Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

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

The integrity of the Circle of Willis predicted hemodynamic changes after bypass surgery in Moyamoya disease: a prospective cohort study by 4D flow MRI.

AJNR. American journal of neuroradiology·2026

Same author

Systemic Inflammatory Markers and Intracranial Atherosclerosis: Road to Nowhere? A Meta-analysis.

Neuroepidemiology·2026

Same author

Territorial heterogeneity of atherosclerosis and vascular calcification.

Nature cardiovascular research·2026

Same author

Radiomic Carotid Plaque Features Integrated into Machine Learning Models for Cardiovascular Risk Prediction.

Ultrasound in medicine & biology·2026

Same author

Impact of Attenuation Threshold Selection on the Quantification of Carotid Calcification on CTA.

AJNR. American journal of neuroradiology·2026

Same author

Integrating cardiac CT into the diagnostic pathway of Takotsubo syndrome: current evidence and future directions.

European journal of radiology·2026

Search research articles

Related Experiment Video

Updated: Aug 28, 2025

Lung CT Segmentation to Identify Consolidations and Ground Glass Areas for Quantitative Assesment of SARS-CoV Pneumonia

Lung CT Segmentation to Identify Consolidations and Ground Glass Areas for Quantitative Assesment of SARS-CoV Pneumonia

Published on: December 19, 2020

Segmentation-Based Classification Deep Learning Model Embedded with Explainable AI for COVID-19 Detection in Chest

Nillmani¹, Neeraj Sharma¹, Luca Saba²

¹School of Biomedical Engineering, Indian Institute of Technology (BHU), Varanasi 221005, India.

Diagnostics (Basel, Switzerland)

|September 23, 2022

Summary

A new deep learning system for COVID-19 detection using chest X-rays achieved high accuracy. This segmentation-based classification approach shows promise for clinical use with an error rate below 5%.

Keywords:

COVID-19 UNet Xception chest X-ray classification deep learning error rate precision regulatory segmentation

More Related Videos

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Published on: November 11, 2022

Related Experiment Videos

Last Updated: Aug 28, 2025

Lung CT Segmentation to Identify Consolidations and Ground Glass Areas for Quantitative Assesment of SARS-CoV Pneumonia

Lung CT Segmentation to Identify Consolidations and Ground Glass Areas for Quantitative Assesment of SARS-CoV Pneumonia

Published on: December 19, 2020

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Published on: November 11, 2022

Area of Science:

Medical Imaging
Artificial Intelligence
Deep Learning

Background:

Current COVID-19 detection methods using chest X-rays have high error rates, limiting clinical application.
Accurate and rapid COVID-19 diagnosis is crucial for patient management and public health.

Purpose of the Study:

To develop and evaluate deep learning models for accurate COVID-19 detection in chest X-rays.
To achieve a segmentation-based classification error rate below 5% for clinical adaptability.

Main Methods:

Proposed 16 segmentation-based classification deep learning systems combining UNet/UNet+ with 8 classification models.
Evaluated performance using Dice, Jaccard, AUC, ROC, and Grad-CAM for explainability.

Main Results:

The UNet segmentation model achieved 96.35% accuracy, 94.88% Dice, and 90.38% Jaccard index.
The UNet+Xception model demonstrated superior performance with 97.45% accuracy and 0.998 AUC.
The proposed system outperformed existing methods by an average of 8.27%.

Conclusions:

Segmentation-based classification deep learning models are effective for COVID-19 detection.
The developed system meets the <5% error rate threshold, making it suitable for clinical settings.