Sparsier2Sparse: Weakly-supervised learning for streak artifact reduction with unpaired sparse-view CT data

Seongjun Kim, Byeongjoon Kim, Jongduk Baek

Research output: Chapter in Book/Report/Conference proceedingConference contribution

2 Citations (Scopus)

Abstract

Sparse-view computed tomography (CT) becomes a major concern in the medical imaging field due to its reduced X-ray radiation dose. Recently, various convolutional neural network (CNN)-based approaches have been proposed, requiring the pairs of full and sparse-view CT images for network training. However, these paired data acquisition is impractical or difficult in clinical practice. To handle this problem, we propose the weakly-supervised learning for streak artifact reduction with unpaired sparse-view CT data. For CNN training dataset, we generate the pairs of input and target images from the given sparse-view CT data. Then, we iteratively apply the trained network to given sparse-view CT images and acquire the prior images. As the success factor of our novel framework, we estimate the original streak artifacts in the given sparse-view CT images from the prior images and subtract the estimated streak artifacts from the given sparse-view CT images. As a result, the proposed method has the best performance of lesion detection compared to the other methods.

Original languageEnglish
Title of host publication7th International Conference on Image Formation in X-Ray Computed Tomography
EditorsJoseph Webster Stayman
PublisherSPIE
ISBN (Electronic)9781510656697
DOIs
Publication statusPublished - 2022
Event7th International Conference on Image Formation in X-Ray Computed Tomography - Virtual, Online
Duration: 2022 Jun 122022 Jun 16

Publication series

NameProceedings of SPIE - The International Society for Optical Engineering
Volume12304
ISSN (Print)0277-786X
ISSN (Electronic)1996-756X

Conference

Conference7th International Conference on Image Formation in X-Ray Computed Tomography
CityVirtual, Online
Period22/6/1222/6/16

Bibliographical note

Publisher Copyright:
© 2022 SPIE.

All Science Journal Classification (ASJC) codes

  • Electronic, Optical and Magnetic Materials
  • Condensed Matter Physics
  • Computer Science Applications
  • Applied Mathematics
  • Electrical and Electronic Engineering

Fingerprint

Dive into the research topics of 'Sparsier2Sparse: Weakly-supervised learning for streak artifact reduction with unpaired sparse-view CT data'. Together they form a unique fingerprint.

Cite this