IMPLEMENTASI KOMBINASI ARSITEKTUR DOUBLE U-NET, BiLSTM DAN ATTENTION GATE DALAM SEGMENTASI EXUDATE PADA CITRA RETINA PENYAKIT DIABETIC RETINOPATHY

KURNIAWAN, RIFKI and Desiani, Anita and Irmeilyana, Irmeilyana (2025) IMPLEMENTASI KOMBINASI ARSITEKTUR DOUBLE U-NET, BiLSTM DAN ATTENTION GATE DALAM SEGMENTASI EXUDATE PADA CITRA RETINA PENYAKIT DIABETIC RETINOPATHY. Undergraduate thesis, Sriwijaya University.

[thumbnail of RAMA_44201_08011382126094_cover.jpg]
Preview
Image
RAMA_44201_08011382126094_cover.jpg - Cover Image
Available under License Creative Commons Public Domain Dedication.

Download (98kB) | Preview
[thumbnail of RAMA_44201_08011382126094.pdf] Text
RAMA_44201_08011382126094.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_08011382126094_TURNITIN.pdf] Text
RAMA_44201_08011382126094_TURNITIN.pdf - Accepted Version
Restricted to Repository staff only
Available under License Creative Commons Public Domain Dedication.

Download (12MB) | Request a copy
[thumbnail of RAMA_44201_08011382126094_0011127702_0017057403_01_front_ref.pdf] Text
RAMA_44201_08011382126094_0011127702_0017057403_01_front_ref.pdf - Accepted Version
Available under License Creative Commons Public Domain Dedication.

Download (891kB)
[thumbnail of RAMA_44201_08011382126094_0011127702_0017057403_02.pdf] Text
RAMA_44201_08011382126094_0011127702_0017057403_02.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_08011382126094_0011127702_0017057403_03.pdf] Text
RAMA_44201_08011382126094_0011127702_0017057403_03.pdf - Accepted Version
Restricted to Repository staff only
Available under License Creative Commons Public Domain Dedication.

Download (410kB) | Request a copy
[thumbnail of RAMA_44201_08011382126094_0011127702_0017057403_04.pdf] Text
RAMA_44201_08011382126094_0011127702_0017057403_04.pdf - Accepted Version
Restricted to Repository staff only
Available under License Creative Commons Public Domain Dedication.

Download (2MB) | Request a copy
[thumbnail of RAMA_44201_08011382126094_0011127702_0017057403_05.pdf] Text
RAMA_44201_08011382126094_0011127702_0017057403_05.pdf - Accepted Version
Restricted to Repository staff only
Available under License Creative Commons Public Domain Dedication.

Download (165kB) | Request a copy
[thumbnail of RAMA_44201_08011382126094_0011127702_0017057403_06_ref.pdf] Text
RAMA_44201_08011382126094_0011127702_0017057403_06_ref.pdf - Bibliography
Restricted to Repository staff only
Available under License Creative Commons Public Domain Dedication.

Download (230kB) | Request a copy

Abstract

Diabetic retinopathy is an eye disease caused by high glucose levels and high blood pressure that can lead to blindness. One of the signs of diabetic retinopathy is the presence of exudate in the retinal image. Diabetic retinopathy can be analysed by segmenting exudate using Convolutional Neural Network (CNN) method. This research used Double U-Net, BiLSTM, and Attention Gate architecture for exudate segmentation in retinal images. BiLSTM is applied in the bridge part to reduce the risk of redundancy and model complexity through bidirectional drilling. Attention Gate inserted in the decoder section improves feature representation by giving more attention to relevant features. The exudate segmentation results with the application of the proposed architecture obtained an accuracy value of 98% indicates the model is very good at predicting all labels correctly overall. Sensitivity of 72% indicates the model predicts the exudate area quite well. Specificity of 99% indicates the model is very good at predicting areas that are not part of the exudate. F1-Score 76% indicates the model has a good balance between sensitivity and specificity. IoU 62% indicates a poor level of overlap between the predicted image and the ground truth. The results of this study show that the model predicts and performs well in segmenting exudates in retinal images. However, improvements in F1-score and IoU are needed to improve the segmentation performance to be more optimal.

Item Type: Thesis (Undergraduate)
Uncontrolled Keywords: Segmentasi, Exudate, Diabetic Retinopathy, Double U-Net, BiLSTM, Attention Gate
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: Rifki Kurniawan
Date Deposited: 25 May 2025 02:39
Last Modified: 25 May 2025 02:39
URI: http://repository.unsri.ac.id/id/eprint/173998

Actions (login required)

View Item View Item