EUVIMEDObjevte EUVIMED
Open access · CC BY-NC-ND 4.0

Mitigation of motion‐induced artifacts in cone beam computed tomography using deep convolutional neural networks

Mohammadreza Amirian, Javier A Montoya-Zegarra, Ivo Herzig, Peter Eggenberger Hotz, Lukas Lichtensteiger, Marco Morf, Alexander Züst, Pascal Paysan, Igor Peterlik, Stefan Scheib, Rudolf Marcel Füchslin, Thilo Stadelmann and 1 more

Medical Physics · 2023

DOI: 10.1002/mp.16405 ↗

At a glance

Journal article in Medical Physics, 2023. Written by Mohammadreza Amirian and 12 co-authors. Institution: Centre for Artificial Intelligence CAI, Zurich University of Applied Sciences ZHAW, Winterthur, Switzerland. Major MEDLINE topics: Artifacts, Image Processing, Computer-Assisted. Cited 15 times so far (Crossref); 72 references. The full text is freely available (open access, CC BY-NC-ND 4.0). Funded by: Innosuisse - Schweizerische Agentur für Innovationsförderung.

AbstraktSubjectsBibliografické údajeCiteRelated studies

Abstract (original language)

Background

Cone beam computed tomography (CBCT) is often employed on radiation therapy treatment devices (linear accelerators) used in image‐guided radiation therapy (IGRT). For each treatment session, it is necessary to obtain the image of the day in order to accurately position the patient and to enable adaptive treatment capabilities including auto‐segmentation and dose calculation. Reconstructed CBCT images often suffer from artifacts, in particular those induced by patient motion. Deep‐learning based approaches promise ways to mitigate such artifacts.

Purpose

We propose a novel deep‐learning based approach with the goal to reduce motion induced artifacts in CBCT images and improve image quality. It is based on supervised learning and includes neural network architectures employed as pre‐ and/or post‐processing steps during CBCT reconstruction.

Methods

Our approach is based on deep convolutional neural networks which complement the standard CBCT reconstruction, which is performed either with the analytical Feldkamp‐Davis‐Kress (FDK) method, or with an iterative algebraic reconstruction technique (SART‐TV). The neural networks, which are based on refined U‐net architectures, are trained end‐to‐end in a supervised learning setup. Labeled training data are obtained by means of a motion simulation, which uses the two extreme phases of 4D CT scans, their deformation vector fields, as well as time‐dependent amplitude signals as input. The trained networks are validated against ground truth using quantitative metrics, as well as by using real patient CBCT scans for a qualitative evaluation by clinical experts.

Results

The presented novel approach is able to generalize to unseen data and yields significant reductions in motion induced artifacts as well as improvements in image quality compared with existing state‐of‐the‐art CBCT reconstruction algorithms (up to +6.3 dB and +0.19 improvements in peak signal‐to‐noise ratio, PSNR, and structural similarity index measure, SSIM, respectively), as evidenced by validation with an unseen test dataset, and confirmed by a clinical evaluation on real patient scans (up to 74% preference for motion artifact reduction over standard reconstruction).

Conclusions

For the first time, it is demonstrated, also by means of clinical evaluation, that inserting deep neural networks as pre‐ and post‐processing plugins in the existing 3D CBCT reconstruction and trained end‐to‐end yield significant improvements in image quality and reduction of motion artifacts.

Subjects

MeSH terms (MEDLINE)

ArtifactsImage Processing, Computer-AssistedHumansNeural Networks, ComputerMotionAlgorithmsCone-Beam Computed TomographyFour-Dimensional Computed TomographyPhantoms, Imaging

Author keywords

cone beam computed tomographydeep learningmotion artifacts

Authors and institutions

  • Centre for Artificial Intelligence CAI, Zurich University of Applied Sciences ZHAW, Winterthur, Switzerland.
  • Institute of Neural Information Processing, Ulm University, Ulm, Germany.
  • Institute for Applied Mathematics and Physics IAMP, Zurich University of Applied Sciences ZHAW, Winterthur, Switzerland.
  • Varian Medical Systems Imaging Laboratory GmbH, Baden, Switzerland.
  • European Centre for Living Technology, Venice, Italy.

Funding

  • Innosuisse - Schweizerische Agentur für Innovationsförderung

Cite

APA

Amirian, M., Montoya-Zegarra, J. A., Herzig, I., Eggenberger Hotz, P., Lichtensteiger, L., Morf, M., Züst, A., Paysan, P., Peterlik, I., Scheib, S., Füchslin, R. M., Stadelmann, T., & Schilling, F. P. (2023). Mitigation of motion‐induced artifacts in cone beam computed tomography using deep convolutional neural networks. Medical Physics. https://doi.org/10.1002/mp.16405

Vancouver

Amirian M, Montoya-Zegarra JA, Herzig I, Eggenberger Hotz P, Lichtensteiger L, Morf M, et al. Mitigation of motion‐induced artifacts in cone beam computed tomography using deep convolutional neural networks. Medical Physics. 2023. doi:10.1002/mp.16405

BibTeX
@article{Amirian2023,
  author = {Amirian, Mohammadreza and Montoya-Zegarra, Javier A and Herzig, Ivo and Eggenberger Hotz, Peter and Lichtensteiger, Lukas and Morf, Marco and Züst, Alexander and Paysan, Pascal and Peterlik, Igor and Scheib, Stefan and Füchslin, Rudolf Marcel and Stadelmann, Thilo and Schilling, Frank-Peter},
  title = {Mitigation of motion‐induced artifacts in cone beam computed tomography using deep convolutional neural networks},
  journal = {Medical Physics},
  year = {2023},
  doi = {10.1002/mp.16405}
}
Start for free →