Abstract
In PET, the amount of relative (signal-dependent) noise present in different body regions can be significantly different and is inherently related to the number of counts present in that region. The number of counts in a region depends, in principle and among other factors, on the total administered activity, scanner sensitivity, image acquisition duration, radiopharmaceutical tracer uptake in the region, and patient local body morphometry surrounding the region. In theory, less amount of denoising operations is needed to denoise a high-count (low relative noise) area than images a low-count (high relative noise) area, and vice versa. The current deep-learning-based methods for PET image denoising are predominantly trained on whole images using image appearance only and have not taken into account any prior knowledge about the spatially varying noise in PET. Our hypothesis is that by explicitly providing the relative noise level of each local area of a PET image to a deep convolutional neural network (DCNN), the DCNN learn noise-level-specific denoising features at different noise-levels and apply these features to areas with different denoising needs, thus outperforming the DCNN trained on whole images using image appearance only. To this end, we propose a noise-level-aware framework denoising framework that allows embedding of local noise level into a DCNN. The proposed is trained and tested on 30 and 15 patient PET images acquired on a GE Discovery MI PET/CT system. Our experiments showed that the increases in both PSNR and SSIM from our backbone network with relative noise level embedding (NLE) versus the same network without NLE were statistically significant with pā<ā0.001, and the proposed method significantly outperformed a strong baseline method by a large margin.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Gong, K., et al.: PET image denoising using a deep neural network through fine tuning. IEEE Trans. Radiat. Plasma Med. Sci. 3(2), 153ā161 (2019)
Dutta, J., Leahy, R.M., Li, Q.: Non-local means denoising of dynamic PET images. PLoS ONE 8(12), e81390 (2013)
Chan, C., et al.: Postreconstruction nonlocal means filtering of whole-body PET with an anatomical prior. IEEE Trans. Med. Imaging 33(3), 636ā650 (2014)
Cui, J., et al.: PET image denoising using unsupervised deep learning. Eur. J. Nucl. Med. Mol. Imaging 46(13), 2780ā2789 (2019). https://doi.org/10.1007/s00259-019-04468-4
Ouyang, J.H., et al.: Ultra-low-dose PET reconstruction using generative adversarial network with feature matching and task-specific perceptual loss. Med. Phys. 46(8), 3555ā3564 (2019)
Cui, J.A., et al.: Populational and individual information based PET image denoising using conditional unsupervised learning. Phys. Med. Biol. 66(15) (2021)
Zhou, L., et al.: Supervised learning with cyclegan for low-dose FDG PET image denoising. Med. Image Anal. 65 (2020)
Zhou, B., et al.: MDPET: a unified motion correction and denoising adversarial network for low-dose gated PET. IEEE Trans. Med. Imaging 40(11), 3154ā3164 (2021)
Song, T.A., Yang, F., Dutta, J.: Noise2Void: unsupervised denoising of PET images. Phys. Med. Biol. 66(21) (2021)
Onishi, Y., et al., Anatomical-guided attention enhances unsupervised PET image denoising performance. Med. Image Anal. 74 (2021)
Zamir, S.W., et al.: Multi-Stage Progressive Image Restoration. in CVPR (2021)
Li, Y., et al.: A projection image database to investigate factors affecting image quality in weight-based dosing: application to pediatric renal SPECT. Phys. Med. Biol. 63(14), 145004 (2018)
Otsu, N.: A Threshold Selection Method from Gray-Level Histograms. IEEE Trans. Syst. Man Cybern. 9(1) (1979)
Ba, J., Kingma, D.P.: Adam: a method for stochastic optimization. arXiv:1412.6980 (2014)
Hutter, F., Loshchilov, I.: SGDR: Stochastic gradient descent with warm restarts, in ICLR (2017)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
Ā© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Li, Y. et al. (2022). A Noise-Level-Aware Framework for PET Image Denoising. In: Haq, N., Johnson, P., Maier, A., Qin, C., WĆ¼rfl, T., Yoo, J. (eds) Machine Learning for Medical Image Reconstruction. MLMIR 2022. Lecture Notes in Computer Science, vol 13587. Springer, Cham. https://doi.org/10.1007/978-3-031-17247-2_8
Download citation
DOI: https://doi.org/10.1007/978-3-031-17247-2_8
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-17246-5
Online ISBN: 978-3-031-17247-2
eBook Packages: Computer ScienceComputer Science (R0)