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

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

Metagenome-assembled genome of <i>Oscillospiraceae</i> bacterium strain ZGZL, an anaerobic chloromethane-degrading bacterium enriched from rice paddy soil.

Microbiology resource announcements·2026

Same author

Transcriptomic analysis of response to high-temperature stress in cotton.

Plant physiology and biochemistry : PPB·2026

Same author

Hepatoprotective Mechanisms of Lactiplantibacillus plantarum SCS7 Cell-Free Extract Against Aflatoxin B1 Toxicity.

Probiotics and antimicrobial proteins·2026

Same author

Metabolic engineering of Halomonas cupida for co-mineralization of phenol and p-nitrophenol in high-saline wastewater.

Journal of environmental management·2026

Same author

ITS-ShipFormer: An Informative Token Selection Former for SAR Ship Recognition.

IEEE transactions on neural networks and learning systems·2026

Same author

Evaluation of Three Treatments for the Resource Utilization of Cephalosporin C Fermentation Residue.

Toxics·2026

Same journal

Turbulent flow in a vortex separator with a directed pipe inlet.

Scientific reports·2026

Same journal

Systematic characteristic evaluation of clay-based cementitious material derived from calcium carbide residue and waste tile powder.

Scientific reports·2026

Same journal

Retraction Note: Improvement of a rapid diagnostic application of monoclonal antibodies against avian influenza H7 subtype virus using Europium nanoparticles.

Scientific reports·2026

Same journal

Applying large language models to spam detection in the Kazakh low-resource language setting.

Scientific reports·2026

Same journal

An open-source 3D printing system enabling in-situ freeze-thaw processing of hydrogels.

Scientific reports·2026

Same journal

An enhanced EfficientNet framework for automated waste classification using cosine annealing and label smoothing.

Scientific reports·2026

See all related articles

Search research articles

Related Experiment Video

Updated: Jul 8, 2025

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

Retina image segmentation using the three-path Unet model.

Ruihua Liu¹, Wei Pu^2,3, Haoyu Nan^4,5

¹School of Artificial Intelligence, Chongqing University of Technology, Chongqing, China. lruih@cqut.edu.cn.

Scientific Reports

|December 19, 2023

Summary

This summary is machine-generated.

This study introduces a novel three-path Unet model for precise retinal image segmentation, improving accuracy in detecting blood vessels. The enhanced model significantly outperforms existing methods, aiding in medical diagnosis.

More Related Videos

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Published on: November 11, 2022

Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application

Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application

Published on: April 14, 2023

Related Experiment Videos

Last Updated: Jul 8, 2025

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Published on: November 11, 2022

Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application

Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application

Published on: April 14, 2023

Area of Science:

Medical Imaging
Computer Vision
Biomedical Engineering

Background:

Unsupervised image segmentation offers flexibility but faces challenges in retinal imaging due to data variability and noise.
Manual adjustments in retinal image segmentation can lead to inaccurate results, like over- or under-segmentation of blood vessels.

Purpose of the Study:

To develop a novel supervised segmentation network for enhanced precision in retinal image segmentation.
To improve the accuracy and reliability of retinal vessel segmentation for diagnostic assistance.

Main Methods:

A three-path Unet model (TP-Unet) was developed, integrating Haar wavelet transform for high-frequency information extraction (HaarNet) with Unet and SegNet.
The TP-Unet model was further refined into TP-Unet+AE+DSL by incorporating auto-encoding (AE) and deep supervised learning (DSL).
Experiments were conducted on the public DRIVE and CHASE retinal image datasets.

Main Results:

The proposed TP-Unet+AE+DSL model achieved a Dice coefficient of 0.8291 and sensitivity of 0.8184 on the DRIVE dataset, outperforming the Unet model.
On the CHASE dataset, the model achieved a Dice coefficient of 0.8162, sensitivity of 0.8242, and accuracy of 0.9664, surpassing the Unet model.
The results demonstrate significant improvements in accuracy and reliability for retinal vessel segmentation.

Conclusions:

The novel TP-Unet+AE+DSL model offers superior performance for retinal vessel segmentation compared to the standard Unet.
The proposed method enhances precision and reliability, showing potential for clinical diagnostic support.
Accurate retinal vessel segmentation is crucial for early detection and management of various eye conditions.