021) SEGMENTASI INFEKSI PARU-PARU PENDERITA COVID-19 MENGGUNAKAN SEGNET. Undergraduate thesis, Sriwijaya University.

	Text RAMA_55201_09021281722047.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (3MB) | Request a copy
	Text RAMA_55201_09021281722047_TURNITIN.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (6MB) | Request a copy
Preview	Text RAMA_55201_09021281722047_0222058001_0203128701_01_front_ref.pdf - Accepted Version Available under License Creative Commons Public Domain Dedication. Download (2MB) | Preview
	Text RAMA_55201_09021281722047_0222058001_0203128701_02.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (1MB) | Request a copy
	Text RAMA_55201_09021281722047_0222058001_0203128701_03.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (1MB) | Request a copy
	Text RAMA_55201_09021281722047_0222058001_0203128701_04.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (1MB) | Request a copy
	Text RAMA_55201_09021281722047_0222058001_0203128701_05.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (1MB) | Request a copy
	Text RAMA_55201_09021281722047_0222058001_0203128701_06.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (1MB) | Request a copy
	Text RAMA_55201_09021281722047_0222058001_0203128701_07_ref.pdf - Bibliography Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (1MB) | Request a copy

Abstract

Radiologists analyze CT Scan images for Covid-19 diagnosis. The analysis is currently done manually and took relatively long. Medical image processing can be used to conduct analysis quickly and automatically. This research is looking for solutions to segment Covid-19 lung infections area from CT Scan images. The SegNet models is chosen because of the model efficiency, in both of memory usage and computation time. In this study the CT Scan images of the lungs of Covid-19 patients is converted into PNG format. The image will be segmented into right lung, left lung, and infection. Comparison with manual segmentation CT Scan image was performed to measure the Intersection over Union (IoU), Mean Intersection over Union (MioU), and computational time based on local computer and Google Colab specifications. This study resulted in a MioU value of 76.57%, with the right lung class IoU value of 88.77%, the left lung class of 89.73%, and the infection class of 51.22%. The average computation time obtained is 2.21 seconds based on the specifications of local computer and 0.43 seconds based on the Google Colab specifications.

Item Type:	Thesis (Undergraduate)
Uncontrolled Keywords:	citra medis, covid-19, deep learning, segmentasi, SegNet
Subjects:	Q Science > Q Science (General) > Q300-390 Cybernetics > Q325.5 Machine learning
Divisions:	09-Faculty of Computer Science > 55201-Informatics (S1)
Depositing User:	S.Kom Arizli Romadhon
Date Deposited:	21 Jan 2022 04:36
Last Modified:	21 Jan 2022 04:36
URI:	http://repository.unsri.ac.id/id/eprint/61959

Actions (login required)

View Item