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 Review of Flexible Mechanics Mapping: The Sensing, Transmission, Computation, and Integration Paradigm.

ACS applied materials & interfaces·2026
Same author

Deep learning-driven spectral exploration for metal-insulator-metal plasmonic metasurfaces.

Optics express·2025
Same author

Explainable artificial intelligence-based edge fuzzy images for COVID-19 detection and identification.

Applied soft computing·2022
Same author

A new approach for the detection of pneumonia in children using CXR images based on an real-time IoT system.

Journal of real-time image processing·2021
Same author

Simultaneous Photomultiplication Improvement and Response Acceleration for High-Performance Lateral Polymer Photodetectors Based on Bulk Heterojunction.

ACS applied materials & interfaces·2021
Same author

Analysis of Herbal Mechanisms and Prescriptions for Chronic Cerebral Circulatory Insufficiency Based on Data Mining and Network Pharmacology.

Combinatorial chemistry & high throughput screening·2021

Related Experiment Video

Updated: Dec 26, 2025

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

3.3K

An effective approach for CT lung segmentation using mask region-based convolutional neural networks.

Qinhua Hu1, Luís Fabrício de F Souza2, Gabriel Bandeira Holanda2

  • 1School of Chemical Engineering and Energy Technology, Dongguan University of Technology, Dongguan 523808, China.

Artificial Intelligence in Medicine
|March 8, 2020
PubMed
Summary

This study introduces an automated method for segmenting lung regions in CT scans using Mask R-CNN and K-means, achieving 97.68% accuracy. This computer vision technique significantly speeds up lung cancer diagnosis by automating a previously manual process.

Keywords:
Image segmentation lungMachine learningMask R-CNN

More Related Videos

Lung CT Segmentation to Identify Consolidations and Ground Glass Areas for Quantitative Assesment of SARS-CoV Pneumonia
08:05

Lung CT Segmentation to Identify Consolidations and Ground Glass Areas for Quantitative Assesment of SARS-CoV Pneumonia

Published on: December 19, 2020

14.6K
Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images
14:08

Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images

Published on: April 13, 2013

43.3K

Related Experiment Videos

Last Updated: Dec 26, 2025

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

3.3K
Lung CT Segmentation to Identify Consolidations and Ground Glass Areas for Quantitative Assesment of SARS-CoV Pneumonia
08:05

Lung CT Segmentation to Identify Consolidations and Ground Glass Areas for Quantitative Assesment of SARS-CoV Pneumonia

Published on: December 19, 2020

14.6K
Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images
14:08

Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images

Published on: April 13, 2013

43.3K

Area of Science:

  • Medical Imaging
  • Computer Vision
  • Artificial Intelligence

Background:

  • Computed tomography (CT) is crucial for diagnosing diseases like lung cancer.
  • Manual segmentation of lung regions in CT images is a time-consuming bottleneck.
  • Lung cancer remains a leading global cause of mortality.

Purpose of the Study:

  • To develop an automated lung segmentation method for CT images.
  • To improve the efficiency and accuracy of lung region identification in medical imaging.
  • To reduce the manual effort required for lung segmentation in clinical diagnoses.

Main Methods:

  • Utilized Convolutional Neural Network (CNN) Mask R-CNN for lung region mapping.
  • Integrated supervised (Bayes, SVM) and unsupervised (K-means, GMMs) machine learning methods.
  • Optimized the Mask R-CNN model with the K-means kernel for enhanced segmentation.

Main Results:

  • Achieved a high accuracy of 97.68% ± 3.42% for lung segmentation.
  • Demonstrated an average runtime of 11.2 seconds for the segmentation process.
  • Outperformed existing state-of-the-art methods in both accuracy and speed.

Conclusions:

  • The proposed automated lung segmentation method is highly accurate and efficient.
  • Mask R-CNN combined with K-means offers a superior solution for lung segmentation in CT scans.
  • This approach has the potential to accelerate lung cancer diagnosis and improve patient outcomes.