MODIFIKASI ARSITEKTUR 3D DOUBLE U-NET DALAM SEGMENTASI TUMOR OTAK PADA CITRA HASIL MAGNETIC RESONANCE IMAGING OTAK

BATUBARA, GRACIA MIANDA CAROLINE and Desiani, Anita and Andriani, Yuli (2024) MODIFIKASI ARSITEKTUR 3D DOUBLE U-NET DALAM SEGMENTASI TUMOR OTAK PADA CITRA HASIL MAGNETIC RESONANCE IMAGING OTAK. Undergraduate thesis, Sriwijaya University.

	Text RAMA_44201_08011282025049.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (2MB) | Request a copy
	Text RAMA_44201_08011282025049_TURNITIN.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (5MB) | Request a copy
	Text RAMA_44201_08011282025049_0011127702_0002077202_01_front_ref.pdf - Accepted Version Available under License Creative Commons Public Domain Dedication. Download (1MB)
	Text RAMA_44201_08011282025049_0011127702_0002077202_02.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (534kB) | Request a copy
	Text RAMA_44201_08011282025049_0011127702_0002077202_03.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (181kB) | Request a copy
	Text RAMA_44201_08011282025049_0011127702_0002077202_04.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (587kB) | Request a copy
	Text RAMA_44201_08011282025049_0011127702_0002077202_05.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (165kB) | Request a copy
	Text RAMA_44201_08011282025049_0011127702_0002077202_06_ref.pdf - Bibliography Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (188kB) | Request a copy

Abstract

Based on the International Agency for Research on Cancer, brain tumors in Indonesia ranked 15th as the disease with the most cases in the world. To reduce the high mortality rate due to brain tumors, a segmentation of MRI (Magnetic Resonance Imaging) images of the brain can be done by utilizing machine learning with the Convolutional Neural Network (CNN) method. This research develops a modification of the 3D Double U-Net architecture in segmenting brain tumors in MRI images. The modification is done by adding spatial dropout on each layer and eliminating the bridge on the first U-Net block. The results obtained are accuracy, sensitivity, specificity, Intersection over Union (IoU), and F1-score with values of 99.66%, 95.29%, 98.70%, 89.68%, 94.38%, respectively. The accuracy, sensitivity, specificity, IoU, and F1-score values of the modified 3D Double U-Net architecture are better than some previous studies. Based on these results, the modified 3D Double U-Net architecture has been able to perform brain tumor segmentation very well.

Item Type:	Thesis (Undergraduate)
Uncontrolled Keywords:	Segmentasi, Tumor Otak, Citra MRI, Modifikasi 3D Double U-Net
Subjects:	Q Science > QA Mathematics > QA299.6-433 Analysis > Q334.A755 Artificial intelligence. Computational linguistics. Computer science. Q Science > QA Mathematics > QA75-76.95 Calculating machines > QA76.9.B45 Big data. Machine learning. Quantitative research. Metaheuristics. Q Science > QA Mathematics > QA8.9-QA10.3 Computer science. Artificial intelligence. Computational complexity. Data structures (Computer scienc. Mathematical Logic and Formal Languages
Divisions:	08-Faculty of Mathematics and Natural Science > 44201-Mathematics (S1)
Depositing User:	Gracia Mianda Caroline Batubara
Date Deposited:	05 Apr 2024 06:24
Last Modified:	05 Apr 2024 06:24
URI:	http://repository.unsri.ac.id/id/eprint/143132

Actions (login required)

View Item