Abstract
Parametric imaging obtained from kinetic modeling analysis of dynamic positron emission tomography (PET) data is a useful tool for quantifying tracer kinetics. However, pixel-wise time-activity curves have high noise levels which lead to poor quality of parametric images. To solve this limitation, we proposed a new image denoising method based on deep image prior (DIP). Like the original DIP method, the proposed DIP method is an unsupervised method, in which no training dataset is required. However, the difference is that our method can simultaneously denoise all dynamic PET images. Moreover, we propose a modified version of the DIP method called double DIP (DDIP), which has two DIP architectures. The additional DIP model is used to generate high-quality input data for the second DIP model. Computer simulations were performed to evaluate the performance of the proposed DIP-based methods. Our simulation results showed that the DDIP method outperformed the single DIP method. In addition, the DDIP method combined with data augmentation could generate PET parametric images with superior image quality compared to the spatiotemporal-based non-local means filtering and high constrained backprojection. Our preliminary results show that our proposed DDIP method is a novel and effective unsupervised method for simultaneously denoising dynamic PET images.
Similar content being viewed by others
Availability of Data and Material
If anyone asks for data, we will provide data via e-mail.
Code Availability
If anyone asks for source code, we will provide source code via e-mail.
References
Carson RE. Tracer kinetic modeling in PET. Positron Emiss. Tomogr., Springer-Verlag; 127–159, 2006
Kotasidis FA, Tsoumpas C, Rahmim A: Advanced kinetic modelling strategies: Towards adoption in clinical PET imaging. Clin Transl Imaging 2:219–37, 2014
Ko BS, Cameron JD, DeFrance T, Seneviratne SK: CT stress myocardial perfusion imaging using Multidetector CT-A review. J Cardiovasc Comput Tomogr 5:345–356, 2011
Koh TS, Ng QS, Thng CH, Kwek JW, Kozarski R, Goh V: Primary colorectal cancer: Use of kinetic modeling of dynamic contrast-enhanced CT data to predict clinical outcome. Radiology 267:145–154, 2013
Khalifa F, Soliman A, El-Baz A, Abou El-Ghar M, El-Diasty T, Gimel’Farb G, et al: Models and methods for analyzing DCE-MRI: A review. Med Phys 41:124301, 2014
Gaddikeri S, Gaddikeri RS, Tailor T, Anzai Y: Dynamic contrast-enhanced MR imaging in head and neck cancer: Techniques and clinical applications. Am J Neuroradiol 37:588–595, 2016
Lu L, Karakatsanis NA, Tang J, Chen W, Rahmim A: 3.5D dynamic PET image reconstruction incorporating kinetics-based clusters. Phys Med Biol 57:5035–5055, 2012
Wang G, Qi J: PET image reconstruction using Kernel method. IEEE Trans Med Imaging 34:61–71, 2015
Cao S, He Y, Zhang H, Lv W, Lu L, Chen W: Dynamic PET image reconstruction incorporating multiscale superpixel clusters. IEEE Access 9:28965–28975, 2021
Shidahara M, Ikoma Y, Kershaw J, Kimura Y, Naganawa M, Watabe H: PET kinetic analysis: Wavelet denoising of dynamic PET data with application to parametric imaging. Ann Nucl Med 21:379–386, 2007
Christian BT, Vandehey NT, Floberg JM, Mistretta CA: Dynamic PET denoising with HYPR processing. J Nucl Med 51:1147–1154, 2010
Dutta J, Leahy RM, Li Q: Non-local means denoising of dynamic PET images. PLoS One 8:e81390, 2013
Lu L, Hu D, Ma X, Ma J, Rahmim A, Chen W: Dynamic PET denoising incorporating a composite image guided filter. 2014 IEEE Nucl. Sci. Symp. Med. Imaging Conf. NSS/MIC 2014, Institute of Electrical and Electronics Engineers Inc.; 2016
Guo H, Renaut RA, Chen K, Reiman E: FDG-PET parametric imaging by total variation minimization. Comput Med Imaging Graph 33:295–303, 2009
Huang HM, Liu CC, Lin C: Indirect methods for improving parameter estimation of PET kinetic models. Med Phys 46:1777–1784, 2019
Huang HM: Kernel-based curve-fitting method with spatial regularization for generation of parametric images in dynamic PET. Phys Med Biol 65:225006, 2020
Kamasak ME, Bouman CA, Morris ED, Sauer K: Direct reconstruction of kinetic parameter images from dynamic PET data. IEEE Trans Med Imaging 24:636–650, 2005
Germino M, Gallezot JD, Yan J, Carson RE: Direct reconstruction of parametric images for brain PET with event-by-event motion correction: Evaluation in two tracers across count levels. Phys Med Biol 62:5344–5364, 2017
Gong K, Cheng-Liao J, Wang G, Chen KT, Catana C, Qi J: Direct Patlak reconstruction from dynamic PET data using the Kernel method with MRI information based on structural similarity. IEEE Trans Med Imaging 37:955–965, 2018
Tian C, Fei L, Zheng W, Xu Y, Zuo W, Lin CW: Deep learning on image denoising: An overview. Neural Networks 131:251–275, 2020
Lempitsky V, Vedaldi A, Ulyanov D. Deep image prior. Proc. IEEE Comput. Soc. Conf. Comput. Vis. Pattern Recognit., IEEE Computer Society; 9446–9454, 2018
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 7:96594–96603, 2019
Camuto A, Willetts M, Şimşekli U, Roberts S, Holmes C: Explicit regularisation in Gaussian noise injections. ArXiv 2007.07368v6, 2020
Kingma DP, Ba JL: Adam: A method for stochastic optimization. 3rd Int. Conf. Learn. Represent. ICLR 2015 - Conf. Track Proc., International Conference on Learning Representations, ICLR; 1412.6980, 2015
Huang SC, Phelps ME, Hoffman EJ, Sideris K, Selin CJ, Kuhl DE: Noninvasive determination of local cerebral metabolic rate of glucose in man. Am J Physiol 238:69–82, 1980
Häggström I, Beattie BJ, Schmidtlein CR. Dynamic PET simulator via tomographic emission projection for kinetic modeling and parametric image studies. Med Phys 43:3104-3116, 2016
Branch MA, Coleman TF, Li Y: A subspace, interior, and conjugate gradient method for large-scale bound-constrained minimization problems. SIAM J Sci Comput 21:1–23, 1999
Byrd RH, Schnabel RB, Shultz GA: Approximate solution of the trust region problem by minimization over two-dimensional subspaces. Math Program 40:247–263,1988
Jin SC, Hsieh CJ, Chen JC, Tu SH, Chen YC, Hsiao TC, et al: Development of limited-angle iterative reconstruction algorithms with context encoder-based sinogram completion for micro-CT applications. Sensors 18:4458, 2018
Zhou Q, Zhou C, Hu H, Chen Y, Chen S, Li X: Towards the automation of deep image prior. ArXiv 1911.07185, 2019
Funding
This study has received funding by MOST 110–2221-E-002–029 from Ministry of Science and Technology, Taiwan.
Author information
Authors and Affiliations
Contributions
Cheng-Hsun Yang is responsible for implementation and data analysis. Hsuan-Ming Huang is responsible for writing the manuscript.
Corresponding author
Ethics declarations
Ethics Approval
Not applicable. This is a simulation study.
Consent to Participate
Not applicable.
Consent for Publication
Authors are responsible for correctness of the statements provided in the manuscript. See also Authorship Principles. The Editor-in-Chief reserves the right to reject submissions that do not meet the guidelines described in this section.
Additional Declarations for Articles in Life Science Journals that Report the Results of Studies Involving Humans and/or Animals
Not applicable.
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.
Appendix
Appendix
Rights and permissions
About this article
Cite this article
Yang, CH., Huang, HM. Simultaneous Denoising of Dynamic PET Images Based on Deep Image Prior. J Digit Imaging 35, 834–845 (2022). https://doi.org/10.1007/s10278-022-00606-x
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10278-022-00606-x