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

Pneumothorax-II01:27

Pneumothorax-II

577
Pneumothorax is a medical condition defined by the buildup of air in the pleural space between the lungs and the chest wall. This accumulation of air can lead to partial or complete lung collapse, resulting in a range of clinical manifestations. Understanding the clinical presentation and effective management strategies is crucial for healthcare professionals in providing timely and appropriate care to individuals with pneumothorax.
Clinical Manifestations:
577
Pneumothorax-I01:26

Pneumothorax-I

731
A pneumothorax is a condition where air builds up in the space between the lung and the chest wall, causing the lung to collapse. This condition arises when air enters the space between the parietal and visceral pleura, disrupting the negative pressure essential for lung inflation. This can lead to a partial or complete collapse of the lung.
Pneumothorax can be even further classified as spontaneous, traumatic, and tension pneumothorax.
731
Assessment of Respiration01:23

Assessment of Respiration

1.5K
The respiratory system's basic structures and primary functions lay the foundation for nurses' comprehensive respiratory assessments. This assessment includes subjective and objective data to gauge the patient's respiratory health.
Subjective Assessment: Nurses interview the patient to gather information directly during the subjective assessment. It includes questions about the individual's medical history, medications, and symptoms, focusing on past respiratory conditions like...
1.5K
Pneumonia III: Complications and Assessment01:30

Pneumonia III: Complications and Assessment

569
Pneumonia poses the potential for numerous complications that warrant consideration. These complications include the following:
569

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

A Whole-Body PSMA-PET/CT dataset with manually annotated tumor lesions.

Scientific data·2026
Same author

PatchCLIP enables region specific contrastive health record and image joint training with patch embedding loss.

Scientific reports·2026
Same author

Virtual simulation accurately predicts in vivo flow diverter length for intracranial aneurysm treatment: a multicenter validation study.

Journal of neurointerventional surgery·2026
Same author

AutoPET Challenge on Fully Automated Lesion Segmentation in Oncologic PET/CT Imaging, Part 2: Domain Generalization.

Journal of nuclear medicine : official publication, Society of Nuclear Medicine·2025
Same author

Fast machine learning image reconstruction of radially undersampled k-space data for low-latency real-time MRI.

PloS one·2025
Same author

Threshold optimization in AI chest radiography analysis: integrating real-world data and clinical subgroups.

European radiology experimental·2025

Related Experiment Video

Updated: Nov 11, 2025

Author Spotlight: Advancing 3D Modeling for Enhanced Diagnosis and Treatment of Pulmonary Nodules in Early-Stage Lung Cancer
07:53

Author Spotlight: Advancing 3D Modeling for Enhanced Diagnosis and Treatment of Pulmonary Nodules in Early-Stage Lung Cancer

Published on: October 13, 2023

1.8K

Pneumothorax detection in chest radiographs: optimizing artificial intelligence system for accuracy and confounding

Johannes Rueckel1, Christian Huemmer2, Andreas Fieselmann2

  • 1Department of Radiology, University Hospital, LMU Munich, Marchioninistr. 15, 81377, Munich, Germany. johannes.rueckel@med.uni-muenchen.de.

European Radiology
|March 28, 2021
PubMed
Summary

Artificial intelligence (AI) for pneumothorax (PTX) detection is improved by using in-image annotations. This method boosts AI performance and reduces bias from confounding factors like thoracic tubes in chest radiographs.

Keywords:
Artificial intelligenceChest radiographyChest tubesPneumothorax

More Related Videos

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

14.4K
Author Spotlight: A 3D Digital Model for the Diagnosis and Treatment of Pulmonary Nodules
10:26

Author Spotlight: A 3D Digital Model for the Diagnosis and Treatment of Pulmonary Nodules

Published on: May 19, 2023

2.2K

Related Experiment Videos

Last Updated: Nov 11, 2025

Author Spotlight: Advancing 3D Modeling for Enhanced Diagnosis and Treatment of Pulmonary Nodules in Early-Stage Lung Cancer
07:53

Author Spotlight: Advancing 3D Modeling for Enhanced Diagnosis and Treatment of Pulmonary Nodules in Early-Stage Lung Cancer

Published on: October 13, 2023

1.8K
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

14.4K
Author Spotlight: A 3D Digital Model for the Diagnosis and Treatment of Pulmonary Nodules
10:26

Author Spotlight: A 3D Digital Model for the Diagnosis and Treatment of Pulmonary Nodules

Published on: May 19, 2023

2.2K

Area of Science:

  • Artificial Intelligence in Medical Imaging
  • Radiology
  • Diagnostic Accuracy

Background:

  • Existing artificial intelligence (AI) algorithms for pneumothorax (PTX) detection in chest radiographs (CXR) suffer from limited accuracy.
  • Noisy annotations in public training data and confounding factors, such as thoracic tubes (TT), hinder the performance of current AI models.
  • There is a need for improved AI systems that can accurately detect PTX while mitigating biases from confounding elements.

Purpose of the Study:

  • To investigate the impact of in-image annotations of the dehiscent visceral pleura on AI algorithm performance for PTX detection.
  • To enhance the diagnostic accuracy of AI in identifying PTX by suppressing confounders, particularly thoracic tubes.
  • To develop a more robust AI system for PTX detection in chest radiographs.

Main Methods:

  • A single-center evaluation cohort of 3062 supine CXRs was analyzed, including 760 PTX-positive cases.
  • Three progressively improved AI algorithms were developed, varying in architecture, training data sources, and the inclusion of in-image annotations.
  • Algorithm performance was assessed using the area under the receiver operating characteristics (AUROC) curve and compared against the CheXNet algorithm.

Main Results:

  • AI algorithms trained solely on public data without in-image annotations achieved limited AUROCs (0.778) and showed significant bias towards thoracic tubes.
  • The final AI algorithm, trained with in-image annotations of the dehiscent pleura, achieved a higher overall AUROC of 0.877 for unilateral PTX detection.
  • The refined algorithm demonstrated a significantly reduced confounding bias related to thoracic tubes, improving diagnostic reliability.

Conclusions:

  • High-quality in-image localization in training data is crucial for developing effective AI algorithms for pathology detection.
  • Designing AI systems capable of both classifying and localizing PTX significantly reduces limitations and biases associated with confounding factors.
  • In-image annotations can potentially address hidden confounders in AI training, leading to more accurate and reliable diagnostic tools.