SEGMENTASI TUMOR OTAK PADA CITRA HASIL MAGNETIC RESONANCE IMAGING (MRI) OTAK MENGGUNAKAN PERBAIKAN ARSITEKTUR 3D V-NET

GEOVANI, DITE and Desiani, Anita and Yahdin, Sugandi (2023) SEGMENTASI TUMOR OTAK PADA CITRA HASIL MAGNETIC RESONANCE IMAGING (MRI) OTAK MENGGUNAKAN PERBAIKAN ARSITEKTUR 3D V-NET. Undergraduate thesis, Sriwijaya University.

	Text RAMA_44201_08011181924015.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (1MB) | Request a copy
	Text RAMA_44201_08011181924015_TURNITIN.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (7MB) | Request a copy
	Text RAMA_44201_08011181924015_011127702_0027075803_01_front_ref.pdf - Accepted Version Available under License Creative Commons Public Domain Dedication. Download (854kB)
	Text RAMA_44201_08011181924015_011127702_0027075803_02.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (422kB) | Request a copy
	Text RAMA_44201_08011181924015_011127702_0027075803_03.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (51kB) | Request a copy
	Text RAMA_44201_08011181924015_011127702_0027075803_04.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (413kB) | Request a copy
	Text RAMA_44201_08011181924015_011127702_0027075803_05.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (42kB) | Request a copy
	Text RAMA_44201_08011181924015_011127702_0027075803_06_ref.pdf - Bibliography Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (198kB) | Request a copy

Abstract

Detection of abnormalities in brain MRI images as an effort to detect brain tumors early can be implemented with image segmentation using Convolutional Neural Network (CNN). An architecture frequently used in 3D image segmentation is the 3D U-Net architecture. In this study, a modification was made to the 3D U-Net architecture by removing the bridge part to produce a new architecture is 3D V-Net for brain tumor segmentation in magnetic resonance imaging (MRI)images of the brain. Results of this study using Brain Tumor Segmentation dataset is score of accuracy, Intersection over Union (IoU), F1-Score, sensitivity, and specificity 97.95%, 73,84%, 80,30%, 89,42 %, and 98,16% respectively. Based on the results, it can be shown that 3D V-Net architecture is capable of segmenting brain tumors on brain MRI images, but still has a fairly low IoU value.

Item Type:	Thesis (Undergraduate)
Uncontrolled Keywords:	Segmentasi, Tumor Otak, Citra MRI, 3D V-Net
Subjects:	Q Science > Q Science (General) > Q334-342 Computer science. Artificial intelligence. Algorithms. Robotics. Automation.
Divisions:	08-Faculty of Mathematics and Natural Science > 44201-Mathematics (S1)
Depositing User:	Dite Geovani -
Date Deposited:	27 Feb 2023 04:20
Last Modified:	27 Feb 2023 04:20
URI:	http://repository.unsri.ac.id/id/eprint/90036

Actions (login required)

View Item