X-ray spectral reconstruction from attenuation data using neural networks

Research output: Contribution to journalArticle

18 Citations (Scopus)

Abstract

An artifical neural network using input data derived from attenuation measurements was trained to generate spectral profiles (relative number of photons versus energy). Once the relative spectral distribution is reconstructed, absolute spectra (number of photons per unit exposure versus energy) can be calculated. A neural network was trained on spectra generated mathematically using the Birch-Marshall model, combined with attenuation data, calculated from the spectra by munerical integration. Wheras attenuation data can be calculated in a straightforward manner from the x-ray spectra, the reverse is not true. Several neural networks were successfully taught to reconstruct the spectra, given the attenuation data. The networks were tested using kV/inherent filtration combinations that were not in the training set, and the performance of the reconstruction was excellent. Noise in the attenuation data was simulated to test the effects of noise propagation in the reconstruction. The effects of network architecture and data averaging on noise propagation were investigated. Experimentally determined spectral data compiled by Fewell were also used to train a neural network, and the results of the reconstruction were also found to be excellent.

Original languageEnglish (US)
Pages (from-to)647-654
Number of pages8
JournalMedical Physics
Volume17
Issue number4
DOIs
StatePublished - 1990
Externally publishedYes

Fingerprint

Noise
X-Rays
Photons
Betula
carbosulfan

ASJC Scopus subject areas

  • Biophysics

Cite this

X-ray spectral reconstruction from attenuation data using neural networks. / Boone, John M.

In: Medical Physics, Vol. 17, No. 4, 1990, p. 647-654.

Research output: Contribution to journalArticle

@article{3336e7047303412c994c9b939813acff,
title = "X-ray spectral reconstruction from attenuation data using neural networks",
abstract = "An artifical neural network using input data derived from attenuation measurements was trained to generate spectral profiles (relative number of photons versus energy). Once the relative spectral distribution is reconstructed, absolute spectra (number of photons per unit exposure versus energy) can be calculated. A neural network was trained on spectra generated mathematically using the Birch-Marshall model, combined with attenuation data, calculated from the spectra by munerical integration. Wheras attenuation data can be calculated in a straightforward manner from the x-ray spectra, the reverse is not true. Several neural networks were successfully taught to reconstruct the spectra, given the attenuation data. The networks were tested using kV/inherent filtration combinations that were not in the training set, and the performance of the reconstruction was excellent. Noise in the attenuation data was simulated to test the effects of noise propagation in the reconstruction. The effects of network architecture and data averaging on noise propagation were investigated. Experimentally determined spectral data compiled by Fewell were also used to train a neural network, and the results of the reconstruction were also found to be excellent.",
author = "Boone, {John M}",
year = "1990",
doi = "10.1118/1.596495",
language = "English (US)",
volume = "17",
pages = "647--654",
journal = "Medical Physics",
issn = "0094-2405",
publisher = "AAPM - American Association of Physicists in Medicine",
number = "4",

}

TY - JOUR

T1 - X-ray spectral reconstruction from attenuation data using neural networks

AU - Boone, John M

PY - 1990

Y1 - 1990

N2 - An artifical neural network using input data derived from attenuation measurements was trained to generate spectral profiles (relative number of photons versus energy). Once the relative spectral distribution is reconstructed, absolute spectra (number of photons per unit exposure versus energy) can be calculated. A neural network was trained on spectra generated mathematically using the Birch-Marshall model, combined with attenuation data, calculated from the spectra by munerical integration. Wheras attenuation data can be calculated in a straightforward manner from the x-ray spectra, the reverse is not true. Several neural networks were successfully taught to reconstruct the spectra, given the attenuation data. The networks were tested using kV/inherent filtration combinations that were not in the training set, and the performance of the reconstruction was excellent. Noise in the attenuation data was simulated to test the effects of noise propagation in the reconstruction. The effects of network architecture and data averaging on noise propagation were investigated. Experimentally determined spectral data compiled by Fewell were also used to train a neural network, and the results of the reconstruction were also found to be excellent.

AB - An artifical neural network using input data derived from attenuation measurements was trained to generate spectral profiles (relative number of photons versus energy). Once the relative spectral distribution is reconstructed, absolute spectra (number of photons per unit exposure versus energy) can be calculated. A neural network was trained on spectra generated mathematically using the Birch-Marshall model, combined with attenuation data, calculated from the spectra by munerical integration. Wheras attenuation data can be calculated in a straightforward manner from the x-ray spectra, the reverse is not true. Several neural networks were successfully taught to reconstruct the spectra, given the attenuation data. The networks were tested using kV/inherent filtration combinations that were not in the training set, and the performance of the reconstruction was excellent. Noise in the attenuation data was simulated to test the effects of noise propagation in the reconstruction. The effects of network architecture and data averaging on noise propagation were investigated. Experimentally determined spectral data compiled by Fewell were also used to train a neural network, and the results of the reconstruction were also found to be excellent.

UR - http://www.scopus.com/inward/record.url?scp=0025143743&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0025143743&partnerID=8YFLogxK

U2 - 10.1118/1.596495

DO - 10.1118/1.596495

M3 - Article

C2 - 2215410

AN - SCOPUS:0025143743

VL - 17

SP - 647

EP - 654

JO - Medical Physics

JF - Medical Physics

SN - 0094-2405

IS - 4

ER -