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: Jul 10, 2025

Human Fetal Blood Flow Quantification with Magnetic Resonance Imaging and Motion Compensation
06:56

Human Fetal Blood Flow Quantification with Magnetic Resonance Imaging and Motion Compensation

Published on: January 7, 2021

2.5K

Inverse radon transform with deep learning: an application in cardiac motion correction.

Haoran Chang1, Valerie Kobzarenko1, Debasis Mitra1

  • 1Department of Electrical Engineering and Computer Science, Florida Institute of Technology, Melbourne, FL 32901, United States of America.

Physics in Medicine and Biology
|November 21, 2023
PubMed
Summary

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

Physical phantom validation of clustering-initiated factorization in dynamic PET.

Medical physics·2025
Same author

Efficient discovery of frequently co-occurring mutations in a sequence database with matrix factorization.

PLoS computational biology·2025
Same author

Heavy-chain CDR3-engineered B cells facilitate in vivo evaluation of HIV-1 vaccine candidates.

Immunity·2023
Same author

Incorporating Radiomics into Machine Learning Models to Predict Outcomes of Neuroblastoma.

Journal of digital imaging·2022
Same author

Mask-Guided Convolutional Neural Network for Breast Tumor Prognostic Outcome Prediction on 3D DCE-MR Images.

Journal of digital imaging·2021
Same author

Exploration of PET and MRI radiomic features for decoding breast cancer phenotypes and prognosis.

NPJ breast cancer·2018

This study introduces a novel artificial neural network (ANN) for cardiac image reconstruction, performing inverse radon transform and motion correction simultaneously. This deep learning approach eliminates the need for hardware gating in medical imaging.

Area of Science:

  • Medical Imaging
  • Artificial Intelligence
  • Computational Science

Background:

  • Cardiac imaging often requires gating to correct for motion, adding complexity.
  • Inverse Radon Transform (IRT) is crucial for image reconstruction in tomography.
  • Artificial Neural Networks (ANNs) show potential in medical image processing.

Purpose of the Study:

  • To develop an ANN architecture for simultaneous Inverse Radon Transform (IRT) and cardiac Motion Correction (MC).
  • To enable direct cardiac image reconstruction from motion-corrupted sinograms.
  • To eliminate the need for hardware gating in cardiac imaging.

Main Methods:

  • Proposed a novel ANN architecture for joint IRT and MC.
  • Validated the ANN using simulated motion-blurred radon transforms of a heart-shaped object.
Keywords:
deep learningimaging processingmachine learningmotion correctionnuclear imagingradon transformsingle photon emission computed tomography

More Related Videos

Author Spotlight: Revolutionizing Remote Surgery with Augmented Reality and Robotics for Enhanced Precision and Accessibility
07:46

Author Spotlight: Revolutionizing Remote Surgery with Augmented Reality and Robotics for Enhanced Precision and Accessibility

Published on: August 9, 2024

749
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

295

Related Experiment Videos

Last Updated: Jul 10, 2025

Human Fetal Blood Flow Quantification with Magnetic Resonance Imaging and Motion Compensation
06:56

Human Fetal Blood Flow Quantification with Magnetic Resonance Imaging and Motion Compensation

Published on: January 7, 2021

2.5K
Author Spotlight: Revolutionizing Remote Surgery with Augmented Reality and Robotics for Enhanced Precision and Accessibility
07:46

Author Spotlight: Revolutionizing Remote Surgery with Augmented Reality and Robotics for Enhanced Precision and Accessibility

Published on: August 9, 2024

749
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

295
  • Trained and validated the ANN on human cardiac gated datasets using ECG signals.

    • Main Results:

    • Demonstrated that trained ANNs can perform motion-corrected image reconstruction directly from motion-corrupted sinograms.
    • Achieved effective cardiac motion correction using the proposed ANN.
    • Outperformed two other known ANN-based approaches in validation tests.

    Conclusions:

    • The developed ANN effectively performs simultaneous IRT and MC for cardiac imaging.
    • This deep learning method offers a viable alternative to hardware gating.
    • Paves the way for simplified and potentially more efficient cardiac image reconstruction.