Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

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

A Deep Neural Network Method for Arterial Blood Flow Profile Reconstruction.

Entropy (Basel, Switzerland)·2021
Same author

Application of a Generative Adversarial Network in Image Reconstruction of Magnetic Induction Tomography.

Sensors (Basel, Switzerland)·2021
Same author

Application of Linear Gradient Magnetic Field in Arterial Profile Scanning Imaging.

Sensors (Basel, Switzerland)·2020
Same author

A Blood Flow Volume Linear Inversion Model Based on Electromagnetic Sensor for Predicting the Rate of Arterial Stenosis.

Sensors (Basel, Switzerland)·2019
Same author

Solution-solid-solid mechanism: superionic conductors catalyze nanowire growth.

Nano letters·2013
Same author

Depending on the stage of hepatosteatosis, p53 causes apoptosis primarily through either DRAM-induced autophagy or BAX.

Liver international : official journal of the International Association for the Study of the Liver·2013

Related Experiment Video

Updated: Nov 27, 2025

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

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

Published on: November 30, 2022

3.2K

A Multi-Scale Feature Fusion Method Based on U-Net for Retinal Vessel Segmentation.

Dan Yang1,2, Guoru Liu3, Mengcheng Ren3

  • 1Key Laboratory of Data Analytics and Optimization for Smart Industry (Northeastern University), Ministry of Education, Shenyang 110819, China.

Entropy (Basel, Switzerland)
|December 8, 2020
PubMed
Summary
This summary is machine-generated.

This study introduces MSFFU-Net, a novel deep learning model for segmenting retinal blood vessels. The model enhances disease diagnosis by improving accuracy and robustness in retinal image analysis.

Keywords:
U-Netinception structuremax-pooling indexmulti-scaleretinal vessel segmentation

More Related Videos

Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application
05:56

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

Published on: April 14, 2023

2.9K
Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

656

Related Experiment Videos

Last Updated: Nov 27, 2025

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

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

Published on: November 30, 2022

3.2K
Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application
05:56

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

Published on: April 14, 2023

2.9K
Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

656

Area of Science:

  • Medical Imaging
  • Computer Vision
  • Ophthalmology

Background:

  • Accurate retinal blood vessel segmentation is crucial for diagnosing diabetic retinopathy, glaucoma, and macular degeneration.
  • Existing methods often struggle with complex retinal structures and variations.

Purpose of the Study:

  • To propose a multi-scale feature fusion retinal vessel segmentation model named MSFFU-Net.
  • To enhance the accuracy and robustness of automated retinal vessel segmentation.

Main Methods:

  • Developed MSFFU-Net incorporating inception modules for multi-scale feature extraction and max-pooling index for improved upsampling.
  • Utilized skip layer connections for effective feature map transfer.
  • Implemented a cost-sensitive loss function combining Dice coefficient and cross-entropy.
  • Applied CLAHE for preprocessing and data augmentation techniques.

Main Results:

  • Achieved high performance on DRIVE and STARE datasets with sensitivity (0.7762, 0.7721), specificity (0.9835, 0.9885), accuracy (0.9694, 0.9537), and AUC (0.9790, 0.9680).
  • Demonstrated superior performance compared to the standard U-Net model and other state-of-the-art methods.

Conclusions:

  • The proposed MSFFU-Net model is effective and robust for retinal blood vessel segmentation.
  • The model shows competitive results, highlighting its potential for clinical applications in diagnosing retinal diseases.