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 Association of Race and Ethnicity with Six-Minute Walk Distance: The Multi-Ethnic Study of Atherosclerosis.

Ethnicity & disease·2026
Same author

Deep learning-based CT-derived vertebral bone mineral density and metformin therapy: a longitudinal study in the Multi-Ethnic Study of Atherosclerosis.

Skeletal radiology·2026
Same author

CT Emphysema and Deep Learning-derived Vertebral Bone Loss in Individuals without COPD: Findings from MESA.

Radiology·2026
Same author

A Randomized, Placebo-Controlled, Double-Blind, Crossover Trial of Inhaled Nitric Oxide in Patients With Mild-to-Severe COPD.

Chest·2026
Same author

Sotatercept improves small airway disease and hyperinflation in patients with pulmonary hypertension.

The European respiratory journal·2026
Same author

Mucus plugs in chronic obstructive pulmonary disease are heterogeneous in size and shape and occur in relatively large airways.

American journal of respiratory and critical care medicine·2026
Same journal

LATEST: Local AdapTivE and Sequential Training for Tissue Segmentation of Isointense Infant Brain MR Images.

Medical computer vision and Bayesian and graphical models for biomedical imaging : MICCAI 2016 international workshop, MCV and BAMBI, Athens, Greece, October 21, 2016 : revised selected papers·2017
Same journal

Landmark-Based Alzheimer's Disease Diagnosis Using Longitudinal Structural MR Images.

Medical computer vision and Bayesian and graphical models for biomedical imaging : MICCAI 2016 international workshop, MCV and BAMBI, Athens, Greece, October 21, 2016 : revised selected papers·2017
See all related articles

Related Experiment Video

Updated: Feb 17, 2026

Multi-modal Pulmonary Imaging: Using Complementary Information from CT and Hyperpolarized 129Xe MRI to Evaluate Lung Structure-Function
02:09

Multi-modal Pulmonary Imaging: Using Complementary Information from CT and Hyperpolarized 129Xe MRI to Evaluate Lung Structure-Function

Published on: April 12, 2024

1.1K

Explaining Radiological Emphysema Subtypes with Unsupervised Texture Prototypes: MESA COPD Study.

Jie Yang1, Elsa D Angelini1,2, Benjamin M Smith3,4

  • 1Dept. of Biomedical Engineering, Columbia University, New York, NY, USA.

Medical Computer Vision and Bayesian and Graphical Models for Biomedical Imaging : MICCAI 2016 International Workshop, MCV and BAMBI, Athens, Greece, October 21, 2016 : Revised Selected Papers
|December 5, 2017
PubMed
Summary
This summary is machine-generated.

Unsupervised learning on CT scans identified distinct emphysema subtypes. This method accurately predicts standard radiological subtypes, enabling automated lung volume labeling for improved chronic obstructive pulmonary disease diagnosis.

More Related Videos

Automated Measurement of Pulmonary Emphysema and Small Airway Remodeling in Cigarette Smoke-exposed Mice
10:37

Automated Measurement of Pulmonary Emphysema and Small Airway Remodeling in Cigarette Smoke-exposed Mice

Published on: January 16, 2015

13.7K
Author Spotlight: Optimized Lung MRI Protocol with Computationally Efficient Reconstruction Methods
05:07

Author Spotlight: Optimized Lung MRI Protocol with Computationally Efficient Reconstruction Methods

Published on: September 6, 2024

781

Related Experiment Videos

Last Updated: Feb 17, 2026

Multi-modal Pulmonary Imaging: Using Complementary Information from CT and Hyperpolarized 129Xe MRI to Evaluate Lung Structure-Function
02:09

Multi-modal Pulmonary Imaging: Using Complementary Information from CT and Hyperpolarized 129Xe MRI to Evaluate Lung Structure-Function

Published on: April 12, 2024

1.1K
Automated Measurement of Pulmonary Emphysema and Small Airway Remodeling in Cigarette Smoke-exposed Mice
10:37

Automated Measurement of Pulmonary Emphysema and Small Airway Remodeling in Cigarette Smoke-exposed Mice

Published on: January 16, 2015

13.7K
Author Spotlight: Optimized Lung MRI Protocol with Computationally Efficient Reconstruction Methods
05:07

Author Spotlight: Optimized Lung MRI Protocol with Computationally Efficient Reconstruction Methods

Published on: September 6, 2024

781

Area of Science:

  • Radiology
  • Medical Imaging
  • Artificial Intelligence

Background:

  • Pulmonary emphysema is traditionally classified into three subtypes based on distinct computed tomography (CT) appearances.
  • These subtypes aid in diagnosing chronic obstructive pulmonary disease (COPD).
  • Supervised learning has enabled automated texture-based quantification of these emphysema subtypes.

Purpose of the Study:

  • To investigate the efficacy of unsupervised learning in identifying texture prototypes for emphysema subtyping.
  • To determine if these prototypes can accurately predict the three standard radiological subtypes.
  • To enable automated labeling of lung volumes for finer emphysema subtyping.

Main Methods:

  • Utilized unsupervised learning on a large, heterogeneous database of CT scans.
  • Generated texture prototypes that are visually homogeneous and distinct.
  • Validated the reproducibility of prototypes across subjects.

Main Results:

  • Unsupervised learning successfully generated reproducible texture prototypes.
  • These prototypes accurately predicted the three standard radiological emphysema subtypes.
  • The prototypes facilitate automated labeling of lung volumes.

Conclusions:

  • Unsupervised learning offers a robust method for emphysema subtyping using CT scans.
  • This approach enables more precise interpretations of lung CT scans.
  • It paves the way for finer subtyping of emphysema and improved COPD diagnosis.