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
. 2024 Sep;17(3):776-781.
doi: 10.1007/s12194-024-00831-9. Epub 2024 Aug 3.

Two-step optimization for accelerating deep image prior-based PET image reconstruction

Fumio Hashimoto  1   2   3 , Yuya Onishi  4 , Kibo Ote  4 , Hideaki Tashima  5 , Taiga Yamaya  6   5
Affiliations

Two-step optimization for accelerating deep image prior-based PET image reconstruction

Fumio Hashimoto et al. Radiol Phys Technol. 2024 Sep.

Abstract

Deep learning, particularly convolutional neural networks (CNNs), has advanced positron emission tomography (PET) image reconstruction. However, it requires extensive, high-quality training datasets. Unsupervised learning methods, such as deep image prior (DIP), have shown promise for PET image reconstruction. Although DIP-based PET image reconstruction methods demonstrate superior performance, they involve highly time-consuming calculations. This study proposed a two-step optimization method to accelerate end-to-end DIP-based PET image reconstruction and improve PET image quality. The proposed two-step method comprised a pre-training step using conditional DIP denoising, followed by an end-to-end reconstruction step with fine-tuning. Evaluations using Monte Carlo simulation data demonstrated that the proposed two-step method significantly reduced the computation time and improved the image quality, thereby rendering it a practical and efficient approach for end-to-end DIP-based PET image reconstruction.

Keywords: 3D PET image reconstruction; Deep image prior; End-to-end reconstruction; Positron emission tomography (PET).

PubMed Disclaimer

References

    1. Phelps ME. PET: molecular imaging and its biological applications. New York: Springer; 2012.
    1. Lodge MA, Chaudhry MA, Wahl RL. Noise considerations for PET quantification using maximum and peak standardized uptake value. J Nucl Med. 2012;53(7):1041–7. - DOI - PubMed
    1. Akamatsu G, Ikari Y, Nishida H, et al. Influence of statistical fluctuation on reproducibility and accuracy of SUVmax and SUVpeak: a phantom study. J Nucl Med. 2015;43(3):222–6. - DOI
    1. Delcroix O, Bourhis D, Keromnes N, et al. Assessment of image quality and lesion detectability with digital PET/CT system. Front Med. 2021;8:629096. - DOI
    1. Reader AJ, Corda G, Mehranian A, da Costa-Luis C, Ellis S, Schnabel JA. Deep learning for PET image reconstruction. IEEE Trans Radiat Plasma Med Sci. 2020;5(1):1–25. - DOI

Grants and funding

LinkOut - more resources