Abstract
Computed tomography (CT) is one of the most popular non-invasive medical imaging modalities. A major downside of medical CT is the exposure of the patient to high-energy X-rays during image acquisition. One way to reduce the amount of ionising radiation is to record fewer projective views and then upsample the resulting subsampled sinogram. Post acquisition, this can be achieved through conventional sinogram interpolation algorithms or using neural networks. This paper compares the results of two upsampling network architectures with the results of conventional sinogram interpolation. We found that for subsampling factors two and four, the neural networks did not substantially improve the model predictions in terms of structured similarity and peak signal-to-noise ratio compared to conventional sinogram interpolation. This suggests that, for these subsampling factors and the given dataset, interpolation approximates the problemwell enough.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Giordano B, Grauer J, Miller C, Morgan T, Rechtine G et al. Radiation exposure issues in orthopaedics. JBJS. 2011;93(12):e69.
Ma Y, Wei B, Feng P, He P, Guo X, Wang G. Low-dose CT image denoising using a generative adversarial network with a hybrid loss function for noise learning. IEEE Access. 2020;8:67519–29.
Lee H, Lee J, Cho S. View-interpolation of sparsely sampled sinogram using convolutional neural network. Proc SPIE. Vol. 10133. 2017:617–24.
Li S, Ye W, Li F. LU-Net: combining LSTM and u-net for sinogram synthesis in sparse-view SPECT reconstruction. Math Biosci Eng. 2022;19(4):4320–40.
Yu M, Han M, Baek J. A convolutional neural network based super resolution technique of CT image utilizing both sinogram domain and image domain data. MProc SPIE. Vol. 12032. 2022:564–9.
McCollough C, Chen B, Holmes D, Duan X, Yu Z, Yu L et al. Low dose CT image and projection data. 2020.
Wagner F, Thies M, Pfaff L, Aust O, Pechmann S, Maul N et al. On the benefit of dual-domain denoising in a self-supervised low-dose CT setting. Proc IEEE ISBI. 2023:1–5.
Ronchetti M. TorchRadon: Fast Differentiable Routines for Computed Tomography. 2020.
Falcon W, The PyTorch Lightning Team. PyTorch Lightning. Version 1.4. 2019.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2024 Der/die Autor(en), exklusiv lizenziert an Springer Fachmedien Wiesbaden GmbH, ein Teil von Springer Nature
About this paper
Cite this paper
Augustin, L., Wagner, F., Thies, M., Maier, A. (2024). Neural Network-based Sinogram Upsampling in Real-measured CT Reconstruction. In: Maier, A., Deserno, T.M., Handels, H., Maier-Hein, K., Palm, C., Tolxdorff, T. (eds) Bildverarbeitung für die Medizin 2024. BVM 2024. Informatik aktuell. Springer Vieweg, Wiesbaden. https://doi.org/10.1007/978-3-658-44037-4_80
Download citation
DOI: https://doi.org/10.1007/978-3-658-44037-4_80
Published:
Publisher Name: Springer Vieweg, Wiesbaden
Print ISBN: 978-3-658-44036-7
Online ISBN: 978-3-658-44037-4
eBook Packages: Computer Science and Engineering (German Language)