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: Nov 8, 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

153

Optimal hyperparameter selection of deep learning models for COVID-19 chest X-ray classification.

Adeyinka P Adedigba1, Steve A Adeshina2, Oluwatomisin E Aina2

  • 1Department of Mechatronics Engineering, Federal University of Technology, Minna, Nigeria.

Intelligence-Based Medicine
|April 26, 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

Bag of Tricks for Improving Deep Learning Performance on Multimodal Image Classification.

Bioengineering (Basel, Switzerland)·2022
Same author

Performance Evaluation of Deep Learning Models on Mammogram Classification Using Small Dataset.

Bioengineering (Basel, Switzerland)·2022
Same author

Automatic learning sparse correspondences for initialising groupwise registration.

Medical image computing and computer-assisted intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted Intervention·2010
Same journal

Diffusion models vs. DCGANs for class-imbalanced lung cancer CT classification: A comparative study.

Intelligence-based medicine·2026
Same journal

Physician documentation matters. Using natural language processing to predict mortality in sepsis.

Intelligence-based medicine·2025
Same journal

Estimating the prevalence of diabetic retinopathy in electronic health records with massive missing labels.

Intelligence-based medicine·2024
Same journal

Automatic generation of operation notes in endoscopic pituitary surgery videos using workflow recognition.

Intelligence-based medicine·2024
Same journal

Integrating unsupervised and supervised learning techniques to predict traumatic brain injury: A population-based study.

Intelligence-based medicine·2024
Same journal

Machine learning-based prediction of low-value care for hospitalized patients.

Intelligence-based medicine·2023
See all related articles

This study introduces a novel deep learning technique for diagnosing COVID-19 from chest X-rays (CXRs), overcoming data limitations. The model achieved high accuracy, aiding rapid screening of coronavirus disease.

Area of Science:

  • Medical Imaging
  • Artificial Intelligence
  • Computational Biology

Background:

  • Current COVID-19 testing methods face challenges with speed and supply shortages.
  • Diagnosing COVID-19 from chest X-rays (CXRs) is crucial but hindered by limited datasets and class imbalance in deep learning models.

Purpose of the Study:

  • To develop and validate a deep learning approach for accurate COVID-19 diagnosis using CXR images.
  • To address challenges of small datasets and class imbalance in training deep models for medical image analysis.

Main Methods:

  • Utilized discriminative fine-tuning with cyclical learning rates for dynamic layer-wise training.
  • Implemented memory- and computationally-efficient mixed-precision training to manage high computational demands.
  • Employed advanced deep learning techniques to train models on limited chest X-ray datasets.
Keywords:
COVID-19Chest X-rayComputer-aided diagnosisCyclical learning rateDeep convolutional neural network (CNN)Discriminative fine-tuningHyperparameter optimisationMemory and computation efficientMixed-precision trainingOverfitting

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

14.4K

Related Experiment Videos

Last Updated: Nov 8, 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

153
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

Main Results:

  • Achieved high validation accuracy (96.83%), sensitivity (96.26%), and specificity (95.54%).
  • Demonstrated excellent generalisation, reaching 97% accuracy on an unseen dataset without retraining.
  • Visual interpretation confirmed the model's utility in assisting radiologists with rapid COVID-19 symptom screening.

Conclusions:

  • The proposed deep learning method effectively diagnoses COVID-19 from CXRs, even with limited data.
  • This approach offers a viable solution to supplement existing diagnostic tools, improving screening efficiency.
  • The model shows potential to aid radiologists in the rapid identification of COVID-19 symptoms.