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

NUF2 promotes the malignant development of lung adenocarcinoma through the mTORC1 signaling pathway via binding to BUB1B.

Journal of thoracic disease·2025
Same author

Application of Large Language Models in Complex Clinical Cases: Cross-Sectional Evaluation Study.

JMIR medical informatics·2025
Same author

Treatment with Anlotinib After Chemotherapy and EGFR-TKI Resistance in Lung Adenosquamous Carcinoma with Concurrent <i>EGFR</i> and <i>PIK3CA</i> Mutations: A Case Report and Literature Review.

Cancer management and research·2021
Same author

Serum concentrations of antioxidant vitamins and carotenoids are low in individuals with a history of attempted suicide.

Nutritional neuroscience·2007
Same author

Arsenic trioxide induces different gene expression profiles of genes related to growth and apoptosis in glioma cells dependent on the p53 status.

Molecular biology reports·2007
Same author

Role of p38 mitogen-activated protein kinases in cardioprotection of morphine preconditioning.

Chinese medical journal·2007

Related Experiment Video

Updated: Sep 13, 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

Machine Learning Model for Predicting Pathological Invasiveness of Pulmonary Ground-Glass Nodules Based on

Guozhen Yang1, Yuanheng Huang1, Huiguo Chen1

  • 1Department of Cardiothoracic Surgery, Third Affiliated Hospital of Sun Yat-sen University, Guangzhou, China.

Thoracic Cancer
|August 1, 2025
PubMed
Summary

A new AI model accurately predicts lung cancer invasiveness in ground-glass nodules (GGNs) using CT radiomic features. This machine learning approach aids in distinguishing preinvasive lesions from invasive adenocarcinomas (IAC) for better surgical planning.

Keywords:
artificial intelligenceinvasivenesspulmonary ground‐glass nodulesradiomics

More Related Videos

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model
07:15

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Published on: August 16, 2020

6.9K
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

Related Experiment Videos

Last Updated: Sep 13, 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
Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model
07:15

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Published on: August 16, 2020

6.9K
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

Area of Science:

  • Radiology
  • Artificial Intelligence
  • Oncology

Background:

  • Pulmonary ground-glass nodules (GGNs) detection increased with low-dose CT screening.
  • Distinguishing preinvasive lesions from invasive adenocarcinomas (IAC) poses diagnostic challenges.

Purpose of the Study:

  • Develop a machine learning (ML) model using AI-extracted CT radiomic features.
  • Predict the invasiveness of GGNs to aid in clinical decision-making.

Main Methods:

  • Retrospective analysis of 285 patients (training/validation) and 210 patients (external validation).
  • Extracted and filtered 19 radiomic features using Boruta and LASSO algorithms.
  • Evaluated 7 ML classifiers, focusing on Gradient Boosting Machine (GBM) performance using AUC-ROC, DCA, and SHAP.

Main Results:

  • The GBM model achieved high performance: 0.965 AUC (training), 0.908 (internal validation), and 0.965 (external validation).
  • External validation showed 88.1% accuracy, 80.7% specificity, and 0.87 F1 score.
  • SHAP analysis identified median CT value and skewness as key predictors.

Conclusions:

  • A simplified ML model using AI-extracted radiomic features demonstrates strong predictive performance for GGN invasiveness.
  • The model enables accurate, noninvasive differentiation between IAC and indolent lesions.
  • This supports preoperative risk stratification and precise surgical planning for GGNs.