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

Reducing windmill artifacts in clinical spiral CT using a deep learning‐based projection raw data upsampling: Method and robustness evaluation

Jan Magonov, Joscha Maier, Julien Erath, Johan Sunnegårdh, Eric Fournié, Karl Stierstorfer, Marc Kachelrieß

Medical Physics · 2024

DOI: 10.1002/mp.16938 ↗

At a glance

Journal article in Medical Physics, 2024. Written by Jan Magonov and 6 co-authors. Institution: Division of X-Ray Imaging and Computed Tomography, German Cancer Research Center (DKFZ) Heidelberg, Heidelberg, Germany. Major MEDLINE topics: Artifacts, Deep Learning. Cited 3 times so far (Crossref); 27 references. The full text is freely available (open access, CC BY-NC-ND 4.0). Funded by: Siemens Healthineers AG, Siemens Healthineers.

AbstraktSubjectsBibliografické údajeCiteRelated studies

Abstract (original language)

Background

Multislice spiral computed tomography (MSCT) requires an interpolation between adjacent detector rows during backprojection. Not satisfying the Nyquist sampling condition along the z‐axis results in aliasing effects, also known as windmill artifacts. These image distortions are characterized by bright streaks diverging from high contrast structures.

Purpose

The z‐flying focal spot (zFFS) is a well‐established hardware‐based solution that aims to double the sampling rate in longitudinal direction and therefore reduce aliasing artifacts. However, given the technical complexity of the zFFS, this work proposes a deep learning‐based approach as an alternative solution.

Methods

We propose a supervised learning approach to perform a mapping between input projections and the corresponding rows required for double sampling in the z‐direction. We present a comprehensive evaluation using both a clinical dataset obtained using raw data from 40 real patient scans acquired with zFFS and a synthetic dataset consisting of 100 simulated spiral scans using a phantom specifically designed for our problem. For the clinical dataset, we utilized 32 scans as training set and 8 scans as validation set, whereas for the synthetic dataset, we used 80 scans for training and 20 scans for validation purposes. Both qualitative and quantitative assessments are conducted on a test set consisting of nine real patient scans and six phantom measurements to validate the performance of our approach. A simulation study was performed to investigate the robustness against different scan configurations in terms of detector collimation and pitch value.

Results

In the quantitative comparison based on clinical patient scans from the test set, all network configurations show an improvement in the root mean square error (RMSE) of approximately 20% compared to neglecting the doubled longitudinal sampling by the zFFS. The results of the qualitative analysis indicate that both clinical and synthetic training data can reduce windmill artifacts through the application of a correspondingly trained network. Together with the qualitative results from the test set phantom measurements it is emphasized that a training of our method with synthetic data resulted in superior performance in windmill artifact reduction.

Conclusions

Deep learning‐based raw data interpolation has the potential to enhance the sampling in z‐direction and thus minimize aliasing effects, as it is the case with the zFFS. Especially a training with synthetic data showed promising results. While it may not outperform zFFS, our method represents a beneficial solution for CT scanners lacking the necessary hardware components for zFFS.

Subjects

MeSH terms (MEDLINE)

ArtifactsDeep LearningHumansTomography, Spiral ComputedTomography Scanners, X-Ray ComputedPhantoms, ImagingImage Processing, Computer-AssistedAlgorithms

Author keywords

clinical spiral CTcomputed tomographyconvolutional neural networkdeep learningimage qualitymedical imagingprojection rawdata upsamplingwindmill artifact reductionz-flying focal spot

Authors and institutions

  • Division of X-Ray Imaging and Computed Tomography, German Cancer Research Center (DKFZ) Heidelberg, Heidelberg, Germany.
  • Computed Tomography Division, Siemens Healthineers AG, Forchheim, Germany.
  • Medical Faculty, Heidelberg University, Heidelberg, Germany.

Funding

  • Siemens Healthineers AG
  • Siemens Healthineers

Cite

APA

Magonov, J., Maier, J., Erath, J., Sunnegårdh, J., Fournié, E., Stierstorfer, K., & Kachelrieß, M. (2024). Reducing windmill artifacts in clinical spiral CT using a deep learning‐based projection raw data upsampling: Method and robustness evaluation. Medical Physics. https://doi.org/10.1002/mp.16938

Vancouver

Magonov J, Maier J, Erath J, Sunnegårdh J, Fournié E, Stierstorfer K, et al. Reducing windmill artifacts in clinical spiral CT using a deep learning‐based projection raw data upsampling: Method and robustness evaluation. Medical Physics. 2024. doi:10.1002/mp.16938

BibTeX
@article{Magonov2024,
  author = {Magonov, Jan and Maier, Joscha and Erath, Julien and Sunnegårdh, Johan and Fournié, Eric and Stierstorfer, Karl and Kachelrieß, Marc},
  title = {Reducing windmill artifacts in clinical spiral CT using a deep learning‐based projection raw data upsampling: Method and robustness evaluation},
  journal = {Medical Physics},
  year = {2024},
  doi = {10.1002/mp.16938}
}
Start for free →