EUVIMEDScopri EUVIMED
Open access · CC BY 4.0

Deep learning‐based cone‐beam CT motion compensation with single‐view temporal resolution

Joscha Maier, Stefan Sawall, Marcel Arheit, Pascal Paysan, Marc Kachelrieß

Medical Physics · 2025

DOI: 10.1002/mp.17911 ↗

At a glance

Journal article in Medical Physics, 2025. Written by Joscha Maier and 4 co-authors. Institution: Division of X-Ray Imaging and Computed Tomography, German Cancer Research Center (DKFZ), Heidelberg, Germany. Major MEDLINE topics: Cone-Beam Computed Tomography, Deep Learning, Image Processing, Computer-Assisted. Cited 4 times so far (Crossref); 46 references. The full text is freely available (open access, CC BY 4.0). Funded by: Varian Medical Systems.

AbstractSubjectsDati bibliograficiCiteRelated studies

Abstract (original language)

Background

Cone‐beam CT (CBCT) scans that are affected by motion often require motion compensation to reduce artifacts or to reconstruct 4D (3D+time) representations of the patient. To do so, most existing strategies rely on some sort of gating strategy that sorts the acquired projections into motion bins. Subsequently, these bins can be reconstructed individually before further post‐processing may be applied to improve image quality. While this concept is useful for periodic motion patterns, it fails in case of non‐periodic motion as observed, for example, in irregularly breathing patients.

Purpose

To address this issue and to increase temporal resolution, we propose the deep single angle‐based motion compensation (SAMoCo).

Methods

To avoid gating, and therefore its downsides, the deep SAMoCo trains a U‐net‐like network to predict displacement vector fields (DVFs) representing the motion that occurred between any two given time points of the scan. To do so, 4D clinical CT scans are used to simulate 4D CBCT scans as well as the corresponding ground truth DVFs that map between the different motion states of the scan. The network is then trained to predict these DVFs as a function of the respective projection views and an initial 3D reconstruction. Once the network is trained, an arbitrary motion state corresponding to a certain projection view of the scan can be recovered by estimating DVFs from any other state or view and by considering them during reconstruction.

Results

Applied to 4D CBCT simulations of breathing patients, the deep SAMoCo provides high‐quality reconstructions for periodic and non‐periodic motion. Here, the deviations with respect to the ground truth are less than 27 HU on average, while respiratory motion, or the diaphragm position, can be resolved with an accuracy of about 0.75 mm. Similar results were obtained for real measurements where a high correlation with external motion monitoring signals could be observed, even in patients with highly irregular respiration.

Conclusions

The ability to estimate DVFs as a function of two arbitrary projection views and an initial 3D reconstruction makes deep SAMoCo applicable to arbitrary motion patterns with single‐view temporal resolution. Therefore, the deep SAMoCo is particularly useful for cases with unsteady breathing, compensation of residual motion during a breath‐hold scan, or scans with fast gantry rotation times in which the data acquisition only covers a very limited number of breathing cycles. Furthermore, not requiring gating signals may simplify the clinical workflow and reduces the time needed for patient preparation.

Subjects

MeSH terms (MEDLINE)

Cone-Beam Computed TomographyDeep LearningImage Processing, Computer-AssistedMovementFour-Dimensional Computed TomographyTime FactorsHumansRespirationArtifacts

Author keywords

4D CBCTdeep learningmotion compensation

Authors and institutions

  • Division of X-Ray Imaging and Computed Tomography, German Cancer Research Center (DKFZ), Heidelberg, Germany.
  • Medical Faculty Heidelberg, Heidelberg University, Heidelberg, Germany.
  • Varian Medical Systems Imaging Laboratory, GmbH, Baden-Daettwil, Switzerland.

Funding

  • Varian Medical Systems

Cite

APA

Maier, J., Sawall, S., Arheit, M., Paysan, P., & Kachelrieß, M. (2025). Deep learning‐based cone‐beam CT motion compensation with single‐view temporal resolution. Medical Physics. https://doi.org/10.1002/mp.17911

Vancouver

Maier J, Sawall S, Arheit M, Paysan P, Kachelrieß M. Deep learning‐based cone‐beam CT motion compensation with single‐view temporal resolution. Medical Physics. 2025. doi:10.1002/mp.17911

BibTeX
@article{Maier2025,
  author = {Maier, Joscha and Sawall, Stefan and Arheit, Marcel and Paysan, Pascal and Kachelrieß, Marc},
  title = {Deep learning‐based cone‐beam CT motion compensation with single‐view temporal resolution},
  journal = {Medical Physics},
  year = {2025},
  doi = {10.1002/mp.17911}
}
Start for free →