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 simulated dataset and evaluation framework for assessing AI detection limits in digital holographic microscopy.

Scientific reports·2026
Same author

Evaluation of the ROX index for predicting intubation in ICU patients.

International journal of medical informatics·2026
Same author

Pulmonary and cerebral damage in COVID-19 survivors: is there any association?

Annals of medicine·2026
Same author

Longitudinal μCT uncovers divergent trajectories of lung maturation in preterm and hyperoxia-exposed neonatal rabbits.

American journal of respiratory cell and molecular biology·2026
Same author

Innovative Wearable Platform for Synchronized Biosignals Acquisition: A Proof of Concept in a Cuff-Less Blood Pressure Monitoring Case Study.

IEEE journal of translational engineering in health and medicine·2026
Same author

Calibrated ROI-gated conditional computation for high-throughput and backbone-agnostic brain tumor MRI classification.

Computer methods and programs in biomedicine·2026

Related Experiment Video

Updated: Nov 11, 2025

Machine Learning-Based Cough Tone Classification: Diagnostic Exploration of Chronic Obstructive Pulmonary Disease and Respiratory Tract Infections
06:22

Machine Learning-Based Cough Tone Classification: Diagnostic Exploration of Chronic Obstructive Pulmonary Disease and Respiratory Tract Infections

Published on: September 19, 2025

168

Detection and Classification of Bronchiectasis Through Convolutional Neural Networks.

Lorenzo Aliboni1, Francesca Pennati1, Alice Gelmini2,3

  • 1Dipartimento di Elettronica, Informazione e Bioingegneria, Politecnico di Milano.

Journal of Thoracic Imaging
|March 24, 2021
PubMed
Summary

This study developed an AI tool using convolutional neural networks to automatically detect and classify bronchiectasis subtypes (cylindrical, varicose, cystic) from CT scans, improving diagnostic accuracy.

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

2.2K
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

14.4K

Related Experiment Videos

Last Updated: Nov 11, 2025

Machine Learning-Based Cough Tone Classification: Diagnostic Exploration of Chronic Obstructive Pulmonary Disease and Respiratory Tract Infections
06:22

Machine Learning-Based Cough Tone Classification: Diagnostic Exploration of Chronic Obstructive Pulmonary Disease and Respiratory Tract Infections

Published on: September 19, 2025

168
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

2.2K
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

14.4K

Area of Science:

  • Medical Imaging
  • Artificial Intelligence in Medicine
  • Pulmonology

Background:

  • Bronchiectasis is a chronic lung disease causing irreversible bronchial dilation, leading to recurrent infections and progressive lung damage.
  • Clinical classification includes cylindrical, varicose, and cystic patterns, but accurate characterization is challenging and prone to interobserver variability.
  • Automated tools are needed to objectively assess bronchiectasis patterns and severity.

Purpose of the Study:

  • To develop and evaluate an automated system for detecting and classifying bronchiectasis using convolutional neural networks (CNNs).
  • To differentiate between healthy lung tissue and three distinct bronchiectasis subtypes: cylindrical, varicose, and cystic.
  • To provide quantitative data on bronchiectasis severity and subtype distribution.

Main Methods:

  • Two CNN approaches were investigated: a direct multilabel classification network and a serial two-network approach.
  • The serial approach first classified normal vs. bronchiectasis, then subtyped the detected bronchiectasis into cylindrical, varicose, or cystic.
  • Performance was evaluated using accuracy and F1 scores on a dataset of 19,059 regions of interest from CT scans.

Main Results:

  • The serial two-network approach achieved the highest performance, with an average accuracy of 0.84 and an average F1 score of 0.84.
  • The direct network showed slightly lower performance (accuracy=0.81, F1 score=0.82).
  • Cylindrical bronchiectasis was classified most accurately, while varicose patterns were most frequently misclassified as cylindrical.

Conclusions:

  • The developed CNN-based networks accurately detect and classify bronchiectasis and its subtypes from CT images.
  • This automated tool offers a reliable method for obtaining quantitative radiologic information on bronchiectasis severity and distribution.
  • The findings suggest potential for improved objective assessment and management of bronchiectasis patients.