The diagnosis of diabetic retinopathy by means of transfer learning and fine-tuned dense layer pipeline

Diabetes is a global disease that occurs when the body is disabled pancreas to secrete insulin to convert the sugar to power in the blood. As a result, some tiny blood vessels on the part of the body, such as the eyes, are affected by high sugar and cause blocking blood flow in the vessels, which is...

Full description

Bibliographic Details
Main Authors: Abdo Salman, Abdulaziz, Ismail, Mohd Khairuddin, Anwar P. P., Abdul Majeed, Mohd Azraai, Mohd Razman
Format: Article
Language:English
Published: Penerbit UMP 2020
Subjects:
Online Access:http://umpir.ump.edu.my/id/eprint/33619/
http://umpir.ump.edu.my/id/eprint/33619/1/The%20diagnosis%20of%20diabetic%20retinopathy%20by%20means%20of%20transfer%20learning.pdf
_version_ 1848824301004783616
author Abdo Salman, Abdulaziz
Ismail, Mohd Khairuddin
Anwar P. P., Abdul Majeed
Mohd Azraai, Mohd Razman
author_facet Abdo Salman, Abdulaziz
Ismail, Mohd Khairuddin
Anwar P. P., Abdul Majeed
Mohd Azraai, Mohd Razman
author_sort Abdo Salman, Abdulaziz
building UMP Institutional Repository
collection Online Access
description Diabetes is a global disease that occurs when the body is disabled pancreas to secrete insulin to convert the sugar to power in the blood. As a result, some tiny blood vessels on the part of the body, such as the eyes, are affected by high sugar and cause blocking blood flow in the vessels, which is called diabetic retinopathy. This disease may lead to permanent blindness due to the growth of new vessels in the back of the retina causing it to detach from the eyes. In 2016, 387 million people were diagnosed with Diabetic retinopathy, and the number is growing yearly, and the old detection approach becomes worse. Therefore, the purpose of this paper is to computerize the old method of detecting different classes of DR from 0-4 according to severity by given fundus images. The method is to construct a fine-tuned deep learning model based on transfer learning with dense layers. The used models here are InceptionV3, VGG16, and ResNet50 with a sharpening filter. Subsequently, InceptionV3 has achieved 94% as the highest accuracy among other models.
first_indexed 2025-11-15T03:10:51Z
format Article
id ump-33619
institution Universiti Malaysia Pahang
institution_category Local University
language English
last_indexed 2025-11-15T03:10:51Z
publishDate 2020
publisher Penerbit UMP
recordtype eprints
repository_type Digital Repository
spelling ump-336192022-04-05T02:55:53Z http://umpir.ump.edu.my/id/eprint/33619/ The diagnosis of diabetic retinopathy by means of transfer learning and fine-tuned dense layer pipeline Abdo Salman, Abdulaziz Ismail, Mohd Khairuddin Anwar P. P., Abdul Majeed Mohd Azraai, Mohd Razman RC Internal medicine TK Electrical engineering. Electronics Nuclear engineering Diabetes is a global disease that occurs when the body is disabled pancreas to secrete insulin to convert the sugar to power in the blood. As a result, some tiny blood vessels on the part of the body, such as the eyes, are affected by high sugar and cause blocking blood flow in the vessels, which is called diabetic retinopathy. This disease may lead to permanent blindness due to the growth of new vessels in the back of the retina causing it to detach from the eyes. In 2016, 387 million people were diagnosed with Diabetic retinopathy, and the number is growing yearly, and the old detection approach becomes worse. Therefore, the purpose of this paper is to computerize the old method of detecting different classes of DR from 0-4 according to severity by given fundus images. The method is to construct a fine-tuned deep learning model based on transfer learning with dense layers. The used models here are InceptionV3, VGG16, and ResNet50 with a sharpening filter. Subsequently, InceptionV3 has achieved 94% as the highest accuracy among other models. Penerbit UMP 2020-06 Article PeerReviewed pdf en cc_by_nc_4 http://umpir.ump.edu.my/id/eprint/33619/1/The%20diagnosis%20of%20diabetic%20retinopathy%20by%20means%20of%20transfer%20learning.pdf Abdo Salman, Abdulaziz and Ismail, Mohd Khairuddin and Anwar P. P., Abdul Majeed and Mohd Azraai, Mohd Razman (2020) The diagnosis of diabetic retinopathy by means of transfer learning and fine-tuned dense layer pipeline. Mekatronika - Journal of Intelligent Manufacturing & Mechatronics, 2 (1). pp. 68-72. ISSN 2637-0883. (Published) https://doi.org/10.15282/mekatronika.v2i1.6741 https://doi.org/10.15282/mekatronika.v2i1.6741
spellingShingle RC Internal medicine
TK Electrical engineering. Electronics Nuclear engineering
Abdo Salman, Abdulaziz
Ismail, Mohd Khairuddin
Anwar P. P., Abdul Majeed
Mohd Azraai, Mohd Razman
The diagnosis of diabetic retinopathy by means of transfer learning and fine-tuned dense layer pipeline
title The diagnosis of diabetic retinopathy by means of transfer learning and fine-tuned dense layer pipeline
title_full The diagnosis of diabetic retinopathy by means of transfer learning and fine-tuned dense layer pipeline
title_fullStr The diagnosis of diabetic retinopathy by means of transfer learning and fine-tuned dense layer pipeline
title_full_unstemmed The diagnosis of diabetic retinopathy by means of transfer learning and fine-tuned dense layer pipeline
title_short The diagnosis of diabetic retinopathy by means of transfer learning and fine-tuned dense layer pipeline
title_sort diagnosis of diabetic retinopathy by means of transfer learning and fine-tuned dense layer pipeline
topic RC Internal medicine
TK Electrical engineering. Electronics Nuclear engineering
url http://umpir.ump.edu.my/id/eprint/33619/
http://umpir.ump.edu.my/id/eprint/33619/
http://umpir.ump.edu.my/id/eprint/33619/
http://umpir.ump.edu.my/id/eprint/33619/1/The%20diagnosis%20of%20diabetic%20retinopathy%20by%20means%20of%20transfer%20learning.pdf