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

Impact of long COVID on diverse Australian populations: a multi-site, longitudinal prospective cohort study protocol.

BMJ open·2026
Same author

Between silence and solutions: a global guideline review of long COVID care and services in Australia.

BMC health services research·2026
Same author

Excess mortality among people with communicable diseases over a 30-year period, Victoria, Australia: a whole of population cohort study.

The Lancet regional health. Western Pacific·2023
Same author

An oral polyphenol host-guest nanoparticle for targeted therapy of inflammatory bowel disease.

Acta biomaterialia·2023
Same author

Low-dose antimony exposure promotes prostate cancer proliferation by inhibiting ferroptosis via activation of the Nrf2-SLC7A11-GPX4 pathway.

Chemosphere·2023
Same author

Improving Small-Scale Human Action Recognition Performance Using a 3D Heatmap Volume.

Sensors (Basel, Switzerland)·2023

Related Experiment Video

Updated: Mar 2, 2026

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

2.6K

Pulmonary nodule classification with deep residual networks.

Aiden Nibali1, Zhen He2, Dennis Wollersheim3

  • 1Department of Computer Science and Computer Engineering, La Trobe University, Melbourne, Australia. anibali@students.latrobe.edu.au.

International Journal of Computer Assisted Radiology and Surgery
|May 15, 2017
PubMed
Summary

This study enhances computer-aided diagnosis (CAD) for lung cancer by using deep learning to accurately classify lung nodules from CT scans. The advanced deep residual learning method significantly improves malignancy prediction accuracy.

Keywords:
CT imagesConvolutional neural networkLung nodule

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

2.2K
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

2.4K

Related Experiment Videos

Last Updated: Mar 2, 2026

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

2.6K
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

2.2K
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

2.4K

Area of Science:

  • Medical Imaging
  • Artificial Intelligence
  • Oncology

Background:

  • Lung cancer is the leading cause of cancer death in the USA.
  • Accurate malignancy prediction of lung nodules from CT scans is crucial for early diagnosis and treatment.
  • Current computer-aided diagnosis (CAD) systems require improvement in predicting nodule malignancy.

Purpose of the Study:

  • To enhance the accuracy of CAD systems for predicting lung nodule malignancy from CT images.
  • To evaluate the effectiveness of very deep convolutional neural networks for expert-level lung nodule classification.
  • To explore the impact of curriculum learning, transfer learning, and network depth on classification accuracy.

Main Methods:

  • Utilized a ResNet architecture as the basis for very deep convolutional neural networks.
  • Investigated the effects of curriculum learning and transfer learning on nodule classification accuracy.
  • Compared the developed system against two state-of-the-art deep learning systems on the LIDC/IDRI dataset.

Main Results:

  • The proposed system achieved superior performance across all measured metrics, including sensitivity, specificity, precision, AUROC, and accuracy.
  • Direct comparison on the LIDC/IDRI dataset demonstrated higher performance than existing state-of-the-art deep learning systems.
  • The combination of deep residual learning, curriculum learning, and transfer learning proved effective.

Conclusions:

  • The integration of deep residual learning, curriculum learning, and transfer learning offers a promising approach for pulmonary nodule CAD systems.
  • This method achieves high nodule classification accuracy, advancing the field of AI in medical imaging.
  • The findings suggest a new direction for developing effective CAD systems for lung nodule analysis.