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

Discovery of an Indole-Based p53-Y220C Reactivator with <i>In Vivo</i> Antitumor Activity via Structure-Guided Design.

Journal of medicinal chemistry·2026

Same author

Memory-augmented neural network equalizer for short-reach optical interconnects.

Optics express·2026

Same author

Vestibular Evoked Myogenic Potentials Reveal Impairments in Vestibular Nerve Pathways in Children with Attention Deficit Hyperactivity Disorder.

Audiology research·2026

Same author

Emotion regulation profiles moderate links between perceived interparental conflict, peer bullying victimization, and adolescent internet gaming disorder.

Addictive behaviors·2026

Same author

Satellite DNA-targeted CRISPR-Cas9-mediated editing enables chromosome truncation and elimination in wheat.

Plant communications·2026

Same author

[MoCA and P300 reveal cognitive decline in patients with sensory age-related hearing loss].

Lin chuang er bi yan hou tou jing wai ke za zhi = Journal of clinical otorhinolaryngology head and neck surgery·2026

Search research articles

Related Experiment Video

Updated: Oct 20, 2025

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

A multi-scale gated multi-head attention depthwise separable CNN model for recognizing COVID-19.

Geng Hong¹, Xiaoyan Chen², Jianyong Chen¹

¹Department of Electrical Information and Automation, Tianjin University of Science and Technology, Tianjin, 300222, China.

Scientific Reports

|September 11, 2021

Summary

This summary is machine-generated.

A new lightweight convolutional neural network (CNN), the multi-scale gated multi-head attention depthwise separable CNN (MGMADS-CNN), accurately detects COVID-19 from X-ray and CT images. This efficient model achieves high accuracy and rapid detection speeds for COVID-19 classification.

More Related Videos

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

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

Related Experiment Videos

Last Updated: Oct 20, 2025

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

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

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

Area of Science:

Medical Imaging
Artificial Intelligence
Computer Vision

Background:

Coronavirus disease 2019 (COVID-19) is a rapidly spreading acute respiratory illness.
Accurate and efficient diagnostic tools are crucial for managing the COVID-19 pandemic.
Existing deep learning models may be computationally intensive for rapid deployment.

Purpose of the Study:

To develop a lightweight and accurate deep learning model for COVID-19 detection using medical images.
To enhance feature extraction from X-ray and CT scans for improved COVID-19 classification.
To evaluate the performance of the proposed model against established CNN architectures.

Main Methods:

Proposed a novel lightweight model: multi-scale gated multi-head attention depthwise separable CNN (MGMADS-CNN).
Incorporated a multi-scale gated multi-head attention mechanism for effective feature extraction.
Utilized depthwise separable convolutions to reduce model size and computational cost.
Performed tenfold cross-validation on X-ray and CT datasets, comparing with LeNet-5, AlexNet, GoogLeNet, ResNet, and VGGNet-16.

Main Results:

The MGMADS-CNN model with three attention layers (MGMADS-3) achieved 96.75% accuracy on X-ray images and 98.25% on CT images.
High specificity (98.06% X-ray, 98.17% CT) and sensitivity (96.6% X-ray, 98.05% CT) were recorded.
The MGMADS-3 model is compact (43.6 MB) and offers rapid inference speeds (6.09 ms/image for X-ray, 4.23 ms/image for CT).

Conclusions:

MGMADS-3 demonstrates superior performance in detecting and classifying COVID-19 from X-ray and CT images.
The model's lightweight design and high efficiency make it suitable for rapid, accurate COVID-19 diagnosis.
This approach offers a promising solution for improving diagnostic capabilities in resource-constrained settings.