Melola Discovery

← Melola Discovery

Open access Journal SINTA 1

Segmentation of Retinal Blood Vessels in Fundus Images Using Attention Mechanisms and Deep Supervised Networks

CommIT (Communication and Information Technology) Journal · Vol. 20 No. 1 (2026) · pp. 183–196

DOI
10.21512/commit.v20i1.13174
ISSN
2460-7010, 1979-2484
Published
2026-04-15
Publisher
Bina Nusantara University
Language
eng
License
creativecommons.org/licenses/by-sa/4.0

Abstract

Retinal blood vessel segmentation is crucial for detecting and monitoring retinal disorders such as diabetic retinopathy, age-related macular degeneration and glaucoma. Automating the segmentation of blood vessels leads to a reduction in the time and cost of manual segmentation, enables large-scale clinical studies, improves accuracy, ensures consistency, allows for realtime analysis, and facilitates early disease detection. The research examines the performance of 7 semantic segmentation architectures, each combined with 10 pretrained backbones, on 5 publicly available fundus image datasets. Models are trained on a NVIDIA GeForce GTX 1080 Graphics Processing Unit (GPU), and key hyperparameters, such as batch size, optimizers, and learning rate schedulers, are systematically optimized. Intersection over Union (IoU), accuracy, sensitivity, and computational time are used as key performance indicators. Approximately 97 experiments are conducted to achieve state-of-the-art accuracies of 97.72%, 98.23%, 97.62%, 97.83%, and 98.42%, along with IoU scores of 67.82%, 66.29%, 63.89%, 71.34%, and 78.45% on the DRIVE, STARE, HRF, HEI-MED-1, and HEI-MED-2 datasets, respectively. The best performance is achieved using the U-Net++ architecture with ResNeSt backbone, RAdam optimizer, and Cosine Annealing scheduler. This combination leverages deep supervision, attention mechanisms, and bottleneck architectures to enhance multiscale feature learning, localization, robustness to image variability, and model generalization. Although the models demonstrate strong performance, challenges remain in addressing dataset imbalance and ensuring generalization to unseen patient populations.

Keywords

Collaboration network of the authors

3 authors · 3 co-authorship links · 2 across different organisations

Hover or tap a name to highlight its co-authors. Double-click to open the author's page.

  • M S Ramaiah University of Applied Sciences
  • HCL Technologies (India)
  • Different organisations
  • Same organisation
  • Affiliation unknown
  • Thicker line = more joint articles · bigger circle = more articles
Show as table
Co-authorOrganisationJoint articles

Affiliations come from OpenAlex; journal OAI-PMH metadata carries none. Authors without an OpenAlex ID are matched by name, which can merge or split people.

Metadata source: OAI-PMH (metadata jurnal) https://journal.binus.ac.id/index.php/commit/oai, first harvested 8 Nov 2026, last seen 16 Nov 2026.
Original metadata (oai_dc)
<oai_dc:dc xmlns="http://www.openarchives.org/OAI/2.0/" xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:oai_dc="http://www.openarchives.org/OAI/2.0/oai_dc/" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://www.openarchives.org/OAI/2.0/oai_dc/  http://www.openarchives.org/OAI/2.0/oai_dc.xsd">
	<dc:title xml:lang="en-US">Segmentation of Retinal Blood Vessels in Fundus Images Using Attention Mechanisms and Deep Supervised Networks</dc:title>
	<dc:creator>Satyakumar, Nikhil</dc:creator>
	<dc:creator>Balasubramanian, Ramaswamy Karthikeyan</dc:creator>
	<dc:creator>Phirke, Manoj Ravindra</dc:creator>
	<dc:subject xml:lang="en-US">Retinal Blood Vessels</dc:subject>
	<dc:subject xml:lang="en-US">Diabetic Retinopathy</dc:subject>
	<dc:subject xml:lang="en-US">Deep Supervision</dc:subject>
	<dc:subject xml:lang="en-US">Semantic Segmentation</dc:subject>
	<dc:subject xml:lang="en-US">Attention Mechanism</dc:subject>
	<dc:description xml:lang="en-US">
Retinal blood vessel segmentation is crucial for detecting and monitoring retinal disorders such as diabetic retinopathy, age-related macular degeneration and glaucoma. Automating the segmentation of blood vessels leads to a reduction in the time and cost of manual segmentation, enables large-scale clinical studies, improves accuracy, ensures consistency, allows for realtime analysis, and facilitates early disease detection. The research examines the performance of 7 semantic segmentation architectures, each combined with 10 pretrained backbones, on 5 publicly available fundus image datasets. Models are trained on a NVIDIA GeForce GTX 1080 Graphics Processing Unit (GPU), and key hyperparameters, such as batch size, optimizers, and learning rate schedulers, are systematically optimized. Intersection over Union (IoU), accuracy, sensitivity, and computational time are used as key performance indicators. Approximately 97 experiments are conducted to achieve state-of-the-art accuracies of 97.72%, 98.23%, 97.62%, 97.83%, and 98.42%, along with IoU scores of 67.82%, 66.29%, 63.89%, 71.34%, and 78.45% on the DRIVE, STARE, HRF, HEI-MED-1, and HEI-MED-2 datasets, respectively. The best performance is achieved using the U-Net++ architecture with ResNeSt backbone, RAdam optimizer, and Cosine Annealing scheduler. This combination leverages deep supervision, attention mechanisms, and bottleneck architectures to enhance multiscale feature learning, localization, robustness to image variability, and model generalization. Although the models demonstrate strong performance, challenges remain in addressing dataset imbalance and ensuring generalization to unseen patient populations.
 
</dc:description>
	<dc:publisher xml:lang="en-US">Bina Nusantara University</dc:publisher>
	<dc:date>2026-04-15</dc:date>
	<dc:type>info:eu-repo/semantics/article</dc:type>
	<dc:type>info:eu-repo/semantics/publishedVersion</dc:type>
	<dc:type xml:lang="en-US">Peer-reviewed Article</dc:type>
	<dc:format>application/pdf</dc:format>
	<dc:identifier>https://journal.binus.ac.id/index.php/commit/article/view/13174</dc:identifier>
	<dc:identifier>10.21512/commit.v20i1.13174</dc:identifier>
	<dc:source xml:lang="en-US">CommIT (Communication and Information Technology) Journal; Vol. 20 No. 1 (2026): CommIT Journal ; 183-196</dc:source>
	<dc:source>2460-7010</dc:source>
	<dc:source>1979-2484</dc:source>
	<dc:language>eng</dc:language>
	<dc:relation>https://journal.binus.ac.id/index.php/commit/article/view/13174/5725</dc:relation>
	<dc:rights xml:lang="en-US">Copyright (c) 2026 Nikhil Satyakumar, Ramaswamy Karthikeyan Balasubramanian, Manoj Ravindra Phirke</dc:rights>
	<dc:rights xml:lang="en-US">https://creativecommons.org/licenses/by-sa/4.0</dc:rights>
</oai_dc:dc>