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 Videos

X-ray spectral reconstruction from attenuation data using neural networks.

J M Boone1

  • 1Department of Radiology, Thomas Jefferson University, Philadelphia, Pennsylvania 19107.

Medical Physics
|July 1, 1990
PubMed
Summary
This summary is machine-generated.

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

GEANT4 Monte Carlo simulations for virtual clinical trials in breast X-ray imaging: Proof of concept.

Physica medica : PM : an international journal devoted to the applications of physics to medicine and biology : official journal of the Italian Association of Biomedical Physics (AIFB)·2020
Same author

Cone-beam CT dose and imaging performance evaluation with a modular, multipurpose phantom.

Medical physics·2019
Same author

Evaluation of the BreastSimulator software platform for breast tomography.

Physics in medicine and biology·2017
Same author

Spectrum of bone marrow morphologic findings in hepatitis C patients with and without prior liver transplantation.

International journal of laboratory hematology·2016
Same author

Radiological Protection in Cone Beam Computed Tomography (CBCT). ICRP Publication 129.

Annals of the ICRP·2015
Same author

Simulated lesion, human observer performance comparison between thin-section dedicated breast CT images versus computed thick-section simulated projection images of the breast.

Physics in medicine and biology·2015
Same journal

Correction to "On the shape of the radiation survival curve in tumor spheroids: The role of oxygen heterogeneity".

Medical physics·2026
Same journal

Multi-view constrained semi-supervised vertebra detection for 3D ultrasound spine volume.

Medical physics·2026
Same journal

Accuracy of quantitative <sup>177</sup>Lu SPECT/CT imaging: A systematic review.

Medical physics·2026
Same journal

Physics-constrained dual-domain network for CBCT reconstruction from orthogonal X-rays in gynecologic radiotherapy.

Medical physics·2026
Same journal

Decomposition-based harmonization for quantitative PET imaging across scanners and radiotracers.

Medical physics·2026
Same journal

Development and evaluation of an in vivo dose-based monitoring system for electron FLASH radiation therapy.

Medical physics·2026
See all related articles

Artificial neural networks can accurately reconstruct X-ray spectral profiles from attenuation data. This method enables precise calculation of absolute X-ray spectra, crucial for radiation physics and medical imaging applications.

Area of Science:

  • Medical Physics
  • Computational Physics
  • Artificial Intelligence

Background:

  • X-ray spectral data is essential for accurate radiation dosimetry and imaging.
  • Reconstructing X-ray spectra from attenuation measurements is challenging due to the non-unique nature of the inverse problem.
  • Artificial neural networks (ANNs) offer a potential solution for complex data inversion tasks.

Purpose of the Study:

  • To develop and validate an ANN model for reconstructing X-ray spectral profiles from attenuation data.
  • To assess the accuracy of the ANN in predicting absolute X-ray spectra.
  • To investigate the impact of noise and network parameters on spectral reconstruction fidelity.

Main Methods:

  • Training ANNs on mathematically generated X-ray spectra (Birch-Marshall model) and corresponding attenuation data.

Related Experiment Videos

  • Calculating attenuation data via numerical integration from simulated X-ray spectra.
  • Testing the trained networks on unseen kV/filtration combinations and simulated noisy attenuation data.
  • Validating the model using experimentally determined spectral data.

    • Main Results:

    • ANNs were successfully trained to reconstruct relative spectral profiles from attenuation data.
    • The reconstruction of absolute spectra from the generated profiles proved accurate.
    • The model demonstrated excellent performance on test datasets, including those with noise.
    • Network architecture and data averaging influenced noise propagation.

    Conclusions:

    • ANNs provide a robust and accurate method for reconstructing X-ray spectra from attenuation measurements.
    • This approach facilitates the calculation of absolute X-ray spectra, enhancing applications in radiation physics and medical imaging.
    • The developed method is effective even with noisy input data and for un-trained X-ray beam qualities.