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

Anatomically Guided Cascaded U-Net Ensemble for Coronary Artery Calcification Segmentation in Cardiac CT.

Bioengineering (Basel, Switzerland)·2025
Same author

Ischemic Stroke Lesion Core Segmentation from CT Perfusion Scans Using Attention ResUnet Deep Learning.

Journal of imaging informatics in medicine·2025
Same author

Efficient Extraction of Coronary Artery Vessels from Computed Tomography Angiography Images Using ResUnet and Vesselness.

Bioengineering (Basel, Switzerland)·2024
Same author

Deep learning and level set approach for liver and tumor segmentation from CT scans.

Journal of applied clinical medical physics·2020
Same author

Automatic atlas-based liver segmental anatomy identification for hepatic surgical planning.

International journal of computer assisted radiology and surgery·2019
Same author

Survey on Liver Tumour Resection Planning System: Steps, Techniques, and Parameters.

Journal of digital imaging·2019

Related Experiment Video

Updated: Oct 19, 2025

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

Automatic deep learning system for COVID-19 infection quantification in chest CT.

Omar Ibrahim Alirr1

  • 1College of Engineering and Technology, American University of the Middle East, Egaila, Kuwait.

Multimedia Tools and Applications
|September 20, 2021
PubMed
Summary
This summary is machine-generated.

This study introduces an automated deep learning system for segmenting COVID-19 infection areas in CT scans. The system accurately identifies lung and infection regions, offering a reliable alternative to PCR testing for coronavirus disease.

Keywords:
COVID-19 infectionChest CTDeep learningSegmentation

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

1.7K
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

Related Experiment Videos

Last Updated: Oct 19, 2025

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
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

1.7K
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

Area of Science:

  • Medical Imaging
  • Artificial Intelligence
  • Computer-Aided Diagnosis

Background:

  • Polymerase Chain Reaction (PCR) is the standard for COVID-19 detection but suffers from low sensitivity and is time-consuming.
  • Computed Tomography (CT) imaging shows promise for detecting COVID-19, including in asymptomatic cases, serving as a viable alternative to PCR.
  • Accurate segmentation of infection areas in CT scans is crucial for effective diagnosis and patient management.

Purpose of the Study:

  • To develop and evaluate an automatic deep learning system for segmenting COVID-19 infection areas in chest CT scans.
  • To enhance the accuracy and efficiency of COVID-19 detection using medical imaging.
  • To provide a robust and generalizable tool for analyzing CT scans for coronavirus disease.

Main Methods:

  • A deep learning framework utilizing a U-net architecture with a modified residual block and concatenation skip connection was employed.
  • The system preprocesses CT scans by segmenting lung organs and applying edge-enhancing diffusion filtering (EED) to improve contrast and homogeneity of infection areas.
  • The model was trained and tested on diverse 2D CT slices from multiple sources to ensure generalization.

Main Results:

  • The proposed system achieved a Dice overlapping score of 0.961 for lung segmentation and 0.780 for COVID-19 infection areas segmentation.
  • The system demonstrated effectiveness and generalization capabilities across various datasets.
  • The modified residual block with skip connections improved the learning of gradient values and feature propagation.

Conclusions:

  • The developed automatic deep learning system provides accurate and effective segmentation of COVID-19 infection areas in chest CT scans.
  • The system's performance indicates its potential as a valuable tool in the diagnosis of coronavirus disease, complementing or potentially replacing PCR.
  • Further improvements in accuracy and generalization can be achieved with access to larger and more diverse datasets in the future.