Jove
Visualize
Contact Us

Related Experiment Video

Updated: May 30, 2026

A Method for 3D Reconstruction and Virtual Reality Analysis of Glial and Neuronal Cells
12:49

A Method for 3D Reconstruction and Virtual Reality Analysis of Glial and Neuronal Cells

Published on: September 28, 2019

Neural network algorithm for image reconstruction using the "grid-friendly" projections.

Robert Cierniak1

  • 1Department of Computer Engineering, Czestochowa University of Technology, Armii Krajowej Avenue 36, 42-200 Częstochowa, Poland. cierniak@kik.pcz.czest.pl

Australasian Physical & Engineering Sciences in Medicine
|August 5, 2011
PubMed
Summary

This study introduces a novel recurrent neural network for image reconstruction, reducing projection requirements using discrete Radon transform concepts. The new method enhances reconstructed image quality compared to traditional techniques.

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

Comparison of algebraic and analytical approaches to the formulation of the statistical model-based reconstruction problem for X-ray computed tomography.

Computerized medical imaging and graphics : the official journal of the Computerized Medical Imaging Society·2016
Same author

A 2D approach to tomographic image reconstruction using a Hopfield-type neural network.

Artificial intelligence in medicine·2008
See all related articles
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

Area of Science:

  • Medical Imaging
  • Computer Vision
  • Artificial Intelligence

Background:

  • Image reconstruction is crucial in medical imaging, often requiring numerous projections.
  • Conventional methods can be computationally intensive and may yield suboptimal image quality.
  • Developing efficient and accurate reconstruction algorithms is an ongoing challenge.

Purpose of the Study:

  • To develop an original approach for image reconstruction using recurrent neural networks.
  • To decrease the number of projections required by selecting "grid-friendly" angles based on the discrete Radon transform (DRT).
  • To adapt the reconstruction algorithm for practical discrete fan beam projections.

Main Methods:

  • Utilizing a recurrent neural network for the reconstruction problem.

More Related Videos

Large-scale Reconstructions and Independent, Unbiased Clustering Based on Morphological Metrics to Classify Neurons in Selective Populations
12:27

Large-scale Reconstructions and Independent, Unbiased Clustering Based on Morphological Metrics to Classify Neurons in Selective Populations

Published on: February 15, 2017

Related Experiment Videos

Last Updated: May 30, 2026

A Method for 3D Reconstruction and Virtual Reality Analysis of Glial and Neuronal Cells
12:49

A Method for 3D Reconstruction and Virtual Reality Analysis of Glial and Neuronal Cells

Published on: September 28, 2019

Large-scale Reconstructions and Independent, Unbiased Clustering Based on Morphological Metrics to Classify Neurons in Selective Populations
12:27

Large-scale Reconstructions and Independent, Unbiased Clustering Based on Morphological Metrics to Classify Neurons in Selective Populations

Published on: February 15, 2017

  • Selecting projection angles based on discrete Radon transform (DRT) principles.
  • Reformulating the reconstruction as an optimization problem solved via maximum likelihood methodology.
  • Adapting the algorithm for discrete fan beam projections.

    • Main Results:

    • The proposed neural network approach successfully reduces the number of required projections.
    • The algorithm demonstrates improved reconstructed image quality compared to conventional methods.
    • Computer simulations validate the effectiveness of the neural network reconstruction algorithm.

    Conclusions:

    • The developed recurrent neural network approach offers an effective solution for image reconstruction.
    • The method enhances image quality and reduces computational demands in medical imaging.
    • This work provides a foundation for more advanced neural network-based reconstruction techniques.