Skip to main content
SpringerLink
Log in

Generating PET Attenuation Maps via Sim2Real Deep Learning–Based Tissue Composition Estimation Combined with MLACF

  • Published:
Journal of Imaging Informatics in Medicine Aims and scope Submit manuscript

Abstract

Deep learning (DL) has recently attracted attention for data processing in positron emission tomography (PET). Attenuation correction (AC) without computed tomography (CT) data is one of the interests. Here, we present, to our knowledge, the first attempt to generate an attenuation map of the human head via Sim2Real DL-based tissue composition estimation from model training using only the simulated PET dataset. The DL model accepts a two-dimensional non-attenuation-corrected PET image as input and outputs a four-channel tissue-composition map of soft tissue, bone, cavity, and background. Then, an attenuation map is generated by a linear combination of the tissue composition maps and, finally, used as input for scatter+random estimation and as an initial estimate for attenuation map reconstruction by the maximum likelihood attenuation correction factor (MLACF), i.e., the DL estimate is refined by the MLACF. Preliminary results using clinical brain PET data showed that the proposed DL model tended to estimate anatomical details inaccurately, especially in the neck-side slices. However, it succeeded in estimating overall anatomical structures, and the PET quantitative accuracy with DL-based AC was comparable to that with CT-based AC. Thus, the proposed DL-based approach combined with the MLACF is also a promising CT-less AC approach.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11
Fig. 12

Similar content being viewed by others

References

  1. Phelps ME. PET: Molecular imaging and its biological applications. New York: Springer; 2012.

    Google Scholar 

  2. Habib Z, Montandon M, Alavi A. Advances in attenuation correction techniques in PET. PET Clin. 2007;2:191–217. https://doi.org/10.1016/j.cpet.2007.12.002.

    Article  Google Scholar 

  3. Habib Z, Montandon M. Scatter compensation techniques in PET. PET Clin. 2007;2:219–234. https://doi.org/10.1016/j.cpet.2007.10.003.

    Article  Google Scholar 

  4. Mohammad D, Jiang X, Schäfers K. Correction techniques in emission tomography. Boca Raton: CRC Press; 2012.

    Google Scholar 

  5. Burger C, Goerres G, Schoenes S, Buck A, Lonn AHR, Von Schulthess GK. PET attenuation coefficients from CT images: experimental evaluation of the transformation of CT into PET 511-keV attenuation coefficients. Eur J Nucl Med Mol Imaging. 2002;29:922–927. https://doi.org/10.1007/s00259-002-0796-3.

    Article  CAS  PubMed  Google Scholar 

  6. Ladefoged CN, Law I, Anazoda U, Lawrence KS, Izquierdo-Garcia D, Catana C, et al. A multi-centre evaluation of eleven clinically feasible brain PET/MRI attenuation correction techniques using a large cohort of patients. Neuroimage. 2017;147:346–359. https://doi.org/10.1016/j.neuroimage.2016.12.010.

    Article  PubMed  Google Scholar 

  7. Bailey DL. Transmission scanning in emission tomography. Eur J Nucl Med. 1998;25:774–787. https://doi.org/10.1007/s002590050282.

    Article  CAS  PubMed  Google Scholar 

  8. Defrise M, Ahmadreza R, Nuyts J. Time-of-flight PET data determine the attenuation sinogram up to a constant. Phys Med Biol. 2012;57.4:885. https://doi.org/10.1088/0031-9155/57/4/885

    Article  PubMed  Google Scholar 

  9. Berker Y, Li Y. Attenuation correction in emission tomography using the emission data—a review. Med Phys. 2016;43.2:807-832. https://doi.org/10.1118/1.4938264

    Article  PubMed  PubMed Central  Google Scholar 

  10. Bal H, Panin VY, Platsch G, Defrise M, Hayden G, Hutton C, Serrano B, Paulmier B, Casey ME. Evaluation of MLACF based calculated attenuation brain PET imaging for FDG patient studies. Phys Med Biol. 2017;62.7:2542. https://doi.org/10.1088/1361-6560/aa5e99

    Article  CAS  PubMed  Google Scholar 

  11. Morimoto-Ishikawa D, Hanaoka K, Watanabe S, Yamada T, Yamakawa Y, Minagawa S, Tekenouchi S, Ohtani A, Mizuta T, Kaida H, Ishii K. Evaluation of the performance of a high-resolution time-of-flight PET system dedicated to the head and breast according to NEMA NU 2-2012 standard. EJNMMI Phys. 2022;9:88. https://doi.org/10.1186/s40658-022-00518-3.

    Article  PubMed  PubMed Central  Google Scholar 

  12. Kobayashi T, Kitamura K. A solution for scaling problem in joint estimation of activity and attenuation. 2017 IEEE NSS/MIC, Atlanta, GA, USA. 2017:1–5. https://doi.org/10.1109/NSSMIC.2017.8532856.

  13. Mizuta T, Kobayashi T, Yamakawa Y, Hanaoka K, Watanabe S, Morimoto-Ishikawa D, Yamada T, Kaida H, Ishii K. Initial evaluation of a new maximum-likelihood attenuation correction factor-based attenuation correction for time-of-flight brain PET. Ann Nucl Med. 2022;36:420–426. https://doi.org/10.1007/s12149-022-01721-z.

    Article  PubMed  Google Scholar 

  14. Gong K, Berg E, Cherry S, Qi J. Machine learning in PET: from photon detection to quantitative image reconstruction. Proc IEEE. 2019;108:51–68. https://doi.org/10.1109/JPROC.2019.2936809.

    Article  Google Scholar 

  15. Wang T, Lei Y, Curran WJ, Liu T, Nye JA, Yang X. Machine learning in quantitative PET: A review of attenuation correction and low-count image reconstruction methods. Phys Med. 2020;76:294–306. https://doi.org/10.1016/j.ejmp.2020.07.028.

    Article  PubMed  PubMed Central  Google Scholar 

  16. Arabi H, Allaf AA, Sanaat A, Shiri I, Zaidi H. The promise of artificial intelligence and deep learning in PET and SPECT imaging. Phys Med. 2021;83:122–137. https://doi.org/10.1016/j.ejmp.2021.03.008.

    Article  PubMed  Google Scholar 

  17. Lee JS. A review of deep-learning-based approaches for attenuation correction in positron emission tomography. IEEE Trans Radiat Plasma Med Sci. 2020;5:160–184. https://doi.org/10.1109/TRPMS.2020.3009269.

    Article  Google Scholar 

  18. Wagenknecht G, Kaiser HJ, Mottaghy MF, Herzog H. MRI for attenuation correction in PET: methods and challenges. MAGMA. 2013;26:99–113. https://doi.org/10.1007/s10334-012-0353-4.

    Article  PubMed  Google Scholar 

  19. Ahmadreza R, Defrise M, Nuyts J. ML-reconstruction for TOF-PET with simultaneous estimation of the attenuation factors. IEEE Trans Med Imaging. 2014;33:1563–1572. https://doi.org/10.1109/TMI.2014.2318175.

    Article  Google Scholar 

  20. Aksoy Y, Oh T, Paris S, Pollefeys M, Matusik W. Semantic soft segmentation. ACM Trans Graph. 2018;37:1-13. https://doi.org/10.1145/3197517.3201275.

    Article  Google Scholar 

  21. Ronneberger O, Fischer P, Brox T. U-Net: Convolutional networks for biomedical image segmentation. In: Navab N, Hornegger J, Wells W, Frangi A, editors. Medical Image Computing and Computer-Assisted Intervention. MICCAI 2015. Lecture Notes in Computer Science, vol. 9351. Springer; 2015. https://doi.org/10.1007/978-3-319-24574-4_28

  22. Ishii K, Hanaoka K, Watanabe S, Morimoto-Ishikawa D, Yamada T, Kaida H, Yamakawa Y, Minagawa S, Takenouchi S, Ohtani A, Mizuta T. High-resolution silicon photomultiplier time-of-flight dedicated head PET system for clinical brain studies. J Nucl Med. 2023;64:153–158. https://doi.org/10.2967/jnumed.122.264080.

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  23. Liu F, Jang H, Kijowski R, Zhao G, Bradshaw T, McMillan AB. A deep learning approach for 18F-FDG PET attenuation correction. EJNMMI Phys. 2018;5:1–15. https://doi.org/10.1186/s40658-018-0225-8.

    Article  Google Scholar 

  24. Dong X, Wang T, Lei Y, Higgins K, Liu T, Curran WJ, Mai H, Nye JA, Yang X. Synthetic CT generation from non-attenuation corrected PET images for whole-body PET imaging. Phys Med Biol. 2019;64:215016. https://doi.org/10.1088/1361-6560/ab4eb7.

    Article  PubMed  PubMed Central  Google Scholar 

  25. Armanious K, Hepp T, Küstner T, Dittman H, Nikolaou K, La Fougere C, Yang B, Gatidis S. Independent attenuation correction of whole body [18F] FDG-PET using a deep learning approach with Generative Adversarial Networks. EJNMMI Res. 2020;10:1–9. https://doi.org/10.1186/s13550-020-00644-y.

    Article  Google Scholar 

  26. Aubert-Broche B, Griffin M, Pike GB, Evans AC, Collins DL. Twenty new digital brain phantoms for creation of validation image data bases. IEEE Trans Med Imaging. 2006;25:1410–1416. https://doi.org/10.1109/TMI.2006.883453.

    Article  PubMed  Google Scholar 

  27. Watson CC, Newport DF, Casey ME. A single scatter simulation technique for scatter correction in 3D PET. In: Grangeat P, Amans JL, editors. Three-dimensional image reconstruction in radiology and nuclear medicine. Computation imaging and vision, vol. 4. Dordrecht: Springer; 1996. pp. 255–268. https://doi.org/10.1007/978-94-015-8749-5_18.

  28. Hudson HM, Larkin RS. Accelerated image reconstruction using ordered subsets of projection data. IEEE Trans Med Imaging. 1994;13:601–609. https://doi.org/10.1109/42.363108.

    Article  CAS  PubMed  Google Scholar 

  29. Hashimoto F, Ito M, Ote K, Isobe T, Okada H, Ouchi Y. Deep learning-based attenuation correction for brain PET with various radiotracers. Ann Nucl Med. 2021;35:691–701. https://doi.org/10.1007/s12149-021-01611-w.

    Article  CAS  PubMed  Google Scholar 

  30. Kingma DP, Ba AJ. A method for stochastic optimization. ArXiv e-prints [Internet]. 2014. Available from: http://arxiv.org/abs/1412.6980. Accessed 13 Nov 2023.

  31. Abadi M, Agarwal A, Barham P, Brevdo E, Chen Z, Citro C, et al. TensorFlow: large-scale machine learning on heterogeneous distributed systems. ArXiv e-prints [Internet]. 2016. Available from: http://arxiv.org/abs/1603.04467. Accessed 13 Nov 2023.

  32. Nakayama T, Kudo H. Derivation and implementation of ordered-subsets algorithms for list-mode PET data. IEEE Nucl Sci Symp Conf Rec, Fajardo, PR, USA. 2005;4:1954. https://doi.org/10.1109/NSSMIC.2005.1596714

  33. Maes F, Collignon A, Vandermeulen D, Marchal G, Suetens P. Multimodality image registration by maximization of mutual information. IEEE Trans Med Imaging. 1997;16:187–198. https://doi.org/10.1109/42.563664

    Article  CAS  PubMed  Google Scholar 

Download references

Acknowledgements

This study continues from a previous research project (jRCTs052200055) funded by Shimadzu Corporation. The NAC images in Figs. 6, 7, and 8 are part of previous research data. We thank Edanz (https://jp.edanz.com/ac) for editing a draft of this manuscript.

Author information

Authors and Affiliations

  1. Technology Research Laboratory, Shimadzu Corporation, 3-9-4, Hikaridai, Seika-cho, Soraku-gun, Kyoto, 619-0237, Japan

    Tetsuya Kobayashi & Yui Shigeki

  2. Medical Systems Division, Shimadzu Corporation, 1, Nishinokyo Kuwabara-cho, Nakagyo-ku, Kyoto, 604-8511, Japan

    Yoshiyuki Yamakawa, Yumi Tsutsumida & Tetsuro Mizuta

  3. Division of Positron Emission Tomography, Institute of Advanced Clinical Medicine, Kindai University, 377-2, Onohigashi, Osakasayama, Osaka, 589-8511, Japan

    Kohei Hanaoka, Shota Watanabe, Daisuke Morimoto‑Ishikawa, Takahiro Yamada, Hayato Kaida & Kazunari Ishii

  4. Department of Radiology, Faculty of Medicine, Kindai University, 377-2, Onohigashi, Osakasayama, Osaka, 589-8511, Japan

    Hayato Kaida & Kazunari Ishii

Authors
  1. Tetsuya Kobayashi
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Yui Shigeki
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Yoshiyuki Yamakawa
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Yumi Tsutsumida
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Tetsuro Mizuta
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Kohei Hanaoka
    View author publications

    You can also search for this author in PubMed Google Scholar

  7. Shota Watanabe
    View author publications

    You can also search for this author in PubMed Google Scholar

  8. Daisuke Morimoto‑Ishikawa
    View author publications

    You can also search for this author in PubMed Google Scholar

  9. Takahiro Yamada
    View author publications

    You can also search for this author in PubMed Google Scholar

  10. Hayato Kaida
    View author publications

    You can also search for this author in PubMed Google Scholar

  11. Kazunari Ishii
    View author publications

    You can also search for this author in PubMed Google Scholar

Contributions

TK and YS conceived the idea of the study. TK, YS, YY, and YT developed and implemented the computational algorithm. TK and YS designed and conducted the experiments to evaluate the performance of the algorithm. TK, YS, KH, SW, DMI, and TY contributed to the interpretation of the results. TK, YS, and TM drafted the original manuscript. TM, HK, and KI supervised the conduct of this study. All authors reviewed the manuscript draft and revised it.

Corresponding author

Correspondence to Tetsuya Kobayashi.

Ethics declarations

Ethics Approval

There are no procedures requiring ethics approval relevant to this article.

Consent to Participate

There are no procedures requiring informed consent relevant to this article.

Consent for Publication

All authors have approved the manuscript and agree with the submission.

Competing Interests

Tetsuya Kobayashi, Yui Shigeki, Yoshiyuki Yamakawa, Yumi Tsutsumida, and Tetsuro Mizuta are employees of Shimadzu Corp. There are no other potential conflicts of interest relevant to this article.

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.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Kobayashi, T., Shigeki, Y., Yamakawa, Y. et al. Generating PET Attenuation Maps via Sim2Real Deep Learning–Based Tissue Composition Estimation Combined with MLACF. J Digit Imaging. Inform. med. 37, 167–179 (2024). https://doi.org/10.1007/s10278-023-00902-0

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s10278-023-00902-0

Keywords

Search

Navigation