A Physics-Motivated DNN for X-Ray CT Scatter Correction

Berk Iskender, Yoram Bresler

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

Abstract

The scattering of photons by the imaged object in X-ray computed tomography (CT) produces degradations of the reconstructions in the form of streaks, cupping, shading artifacts and decreased contrast. We describe a new physics-motivated deep-learning-based method to estimate scatter and correct for it in the acquired projection measurements. The method incorporates both an initial reconstruction and the scatter-corrupted measurements using a specific deep neural network architecture and a cost function tailored to the problem. Numerical experiments show significant improvement over a recent projection-based deep neural network method.

Original languageEnglish (US)
Title of host publicationISBI 2020 - 2020 IEEE International Symposium on Biomedical Imaging
PublisherIEEE Computer Society
Pages609-613
Number of pages5
ISBN (Electronic)9781538693308
DOIs
StatePublished - Apr 2020
Event17th IEEE International Symposium on Biomedical Imaging, ISBI 2020 - Iowa City, United States
Duration: Apr 3 2020Apr 7 2020

Publication series

NameProceedings - International Symposium on Biomedical Imaging
Volume2020-April
ISSN (Print)1945-7928
ISSN (Electronic)1945-8452

Conference

Conference17th IEEE International Symposium on Biomedical Imaging, ISBI 2020
CountryUnited States
CityIowa City
Period4/3/204/7/20

Keywords

  • CNN
  • Compton X-ray scatter
  • computed tomography (CT)
  • deep learning
  • monte carlo

ASJC Scopus subject areas

  • Biomedical Engineering
  • Radiology Nuclear Medicine and imaging

Fingerprint Dive into the research topics of 'A Physics-Motivated DNN for X-Ray CT Scatter Correction'. Together they form a unique fingerprint.

  • Cite this

    Iskender, B., & Bresler, Y. (2020). A Physics-Motivated DNN for X-Ray CT Scatter Correction. In ISBI 2020 - 2020 IEEE International Symposium on Biomedical Imaging (pp. 609-613). [9098512] (Proceedings - International Symposium on Biomedical Imaging; Vol. 2020-April). IEEE Computer Society. https://doi.org/10.1109/ISBI45749.2020.9098512