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

Efficacy of Prophylactic Tranexamic Acid in Preventing Postpartum Hemorrhage after Vaginal Delivery: Evidence from a Randomized Controlled Study.

Annals of African medicine·2026
Same author

Does Age Have a Role in Color and Whiteness Variations After Dehydration and Rehydration in Maxillary Anterior Teeth? An In Vivo Study.

Operative dentistry·2022
Same author

Familial Leukodermic Darier Disease with Faun Tail Nevus in a Female Child - An Uncommmon Coexistence.

Indian dermatology online journal·2021
Same author

Evaluation of Clinical Significance of Dermoscopy in Alopecia Areata.

Indian journal of dermatology·2016
Same author

Dentigerous Cysts of Maxillofacial Region- Clinical, Radiographic and Biochemical Analysis.

Kathmandu University medical journal (KUMJ)·2015
Same author

Dental prosthetic status and prosthetic needs of the institutionalized elderly living in geriatric homes in Hyderabad: a pilot study.

The journal of contemporary dental practice·2014

Related Experiment Video

Updated: Aug 10, 2025

Author Spotlight: Demonstrating Systematic Endobronchial Ultrasound to New Endoscopists
05:22

Author Spotlight: Demonstrating Systematic Endobronchial Ultrasound to New Endoscopists

Published on: August 11, 2023

2.1K

An optimized EBRSA-Bi LSTM model for highly undersampled rapid CT image reconstruction.

A V P Sarvari1, K Sridevi1

  • 1Department of Electronics and Communication Engineering, GITAM Deemed to be University, Andhra Pradesh 530045, India.

Biomedical Signal Processing and Control
|February 13, 2023
PubMed
Summary

This study introduces a novel deep learning model for faster and more accurate COVID-19 chest CT image reconstruction from under-sampled data. The enhanced battle royale self-attention based bi-directional long short-term model achieves high reconstruction accuracy, improving diagnostic capabilities.

Keywords:
Computed tomography (CT)Deep learningImage reconstructionK-space dataUnder-sampling

More Related Videos

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

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

Published on: November 30, 2022

2.9K
Author Spotlight: Optimized Lung MRI Protocol with Computationally Efficient Reconstruction Methods
05:07

Author Spotlight: Optimized Lung MRI Protocol with Computationally Efficient Reconstruction Methods

Published on: September 6, 2024

443

Related Experiment Videos

Last Updated: Aug 10, 2025

Author Spotlight: Demonstrating Systematic Endobronchial Ultrasound to New Endoscopists
05:22

Author Spotlight: Demonstrating Systematic Endobronchial Ultrasound to New Endoscopists

Published on: August 11, 2023

2.1K
Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

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

Published on: November 30, 2022

2.9K
Author Spotlight: Optimized Lung MRI Protocol with Computationally Efficient Reconstruction Methods
05:07

Author Spotlight: Optimized Lung MRI Protocol with Computationally Efficient Reconstruction Methods

Published on: September 6, 2024

443

Area of Science:

  • Medical Imaging
  • Artificial Intelligence
  • Radiology

Background:

  • Chest computed tomography (CT) is crucial for diagnosing COVID-19.
  • Fast and accurate CT image reconstruction is essential for timely diagnosis.
  • Existing deep learning methods often focus on single domains, limiting reconstruction quality.

Purpose of the Study:

  • To propose a novel deep learning model for reconstructing under-sampled CT images.
  • To enhance the accuracy and quality of COVID-19 chest CT reconstructions.
  • To address limitations of single-domain deep learning approaches in CT reconstruction.

Main Methods:

  • Developed the enhanced battle royale self-attention based bi-directional long short-term (EBRSA-bi LSTM) model for CT image reconstruction.
  • Implemented a two-phase approach: pre-processing with an extended cascaded filter (ECF) and reconstruction using battle royale optimization (BrO).
  • Tested the model on COVID-CT- and SARS-CoV-2 CT datasets.

Main Results:

  • Achieved high reconstruction accuracy: 93.5% on COVID-CT- and 97.7% on SARS-CoV-2 CT datasets.
  • Demonstrated excellent image quality with PSNR (45-46 dB), low RMSE (0.0022-0.0026), and high SSIM (0.992-0.996).
  • The ECF effectively suppressed noise and improved reconstruction accuracy.

Conclusions:

  • The proposed EBRSA-bi LSTM model significantly improves under-sampled CT image reconstruction for COVID-19.
  • The model offers a promising solution for faster and more reliable COVID-19 diagnosis using CT.
  • The combined approach of advanced pre-processing and optimized deep learning enhances diagnostic imaging quality.