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

Effects of high-speed shear and esterification modification on physicochemical and structural properties of cassava starch and microencapsulation for olive oils.

Current research in food science·2026
Same author

Beyond Binary: Injury Level, Age, and Weaning Prediction in Cervical Spinal Cord Injury.

Respiratory care·2026
Same author

A Blood-Derived Double-Network Hydrogel with Robust Wet Adhesion for Keratinized Mucosa Regeneration via Neutrophil Phenotype Reprogramming and Mechanophysical Niche Modulation.

Advanced science (Weinheim, Baden-Wurttemberg, Germany)·2026
Same author

Spontaneous bone formation after sinus graft infection control: a case report and review of the literature.

BMC oral health·2026
Same author

Spatiotemporally programmable hydrogel enables NIR-triggered biofilm disruption and mitophagy-driven immunometabolic remodeling for periodontitis.

Biomaterials·2026
Same author

Spatiotemporally Responsive BEC Nanoplatform Targets Neutrophils to Reprogram Immune Crosstalk and Alleviate Periodontal Inflamm-Ageing in Periodontitis.

Journal of clinical periodontology·2026

Related Experiment Video

Updated: Sep 22, 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

3.0K

Automatic lung segmentation in chest X-ray images using improved U-Net.

Wufeng Liu1, Jiaxin Luo2, Yan Yang2

  • 1Henan University of Technology, Zhengzhou, 450001, China. lwf@haut.edu.cn.

Scientific Reports
|May 23, 2022
PubMed
Summary
This summary is machine-generated.

This study enhances automatic lung segmentation in chest X-rays (CXRs) using an improved U-Net model. The new method achieves higher accuracy and robustness for lung disease diagnosis.

More Related Videos

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

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

531
Lung CT Segmentation to Identify Consolidations and Ground Glass Areas for Quantitative Assesment of SARS-CoV Pneumonia
08:05

Lung CT Segmentation to Identify Consolidations and Ground Glass Areas for Quantitative Assesment of SARS-CoV Pneumonia

Published on: December 19, 2020

14.3K

Related Experiment Videos

Last Updated: Sep 22, 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

3.0K
Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

531
Lung CT Segmentation to Identify Consolidations and Ground Glass Areas for Quantitative Assesment of SARS-CoV Pneumonia
08:05

Lung CT Segmentation to Identify Consolidations and Ground Glass Areas for Quantitative Assesment of SARS-CoV Pneumonia

Published on: December 19, 2020

14.3K

Area of Science:

  • Medical Imaging
  • Artificial Intelligence in Medicine
  • Radiology

Background:

  • Accurate lung segmentation in chest X-rays (CXRs) is crucial for diagnosing various lung diseases.
  • Existing automatic segmentation models struggle with extreme lung shape variations and fuzzy boundaries common in severe lung conditions.

Purpose of the Study:

  • To develop an improved U-Net based model for robust and accurate automatic lung segmentation in CXRs.
  • To address limitations of traditional models in handling challenging lung anatomies and image qualities.

Main Methods:

  • Modified U-Net architecture incorporating EfficientNet-b4 as the encoder.
  • Integration of Residual blocks and LeakyReLU activation in the decoder for enhanced feature extraction and gradient stability.
  • Training and evaluation on benchmark and private lung segmentation datasets.

Main Results:

  • Achieved approximately 2.5% higher Dice coefficient and 6% higher Jaccard Index on benchmark datasets compared to traditional U-Net.
  • Demonstrated approximately 5% higher Dice coefficient and 9% higher Jaccard Index on private datasets.
  • Exhibited improved accuracy, lower standard deviation, and enhanced robustness in lung segmentation.

Conclusions:

  • The proposed improved U-Net model significantly enhances the accuracy and reliability of automatic lung segmentation in CXR images.
  • The model's architecture effectively extracts lung field features and mitigates gradient instability, leading to superior performance.
  • This advancement holds promise for improving the diagnostic capabilities in medical imaging analysis for lung diseases.