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

The Impact of Artificial Intelligence on Radiology Specialty Preferences Among Canadian Medical Students and Residents.

Academic radiology·2026
Same author

Evaluating data heterogeneity's impact on convolutional neural network performance in medical imaging.

International journal of computer assisted radiology and surgery·2026
Same author

Cognitively Biased Prompt Effects on Large Language Model Accuracy for Radiology Board-style Examination Questions.

Radiology. Artificial intelligence·2026
Same author

Deep learning for pediatric synovial recess distension detection in hemophilia: synthetic image augmentation with styleGAN2-ADA.

International journal of computer assisted radiology and surgery·2026
Same author

Physician AI literacy: A key to unlocking AI's clinical potential.

Reproductive biomedicine online·2026
Same author

Digital pathology imaging artificial intelligence in cancer research and clinical trials: An NCI workshop report.

Journal of pathology informatics·2026

Related Experiment Video

Updated: Dec 21, 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

2.3K

3D-MCN: A 3D Multi-scale Capsule Network for Lung Nodule Malignancy Prediction.

Parnian Afshar1, Anastasia Oikonomou2, Farnoosh Naderkhani1

  • 1Concordia Institute for Information Systems Engineering, Montreal, QC, Canada.

Scientific Reports
|May 16, 2020
PubMed
Summary

A new 3D Multi-scale Capsule Network (3D-MCN) improves lung cancer prediction accuracy and sensitivity. This novel approach effectively analyzes nodules and surrounding tissues, even with limited data, outperforming traditional methods.

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

1.9K
Multifractal Spectrum Analysis for Assessing Pulmonary Nodule Malignancy
05:24

Multifractal Spectrum Analysis for Assessing Pulmonary Nodule Malignancy

Published on: January 10, 2025

694

Related Experiment Videos

Last Updated: Dec 21, 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

2.3K
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

1.9K
Multifractal Spectrum Analysis for Assessing Pulmonary Nodule Malignancy
05:24

Multifractal Spectrum Analysis for Assessing Pulmonary Nodule Malignancy

Published on: January 10, 2025

694

Area of Science:

  • Medical Imaging
  • Artificial Intelligence
  • Oncology

Background:

  • Accurate lung cancer malignancy prediction is crucial but challenging.
  • Existing Convolutional Neural Networks (CNNs) require extensive data and often overlook surrounding tissue context.
  • Interpretability and sensitivity remain key challenges in clinical applications.

Purpose of the Study:

  • To develop a novel deep learning model for enhanced lung nodule malignancy prediction.
  • To address limitations of CNNs, including data requirements and focus on nodule-only regions.
  • To improve the accuracy, sensitivity, and interpretability of automated lung cancer detection.

Main Methods:

  • Proposed a 3D Multi-scale Capsule Network (3D-MCN) leveraging Capsule Networks (CapsNets).
  • Utilized 3D inputs for comprehensive nodule analysis.
  • Incorporated multi-scale inputs to capture both local nodule features and surrounding tissue characteristics.

Main Results:

  • The 3D-MCN achieved 93.12% accuracy, 94.94% sensitivity, and 90% specificity for nodule malignancy prediction on the LIDC-IDRI dataset.
  • Achieved an Area Under the Curve (AUC) of 0.9641.
  • For patient-level classification (malignant vs. non-malignant), the model demonstrated 83% accuracy, 84% sensitivity, and 81% specificity.

Conclusions:

  • The 3D-MCN offers a promising solution for lung nodule malignancy prediction, particularly effective with limited training data.
  • The multi-scale and 3D approach enhances feature extraction, improving diagnostic performance.
  • The CapsNet architecture shows potential for clinical translation in medical imaging analysis.