Abstract
Purpose
Due to various physical degradation factors and limited counts received, PET image quality needs further improvements. The denoising diffusion probabilistic model (DDPM) was a distribution learning-based model, which tried to transform a normal distribution into a specific data distribution based on iterative refinements. In this work, we proposed and evaluated different DDPM-based methods for PET image denoising.
Methods
Under the DDPM framework, one way to perform PET image denoising was to provide the PET image and/or the prior image as the input. Another way was to supply the prior image as the network input with the PET image included in the refinement steps, which could fit for scenarios of different noise levels. 150 brain [\(^{18}\)F]FDG datasets and 140 brain [\(^{18}\)F]MK-6240 (imaging neurofibrillary tangles deposition) datasets were utilized to evaluate the proposed DDPM-based methods.
Results
Quantification showed that the DDPM-based frameworks with PET information included generated better results than the nonlocal mean, Unet and generative adversarial network (GAN)-based denoising methods. Adding additional MR prior in the model helped achieved better performance and further reduced the uncertainty during image denoising. Solely relying on MR prior while ignoring the PET information resulted in large bias. Regional and surface quantification showed that employing MR prior as the network input while embedding PET image as a data-consistency constraint during inference achieved the best performance.
Conclusion
DDPM-based PET image denoising is a flexible framework, which can efficiently utilize prior information and achieve better performance than the nonlocal mean, Unet and GAN-based denoising methods.
Similar content being viewed by others
References
Lin J-W, Laine AF, Bergmann SR. Improving pet-based physiological quantification through methods of wavelet denoising. IEEE Trans Biomed Eng. 2001;48(2):202–12.
Christian BT, Vandehey NT, Floberg JM, Mistretta CA. Dynamic pet denoising with hypr processing. J Nuclear Med. 2010;51(7):1147–54.
Chan C, Fulton R, Barnett R, Feng DD, Meikle S. Postreconstruction nonlocal means filtering of whole-body pet with an anatomical prior. IEEE Trans Med Imaging. 2014;33(3):636–50.
Dutta J, Leahy RM, Li Q. Non-local means denoising of dynamic pet images. PloS One. 2013;8(12):81390.
Yan J, Lim JC-S, Townsend DW. Mri-guided brain pet image filtering and partial volume correction. Phys Med Biol. 2015;60(3):961
Ote K, Hashimoto F, Kakimoto A, Isobe T, Inubushi T, Ota R, Tokui A, Saito A, Moriya T, Omura T, et al. Kinetics-induced block matching and 5-d transform domain filtering for dynamic pet image denoising. IEEE Trans Rad Plasma Med Sci. 2020;4(6):720–8.
Wang Y, Ma G, An L, Shi F, Zhang P, Lalush DS, Wu X, Pu Y, Zhou J, Shen D. Semisupervised tripled dictionary learning for standard-dose pet image prediction using low-dose pet and multimodal mri. IEEE Trans Biomed Eng. 2016;64(3):569–79.
Xiang L, Qiao Y, Nie D, An L, Lin W, Wang Q, Shen D. Deep auto-context convolutional neural networks for standard-dose pet image estimation from low-dose pet/mri. Neurocomputing. 2017;267:406–16.
Kaplan S, Zhu Y-M. Full-dose pet image estimation from low-dose pet image using deep learning: a pilot study. J Digit Imaging. 2019;32(5):773–8.
Cui J, Gong K, Guo N, Wu C, Meng X, Kim K, Zheng K, Wu Z, Fu L, Xu B, et al. Pet image denoising using unsupervised deep learning. Eur J Nuclear Med Mol Imaging. 2019;46(13):2780–9.
Chen KT, Gong E, Carvalho Macruz FB, Xu J, Boumis A, Khalighi M, Poston KL, Sha SJ, Greicius MD, Mormino E, et al. Ultra-low-dose 18f-florbetaben amyloid pet imaging using deep learning with multi-contrast mri inputs. Radiol. 2019;290(3):649–56.
Hashimoto F, Ohba H, Ote K, Teramoto A, Tsukada H. Dynamic pet image denoising using deep convolutional neural networks without prior training datasets. IEEE Access. 2019;7:96594–603.
Costa-Luis CO, Reader AJ. Micro-networks for robust mr-guided low count pet imaging. IEEE Trans Rad Plasma Med Sci. 2020;5(2):202–12.
Schramm G, Rigie D, Vahle T, Rezaei A, Van Laere K, Shepherd T, Nuyts J, Boada F. Approximating anatomically-guided pet reconstruction in image space using a convolutional neural network. Neuroimage. 2021;224:117399.
Mehranian A, Wollenweber SD, Walker MD, Bradley KM, Fielding PA, Su K-H, Johnsen R, Kotasidis F, Jansen FP, McGowan DR. Image enhancement of whole-body oncology [18f]-fdg pet scans using deep neural networks to reduce noise. Eur J Nuclear Med Mol Imaging. 2022;49(2):539–49.
Daveau RS, Law I, Henriksen OM, Hasselbalch SG, Andersen UB, Anderberg L, Højgaard L, Andersen FL, Ladefoged CN. Deep learning based low-activity pet reconstruction of [11c] pib and [18f] fe-pe2i in neurodegenerative disorders. NeuroImage. 2022;259:119412.
Ouyang J, Chen KT, Gong E, Pauly J, Zaharchuk G. Ultra-low-dose pet reconstruction using generative adversarial network with feature matching and task-specific perceptual loss. Med Phy. 2019;46(8):3555–64.
Lei Y, Dong X, Wang T, Higgins K, Liu T, Curran WJ, Mao H, Nye JA. Yang X Whole-body pet estimation from low count statistics using cycle-consistent generative adversarial networks. Phys Med Biol. 2019;64(21):215017.
Zhou L, Schaefferkoetter JD, Tham IW, Huang G, Yan J. Supervised learning with cyclegan for low-dose fdg pet image denoising. Med Image Anal. 2020;65:101770.
Song T-A, Chowdhury SR, Yang F, Dutta J. Pet image super-resolution using generative adversarial networks. Neural Netw. 2020;125:83–91.
Sanaat A, Shiri I, Arabi H, Mainta I, Nkoulou R, Zaidi H. Deep learning-assisted ultra-fast/low-dose whole-body pet/ct imaging. Eur J Nuclear Med Mol Imaging. 2021;48(8):2405–15.
Xue S, Guo R, Bohn KP, Matzke J, Viscione M, Alberts I, Meng H, Sun C, Zhang M, Zhang M, et al. A cross-scanner and cross-tracer deep learning method for the recovery of standard-dose imaging quality from low-dose pet. Eur J Nuclear Med Mol Imaging. 2022;49(6):1843–56.
Gong K, Guan J, Liu C-C, Qi J. Pet image denoising using a deep neural network through fine tuning. IEEE Trans Rad Plasma Med Sci. 2018;3(2):153–61.
Liu H, Wu J, Lu W, Onofrey JA, Liu Y-H, Liu C. Noise reduction with cross-tracer and cross-protocol deep transfer learning for low-dose pet. Phys Med Biol. 2020;65(18):185006.
Chen KT, Schürer M, Ouyang J, Koran MEI, Davidzon G, Mormino E, Tiepolt S, Hoffmann K-T, Sabri O, Zaharchuk G, et al. Generalization of deep learning models for ultra-low-count amyloid pet/mri using transfer learning. Eur J Nuclear Med Mol Imaging. 2020;47(13):2998–3007.
Cui J, Gong K, Guo N, Wu C, Kim K, Liu H, Li Q. Populational and individual information based pet image denoising using conditional unsupervised learning. Phys Med Biol. 2021;66(15):155001.
Zhou B, Miao T, Mirian N, Chen X, Xie H, Feng Z, Guo X, Li X, Zhou SK, Duncan JS, et al. Federated transfer learning for low-dose pet denoising: a pilot study with simulated heterogeneous data. IEEE Transactions on Radiation and Plasma Medical Sciences; 2022
Ho J, Jain A, Abbeel P. Denoising diffusion probabilistic models. Adv Neural Inf Process Syst. 2020;33:6840–51.
Song Y, Ermon S. Generative modeling by estimating gradients of the data distribution. Advances in Neural Information Processing Systems. 2019;32
Song Y, Sohl-Dickstein J, Kingma DP, Kumar A, Ermon S, Poole B. Score-based generative modeling through stochastic differential equations. 2020. arXiv:2011.13456
Edupuganti V, Mardani M, Vasanawala S, Pauly J. Uncertainty quantification in deep MRI reconstruction. IEEE Trans Med Imaging. 2020;40(1):239–50.
Wu P, Sisniega A, Uneri A, Han R, Jones C, Vagdargi P, Zhang X, Luciano M, Anderson W, Siewerdsen J. Using uncertainty in deep learning reconstruction for cone-beam CT of the brain. 2021. arXiv:2108.09229
Sudarshan VP, Upadhyay U, Egan GF, Chen Z, Awate SP. Towards lower-dose PET using physics-based uncertainty-aware multimodal learning with robustness to out-of-distribution data. Med Image Anal. 2021;73:102187.
Dhariwal P, Nichol A. Diffusion models beat gans on image synthesis. Adv Neural Inf Process Syst. 2021;34:8780–94.
Rombach R, Blattmann A, Lorenz D, Esser P, Ommer B. High-resolution image synthesis with latent diffusion models. In: Proceedings of the IEEE/CVF Conference on computer vision and pattern recognition; 2022. pp. 10684–10695
Saharia C, Ho J, Chan W, Salimans T, Fleet DJ, Norouzi M. Image super-resolution via iterative refinement. 2021. arXiv:2104.07636
Lugmayr A, Danelljan M, Romero A, Yu F, Timofte R, Van Gool L. Repaint: inpainting using denoising diffusion probabilistic models. In: Proceedings of the IEEE/CVF Conference on computer vision and pattern recognition; 2022. pp. 11461–11471
Jalal A, Arvinte M, Daras G, Price E, Dimakis AG, Tamir J. Robust compressed sensing mri with deep generative priors. Adv Neural Inf Process Syst. 2021;34:14938–54.
Chung H, Ye JC. Score-based diffusion models for accelerated mri. Medical Image Analysis; 2022 102479
Isola P, Zhu J-Y, Zhou T, Efros AA. Image-to-image translation with conditional adversarial networks. In: Proceedings of the IEEE Conference on computer vision and pattern recognition; 2017. pp. 1125–1134
Tiepolt S, Hesse S, Patt M, Luthardt J, Schroeter ML, Hoffmann K-T, Weise D, Gertz H-J, Sabri O, Barthel H. Early [18f] florbetaben and [11c] pib pet images are a surrogate biomarker of neuronal injury in alzheimer’s disease. Eur J Nuclear Med Mol Imaging. 2016;43(9):1700–9.
Hammes J, Leuwer I, Bischof GN, Drzezga A, Eimeren T. Multimodal correlation of dynamic [18f]-av-1451 perfusion pet and neuronal hypometabolism in [18f]-fdg pet. Eur J Nuclear Med Mol Imaging. 2017;44(13):2249–56.
Visser D, Wolters EE, Verfaillie SC, Coomans EM, Timmers T, Tuncel H, Reimand J, Boellaard R, Windhorst AD, Scheltens P, et al. Tau pathology and relative cerebral blood flow are independently associated with cognition in alzheimer’s disease. Eur J Nuclear Med Mol Imaging. 2020;47(13):3165–75.
Avants BB, Tustison N, Song G, et al. Advanced normalization tools (ants). Insight J. 2009;2(365):1–35.
Fischl B. Freesurfer Neuroimage. 2012;62(2):774–81.
Qi J, Leahy RM. Iterative reconstruction techniques in emission computed tomography. Phys Med Biol. 2006;51(15):541.
Chung H, Sim B, Ye JC. Come-closer-diffuse-faster: accelerating conditional diffusion models for inverse problems through stochastic contraction. In: Proceedings of the IEEE/CVF Conference on computer vision and pattern recognition; 2022. pp. 12413–12422
Funding
This work was supported by the National Institutes of Health under grants R21AG067422, R03EB030280, R01AG078250, P41EB022544 and P01AG036694.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Ethical approval
All procedures performed in studies involving human participants were in accordance with the ethical standards of the institutional and/or national research committee and with the 1964 Helsinki declaration and its later amendments or comparable ethical standards.
Informed consent
For the [\(^{18}\)F]FDG datasets, informed consent was waived due to the retrospective merits of the datasets. For the [\(^{18}\)F]MK-6240 datasets, informed consent was obtained from all the participants.
Conflict of interest
The authors declare no competing interests.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Gong, K., Johnson, K., El Fakhri, G. et al. PET image denoising based on denoising diffusion probabilistic model. Eur J Nucl Med Mol Imaging 51, 358–368 (2024). https://doi.org/10.1007/s00259-023-06417-8
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00259-023-06417-8