SEGMENTASI SEL TUMOR OTAK MENGGUNAKAN MODIFIKASI ARSITEKTUR 3D U-NET INCEPTION PADA CITRA MAGNETIC RESONANCE IMAGING OTAK

MUZAKIR, ADI and Amran, Ali and Desiani, Anita (2024) SEGMENTASI SEL TUMOR OTAK MENGGUNAKAN MODIFIKASI ARSITEKTUR 3D U-NET INCEPTION PADA CITRA MAGNETIC RESONANCE IMAGING OTAK. Undergraduate thesis, Sriwijaya University.

	Text RAMA_44201_08011182025005.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (1MB) | Request a copy
	Text RAMA_44201_08011182025005_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_08011182025005_0013126603_0011127702_01_front_ref.pdf - Accepted Version Available under License Creative Commons Public Domain Dedication. Download (984kB)
	Text RAMA_44201_08011182025005_0013126603_0011127702_02.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (453kB) | Request a copy
	Text RAMA_44201_08011182025005_0013126603_0011127702_03.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (180kB) | Request a copy
	Text RAMA_44201_08011182025005_0013126603_0011127702_04.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (699kB) | Request a copy
	Text RAMA_44201_08011182025005_0013126603_0011127702_05.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (68kB) | Request a copy
	Text RAMA_44201_08011182025005_0013126603_0011127702_06_ref.pdf - Bibliography Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (214kB) | Request a copy

Abstract

Brain tumor cells can be identified by applying image segmentation techniques using Convolutional Neural Network (CNN). The CNN architecture that is often used in 3-dimensional image segmentation is 3D U-Net. In this study, the implementation of 3D U-Net Inception architecture was carried out which is a modification of 3D U-Net and Inception architecture for brain tumor cell segmentation on brain Magnetic Resonance Imaging (MRI) images. The stages of research carried out are data collection, data preprocessing, training, testing, evaluation, analysis and interpretation of results, and conclusion making. The results of the study using the Brain Tumor Segmentation dataset were the values of accuracy, sensitivity, specificity, Intersection over Union (IoU), and f1-score respectively of 99.04%, 83.68%, 93.73%, 70.86%, and 81.94%. Based on the results obtained, it can be said that the 3D U-Net Inception architecture is able to segment brain tumor cells on brain MRI images, but still has a fairly low IoU value.

Item Type:	Thesis (Undergraduate)
Uncontrolled Keywords:	Deep Learning, Convolutional Neural Network, Segmentasi Citra, 3D U-Net, Inception
Subjects:	Q Science > Q Science (General) > Q334-342 Computer science. Artificial intelligence. Algorithms. Robotics. Automation. Q Science > QA Mathematics > QA299.6-433 Analysis > Q334.A755 Artificial intelligence. Computational linguistics. Computer science. Q Science > QA Mathematics > QA1-939 Mathematics > QA1.T553 Mathematics--Periodicals. Computer science--Periodicals. Computer science. 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:	Adi Adi Muzakir
Date Deposited:	27 Mar 2024 06:11
Last Modified:	27 Mar 2024 06:11
URI:	http://repository.unsri.ac.id/id/eprint/142828

Actions (login required)

View Item