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

Identification of metabolomics-based biomarker discovery in individuals with down syndrome utilizing kernel-tree model-enhanced explainable artificial intelligence methodology.

Frontiers in molecular biosciences·2025
Same author

A review of machine learning and deep learning for Parkinson's disease detection.

Discover artificial intelligence·2025
Same author

A Novel Ensemble Meta-Model for Enhanced Retinal Blood Vessel Segmentation Using Deep Learning Architectures.

Biomedicines·2025
Same author

Hospital Re-Admission Prediction Using Named Entity Recognition and Explainable Machine Learning.

Diagnostics (Basel, Switzerland)·2024
Same author

Deep learning for report generation on chest X-ray images.

Computerized medical imaging and graphics : the official journal of the Computerized Medical Imaging Society·2023
Same author

Explainable COVID-19 Detection Based on Chest X-rays Using an End-to-End RegNet Architecture.

Viruses·2023

Related Experiment Video

Updated: Jul 28, 2025

Three-Dimensional Phase Resolved Functional Lung Magnetic Resonance Imaging
10:44

Three-Dimensional Phase Resolved Functional Lung Magnetic Resonance Imaging

Published on: June 21, 2024

551

Vision Transformers for Lung Segmentation on CXR Images.

Rafik Ghali1, Moulay A Akhloufi1

  • 1Perception, Robotics, and Intelligent Machines (PRIME), Department of Computer Science, Université de Moncton, Moncton, NB E1A 3E9 Canada.

SN Computer Science
|May 30, 2023
PubMed
Summary

Accurate lung segmentation in chest X-ray (CXR) images is crucial for automated analysis. Our models achieve 97.47% F1 score, improving disease detection and diagnosis.

Keywords:
Chest X-raysDeep learningLung segmentationMedical image analysisVision transformers

More Related Videos

Author Spotlight: Standardization and Best Practices for Advancing Lung Imaging Using 129Xe MRI
09:08

Author Spotlight: Standardization and Best Practices for Advancing Lung Imaging Using 129Xe MRI

Published on: November 21, 2023

893
Multi-modal Pulmonary Imaging: Using Complementary Information from CT and Hyperpolarized 129Xe MRI to Evaluate Lung Structure-Function
02:09

Multi-modal Pulmonary Imaging: Using Complementary Information from CT and Hyperpolarized 129Xe MRI to Evaluate Lung Structure-Function

Published on: April 12, 2024

642

Related Experiment Videos

Last Updated: Jul 28, 2025

Three-Dimensional Phase Resolved Functional Lung Magnetic Resonance Imaging
10:44

Three-Dimensional Phase Resolved Functional Lung Magnetic Resonance Imaging

Published on: June 21, 2024

551
Author Spotlight: Standardization and Best Practices for Advancing Lung Imaging Using 129Xe MRI
09:08

Author Spotlight: Standardization and Best Practices for Advancing Lung Imaging Using 129Xe MRI

Published on: November 21, 2023

893
Multi-modal Pulmonary Imaging: Using Complementary Information from CT and Hyperpolarized 129Xe MRI to Evaluate Lung Structure-Function
02:09

Multi-modal Pulmonary Imaging: Using Complementary Information from CT and Hyperpolarized 129Xe MRI to Evaluate Lung Structure-Function

Published on: April 12, 2024

642

Area of Science:

  • Medical Imaging
  • Computer Vision
  • Artificial Intelligence

Background:

  • Accurate lung segmentation in chest X-ray (CXR) images is fundamental for automated analysis systems.
  • Challenges include rib cage interference, diverse lung shapes, and disease-related variations.
  • Effective segmentation aids radiologists in early disease detection and diagnosis.

Purpose of the Study:

  • To develop and evaluate models for precise lung segmentation in both healthy and unhealthy CXR images.
  • To address the challenges posed by anatomical variations and pathological findings.
  • To enhance the accuracy of automated lung region identification.

Main Methods:

  • Five distinct models were developed for lung region detection and segmentation.
  • Two different loss functions were utilized for model training.
  • Performance was evaluated across three benchmark CXR datasets.

Main Results:

  • The developed models successfully extracted salient global and local features from CXR images.
  • The top-performing model achieved a high F1 score of 97.47%.
  • Models demonstrated effectiveness in separating lung regions from surrounding structures and handling diverse lung shapes and anomalies.

Conclusions:

  • The proposed models offer a robust solution for lung segmentation in CXR analysis.
  • Achieved high accuracy in segmenting lungs, even in cases with anomalies like tuberculosis and nodules.
  • The approach shows significant potential for improving diagnostic accuracy in radiological assessments.