Skip to main content

Advertisement

SpringerLink
Log in

Deep learning–based attenuation correction for whole-body PET — a multi-tracer study with 18F-FDG, 68 Ga-DOTATATE, and 18F-Fluciclovine

  • Original Article
  • Published:
European Journal of Nuclear Medicine and Molecular Imaging Aims and scope Submit manuscript

Abstract

A novel deep learning (DL)-based attenuation correction (AC) framework was applied to clinical whole-body oncology studies using 18F-FDG, 68 Ga-DOTATATE, and 18F-Fluciclovine. The framework used activity (λ-MLAA) and attenuation (µ-MLAA) maps estimated by the maximum likelihood reconstruction of activity and attenuation (MLAA) algorithm as inputs to a modified U-net neural network with a novel imaging physics-based loss function to learn a CT-derived attenuation map (µ-CT).

Methods

Clinical whole-body PET/CT datasets of 18F-FDG (N = 113), 68 Ga-DOTATATE (N = 76), and 18F-Fluciclovine (N = 90) were used to train and test tracer-specific neural networks. For each tracer, forty subjects were used to train the neural network to predict attenuation maps (µ-DL). µ-DL and µ-MLAA were compared to the gold-standard µ-CT. PET images reconstructed using the OSEM algorithm with µ-DL (OSEMDL) and µ-MLAA (OSEMMLAA) were compared to the CT-based reconstruction (OSEMCT). Tumor regions of interest were segmented by two radiologists and tumor SUV and volume measures were reported, as well as evaluation using conventional image analysis metrics.

Results

µ-DL yielded high resolution and fine detail recovery of the attenuation map, which was superior in quality as compared to µ-MLAA in all metrics for all tracers. Using OSEMCT as the gold-standard, OSEMDL provided more accurate tumor quantification than OSEMMLAA for all three tracers, e.g., error in SUVmax for OSEMMLAA vs. OSEMDL: − 3.6 ± 4.4% vs. − 1.7 ± 4.5% for 18F-FDG (N = 152), − 4.3 ± 5.1% vs. 0.4 ± 2.8% for 68 Ga-DOTATATE (N = 70), and − 7.3 ± 2.9% vs. − 2.8 ± 2.3% for 18F-Fluciclovine (N = 44). OSEMDL also yielded more accurate tumor volume measures than OSEMMLAA, i.e., − 8.4 ± 14.5% (OSEMMLAA) vs. − 3.0 ± 15.0% for 18F-FDG, − 14.1 ± 19.7% vs. 1.8 ± 11.6% for 68 Ga-DOTATATE, and − 15.9 ± 9.1% vs. − 6.4 ± 6.4% for 18F-Fluciclovine.

Conclusions

The proposed framework provides accurate and robust attenuation correction for whole-body 18F-FDG, 68 Ga-DOTATATE and 18F-Fluciclovine in tumor SUV measures as well as tumor volume estimation. The proposed method provides clinically equivalent quality as compared to CT in attenuation correction for the three tracers.

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

Similar content being viewed by others

References

  1. Barrett JF, Keat N. Artifacts in CT: recognition and avoidance. Radiographics. 2004;24:1679–91. https://doi.org/10.1148/rg.246045065.

    Article  PubMed  Google Scholar 

  2. Ladefoged CN, Law I, Anazodo U, St Lawrence K, 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;147:346–59. https://doi.org/10.1016/j.neuroimage.2016.12.010.

    Article  PubMed  Google Scholar 

  3. Chen Y, An H. Attenuation correction of PET/MR imaging. Magn Reson Imaging Clin N Am. 2017;25:245–55. https://doi.org/10.1016/j.mric.2016.12.001.

    Article  PubMed  PubMed Central  Google Scholar 

  4. Rezaei A, Defrise M, Bal G, Michel C, Conti M, Watson C, et al. Simultaneous reconstruction of activity and attenuation in time-of-flight PET. IEEE Trans Med Imaging. 2012;31:2224–33. https://doi.org/10.1109/TMI.2012.2212719.

    Article  PubMed  Google Scholar 

  5. Rezaei A, Deroose CM, Vahle T, Boada F, Nuyts J. Joint reconstruction of activity and attenuation in time-of-flight pet: a quantitative analysis. J Nucl Med. 2018;59:1630. https://doi.org/10.2967/jnumed.117.204156.

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  6. Hwang D, Kang SK, Kim KY, Seo S, Paeng JC, Lee DS, et al. Generation of PET attenuation map for whole-body time-of-flight (18)F-FDG PET/MRI using a deep neural network trained with simultaneously reconstructed activity and attenuation maps. J Nucl Med. 2019;60:1183–9. https://doi.org/10.2967/jnumed.118.219493.

    Article  PubMed  PubMed Central  Google Scholar 

  7. Shi L, Onofrey J, Revilla EM, Toyonaga T, Menard D, Ankrah J, et al. A novel loss function incorporating imaging acquisition physics for PET attenuation map generation using deep learning. Med Image Comput Comput Assist Interv. 2019;11767:723–31. https://doi.org/10.1007/978-3-030-32251-9_79.

    Article  Google Scholar 

  8. Maurer T, Eiber M, Schwaiger M, Gschwend JE. Current use of PSMA-PET in prostate cancer management. Nat Rev Urol. 2016;13:226–35. https://doi.org/10.1038/nrurol.2016.26.

    Article  CAS  PubMed  Google Scholar 

  9. Calais J, Ceci F, Eiber M, Hope TA, Hofman MS, Rischpler C, et al. (18)F-fluciclovine PET-CT and (68)Ga-PSMA-11 PET-CT in patients with early biochemical recurrence after prostatectomy: a prospective, single-centre, single-arm, comparative imaging trial. Lancet Oncol. 2019;20:1286–94. https://doi.org/10.1016/S1470-2045(19)30415-2.

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  10. Poeppel TD, Binse I, Petersenn S, Lahner H, Schott M, Antoch G, et al. 68Ga-DOTATOC versus 68Ga-DOTATATE PET/CT in functional imaging of neuroendocrine tumors. J Nucl Med. 2011;52:1864–70. https://doi.org/10.2967/jnumed.111.091165.

    Article  CAS  PubMed  Google Scholar 

  11. Panin VY, Aykac M, Casey ME. Simultaneous reconstruction of emission activity and attenuation coefficient distribution from TOF data, acquired with external transmission source. Phys Med Biol. 2013;58:3649–69. https://doi.org/10.1088/0031-9155/58/11/3649.

    Article  CAS  PubMed  Google Scholar 

  12. Onofrey JA, Casetti-Dinescu DI, Lauritzen AD, Sarkar S, Venkataraman R, Fan RE, et al. Generalizable multi-site training and testing of deep neural networks using image normalization. Biomedical Imaging (ISBI), 2019 IEEE 16th International Symposium on; 2019. p. pp. 1–4.

  13. Ronneberger O, Fischer P, Brox T. U-Net: Convolutional networks for biomedical image segmentation. Cham: Springer International Publishing; 2015. p. 234–41.

    Google Scholar 

  14. Shi L, Onofrey JA, Revilla EM, Toyonaga T, Menard D, Ankrah J, et al. A novel loss function incorporating imaging acquisition physics for PET attenuation map generation using deep learning. Cham: Springer International Publishing; 2019. p. 723–31.

    Google Scholar 

  15. Nie D, Trullo R, Lian J, Wang L, Petitjean C, Ruan S, et al. Medical image synthesis with deep convolutional adversarial networks. Ieee T Bio-Med Eng. 2018;65:2720–30. https://doi.org/10.1109/Tbme.2018.2814538.

    Article  Google Scholar 

  16. Kingma DP, Ba J. Adam: a method for stochastic optimization. 2014. p. arXiv:1412.6980.

  17. Onofrey JA, Casetti-Dinescu DI, Lauritzen AD, Sarkar S, Venkataraman R, Fan RE, et al. Generalizable multi-site training and testing of deep neural networks using image normalization. Proc IEEE Int Symp Biomed Imaging. 2019;2019:348–51. https://doi.org/10.1109/isbi.2019.8759295.

    Article  PubMed  PubMed Central  Google Scholar 

  18. Hirata K, Furuya S, Huang SC, Manabe O, Magota K, Kobayashi K, et al. A semi-automated method to separate tumor from physiological uptakes on FDG PET-CT for efficient generation of training data targeting deep learning. J Nucl Med. 2019;60:supplement 1213.

    Article  Google Scholar 

  19. Bradshaw TJ, Zhao G, Jang H, Liu F, McMillan AB. Feasibility of deep learning-based PET/MR attenuation correction in the pelvis using only diagnostic MR images. Tomography. 2018;4:138–47. https://doi.org/10.18383/j.tom.2018.00016.

    Article  PubMed  PubMed Central  Google Scholar 

  20. Arabi H, Zeng G, Zheng G, Zaidi H. Novel adversarial semantic structure deep learning for MRI-guided attenuation correction in brain PET/MRI. Eur J Nucl Med Mol Imaging. 2019;46:2746–59. https://doi.org/10.1007/s00259-019-04380-x.

    Article  PubMed  Google Scholar 

  21. Liu F, Jang H, Kijowski R, Zhao G, Bradshaw T, McMillan AB. A deep learning approach for (18)F-FDG PET attenuation correction. EJNMMI Phys. 2018;5:24. https://doi.org/10.1186/s40658-018-0225-8.

    Article  PubMed  PubMed Central  Google Scholar 

  22. Dong X, Wang T, Lei Y, Higgins K, Liu T, Curran WJ, et al. 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 

  23. Shiri I, Ghafarian P, Geramifar P, Leung KH, Ghelichoghli M, Oveisi M, et al. Direct attenuation correction of brain PET images using only emission data via a deep convolutional encoder-decoder (Deep-DAC). Eur Radiol. 2019;29:6867–79. https://doi.org/10.1007/s00330-019-06229-1.

    Article  PubMed  Google Scholar 

  24. 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. https://doi.org/10.1007/s12149-021-01611-w.

    Article  PubMed  PubMed Central  Google Scholar 

  25. Lee JS. A review of deep-learning-based approaches for attenuation correction in positron emission tomography. IEEE Transactions on Radiation and Plasma Medical Sciences. 2021;5:160–84. https://doi.org/10.1109/TRPMS.2020.3009269.

    Article  Google Scholar 

  26. Gong K, Guan J, Kim K, Zhang X, Yang J, Seo Y, et al. Iterative PET Image reconstruction using convolutional neural network representation. Ieee T Med Imaging. 2019;38:675–85. https://doi.org/10.1109/TMI.2018.2869871.

    Article  Google Scholar 

  27. Lu W, Onofrey JA, Lu Y, Shi L, Ma T, Liu Y, et al. An investigation of quantitative accuracy for deep learning based denoising in oncological PET. Phys Med Biol. 2019;64:165019. https://doi.org/10.1088/1361-6560/ab3242.

    Article  CAS  PubMed  Google Scholar 

  28. Li Y, Jiang L, Wang H, Cai H, Xiang Y, Li L. Effective radiation dose of 18f-Fdg Pet/Ct: how much does diagnostic Ct contribute? Radiat Prot Dosimetry. 2019;187:183–90. https://doi.org/10.1093/rpd/ncz153.

    Article  CAS  PubMed  Google Scholar 

  29. Lu Y, Gallezot JD, Naganawa M, Ren S, Fontaine K, Wu J, et al. Data-driven voluntary body motion detection and non-rigid event-by-event correction for static and dynamic PET. Phys Med Biol. 2019;64:065002. https://doi.org/10.1088/1361-6560/ab02c2.

    Article  CAS  PubMed  Google Scholar 

  30. Lu Y, Fontaine K, Mulnix T, Onofrey JA, Ren S, Panin V, et al. Respiratory motion compensation for PET/CT with motion information derived from matched attenuation-corrected gated PET data. J Nucl Med. 2018;59:1480–6. https://doi.org/10.2967/jnumed.117.203000.

    Article  PubMed  PubMed Central  Google Scholar 

  31. Teimoorisichani M, Sari H, Panin V, Bharkhada D, Rominger A, Conti M. Using LSO background radiation for CT-less attenuation correction of PET data in long axial FOV PET scanners. Journal of Nuclear Medicine. 2021;62:1530-.

  32. Rothfuss H, Panin V, Moor A, Young J, Hong I, Michel C, et al. LSO background radiation as a transmission source using time of flight. Phys Med Biol. 2014;59:5483–500. https://doi.org/10.1088/0031-9155/59/18/5483.

    Article  PubMed  Google Scholar 

Download references

Acknowledgements

We would like to thank Judson Jones and Vladimir Panin from the Siemens Healthcare for the reconstruction software support. We thank Zhongdong Sun for the IT support. Its contents are solely the responsibility of the authors and do not necessarily represent the official view of NIH.

Funding

This work was supported by NIH grants R03EB027209 and R21EB028954.

Author information

Author notes

  1. Takuya Toyonaga and Dan Shao contributed equally to this work.

Authors and Affiliations

  1. Department of Radiology and Biomedical Imaging, Yale University, New Haven, CT, USA

    Takuya Toyonaga, Dan Shao, Jiazhen Zhang, Enette Mae Revilla, Ming-Kai Chen, John A. Onofrey & Yihuan Lu

  2. Guangdong Provincial People’s Hospital, Guangzhou, Guangdong, China

    Dan Shao

  3. Department of Biomedical Engineering, Yale University, New Haven, CT, 06520, USA

    Luyao Shi & John A. Onofrey

  4. Yale New Haven Hospital, New Haven, CT, USA

    David Menard, Joseph Ankrah & Ming-Kai Chen

  5. Department of Diagnostic Imaging, School of Medicine, Hokkaido University, Sapporo, Hokkaido, Japan

    Kenji Hirata

  6. Department of Urology, Yale University, New Haven, CT, USA

    John A. Onofrey

Authors
  1. Takuya Toyonaga
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Dan Shao
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Luyao Shi
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Jiazhen Zhang
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Enette Mae Revilla
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. David Menard
    View author publications

    You can also search for this author in PubMed Google Scholar

  7. Joseph Ankrah
    View author publications

    You can also search for this author in PubMed Google Scholar

  8. Kenji Hirata
    View author publications

    You can also search for this author in PubMed Google Scholar

  9. Ming-Kai Chen
    View author publications

    You can also search for this author in PubMed Google Scholar

  10. John A. Onofrey
    View author publications

    You can also search for this author in PubMed Google Scholar

  11. Yihuan Lu
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Yihuan Lu.

Ethics declarations

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.

Takuya Toyonaga and Dan Shao are the co-first authors.

This article is part of the Topical collection on Advanced Image Analyses (Radiomics and Artificial Intelligence)

Supplementary Information

Below is the link to the electronic supplementary material.

Supplementary file1 (DOCX 5626 KB)

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Toyonaga, T., Shao, D., Shi, L. et al. Deep learning–based attenuation correction for whole-body PET — a multi-tracer study with 18F-FDG, 68 Ga-DOTATATE, and 18F-Fluciclovine. Eur J Nucl Med Mol Imaging 49, 3086–3097 (2022). https://doi.org/10.1007/s00259-022-05748-2

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00259-022-05748-2

Keywords

Search

Navigation