Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Search research articles

Related Experiment Video

Updated: May 28, 2025

Retinal Vascular Reactivity as Assessed by Optical Coherence Tomography Angiography

Retinal Vascular Reactivity as Assessed by Optical Coherence Tomography Angiography

Published on: March 26, 2020

Gabor-modulated depth separable convolution for retinal vessel segmentation in fundus images.

Radha K¹, Yepuganti Karuna²

¹School of Electronics Engineering, Vellore Institute of Technology, Vellore, India.

Computers in Biology and Medicine

|February 13, 2025

Summary

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

Enhanced skin cancer classification for minority classes using Conditional GAN pipeline and CNN-ViT ensemble.

Scientific reports·2026

Same author

Respectful maternity care during childbirth: postnatal women's perspectives. Cross-sectional study from central India: February - December 2023.

Revista colombiana de obstetricia y ginecologia·2025

Same author

Brain tumour segmentation in fused MRI-PET images with permutate U-Net framework.

PloS one·2025

Same author

Histone Deacetylase 2 in Alzheimer's Disease: A Comprehensive Molecular Blueprint for Therapeutic Targeting.

Molecular neurobiology·2025

Same author

Modified energy-based GAN for intensity in homogeneity correction in brain MR images.

Scientific reports·2025

Same author

Latent space autoencoder generative adversarial model for retinal image synthesis and vessel segmentation.

BMC medical imaging·2025

This study introduces a novel Gabor-modulated UNet model for precise retinal vessel segmentation in diabetic retinopathy. The model enhances diagnostic accuracy, even with limited data and on lower-quality images.

Area of Science:

Medical Imaging
Computer Vision
Biomedical Engineering

Background:

Accurate segmentation of retinal vessels is crucial for diagnosing and managing diabetic retinopathy.
Challenges include varying vessel sizes, bifurcations, curved segments, and inconsistent image quality.
Existing deep learning models struggle with geometric transformations and require extensive training data.

Purpose of the Study:

To develop a robust and efficient model for retinal vessel segmentation.
To address limitations of current deep learning approaches in handling data scarcity and image quality variations.
To improve diagnostic accuracy for diabetic retinopathy through enhanced vessel segmentation.

Main Methods:

Proposed a Gabor-modulated depth separable convolution UNet model.

Keywords:

Deep learning Diabetic retinopathy Early diagnosis Fundus image UNet Vessel segmentation

More Related Videos

Doppler Optical Coherence Tomography of Retinal Circulation

Doppler Optical Coherence Tomography of Retinal Circulation

Published on: September 18, 2012

Deep Vascular Imaging in the Eye with Flow-Enhanced Ultrasound

Deep Vascular Imaging in the Eye with Flow-Enhanced Ultrasound

Published on: October 4, 2021

Related Experiment Videos

Last Updated: May 28, 2025

Retinal Vascular Reactivity as Assessed by Optical Coherence Tomography Angiography

Retinal Vascular Reactivity as Assessed by Optical Coherence Tomography Angiography

Published on: March 26, 2020

Doppler Optical Coherence Tomography of Retinal Circulation

Doppler Optical Coherence Tomography of Retinal Circulation

Published on: September 18, 2012

Deep Vascular Imaging in the Eye with Flow-Enhanced Ultrasound

Deep Vascular Imaging in the Eye with Flow-Enhanced Ultrasound

Published on: October 4, 2021

Integrated Gabor filters for enhanced sensitivity to vessel orientation and spatial frequency.

Combined Gabor convolution with depth separable convolution for improved network learning capability.

Main Results:

Demonstrated effectiveness on DRIVE, STARE, and CHASE_DB1 datasets, even with limited training data.
Achieved superior segmentation performance, particularly for vessels with varying orientations and dimensions.
Showcased robustness on noisy and progressed diabetic retinopathy images, outperforming other deep learning models.

Conclusions:

The Gabor-modulated UNet model effectively segments retinal vessels, addressing key challenges in diabetic retinopathy.
The model offers high diagnostic potential, especially in data-limited scenarios and resource-constrained environments.
Its lightweight architecture promotes clinical applicability and integration into various healthcare settings.