Abstract
This study aimed to evaluate a deep learning-based attenuation correction (AC) method to generate pseudo-computed tomography (CT) images from non-AC single-photon emission computed tomography images (SPECTNC) for AC in 99mTc-galactosyl human albumin diethylenetriamine pentaacetic acid (GSA) scintigraphy and to reduce patient dosage. A cycle-consistent generative network (CycleGAN) model was used to generate pseudo-CT images. The training datasets comprised approximately 850 liver phantom images obtained from SPECTNC and real CT images. The training datasets were then input to CycleGAN, and pseudo-CT images were output. SPECT images with real-time CT attenuation correction (SPECTCTAC) and pseudo-CT attenuation correction (SPECTGAN) were acquired. The difference in liver volume between real CT and pseudo-CT images was evaluated. Total counts and uniformity were then used to evaluate the effects of AC. Additionally, the similarity coefficients of SPECTCTAC and SPECTGAN were assessed using a structural similarity (SSIM) index. The pseudo-CT images produced a lower liver volume than the real CT images. SPECTCTAC exhibited a higher total count than SPECTNC and SPECTGAN, which were approximately 60% and 7% lower, respectively. The uniformities of SPECTCTAC and SPECTGAN were better than those of SPECTNC. The mean SSIM value for SPECTCTAC and SPECTGAN was 0.97. We proposed a deep learning-based AC approach to generate pseudo-CT images from SPECTNC images in 99mTc-GSA scintigraphy. SPECTGAN with AC using pseudo-CT images was similar to SPECTCTAC, demonstrating the possibility of SPECT/CT examination with reduced exposure to radiation.
Similar content being viewed by others
References
Ha-Kawa SK, Tanaka Y, Hasebe S, et al. Compartmental analysis of asialoglycoprotein receptor scintigraphy for quantitative measurement of liver function: a multicentre study. Eur J Nucl Med. 1997;24:130–7.
Ogasawara G, Inoue Y, Ito Y, et al. Improved reproducibility of simple quantitative indices from 99mTc-GSA liver function imaging. Ann Nucl Med. 2013;27:487–91.
Yoshida M, Shiraishi S, Sakamoto F, et al. Assessment of hepatic functional regeneration after hepatectomy using 99mTc-GSA SPECT/CT fused imaging. Ann Nucl Med. 2014;28:780–8.
Zeintl J, Vija AH, Yahil A, et al. Quantitative accuracy of clinical 99mTc SPECT/CT using ordered-subset expectation maximization with 3-dimensional resolution recovery, attenuation, and scatter correction. J Nucl Med. 2010;51:921–8.
Larkin AM, Serulle Y, Wagner S, et al. Quantifying the increase in radiation exposure associated with SPECT/CT compared to SPECT alone for routine nuclear medicine examinations. Int Mol Imaging. 2011;2011: 897202.
Decuyper M, Maebe J, Van Holen R, et al. Artificial intelligence with deep learning in nuclear medicine and radiology. EJNMMI Phys. 2021;8:81.
Goodfellow IJ, Pouget-Abadie J, Mirza M, et al. Generative adversarial nets. In: NIPS 27 proceeding, 2014; 2672–2680.
Dong X, Wang T, Lei Y, et al. Synthetic CT generation from non-attenuation corrected PET images for whole-body PET imaging. Phys Med Biol. 2019;64: 215016.
Chen Y, Goorden MC, Beekman FJ. Convolution neural network based attenuation correction for 123I-FP-CIT SPECT with focused striatum imaging. Phys Med Biol. 2021;66: 195007.
Sakaguchi K, Kaida H, Yoshida S, et al. Attenuation correction using deep learning for brain perfusion SPECT images. Ann Nucl Med. 2021;35:589–99.
Torkaman M, Yang J, Shi L, et al. Direct image-based attenuation correction using conditional generative adversarial network for SPECT myocardial perfusion imaging. In: Proc SPIE Int Soc Opt Eng. 2021;11600
Koizumi K, Uchiyama G, Arai T, et al. A new liver functional study using Tc-99m DTPA-galactosyl human serum albumin: evaluation of the validity of several functional parameters. Ann Nucl Med. 1992;6:83–7.
Peters SMB, van der Werf NR, Segbers M, et al. Towards standardization of absolute SPECT/CT quantification: a multi-center and multi-vendor phantom study. EJNMMI Phys. 2019;6:29.
Okuda K, Nakajima K, Yamada M, et al. Optimization of iterative reconstruction parameters with attenuation correction, scatter correction and resolution recovery in myocardial perfusion SPECT/CT. Ann Nucl Med. 2014;28:60–8.
Patton JA, Turkington TG. SPECT/CT physical principles and attenuation correction. J Nucl Med Technol. 2008;36:1–10.
Zhu JY, Park T, Isola P, et al. Unpaired image-to-image translation using cycle-consistent adversarial networks. In: ICCV2017 Conference Proceedings 2017; 1:2242–51.
Fukui R, Fujii S, Ninomiya H, et al. Generation of the pseudo CT image based on the deep learning technique aimed for the attenuation correction of the PET image. Nihon Hoshasen Gijutsu Zasshi. 2020;76:1152–62.
Otsu N. A threshold selection method from gray-level histograms. IEEE Trans Sys Man Cyber. 1979;9:62–6.
Wnag Z, Bovik AC, Sheikh HR, et al. Image quality assessment: from error visibility to structural similarity. IEEE Trans Image Process. 2004;13:600–12.
Onishi H, Motomura N, Fujino K, et al. Quantitative performance of advanced resolution recovery strategies on SPECT images: evaluation with use of digital phantom models. Radio Phys Technol. 2013;6:42–53.
Sumiyoshi T, Shima Y, Tokorodani R, et al. CT/99mTc-GSA SPECT fusion images demonstrate functional differences between the liver lobes. World J Gastroenterol. 2013;19:3217–25.
Nakamura Y, Tomiguchi S, Tanaka M. Reliability and advantages of using non-uniform Chang’s attenuation correction method using a CT-based attenuation coefficient map in 99mTc-GSA SPECT/CT hepatic imaging. EJNMMI Phys. 2015;2:17.
Maeda H, Yamaki N, Azuma M. Development of the software package of the nuclear medicine data processor for education and research. Nihon Hoshasen Gijutsu Zasshi. 2012;68:299–306.
Ronneberger O, Fischer P, Brox T. U-Net: convolutional networks for biomedical image segmentation. arXiv e-prints; 2015.
Nakamoto Y, Chin BB, Cohade C, et al. PET/CT: artifacts caused by bowel motion. Nucl Med Commun. 2004;25:221–5.
Suzuki A, Koshida K, Matsubara K. Effects of pacemaker, implantable cardioverter-defibrillator, and left ventricular leads on CT-based attenuation correction. J Nucl Med Technol. 2014;42:37–41.
Osman MM, Cohade C, Nakamoto Y, et al. Respiratory motion artifacts on PET emission images obtained using CT attenuation correction on PET-CT. Eur J Nucl Med Mol Imaging. 2003;30:603–6.
Funding
None.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
The authors declare no conflicts of interest.
Ethical approval
This article does not include any studies performed on human participants or animals.
Informed consent
No human participants were involved in this work.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
About this article
Cite this article
Miyai, M., Fukui, R., Nakashima, M. et al. Deep learning-based attenuation correction method in 99mTc-GSA SPECT/CT hepatic imaging: a phantom study. Radiol Phys Technol 17, 165–175 (2024). https://doi.org/10.1007/s12194-023-00762-x
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s12194-023-00762-x