EUVIMEDOpdag EUVIMED
Open access · CC BY 4.0

Sinogram Inpainting with Generative Adversarial Networks and Shape Priors

Emilien Valat iD, Katayoun Farrahi iD, Thomas Blumensath

Tomography · 2023-06-13 · 9 (3) · 1137-1152

DOI: 10.3390/tomography9030094 ↗

At a glance

Journal article in Tomography, published online on 2023-06-13. Written by Emilien Valat and 2 co-authors. Institution: Cambridge Image Analysis Group, Department of Applied Mathematics and Theoretical Physics, Centre for Mathematical Sciences, University of Cambridge,…. Major MEDLINE topics: Tomography, X-Ray Computed, Image Processing, Computer-Assisted. Cited 16 times so far (Crossref); 45 references. The full text is freely available (open access, CC BY 4.0). Funded by: Anglo-French DSTL-AID Joint-PhD program.

AbstractSubjectsBibliografiske oplysningerCiteRelated studies

Abstract (original language)

X-ray computed tomography is a widely used, non-destructive imaging technique that computes cross-sectional images of an object from a set of X-ray absorption profiles (the so-called sinogram). The computation of the image from the sinogram is an ill-posed inverse problem, which becomes underdetermined when we are only able to collect insufficiently many X-ray measurements. We are here interested in solving X-ray tomography image reconstruction problems where we are unable to scan the object from all directions, but where we have prior information about the object’s shape. We thus propose a method that reduces image artefacts due to limited tomographic measurements by inferring missing measurements using shape priors. Our method uses a Generative Adversarial Network that combines limited acquisition data and shape information. While most existing methods focus on evenly spaced missing scanning angles, we propose an approach that infers a substantial number of consecutive missing acquisitions. We show that our method consistently improves image quality compared to images reconstructed using the previous state-of-the-art sinogram-inpainting techniques. In particular, we demonstrate a 7 dB Peak Signal-to-Noise Ratio improvement compared to other methods.

Subjects

MeSH terms (MEDLINE)

Tomography, X-Ray ComputedImage Processing, Computer-AssistedSignal-To-Noise RatioArtifacts

Author keywords

Generative Adversarial NetworkX-ray computed tomographycomputer assisted design datamachine-learning

Authors and institutions

  • Cambridge Image Analysis Group, Department of Applied Mathematics and Theoretical Physics, Centre for Mathematical Sciences, University of Cambridge, Wilberforce Rd., Cambridge CB3 0WA, UK.
  • Vision, Learning and Control Group, Department of Electronics and Computer Science, University of Southampton, University Rd., Southampton SO17 1BJ, UK.
  • Institute of Sound and Vibration Research, Department of Engineering and the Environment, University of Southampton, University Rd., Southampton SO17 1BJ, UK.

ORCID profiles: Emilien Valat, Katayoun Farrahi

Funding

  • Anglo-French DSTL-AID Joint-PhD program

Cite

APA

Valat, E., Farrahi, K., & Blumensath, T. (2023). Sinogram Inpainting with Generative Adversarial Networks and Shape Priors. Tomography, 9(3), 1137-1152. https://doi.org/10.3390/tomography9030094

Vancouver

Valat E, Farrahi K, Blumensath T. Sinogram Inpainting with Generative Adversarial Networks and Shape Priors. Tomography. 2023;9(3):1137-1152. doi:10.3390/tomography9030094

BibTeX
@article{Valat2023,
  author = {Valat, Emilien and Farrahi, Katayoun and Blumensath, Thomas},
  title = {Sinogram Inpainting with Generative Adversarial Networks and Shape Priors},
  journal = {Tomography},
  year = {2023},
  volume = {9},
  number = {3},
  pages = {1137--1152},
  doi = {10.3390/tomography9030094}
}
Start for free →