The Sriwijaya University Library

  • Home
  • Information
  • News
  • Help
  • Login
  • Librarian
  • Member Area
  • Select Language :
    Arabic Bengali Brazilian Portuguese English Espanol German Indonesian Japanese Malay Persian Russian Thai Turkish Urdu

Search by :

ALL Author Subject ISBN/ISSN Advanced Search

Last search:

{{tmpObj[k].text}}
Image of PENGEMBANGAN ARSITEKTUR 3D U-NET DENGAN RESIDUAL NETWORK DAN INCEPTIONV3 UNTUK SEGMENTASI KANKER PARU PADA CITRA CT SCAN 3D
Bookmark Share

Skripsi

PENGEMBANGAN ARSITEKTUR 3D U-NET DENGAN RESIDUAL NETWORK DAN INCEPTIONV3 UNTUK SEGMENTASI KANKER PARU PADA CITRA CT SCAN 3D

Sagita, Devinka Intan - Personal Name;

A lung cancer diagnosis can be performed using 3D CT scan images. Cancerous areas are identified through a segmentation process. This study develops a 3D U-Net with Residual Network (ResNet) and InceptionV3 to segment lung cancer in 3D CT scans. The 3D U-Net architecture was applied because it can exploit volumetric spatial information in 3D CT scan images. ResNet is applied to the encoder section to preserve fine features lost due to downsampling. InceptionV3 is inserted into each ResNet layer to produce a more diverse feature representation. Image segmentation is performed with two labels, namely cancer and background. This study aims to obtain optimal performance from the proposed architecture. The lung cancer segmentation results using the proposed architecture achieved an accuracy of 97%, indicating that the model can accurately classify labels. A sensitivity of 90% and specificity of 99% indicate that the model is more effective at detecting background areas than cancer areas. However, an F1-score of 94% shows that the cancer area detection capability is already very good. An Intersection over Union (IoU) of 88% indicates that the model produces segmentation that matches the ground truth. The results of this study show that modifying the 3D U-Net architecture with ResNet and InceptionV3 can achieve optimal performance in lung cancer segmentation on 3D CT scans.


Availability
#
Central Library (REFERENCE) T1944042026
T194404
Available but not for loan - Not for Loan
Detail Information
Series Title
-
Call Number
T1944042026
Publisher
Indralaya : Prodi Ilmu Matematika, Fakultas Matematika Dan Ilmu Pengetahuan Alam Universitas Sriwijaya., 2026
Collation
xvii, 131 hlm.; ilus.; tab.; 29 cm.
Language
Indonesia
ISBN/ISSN
-
Classification
006.370 7
Content Type
Text
Media Type
-
Carrier Type
-
Edition
-
Subject(s)
Prodi Ilmu Matematika
Deep Learning
Specific Detail Info
-
Statement of Responsibility
TUTI
Other version/related

No other version available

File Attachment
  • PENGEMBANGAN ARSITEKTUR 3D U-NET DENGAN RESIDUAL NETWORK DAN INCEPTIONV3 UNTUK SEGMENTASI KANKER PARU PADA CITRA CT SCAN 3D
Comments

You must be logged in to post a comment

The Sriwijaya University Library
  • Information
  • Services
  • Librarian
  • Member Area

About Us

As a complete Library Management System, SLiMS (Senayan Library Management System) has many features that will help libraries and librarians to do their job easily and quickly. Follow this link to show some features provided by SLiMS.

Search

start it by typing one or more keywords for title, author or subject

Keep SLiMS Alive Want to Contribute?

© 2026 — Senayan Developer Community

Powered by SLiMS
Select the topic you are interested in
  • Computer Science, Information & General Works
  • Philosophy & Psychology
  • Religion
  • Social Sciences
  • Language
  • Pure Science
  • Applied Sciences
  • Art & Recreation
  • Literature
  • History & Geography
Icons made by Freepik from www.flaticon.com
Advanced Search
Where do you want to share?