EUVIMEDSkopri EUVIMED
Open access

Neural network guided sinogram‐domain iterative algorithm for artifact reduction

Gengsheng L Zeng

Medical Physics · 2023

DOI: 10.1002/mp.16546 ↗

At a glance

Journal article in Medical Physics, 2023. Written by Gengsheng L Zeng. Institution: Department of Computer Science, Utah Valley University, Salt Lake City, Utah, USA. Major MEDLINE topics: Artifacts, Image Processing, Computer-Assisted. Cited 1 times so far (Crossref); 15 references. The full text is freely available in PubMed Central. Funded by: NIBIB NIH HHS.

AstrattSubjectsDettalji biblijografiċiCiteRelated studies

Abstract (original language)

Background

Artifact reduction or removal is a challenging task when the artifact creation physics are not well modeled mathematically. One of such situations is metal artifacts in x‐ray CT when the metallic material is unknown, and the x‐ray spectrum is wide.

Purpose

A neural network is used to act as the objective function for iterative artifact reduction when the artifact model is unknown.

Methods

A hypothetical unpredictable projection data distortion model is used to illustrate the proposed approach. The model is unpredictable, because it is controlled by a random variable. A convolutional neural network is trained to recognize the artifacts. The trained network is then used to compute the objective function for an iterative algorithm, which tries to reduce the artifacts in a computed tomography (CT) task. The objective function is evaluated in the image domain. The iterative algorithm for artifact reduction is in the projection domain. A gradient descent algorithm is used for the objective function optimization. The associated gradient is calculated with the chain rule.

Results

The learning curves illustrate the decreasing treads of the objective function as the number of iterations increases. The images after the iterative treatment show the reduction of artifacts. A quantitative metric, the Sum Square Difference (SSD), also indicates the effectiveness of the proposed method.

Conclusion

The methodology of using a neural network as an objective function has potential value for situations where a human developed model is difficult to describe the underlying physics. Real‐world applications are expected to be benefit from this methodology.

Subjects

MeSH terms (MEDLINE)

ArtifactsImage Processing, Computer-AssistedHumansMetalsNeural Networks, ComputerAlgorithmsPhantoms, Imaging

Author keywords

artifactscomputed tomographyimage reconstructioniterative algorithmsneural network

Substances

Metals

Authors and institutions

  • Department of Computer Science, Utah Valley University, Salt Lake City, Utah, USA.
  • Department of Radiology and Imaging Sciences, University of Utah, Salt Lake City, Utah, USA.

Funding

  • NIBIB NIH HHS

Cite

APA

Zeng, G. L. (2023). Neural network guided sinogram‐domain iterative algorithm for artifact reduction. Medical Physics. https://doi.org/10.1002/mp.16546

Vancouver

Zeng GL. Neural network guided sinogram‐domain iterative algorithm for artifact reduction. Medical Physics. 2023. doi:10.1002/mp.16546

BibTeX
@article{Zeng2023,
  author = {Zeng, Gengsheng L},
  title = {Neural network guided sinogram‐domain iterative algorithm for artifact reduction},
  journal = {Medical Physics},
  year = {2023},
  doi = {10.1002/mp.16546}
}
Start for free →