Abstract
In radiation treatment, a cone-beam computed tomography (CBCT) scan is conducted for precise positioning of tumors, and the image quality is usually degraded by motion artifacts due to patient’s respiration and movement during scanning. Four-dimensional (4D) CBCT reconstruction with phase binning is typically used to overcome these difficulties. Albeit motion artifacts might be reduced with 4D CBCT, the overall image quality is typically worsened by severe streak artifacts due to the sparse-angle projections available in the 3D reconstruction for each motion phase. This study presents a method for reducing streak artifacts effectively in conventional 4D CBCT reconstruction by using a state-of-the-art convolutional neural network (a residual U-Net was used). We performed a computational simulation and an experiment to investigate the image quality and evaluate the effectiveness of the proposed method. The proposed 4D CBCT reconstruction method reduced streak artifacts noticeably, and its effectiveness was validated by comparing its results to those of other reconstruction methods such as the filtered-backprojection, a compressed-sensing, and a simple CNN-based algorithm for the 4D CBCT datasets.
Similar content being viewed by others
References
D. Jaffray, J. Siewerdsen, J. Wong and A. Martinez, Int. J. Radiat. Oncol. Biol. Phys. 53, 1337 (2002).
International Electrotechnical Commission, Geneva: IEC, 61217, 2008.
P. Keall, Semi. Radiat. Oncol. 14, 81 (2004).
E. Y. Sidky and X. Pan, Phys. Med. Biol. 53, 4777 (2008).
J. Ye, Y. Han and E. Cha, SIAM J. Imaging Sci. 11, 991 (2018).
O. Ronneberger, P. Fischer and T. Brox, in Medical Image Computing and Computer-Assisted Intervention -MICCAI 2015 (2015) Vol. 9351, p. 234.
L. Zijp, J. Sonke and M. Herk, ICCR 14, 507 (2004).
H. Yan et al., Phys. Med. Biol. 58, 1447 (2013).
K. Jin, M. McCann, E. Froustey and M. Unser, IEEE Trans. Image Proc. 26, 4509 (2017).
Y. Han and J. Ye, IEEE Trans. Med. Imaging 37, 1418 (2018).
K. Zhang et al., IEEE Trans. Image Proc. 26, 3142 (2017).
W. Segars et al., Med. Phys. 37, 4902 (2010).
D. Kingma and J. Ba, in 3rd International Conference for Learning Representations (ICLR), arXiv:1412.6980 (2014).
Z. Wang and A. Bovik, IEEE Signal. Proc. Lett. 9, 81 (2002).
Z. Wang, A. Bovik, H. Sheikh and E. Simoncelli, IEEE Trans. Image Proc. 13, 600 (2004).
Acknowledgments
This study was supported by the Basic Science Research Program through the National Research Foundation of Korea (NRF) funded by the Korea Ministry of Science and ICT (NRF-2017R1A2B2002891).
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Lee, D., Kim, K., Kim, W. et al. Four-Dimensional CBCT Reconstruction Based on a Residual Convolutional Neural Network for Improving Image Quality. J. Korean Phys. Soc. 75, 73–79 (2019). https://doi.org/10.3938/jkps.75.73
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.3938/jkps.75.73