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 MODIFIKASI SWIN-UNET DENGAN COORDINATE ATTENTION, DUAL ATTENTION BLOCK, DAN SPATIAL ATTENTION MODULE UNTUK SEGMENTASI SEMANTIK PEMBULUH DARAH RETINA
Bookmark Share

Skripsi

MODIFIKASI SWIN-UNET DENGAN COORDINATE ATTENTION, DUAL ATTENTION BLOCK, DAN SPATIAL ATTENTION MODULE UNTUK SEGMENTASI SEMANTIK PEMBULUH DARAH RETINA

Padhil, Azmi Muhammad - Personal Name;

Abnormalities in retinal blood vessels can be used as indicators for detecting various eye diseases, therefore retinal blood vessel image segmentation is required. Manual segmentation is time-consuming, thus an automatic segmentation method based on deep learning is needed to assist the segmentation process of retinal blood vessel images. This study aims to obtain the performance results of semantic segmentation of retinal blood vessels using a modified Swin-Unet architecture with the application of Coordinate Attention (CA), Dual Attention Block (DAB), and Spatial Attention Module (SAM) on LES-AV images. The proposed modifications focus on three main parts, namely CA to preserve spatial positional information in the encoder, DAB to focus attention on important features in the bottleneck, and SAM to maintain spatial details in the decoder. Retinal images are processed through a preprocessing stage using Contrast Limited Adaptive Histogram Equalization (CLAHE) and data augmentation in the form of flipping, rotation, and zooming to improve data quality and diversity. The model is trained to produce three segmentation classes, namely artery, vein, and background. The results of this study show that the modified Swin-Unet architecture with CA, DAB, and SAM provides better segmentation performance compared to other standard models. Model performance evaluation yields an accuracy of 99.32%, sensitivity of 94.91%, specificity of 97.52%, precision of 95.07%, F1-score of 94.99%, and Intersection over Union (IoU) of 90.67%. These results indicate that the modified Swin-Unet architecture with CA, DAB, and SAM is capable of improving the performance of retinal blood vessel segmentation.


Availability
#
Central Library (REFERENCES) T1985882026
T198588
Available but not for loan - Not for Loan
Detail Information
Series Title
-
Call Number
T1985882026
Publisher
Indralaya : Prodi Ilmu Matematika, Fakultas Matematika Dan Ilmu Pengetahuan Alam Universitas Sriwijaya., 2026
Collation
xiii, 130 hlm.; tab.; 29 cm.
Language
Indonesia
ISBN/ISSN
-
Classification
006.420 7
Content Type
Text
Media Type
-
Carrier Type
-
Edition
-
Subject(s)
Segmentasi Citra
Prodi Ilmu Matematika
Specific Detail Info
-
Statement of Responsibility
TUTI
Other version/related

No other version available

File Attachment
  • MODIFIKASI SWIN-UNET DENGAN COORDINATE ATTENTION, DUAL ATTENTION BLOCK, DAN SPATIAL ATTENTION MODULE UNTUK SEGMENTASI SEMANTIK PEMBULUH DARAH RETINA
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?