Deep learning-based motion compensation for four-dimensional cone-beam computed tomography (4D-CBCT) reconstruction.
Date
2023-02
Journal Title
Journal ISSN
Volume Title
Repository Usage Stats
views
downloads
Citation Stats
Abstract
Background
Motion-compensated (MoCo) reconstruction shows great promise in improving four-dimensional cone-beam computed tomography (4D-CBCT) image quality. MoCo reconstruction for a 4D-CBCT could be more accurate using motion information at the CBCT imaging time than that obtained from previous 4D-CT scans. However, such data-driven approaches are hampered by the quality of initial 4D-CBCT images used for motion modeling.Purpose
This study aims to develop a deep-learning method to generate high-quality motion models for MoCo reconstruction to improve the quality of final 4D-CBCT images.Methods
A 3D artifact-reduction convolutional neural network (CNN) was proposed to improve conventional phase-correlated Feldkamp-Davis-Kress (PCF) reconstructions by reducing undersampling-induced streaking artifacts while maintaining motion information. The CNN-generated artifact-mitigated 4D-CBCT images (CNN enhanced) were then used to build a motion model which was used by MoCo reconstruction (CNN+MoCo). The proposed procedure was evaluated using in-vivo patient datasets, an extended cardiac-torso (XCAT) phantom, and the public SPARE challenge datasets. The quality of reconstructed images for XCAT phantom and SPARE datasets was quantitatively assessed using root-mean-square-error (RMSE) and normalized cross-correlation (NCC).Results
The trained CNN effectively reduced the streaking artifacts of PCF CBCT images for all datasets. More detailed structures can be recovered using the proposed CNN+MoCo reconstruction procedure. XCAT phantom experiments showed that the accuracy of estimated motion model using CNN enhanced images was greatly improved over PCF. CNN+MoCo showed lower RMSE and higher NCC compared to PCF, CNN enhanced and conventional MoCo. For the SPARE datasets, the average (± standard deviation) RMSE in mm-1 for body region of PCF, CNN enhanced, conventional MoCo and CNN+MoCo were 0.0040 ± 0.0009, 0.0029 ± 0.0002, 0.0024 ± 0.0003 and 0.0021 ± 0.0003. Corresponding NCC were 0.84 ± 0.05, 0.91 ± 0.05, 0.91 ± 0.05 and 0.93 ± 0.04.Conclusions
CNN-based artifact reduction can substantially reduce the artifacts in the initial 4D-CBCT images. The improved images could be used to enhance the motion modeling and ultimately improve the quality of the final 4D-CBCT images reconstructed using MoCo.Type
Department
Description
Provenance
Citation
Permalink
Published Version (Please cite this version)
Publication Info
Zhang, Zhehao, Jiaming Liu, Deshan Yang, Ulugbek S Kamilov and Geoffrey D Hugo (2023). Deep learning-based motion compensation for four-dimensional cone-beam computed tomography (4D-CBCT) reconstruction. Medical physics, 50(2). pp. 808–820. 10.1002/mp.16103 Retrieved from https://hdl.handle.net/10161/26984.
This is constructed from limited available data and may be imprecise. To cite this article, please review & use the official citation provided by the journal.
Collections
Scholars@Duke
Deshan Yang
Deshan Yang is the professor of Medical Physics in the Department of Radiation Oncology, Duke University. He received his bachelor's degree in electronics engineering from Tsinghua University in 1992, a master’s degree in computer science from the Illinois Institute of Technologies in 2002, and his master’s and Ph.D. degrees in Biomedical Engineering from the University of Wisconsin-Madison in 2005. He spent two years as a postdoctoral researcher before joining Washington University in St. Louis as a faculty member. He worked as an instructor to a professor at Washington University in St. Louis between 2006 and 2021 before joining Duke University in 2021. His main research areas are medical image processing and analysis for radiation oncology applications, adaptive radiotherapy, cardiac radiosurgery, health information technologies for radiation oncology and medical physics.
Unless otherwise indicated, scholarly articles published by Duke faculty members are made available here with a CC-BY-NC (Creative Commons Attribution Non-Commercial) license, as enabled by the Duke Open Access Policy. If you wish to use the materials in ways not already permitted under CC-BY-NC, please consult the copyright owner. Other materials are made available here through the author’s grant of a non-exclusive license to make their work openly accessible.