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

Primary somatosensory neuron-derived Zn<sup>2+</sup> orchestrates muscle regeneration via Hippo signaling pathway.

Cell discovery·2026

Same author

The diaphragm-intercostal index for predicting weaning failure in mechanically ventilated patients: a prospective cohort study.

Frontiers in medicine·2026

Same author

Polypyrrole-Modified Lead-Free Perovskite Heterojunctions to Facilitate Charge Separation for Photocatalytic Oxidation of Benzylamine.

Langmuir : the ACS journal of surfaces and colloids·2026

Same author

[Research Progress and Application Prospects of Saliva-Based Point-of-Care Testing Technologies].

Zhongguo yi liao qi xie za zhi = Chinese journal of medical instrumentation·2026

Same author

Echinacoside restores levofloxacin activity against multidrug-resistant Pseudomonas aeruginosa: evidence for iron-responsive siderophore-like properties and membrane disruption.

Phytomedicine : international journal of phytotherapy and phytopharmacology·2026

Same author

Adjunctive fecal microbiota transplantation for major depressive disorder: A randomized, double-blind, placebo-controlled trial.

Cell host & microbe·2026

Same journal

Association between retinal microcirculation and cardiac function: A cross-sectional study using OCTA.

Microvascular research·2026

Same journal

Microvascular dysfunction and neurovascular signalling impairment in diabetic silent myocardial ischemia.

Microvascular research·2026

Same journal

Association of circulating biomarkers of glycocalyx injury, sirtuin 1, and NFκB p65 in individuals with type 2 diabetes and concurrent arterial hypertension.

Microvascular research·2026

Same journal

Targeting miR-10 alleviates atherosclerosis by enhancing intestinal ABCA1-mediated cholesterol efflux and repairing intestinal barrier.

Microvascular research·2026

Same journal

The effect of acute high-intensity interval exercise on microvascular function and local skeletal muscle oxygenation.

Microvascular research·2026

Same journal

RNF213 deficiency in human iPSC-derived vascular organoids captures key feature of moyamoya disease vasculopathy.

Microvascular research·2026

See all related articles

Search research articles

Related Experiment Video

Updated: Dec 22, 2025

A Reproducible Computerized Method for Quantitation of Capillary Density using Nailfold Capillaroscopy

A Reproducible Computerized Method for Quantitation of Capillary Density using Nailfold Capillaroscopy

Published on: October 27, 2015

Segmenting nailfold capillaries using an improved U-net network.

Shupeng Liu¹, Yuemei Li¹, Jingjing Zhou²

¹Key Laboratory of Specialty Fiber Optics and Optical Access Networks, Joint International Research Laboratory of Specialty Fiber Optics and Advanced Communication, Shanghai Institute for Advanced Communication and Data Science, Institute of Biomedical Engineering, School of Communication and Information Engineering, Shanghai University, 333 Nanchen Road, Shanghai 200444, China.

Microvascular Research

|May 7, 2020

Summary

This summary is machine-generated.

This study introduces a deep neural network, Res-Unet, to accurately segment capillaries in low-quality nailfold capillaroscopy (NC) images. The method achieved high accuracy, improving diagnosis for diseases affecting capillary morphology.

Keywords:

Nailfold capillaroscopy Res-Unet Segmentation U-Net

More Related Videos

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

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Published on: November 11, 2022

Related Experiment Videos

Last Updated: Dec 22, 2025

A Reproducible Computerized Method for Quantitation of Capillary Density using Nailfold Capillaroscopy

A Reproducible Computerized Method for Quantitation of Capillary Density using Nailfold Capillaroscopy

Published on: October 27, 2015

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

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Published on: November 11, 2022

Area of Science:

Medical Imaging
Biomedical Engineering
Computational Biology

Background:

Nailfold capillaroscopy (NC) is crucial for assessing microcirculation and diagnosing diseases with altered capillary morphology.
Analyzing NC images is challenging due to their typically poor quality, hindering accurate diagnosis.
Automated segmentation of capillaries in NC images is needed to improve diagnostic efficiency and accuracy.

Purpose of the Study:

To develop an accurate method for segmenting capillaries in poor-quality nailfold capillaroscopy (NC) images.
To evaluate the performance of a deep neural network, specifically a Res-Unet structure, for this segmentation task.

Main Methods:

A deep neural network with a Res-Unet architecture was proposed, combining residual networks (ResNet) and U-Net.
The network was trained on 30 NC images to differentiate capillary pixels.
The trained network was tested on 20 NC images to generate a binarized map of capillaries.

Main Results:

The Res-Unet model demonstrated strong performance in capillary segmentation.
The mean accuracy achieved was 91.72% compared to ground truth.
The mean Dice score reached 97.66%, indicating high overlap with actual capillary structures.

Conclusions:

The Res-Unet deep neural network is effective for accurate capillary segmentation in low-quality NC images.
This approach shows promise for improving the diagnosis of microcirculatory disorders.
The method offers a reliable tool for analyzing capillary morphology in clinical settings.