EUVIMEDObjevte EUVIMED
Crossref

Sparsier2Sparse: Self‐supervised convolutional neural network‐based streak artifacts reduction in sparse‐view CT images

Seongjun Kim, Byeongjoon Kim, Jooho Lee, Jongduk Baek

Medical Physics · 2023

DOI: 10.1002/mp.16552 ↗

At a glance

Journal article in Medical Physics, 2023. Written by Seongjun Kim and 3 co-authors. Institution: School of Integrated Technology, Yonsei University, Incheon, South Korea. Major MEDLINE topics: Image Processing, Computer-Assisted, Artifacts. Cited 10 times so far (Crossref); 48 references. Funded by: Ministry of Science and ICT, South Korea, Institute for Information and Communications Technology Promotion.

AbstraktSubjectsBibliografické údajeCiteRelated studies

Abstract (original language)

Background

Sparse‐view computed tomography (CT) has attracted a lot of attention for reducing both scanning time and radiation dose. However, sparsely‐sampled projection data generate severe streak artifacts in the reconstructed images. In recent decades, many sparse‐view CT reconstruction techniques based on fully‐supervised learning have been proposed and have shown promising results. However, it is not feasible to acquire pairs of full‐view and sparse‐view CT images in real clinical practice.

Purpose

In this study, we propose a novel self‐supervised convolutional neural network (CNN) method to reduce streak artifacts in sparse‐view CT images.

Methods

We generate the training dataset using only sparse‐view CT data and train CNN based on self‐supervised learning. Since the streak artifacts can be estimated using prior images under the same CT geometry system, we acquire prior images by iteratively applying the trained network to given sparse‐view CT images. We then subtract the estimated steak artifacts from given sparse‐view CT images to produce the final results.

Results

We validated the imaging performance of the proposed method using extended cardiac‐torso (XCAT) and the 2016 AAPM Low‐Dose CT Grand Challenge dataset from Mayo Clinic. From the results of visual inspection and modulation transfer function (MTF), the proposed method preserved the anatomical structures effectively and showed higher image resolution compared to the various streak artifacts reduction methods for all projection views.

Conclusions

We propose a new framework for streak artifacts reduction when only the sparse‐view CT data are given. Although we do not use any information of full‐view CT data for CNN training, the proposed method achieved the highest performance in preserving fine details. By overcoming the limitation of dataset requirements on fully‐supervised‐based methods, we expect that our framework can be utilized in the medical imaging field.

Subjects

MeSH terms (MEDLINE)

Image Processing, Computer-AssistedArtifactsNeural Networks, ComputerTomography, X-Ray ComputedRadionuclide ImagingAlgorithmsPhantoms, Imaging

Author keywords

computed tomographyconvolutional neural networkself-supervised learningsparse-view CT

Authors and institutions

  • School of Integrated Technology, Yonsei University, Incheon, South Korea.
  • Department of Artificial Intelligence, College of Computing, Yonsei University, Seoul, South Korea.
  • Bareunex Imaging, Inc., Seoul, South Korea.

Funding

  • Ministry of Science and ICT, South Korea
  • Institute for Information and Communications Technology Promotion

Cite

APA

Kim, S., Kim, B., Lee, J., & Baek, J. (2023). Sparsier2Sparse: Self‐supervised convolutional neural network‐based streak artifacts reduction in sparse‐view CT images. Medical Physics. https://doi.org/10.1002/mp.16552

Vancouver

Kim S, Kim B, Lee J, Baek J. Sparsier2Sparse: Self‐supervised convolutional neural network‐based streak artifacts reduction in sparse‐view CT images. Medical Physics. 2023. doi:10.1002/mp.16552

BibTeX
@article{Kim2023,
  author = {Kim, Seongjun and Kim, Byeongjoon and Lee, Jooho and Baek, Jongduk},
  title = {Sparsier2Sparse: Self‐supervised convolutional neural network‐based streak artifacts reduction in sparse‐view CT images},
  journal = {Medical Physics},
  year = {2023},
  doi = {10.1002/mp.16552}
}
Start for free →