Comparison of The Performance of Denoising Filters in Improving The Quality of Low-Dose Brain PET Images With Two Dose Levels of 5% and 10%

Document Type : Research Paper

Authors

1 Department of Medical Radiation Engineering, Shahid Beheshti University, Tehran, Iran

2 Department of Medical Radiation Engineering, Faculty of Medical Radiation Engineering, Shahid Beheshti University, Tehran, Iran

3 Department of Medical Physics and BioMedical Engineering, Tehran University of Medical Sciences

4 Division of Nuclear Medicine and Molecular Imaging, Geneva University Hospital, Geneva CH-1211, Switzerland

Abstract

Positron Emission tomography (PET) as a nuclear medicine imaging modality is increasingly used in clinical practice to diagnose disease and cancer. To achieve a high quality PET image for diagnostic purposes, a standard dose of radioactive tracer must be injected into the patient's body, which increases the risk of radiation damage. However, reducing the tracer dose leads to increase in noise and decrease in the signal-to-noise ratio and the quality of the PET. This paper aims to evaluate the performance of Gaussian filter, Bilateral filter, Non-Local Mean and Wavelet Transform filters in improving the quality of low-dose PET images. First, these filters were optimized separately for two dose levels, and then the optimal filters were applied to 40 PET brain images with a 5% and 10% dose levels. Finally, the performance of these filters was evaluated and compared using PSNR, RMSE criteria in the whole brain and RMSE and Bias criteria in different areas of the brain (e.g, thalamus, cerebellum, putamen, etc.).

Keywords

References

1. Kaplan S, Zhu Y-M. Full-dose PET image
estimation from low-dose PET image using deep
learning: a pilot study. Journal of digital imaging.
2019;32(5):773-8.
2. Wang Y, Zhou L, Yu B, Wang L,
Zu C, Lalush DS, et al. 3D auto-context-based
locality adaptive multi-modality GANs for PET
synthesis. IEEE transactions on medical imaging.
2018;38(6):1328-39.
3. Arabi H, Zeraatkar N, Ay MR,
Zaidi H. Quantitative assessment of inter-crystal
scatter and penetration in the PET subsystem of the
FLEX triumph preclinical multi-modality scanner.
Iranian Journal of Nuclear Medicine.
2010;18(Supplement 1):40.
4. Arabi H, Zaidi H. Deep learningguided estimation of attenuation correction factors
from time-of-flight PET emission data. Medical
Image Analysis. 2020;64:101718.
5. Mehranian A, Arabi H, Zaidi H.
Quantitative analysis of MRI-guided attenuation
correction techniques in time-of-flight brain
PET/MRI. Neuroimage. 2016;130:123-33.
6. Khorami Moghadam A, Fallah
Mohammadi G, Mardanshahi A, Ehsani S. Patient
Dose Estimation in Conventional Radiography
Examinations in Referral Governmental Hospitals,
Sari, Iran. Journal of Mazandaran University of
Medical Sciences. 2016;26(142):222-7.
7. Fallah Mohammadi G.
Assessment of Contrast Media Volume Injected and
Image Contrast in Abdominal Pelvic CT Scan and
Related Factors in Referral Hospitals in
Mazandaran, Iran. Journal of Mazandaran
University of Medical Sciences. 2021;30(194):62-
70.
8. Xu J, Gong E, Pauly J, Zaharchuk
G. 200x low-dose PET reconstruction using deep
learning .arXiv preprint arXiv:171204119. 2017.
9. Sanaat A, Arabi H, Mainta I,
Garibotto V, Zaidi H. Projection Space
Implementation of Deep Learning–Guided LowDose Brain PET Imaging Improves Performance
over Implementation in Image Space. Journal of
Nuclear Medicine. 2020;61(9):1388-96.
10. Arabi H, Zaidi H. Applications of
artificial intelligence and deep learning in molecular
imaging and radiotherapy. European Journal of
Hybrid Imaging. 2020;4(1):1-23.
11. Bland J, Mehranian A, Belzunce
MA, Ellis S, McGinnity CJ, Hammers A, et al. MRguided kernel EM reconstruction for reduced dose
PET imaging. IEEE transactions on radiation and
plasma medical sciences. 2017;2(3):235-43.
12. Arabi H, Zaidi H. Spatially guided
nonlocal mean approach for denoising of PET
images .Medical physics. 2020;47(4):1656-69.
13. Arabi H, Zaidi H. Improvement of
image quality in PET using post-reconstruction
hybrid spatial-frequency domain filtering. Physics
in medicine and biology. 2018;63(21):215010.
14. Arabi H, Zaidi H. Non-local
mean denoising using multiple PET reconstructions.
Annals of Nuclear Medicine. 2020:1-11.
15. Yu S, Muhammed HH, editors.
Noise type evaluation in positron emission
tomography images. 2016 1st International
Conference on Biomedical Engineering
(IBIOMED); 2016 :IEEE.
16. Guo S, Sheng Y, Chai L, Zhang J,
editors. Graph Filtering Approach to PET Image
Denoising. 2019 1st International Conference on
Industrial Artificial Intelligence (IAI); 2019: IEEE.
17. Hofheinz F, Langner J, BeuthienBaumann B, Oehme L, Steinbach J, Kotzerke J, et
al. Suitability of bilateral filtering for edgepreserving noise reduction in PET. EJNMMI
research. 2011;1(1):1-9.
18. Banterle F, Corsini M, Cignoni P,
Scopigno R, editors. A low‐memory,
straightforward and fast bilateral filter through
subsampling in spatial domain. Computer Graphics
Forum; 2012: Wiley Online Library..
Buades A, Coll B, Morel J-M, editors. A
non-local algorithm for image denoising. 2005 IEEE
Computer Society Conference on Computer Vision
and Pattern Recognition (CVPR'05); 2005: IEEE.
19. Peng Z, Chu F. Application of the
wavelet transform in machine condition monitoring
and fault diagnostics: a review with bibliography.
Mechanical systems and signal processing.
2004;18(2):199-221.
20. Jensen A, la Cour-Harbo A .
Ripples in mathematics: the discrete wavelet
transform: Springer Science & Business Media;
2001.
21. Häggström I, Schmidtlein CR,
Campanella G, Fuchs TJ. DeepPET: A deep
encoder–decoder network for directly solving the
PET image reconstruction inverse problem. Medical
image analysis. 2019;54:253-62.
medical journal of mashhad university of medical sciences
Volume 65, Issue 3
May and June 2022
Pages 947-955

Files

Share

How to cite

Statistics