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

A BODIPY-based turn-on fluorescent probe for the selective detection of hydrogen sulfide in solution and in cells.

Talanta·2015
Same author

Analysis of sagittal balance using spinopelvic parameters in ankylosing spondylitis patients treated with vertebral column decancellation surgery.

Acta orthopaedica Belgica·2015
Same author

Using a 3D Culture System to Differentiate Visceral Adipocytes In Vitro.

Endocrinology·2015
Same author

Noncontact Monitoring of Blood Oxygen Saturation Using Camera and Dual-Wavelength Imaging System.

IEEE transactions on bio-medical engineering·2015
Same author

Digital human modeling and its applications: Review and future prospects.

Journal of X-ray science and technology·2015
Same author

Capture-based high-coverage NGS: a powerful tool to uncover a wide spectrum of mutation types.

Genetics in medicine : official journal of the American College of Medical Genetics·2015

Related Experiment Video

Updated: Oct 14, 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

1.6K

Design of lung nodules segmentation and recognition algorithm based on deep learning.

Hui Yu1, Jinqiu Li1, Lixin Zhang1

  • 1Department of Biomedical Engineering, Tianjin Key Laboratory of Biomedical Detecting Techniques and Instruments, Tianjin University, Tianjin, China.

BMC Bioinformatics
|November 9, 2021
PubMed
Summary

This study introduces improved 3D Res U-Net and 3D ResNet50 algorithms for lung nodule segmentation and classification, enhancing early lung cancer diagnosis accuracy.

Keywords:
Convolutional neural networkImage classificationImage segmentationLung noduleResidual learningU-Net

More Related Videos

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

2.1K
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: Oct 14, 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

1.6K
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

2.1K
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:

  • Medical Imaging
  • Artificial Intelligence
  • Computer-Aided Diagnosis

Background:

  • Accurate lung nodule segmentation and recognition are crucial for early lung cancer diagnosis.
  • Existing algorithms require enhancement for improved accuracy and efficiency.
  • 3D Convolutional Neural Networks (CNNs) show promise in analyzing complex medical image data.

Purpose of the Study:

  • To develop and evaluate an advanced algorithm for segmenting and classifying lung nodules using 3D CT images.
  • To improve the accuracy of early lung cancer detection through enhanced image analysis.
  • To leverage deep learning architectures for precise nodule identification and characterization.

Main Methods:

  • Utilized a 3D Res U-Net segmentation network with residual units and Dice loss for improved convergence.
  • Employed a modified 3D ResNet50 classification network with 3D convolutional layers for nodule diagnosis.
  • Trained and tested models on the LIDC-IDRI database, comprising numerous CT subcases and lung nodules.

Main Results:

  • The 3D Res U-Net achieved a Dice coefficient above 0.8 for segmenting lung nodules larger than 10 mm.
  • The 3D ResNet50 classification network demonstrated a diagnostic accuracy of 87.3% and an AUC of 0.907.
  • The enhanced models showed significant improvements in performance compared to baseline architectures.

Conclusions:

  • The 3D Res U-Net significantly enhances lung nodule segmentation, particularly for small and large nodules.
  • The 3D ResNet50 network offers improved classification performance, especially for small benign nodules.
  • These deep learning approaches hold substantial potential for advancing early lung cancer diagnosis.