Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2020 Jun 23;65(12):125016.
doi: 10.1088/1361-6560/ab8f72.

Generative adversarial network based regularized image reconstruction for PET

Zhaoheng Xie  1 , Reheman Baikejiang, Tiantian Li, Xuezhu Zhang, Kuang Gong, Mengxi Zhang, Wenyuan Qi, Evren Asma, Jinyi Qi
Affiliations

Generative adversarial network based regularized image reconstruction for PET

Zhaoheng Xie et al. Phys Med Biol. .

Abstract

Positron emission tomography (PET) is an ill-posed inverse problem and suffers high noise due to limited number of detected events. Prior information can be used to improve the quality of reconstructed PET images. Deep neural networks have also been applied to regularized image reconstruction. One method is to use a pretrained denoising neural network to represent the PET image and to perform a constrained maximum likelihood estimation. In this work, we propose to use a generative adversarial network (GAN) to further improve the network performance. We also modify the objective function to include a data-matching term on the network input. Experimental studies using computer-based Monte Carlo simulations and real patient datasets demonstrate that the proposed method leads to noticeable improvements over the kernel-based and U-net-based regularization methods in terms of lesion contrast recovery versus background noise trade-offs.

PubMed Disclaimer

Figures

Figure 1:
Figure 1:
(a) The schematic of the self-attention GAN with U-net structure. (b) The training and validation mean square errors.
Figure 2:
Figure 2:
Reconstructed low-count images using different methods for the simulated test data set. The bold caption denotes our proposed method.
Figure 3:
Figure 3:
The contrast recovery versus standard derivation curves using different methods for the simulated test data set.
Figure 4:
Figure 4:
Reconstructed low-count images using different methods for the hybrid lesion test dataset. The bold caption denotes our proposed method.
Figure 5:
Figure 5:
The contrast recovery versus standard derivation curves using different methods for the hybrid lesion test dataset.(a) The comparison between the SAGAN and U-net structures. (b) The comparison between SAGAN-based and kernel-based reconstruction.
Figure 6:
Figure 6:
Reconstructed low-counts images using different methods for the lung cancer test dataset. The bold caption denotes our proposed method.
Figure 7:
Figure 7:
The contrast versus standard derivation curves using different methods for the lung cancer test dataset.
Figure 8:
Figure 8:
The effect of parameter η on the log-likelihood.
See this image and copyright information in PMC

References

    1. Ahn S and Leahy RM 2008. Analysis of resolution and noise properties of nonquadratically regularized image reconstruction methods for pet IEEE transactions on medical imaging 27(3), 413–424. - PubMed
    1. Baikejiang R, Gong K, Zhang X and Qi J 2018. An improved deep learning based regularized image reconstruction for PET IEEE Nuclear Science Symposium and Medical Imaging Conference (NSS/MIC).
    1. Bettinardi V, Presotto L, Rapisarda E, Picchio M, Gianolli L and Gilardi M 2011. Physical performance of the new hybrid PET/CT Discovery-690 Medical physics 38(10), 5394–5411. - PubMed
    1. Boyd S, Parikh N, Chu E, Peleato B, Eckstein J et al. 2011. Distributed optimization and statistical learning via the alternating direction method of multipliers Foundations and Trends in Machine learning 3(1), 1–122.
    1. Chen S, Liu H, Shi P and Chen Y 2015. Sparse representation and dictionary learning penalized image reconstruction for positron emission tomography. Physics in Medicine and Biology 60(2), 807–23. - PubMed

Publication types