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

Seed-to-Semantics: Few-shot Prototype-Guided Progressive Learning for Hyperspectral and LiDAR Classification.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2026
Same author

Synergistic enhancement of cadmium remediation by cadmium-resistant microorganisms immobilized on biochar.

RSC advances·2026
Same author

Improved deep reinforcement learning controls anti-lock braking via electro-hydraulic composite systems in in-wheel motor-driven electric vehicles.

Scientific reports·2026
Same author

Granular Ball-Based Noise-Resistant Fuzzy Multineighborhood Feature Selection via Label Enhancement and Feature Graph.

IEEE transactions on neural networks and learning systems·2026
Same author

Aloe vera barbadensis extract regenerator with metabolic regulatory functions promotes skin regeneration and reduces fibrosis deposition in diabetic burn model pigs.

Burns : journal of the International Society for Burn Injuries·2026
Same author

TAFNet: Trusted Multiview Associative Fusion Neural Networks for Analyzing Dynamic Brain Networks.

IEEE transactions on neural networks and learning systems·2026

Related Experiment Video

Updated: Jul 16, 2025

Nasal Brushing Sampling and Processing Using Digital High Speed Ciliary Videomicroscopy – Adaptation for the COVID-19 Pandemic
09:03

Nasal Brushing Sampling and Processing Using Digital High Speed Ciliary Videomicroscopy – Adaptation for the COVID-19 Pandemic

Published on: November 7, 2020

4.9K

Dual-stream EfficientNet with adversarial sample augmentation for COVID-19 computer aided diagnosis.

Weijie Xu1, Lina Nie1, Beijing Chen2

  • 1Engineering Research Center of Digital Forensics, Ministry of Education, Nanjing University of Information Science and Technology, Nanjing, 210044, China.

Computers in Biology and Medicine
|September 11, 2023
PubMed
Summary

This study introduces an advanced dual-stream network for diagnosing coronavirus disease (COVID-19) using CT scans. The novel approach significantly improves diagnostic accuracy, addressing limitations of current deep learning methods.

Keywords:
Adversarial propagationCOVID-19CT scanEfficientNetFeature pyramid network

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

14.2K
Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

440

Related Experiment Videos

Last Updated: Jul 16, 2025

Nasal Brushing Sampling and Processing Using Digital High Speed Ciliary Videomicroscopy – Adaptation for the COVID-19 Pandemic
09:03

Nasal Brushing Sampling and Processing Using Digital High Speed Ciliary Videomicroscopy – Adaptation for the COVID-19 Pandemic

Published on: November 7, 2020

4.9K
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

14.2K
Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

440

Area of Science:

  • Medical Imaging
  • Artificial Intelligence
  • Computer-Aided Diagnosis

Background:

  • Current computer-aided methods for diagnosing COVID-19, including deep learning, often lack sufficient accuracy.
  • Key limitations include a focus on model architecture over image data and challenges with small datasets for deep learning training.

Purpose of the Study:

  • To develop a more accurate deep learning model for COVID-19 diagnosis from CT scans.
  • To address data scarcity and overfitting issues in deep learning models for medical image analysis.

Main Methods:

  • A dual-stream network leveraging EfficientNet architecture was proposed.
  • The network integrates spatial and frequency domain information from CT scans.
  • Adversarial Propagation (AdvProp) and Feature Pyramid Network (FPN) were employed for enhanced training and feature fusion.

Main Results:

  • The proposed dual-stream network demonstrated superior performance compared to 12 existing deep learning methods on the COVIDx CT-2A dataset.
  • Achieved high accuracy: 0.9870 for multi-class classification and 0.9958 for binary classification of COVID-19.

Conclusions:

  • The developed dual-stream network offers a highly accurate and effective approach for COVID-19 diagnosis using CT imaging.
  • The method successfully overcomes common challenges in deep learning for medical diagnosis, particularly data limitations and overfitting.