Image of PENERAPAN MULTIPLANAR RECONSTRUCTION PADA ARSITEKTUR U-RESNET DAN MOBILENET DALAM PROSES SEGMENTASI HATI CITRA TIGA DIMENSI HASIL CT SCAN
Bookmark Share

Skripsi

PENERAPAN MULTIPLANAR RECONSTRUCTION PADA ARSITEKTUR U-RESNET DAN MOBILENET DALAM PROSES SEGMENTASI HATI CITRA TIGA DIMENSI HASIL CT SCAN

U-Net is commonly used for medical image segmentation, such as liver organ segmentation. One tool that can visualize the morphology, shape, and position of the liver is a 3D Abdominal Computed Tomography (CT) Scan. However, U-Net requires a large amount of data for training, and 3D liver datasets are still very limited. Additionally, 3D images have complex structures. A solution to address data limitations and the complexity of 3D structures is to convert 3D images into 2D using Multi-Planar Reconstruction (MPR) techniques. The most parameterheavy parts of U-Net are the encoder and decoder. The large number of parameters can lead to overfitting. One way to reduce parameters is by using ResNet. The ResNet architecture has residual blocks equipped with skip connections that can accelerate the training process. Although the bridge does not contribute as many parameters as the encoder and decoder, it has high computational complexity because it is responsible for effectively linking information between the encoder and decoder. One CNN architecture that can enhance model performance is MobileNet. MobileNet uses depthwise separable convolutions, resulting in a lightweight and fast model. This study achieved an accuracy of 99.08%, sensitivity of 99.49%, specificity of 91.76%, IoU of 99.04%, and F1-Score of 99.52%. These results indicate that the model in this study effectively performs segmentation and identifies the liver organ as white and the background as black with high precision.

Availability
#
Central Library (References) T1543622024
T154362
Available but not for loan - Not for Loan
Detail Information
Series Title
-
Call Number
T1543622024
Publisher
Indralaya : Prodi Ilmu Matematika, Fakultas Matematika Dan Ilmu Pengetahuan Alam Universitas Sriwijaya.,
Collation
ix, 50 hlm.; ilus.; tab, 29 cm.
Language
Indonesia
ISBN/ISSN
-
Classification
518.07
Content Type
Text
Media Type
unmediated
Carrier Type
other (computer)
Edition
-
Subject(s)
Analisis numerik
Prodi Ilmu Matematika
Specific Detail Info
-
Statement of Responsibility
Other version/related
File Attachment
Comments
You must be logged in to post a comment