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 Experiment Video

Updated: Oct 16, 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

Fine-Tuning Convolutional Neural Networks for COVID-19 Detection from Chest X-ray Images.

Wentao Zhao1,2, Wei Jiang1, Xinguo Qiu1

  • 1College of Mechanical Engineering, Zhejiang University of Technology, Hangzhou 310023, China.

Diagnostics (Basel, Switzerland)
|October 23, 2021
PubMed
Summary
This summary is machine-generated.

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

Big Transfer Learning for Fine Art Classification.

Computational intelligence and neuroscience·2022
Same author

Deep learning for COVID-19 detection based on CT images.

Scientific reports·2021
Same author

How to Represent Paintings: A Painting Classification Using Artistic Comments.

Sensors (Basel, Switzerland)·2021
Same author

Compare the performance of the models in art classification.

PloS one·2021

This study demonstrates that transfer learning with fine-tuned convolutional neural networks (CNNs) improves COVID-19 detection from chest X-rays. Pretrained models and higher resolution images enhance diagnostic accuracy for COVID-19 identification.

Area of Science:

  • Medical Imaging
  • Artificial Intelligence
  • Radiology

Background:

  • Chest X-ray (CXR) is a vital tool for diagnosing respiratory diseases.
  • COVID-19 screening relies on RT-PCR, but CXR offers a complementary approach.
  • Convolutional Neural Networks (CNNs) show promise in medical image analysis.

Purpose of the Study:

  • To investigate the effectiveness of transfer learning using CNNs for COVID-19 detection from CXR images.
  • To identify optimal CNN fine-tuning strategies for improved diagnostic performance.
  • To explore the interpretability of CNN-based COVID-19 detection.

Main Methods:

  • Extensive fine-tuning of CNN models pretrained on large, out-of-domain datasets.
  • Evaluation of image resolution and mixup techniques during training.
Keywords:
COVID-19Grad-CAMX-ray imagesconvolutional neural networktransfer learning

More Related Videos

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images
04:23

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images

Published on: April 21, 2023

2.0K
Retrospective Cardiac Gating with A Prototype Small-Animal X-ray Computed Tomograph
05:32

Retrospective Cardiac Gating with A Prototype Small-Animal X-ray Computed Tomograph

Published on: February 21, 2025

470

Related Experiment Videos

Last Updated: Oct 16, 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
A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images
04:23

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images

Published on: April 21, 2023

2.0K
Retrospective Cardiac Gating with A Prototype Small-Animal X-ray Computed Tomograph
05:32

Retrospective Cardiac Gating with A Prototype Small-Animal X-ray Computed Tomograph

Published on: February 21, 2025

470
  • Application of Gradient-weighted Class Activation Mapping (Grad-CAM) for model interpretability.

    • Main Results:

    • Models pretrained on larger datasets significantly improved CXR-based COVID-19 detection performance.
    • Higher resolution images and mixup augmentation enhanced model accuracy.
    • The proposed transfer learning approach achieved state-of-the-art results.
    • The model demonstrated robust performance even with limited downstream training data.

    Conclusions:

    • Transfer learning enhances CNN performance for COVID-19 detection from chest X-rays.
    • Model interpretability using Grad-CAM aids in understanding detection mechanisms.
    • This approach can assist radiologists in screening and potentially identify novel visual biomarkers for COVID-19.