ARSITEKTUR VOLUMETRIC U-NET DAN TRANSFORMER UNTUK SEGMENTASI TUMOR OTAK PADA CITRA HASIL MAGNETIC RESONANCE IMAGING

RAMADHAN, FAISHAL FITRA and Amran, Ali and Suprihatin, Bambang (2025) ARSITEKTUR VOLUMETRIC U-NET DAN TRANSFORMER UNTUK SEGMENTASI TUMOR OTAK PADA CITRA HASIL MAGNETIC RESONANCE IMAGING. Undergraduate thesis, Sriwijaya University.

[thumbnail of RAMA_44201_08011282126060_cover.png]
Preview
Image
RAMA_44201_08011282126060_cover.png - Cover Image
Available under License Creative Commons Public Domain Dedication.

Download (1MB) | Preview
[thumbnail of RAMA_44201_08011282126060.pdf] Text
RAMA_44201_08011282126060.pdf - Accepted Version
Restricted to Repository staff only
Available under License Creative Commons Public Domain Dedication.

Download (23MB) | Request a copy
[thumbnail of RAMA_44201_08011282126060_TURNITIN.pdf] Text
RAMA_44201_08011282126060_TURNITIN.pdf - Accepted Version
Restricted to Repository staff only
Available under License Creative Commons Public Domain Dedication.

Download (10MB) | Request a copy
[thumbnail of RAMA_44201_08011282126060_0013126603_0026017102_01_front_ref.pdf] Text
RAMA_44201_08011282126060_0013126603_0026017102_01_front_ref.pdf - Accepted Version
Available under License Creative Commons Public Domain Dedication.

Download (5MB)
[thumbnail of RAMA_44201_08011282126060_0013126603_0026017102_02.pdf] Text
RAMA_44201_08011282126060_0013126603_0026017102_02.pdf - Accepted Version
Restricted to Repository staff only
Available under License Creative Commons Public Domain Dedication.

Download (4MB) | Request a copy
[thumbnail of RAMA_44201_08011282126060_0013126603_0026017102_03.pdf] Text
RAMA_44201_08011282126060_0013126603_0026017102_03.pdf - Accepted Version
Restricted to Repository staff only
Available under License Creative Commons Public Domain Dedication.

Download (1MB) | Request a copy
[thumbnail of RAMA_44201_08011282126060_0013126603_0026017102_04.pdf] Text
RAMA_44201_08011282126060_0013126603_0026017102_04.pdf - Accepted Version
Restricted to Repository staff only
Available under License Creative Commons Public Domain Dedication.

Download (11MB) | Request a copy
[thumbnail of RAMA_44201_08011282126060_0013126603_0026017102_05.pdf] Text
RAMA_44201_08011282126060_0013126603_0026017102_05.pdf - Accepted Version
Restricted to Repository staff only
Available under License Creative Commons Public Domain Dedication.

Download (239kB) | Request a copy
[thumbnail of RAMA_44201_08011282126060_0013126603_0026017102_06_ref.pdf] Text
RAMA_44201_08011282126060_0013126603_0026017102_06_ref.pdf - Bibliography
Restricted to Repository staff only
Available under License Creative Commons Public Domain Dedication.

Download (1MB) | Request a copy

Abstract

Brain tumors are abnormal tissue growths within the brain that can lead to death. The components of a brain tumor can be classified into background, enhancing tumor, peritumoral edema, and non-enhancing tumor, which are identified in three-dimensional Magnetic Resonance Imaging (MRI) scans. The separation of these components can be achieved through automatic segmentation. This study proposes a combination of Vision Transformer (ViT) and Volumetric U-Net architectures for the segmentation of brain tumor components in MRI images. ViT is utilized in the encoder to capture global spatial relationships, while the decoder maintains the Volumetric U-Net structure to preserve local spatial details. The performance of the proposed architecture achieved accuracy, sensitivity, specificity, IoU, and f1-score values of 98.78%, 80.33%, 97.01%, 74.6%, and 83.3%, respectively. These results indicate a good performance in brain tumor segmentation from MRI images. At the label level, the model achieved accuracy, sensitivity, specificity, IoU, and f1-score values ranging from 78% to 98% for background, enhancing tumor, and peritumoral edema. However, the performance for the non-enhancing tumor label was relatively low, with an accuracy of 98.6%, sensitivity of 43.6%, specificity of 99.9%, IoU of 43.2%, and f1-score of 60.2%. This lower performance is attributed to the relatively small feature size and unclear boundaries of the non-enhancing tumor region. Based on these findings, future studies are encouraged to explore new approaches capable of better detecting small regions in 3D brain tumor segmentation.

Item Type: Thesis (Undergraduate)
Uncontrolled Keywords: Segmentasi tumor otak, MRI, Volumentric U-Net, Vision Transformer, Deep Learning
Subjects: 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: Faishal Firra Ramadhan
Date Deposited: 25 May 2025 03:14
Last Modified: 25 May 2025 03:14
URI: http://repository.unsri.ac.id/id/eprint/174025

Actions (login required)

View Item View Item