Abstract
In Positron Emission Tomography (PET), high radioactivity maps are essential to better understand the physiological processes associated with the disease. In this paper, we propose a deep learning based framework for PET image reconstruction from sinogram domain directly. In the framework, conditional Generative Adversarial Networks (cGANs) is constructed to learn a mapping from sinogram data to reconstructed image and generate a well-trained model. To verify the accuracy and robustness of the model, both Monte Carlo simulation data and real data are adopted in the test. The experimental results show that the proposed framework is of great robustness and the reconstructed image is much more accurate in comparison with the traditional methods.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Qi, J., Leahy, R.M.: Iterative reconstruction techniques in emission computed tomography. Phys. Med. Biol. 51(15), R541–R578 (2006). https://doi.org/10.1088/0031-9155/51/15/R01
Shepp, L.A., Vardi, Y.: Maximum likelihood reconstruction for emission tomography. IEEE Trans. Med. Imaging 1(2), 113–122 (1982). https://doi.org/10.1109/TMI.1982.4307558
Levitan, E., Herman, G.T.: A maximum a posteriori probability expectation maximization algorithm for image reconstruction in emission tomography. IEEE Trans. Med. Imaging 6(3), 185–192 (1987). https://doi.org/10.1109/TMI.1987.4307826
Zhou, J., Luo, L.M.: Sequential weighted least squares algorithm for PET image reconstruction. Digit. Sig. Proc. 16(6), 735–745 (2006). https://doi.org/10.1016/j.dsp.2006.08.006
Cabello, J., Torres-Espallardo, I., Gillam, J.E., Rafecas, M.: PET reconstruction from truncated projections using total-variation regularization for hadron therapy monitoring. IEEE Trans. Nucl. Sci. 60(5), 3364–3372 (2013). https://doi.org/10.1109/TNS.2013.2278121
Xie, S., et al.: Artifact removal using improved GoogLeNet for sparse-view CT reconstruction. Sci. Rep. 8(1), 6700–6709 (2018). https://doi.org/10.1038/s41598-018-25153-w
Kim, K., et al.: Penalized PET reconstruction using deep learning prior and local linear fitting. IEEE Trans. Med. Imaging 37(6), 1478–1487 (2018). https://doi.org/10.1109/TMI.2018.2832613
Gong, K., et al.: Iterative PET image reconstruction using convolutional neural network representation. IEEE Trans. Med. Imaging 38(3), 675–685 (2019). https://doi.org/10.1109/tmi.2018.2869871
Zhu, B., Liu, J.Z., Cauley, S.F., Rosen, B.R., Rosen, M.S.: Image reconstruction by domain-transform manifold learning. Nature 555(7697), 487–492 (2018). https://doi.org/10.1038/nature25988
Häggström, I., Schmidtlein, C.R., Campanella, G., Fuchs, T.J.: DeepPET: a deep encoder–decoder network for directly solving the PET image reconstruction inverse problem. Med. Image Anal. 54, 253–262 (2019). https://doi.org/10.1016/j.media.2019.03.013
Mirza, M., Osindero, S.: Conditional generative adversarial nets (2014)
Isola, P., Zhu, J., Zhou, T., Efros, A.A.: Image-to-image translation with conditional adversarial networks. In: Paper Presented at the 30th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017, pp. 5967–5976 (2017). https://doi.org/10.1109/cvpr.2017.632
Acknowledgements
This work is supported in part by the National Natural Science Foundation of China (No: U1809204, 61525106, 61427807, 61701436), by the National Key Technology Research and Development Program of China (No: 2017YFE0104000, 2016YFC1300302), and by Shenzhen Innovation Funding (No: JCYJ20170818164343304, JCYJ20170816172431715).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Switzerland AG
About this paper
Cite this paper
Liu, Z., Chen, H., Liu, H. (2019). Deep Learning Based Framework for Direct Reconstruction of PET Images. In: Shen, D., et al. Medical Image Computing and Computer Assisted Intervention – MICCAI 2019. MICCAI 2019. Lecture Notes in Computer Science(), vol 11766. Springer, Cham. https://doi.org/10.1007/978-3-030-32248-9_6
Download citation
DOI: https://doi.org/10.1007/978-3-030-32248-9_6
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-32247-2
Online ISBN: 978-3-030-32248-9
eBook Packages: Computer ScienceComputer Science (R0)