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

Radiological Investigation III: Pulmonary Angiogram and PET Scan01:13

Radiological Investigation III: Pulmonary Angiogram and PET Scan

166
Radiological investigations are paramount in the diagnosis and management of various pulmonary diseases. Two essential investigations are the Pulmonary Angiogram and the Positron Emission Tomography (PET) Scan.
Pulmonary Angiogram
A Pulmonary Angiogram is an invasive procedure involving injecting a contrast medium through a catheter threaded into the pulmonary artery or the right side of the heart to visualize the pulmonary vasculature. Computed Tomography (CT) scans have mainly replaced this...
166

You might also read

Related Articles

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

Sort by
Same author

Deep-learning denoising for ultrahigh-resolution photon-counting detector CT: phantom and in vivo evaluation of non-calcified coronary plaques.

The international journal of cardiovascular imaging·2026
Same author

Keeping the story, turning the page: from prognostic to predictive AI in high-risk prostate cancer.

Annals of oncology : official journal of the European Society for Medical Oncology·2026
Same author

Symptom-Only Localization of Brainstem Ischemia Using Large Language Models Versus Neurologists in Diffusion-Weighted Imaging-Positive Cases: Retrospective Single-Center Study.

JMIR formative research·2026
Same author

A deep learning framework for efficient pathology image analysis.

Nature communications·2026
Same author

[National infrastructures and the European Health Data Space].

Radiologie (Heidelberg, Germany)·2026
Same author

Added value of photon-counting CT for triple rule-out imaging: A propensity-matched comparison with energy-integrating CT.

Journal of cardiovascular computed tomography·2026

Related Experiment Video

Updated: Sep 8, 2025

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

2.0K

Diagnostic performance of artificial intelligence models for pulmonary nodule classification: a multi-model

Sarah K Herber1, Lukas Müller2, Daniel Pinto Dos Santos1

  • 1Department of Diagnostic and Interventional Radiology, University Medical Center of the Johannes Gutenberg-University Mainz, Mainz, Germany.

European Radiology
|July 27, 2025
PubMed
Summary

Commercial artificial intelligence (AI) models show low accuracy in classifying pulmonary nodules, with high false-negative rates and many intermediate-risk results. These AI tools are not yet reliable for standalone clinical use in lung cancer diagnosis.

Keywords:
Artificial intelligenceComputed tomographyDiagnostic accuracyLung cancerPulmonary nodules

More Related Videos

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

1.6K
A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images
04:23

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images

Published on: April 21, 2023

2.0K

Related Experiment Videos

Last Updated: Sep 8, 2025

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

2.0K
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

1.6K
A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images
04:23

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images

Published on: April 21, 2023

2.0K

Area of Science:

  • Pulmonary Medicine
  • Radiology
  • Artificial Intelligence in Healthcare

Background:

  • Lung cancer is a leading cause of cancer mortality, and early detection of pulmonary nodules is crucial for improving survival rates.
  • Distinguishing malignant from benign pulmonary nodules using imaging remains a diagnostic challenge.
  • Artificial intelligence (AI) is being explored to enhance the accuracy of pulmonary nodule classification.

Purpose of the Study:

  • To evaluate the diagnostic performance of commercially available AI software models in classifying pulmonary nodules.
  • To compare AI model accuracy against histopathology as the gold standard.
  • To identify potential limitations of AI in clinical application for pulmonary nodule diagnosis.

Main Methods:

  • A retrospective analysis of 158 pulmonary nodules (4-30 mm) from CT scans was conducted.
  • Three AI software models were used to classify nodules, with sensitivity, specificity, and false rates calculated.
  • Diagnostic accuracy was assessed using the area under the receiver operating characteristic curve (AUC), with subgroup analyses performed based on nodule characteristics and CT scan parameters.

Main Results:

  • One AI model classified a significant proportion of nodules as intermediate risk, hindering assessment.
  • The other AI models exhibited moderate sensitivity (53.1-70.3%) but low specificity (46.7-66.7%), resulting in high false-positive rates (45.5-52.4%).
  • Area under the ROC curve (AUC) values ranged from 0.5 to 0.6, indicating limited diagnostic capability. Up to 49% of nodules were classified as intermediate risk, and performance varied with CT scan type.

Conclusions:

  • Current AI-based software models demonstrate insufficient specificity and high false-negative rates for pulmonary nodule classification.
  • A substantial percentage of nodules were classified as intermediate risk, limiting clinical utility.
  • The evaluated AI models are not yet suitable for standalone clinical application in pulmonary nodule diagnosis.