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

Two-Dimensional Metal-Organic Frameworks as Charge Extraction Media Enabling Binary Organic Solar Cells With 20.70% Efficiency.

Angewandte Chemie (International ed. in English)·2026

Same author

Breathing-Controlled Electrical Stimulation (BreEStim) Selectively Modulates Affective and Cognitive Components of Pain-An EEG Study.

Bioengineering (Basel, Switzerland)·2026

Same author

Wet-Assisted Annealing Strategy Enables All-Polymer Solar Cells Efficiency Exceeding 20.

Advanced materials (Deerfield Beach, Fla.)·2026

Same author

An environmental enrichment facilitates the recovery of lower urinary tract function after spinal cord injury through downmodulation of neurogenic activity in female rats.

World journal of urology·2026

Same author

Perylene-Diimide Dimers with Cross Conformations as Cathode Interfacial Layers for High-Performance and Stable Thin-Film Solar Cells.

Angewandte Chemie (International ed. in English)·2025

Same author

Star-branched polymer donors enabling high-performance organic solar cells with superior flexibility and intrinsic stretchability.

Nature communications·2025

Search research articles

Related Experiment Video

Updated: Dec 4, 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

Retinal Vessel Segmentation by Deep Residual Learning with Wide Activation.

Yuliang Ma^1,2, Xue Li¹, Xiaopeng Duan¹

¹Institute of Intelligent Control and Robotics, Hangzhou Dianzi University, Hangzhou 310018, Zhejiang, China.

Computational Intelligence and Neuroscience

|October 26, 2020

Summary

This study introduces WA-Net, an improved deep learning model for retinal blood vessel segmentation. WA-Net accurately segments small vessels, enhancing ophthalmological analysis with superior performance.

More Related Videos

Using Retinal Imaging to Study Dementia

Using Retinal Imaging to Study Dementia

Published on: November 6, 2017

3D Visualization of Retinal Vascular Pericytes in Mice by Immunostaining

3D Visualization of Retinal Vascular Pericytes in Mice by Immunostaining

Published on: November 1, 2024

Related Experiment Videos

Last Updated: Dec 4, 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

Using Retinal Imaging to Study Dementia

Using Retinal Imaging to Study Dementia

Published on: November 6, 2017

3D Visualization of Retinal Vascular Pericytes in Mice by Immunostaining

3D Visualization of Retinal Vascular Pericytes in Mice by Immunostaining

Published on: November 1, 2024

Area of Science:

Ophthalmology
Medical Imaging
Computer Vision

Background:

Retinal blood vessel segmentation is crucial for diagnosing eye conditions.
Accurate segmentation of small vessels is challenging due to low contrast and complex features.

Purpose of the Study:

To develop an improved retinal blood vessel segmentation structure, WA-Net.
To overcome challenges in segmenting small retinal blood vessels.

Main Methods:

Developed WA-Net by broadening ResNet channels and slimming identity mapping pathways.
Incorporated a residual atrous spatial pyramid module for multi-scale vessel capture.
Applied weight normalization to enhance segmentation accuracy and applied cross-training on DRIVE and STARE datasets.

Main Results:

Achieved high global accuracy (95.66%) and specificity (96.45% within datasets).
Demonstrated strong performance with inter-dataset accuracy and AUC diverging only 1%-2% from intra-dataset.
WA-Net showed superior performance in extracting detailed blood vessels.

Conclusions:

WA-Net effectively extracts detailed retinal blood vessels.
The proposed model demonstrates superior performance in retinal blood vessel segmentation tasks.
WA-Net shows generalizability across different datasets.