nach oben

European Journal of Nuclear Medicine and Molecular Imaging

Erschienen in:

09.12.2021 | COVID-19 | Original Article

Comparison of deep learning-based emission-only attenuation correction methods for positron emission tomography

verfasst von: Donghwi Hwang, Seung Kwan Kang, Kyeong Yun Kim, Hongyoon Choi, Jae Sung Lee

Erschienen in: European Journal of Nuclear Medicine and Molecular Imaging | Ausgabe 6/2022

Einloggen, um Zugang zu erhalten

Abstract

Purpose

This study aims to compare two approaches using only emission PET data and a convolution neural network (CNN) to correct the attenuation (μ) of the annihilation photons in PET.

Methods

One of the approaches uses a CNN to generate μ-maps from the non-attenuation-corrected (NAC) PET images (μ-CNN_NAC). In the other method, CNN is used to improve the accuracy of μ-maps generated using maximum likelihood estimation of activity and attenuation (MLAA) reconstruction (μ-CNN_MLAA). We investigated the improvement in the CNN performance by combining the two methods (μ-CNN_MLAA+NAC) and the suitability of μ-CNN_NAC for providing the scatter distribution required for MLAA reconstruction. Image data from ¹⁸F-FDG (n = 100) or ⁶⁸ Ga-DOTATOC (n = 50) PET/CT scans were used for neural network training and testing.

Results

The error of the attenuation correction factors estimated using μ-CT and μ-CNN_NAC was over 7%, but that of scatter estimates was only 2.5%, indicating the validity of the scatter estimation from μ-CNN_NAC. However, CNN_NAC provided less accurate bone structures in the μ-maps, while the best results in recovering the fine bone structures were obtained by applying CNN_MLAA+NAC. Additionally, the μ-values in the lungs were overestimated by CNN_NAC. Activity images (λ) corrected for attenuation using μ-CNN_MLAA and μ-CNN_MLAA+NAC were superior to those corrected using μ-CNN_NAC, in terms of their similarity to λ-CT. However, the improvement in the similarity with λ-CT by combining the CNN_NAC and CNN_MLAA approaches was insignificant (percent error for lung cancer lesions, λ-CNN_NAC = 5.45% ± 7.88%; λ-CNN_MLAA = 1.21% ± 5.74%; λ-CNN_MLAA+NAC = 1.91% ± 4.78%; percent error for bone cancer lesions, λ-CNN_NAC = 1.37% ± 5.16%; λ-CNN_MLAA = 0.23% ± 3.81%; λ-CNN_MLAA+NAC = 0.05% ± 3.49%).

Conclusion

The use of CNN_NAC was feasible for scatter estimation to address the chicken-egg dilemma in MLAA reconstruction, but CNN_MLAA outperformed CNN_NAC.

Nur mit Berechtigung zugänglich

Ollinger JM. Model-based scatter correction for fully 3D PET. Phys Med Biol. 1996;41:153–76. https://doi.org/10.1088/0031-9155/41/1/012.CrossRefPubMed

Watson CC. New, faster, image-based scatter correction for 3D PET. IEEE Trans Nucl Sci. 2000;47:1587–94.CrossRef

Accorsi R, Adam LE, Werner ME, Karp JS. Optimization of a fully 3D single scatter simulation algorithm for 3D PET. Phys Med Biol. 2004;49:2577–98. https://doi.org/10.1088/0031-9155/49/12/008.CrossRefPubMed

Kinahan PE, Townsend DW, Beyer T, Sashin D. Attenuation correction for a combined 3D PET/CT scanner. Med Phys. 1998;25:2046–53. https://doi.org/10.1118/1.598392.CrossRefPubMed

Townsend DW. Dual-modality imaging: combining anatomy and function. J Nucl Med. 2008;49:938–55. https://doi.org/10.2967/jnumed.108.051276.CrossRefPubMed

Martinez-Möller A, Souvatzoglou M, Delso G, Bundschuh RA, Chefd’hotel C, Ziegler SI, et al. Tissue classification as a potential approach for attenuation correction in whole-body PET/MRI: evaluation with PET/CT data. J Nucl Med. 2009;50:520–6.CrossRefPubMed

Keereman V, Fierens Y, Broux T, De Deene Y, Lonneux M, Vandenberghe S. MRI-based attenuation correction for PET/MRI using ultrashort echo time sequences. J Nucl Med. 2010;51:812–8.CrossRefPubMed

Catana C, van der Kouwe A, Benner T, Michel CJ, Hamm M, Fenchel M, et al. Toward implementing an MRI-based PET attenuation-correction method for neurologic studies on the MR-PET brain prototype. J Nucl Med. 2010;51:1431–8.CrossRefPubMed

An HJ, Seo S, Kang H, Choi H, Cheon GJ, Kim H-J, et al. MRI-based attenuation correction for PET/MRI using multiphase level-set method. J Nucl Med. 2016;57:587–93.CrossRefPubMed

10.

Sureshbabu W, Mawlawi O. PET/CT imaging artifacts. J Nucl Med Technol. 2005;33:156–61.PubMed

11.

Beyer T, Bockisch A, Kühl H, Martinez M-J. Whole-body 18F-FDG PET/CT in the presence of truncation artifacts. J Nucl Med. 2006;47:91–9.PubMed

12.

Goerres GW, Ziegler SI, Burger C, Berthold T, Von Schulthess GK, Buck A. Artifacts at PET and PET/CT caused by metallic hip prosthetic material. Radiology. 2003;226:577–84. https://doi.org/10.1148/radiol.2262012141.CrossRefPubMed

13.

Ladefoged CN, Law I, Anazodo 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;147:346–59.CrossRefPubMed

14.

Lee JS. A review of deep-learning-based approaches for attenuation correction in positron emission tomography. IEEE Trans Radiat Plasma Med Sci. 2021;5:160–84. https://doi.org/10.1109/TRPMS.2020.3009269.CrossRef

15.

Kim JH, Lee JS, Song I-C, Lee DS. Comparison of segmentation-based attenuation correction methods for PET/MRI: evaluation of bone and liver standardized uptake value with oncologic PET/CT data. J Nucl Med. 2012;53:1878–82.CrossRefPubMed

16.

Samarin A, Burger C, Wollenweber SD, Crook DW, Burger IA, Schmid DT, et al. PET/MR imaging of bone lesions–implications for PET quantification from imperfect attenuation correction. Eur J Nucl Med Mol Imaging. 2012;39:1154–60.CrossRefPubMed

17.

Lodge MA, Mhlanga JC, Cho SY, Wahl RL. Effect of patient arm motion in whole-body PET/CT. J Nucl Med. 2011;52:1891–7.CrossRefPubMed

18.

Beyer T, Antoch G, Blodgett T, Freudenberg LF, Akhurst T, Mueller S. Dual-modality PET/CT imaging: the effect of respiratory motion on combined image quality in clinical oncology. Eur J Nucl Med Mol Imaging. 2003;30:588–96. https://doi.org/10.1007/s00259-002-1097-6.CrossRefPubMed

19.

Osman MM, Cohade C, Nakamoto Y, Wahl RL. 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. https://doi.org/10.1007/s00259-002-1024-x.CrossRefPubMed

20.

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

21.

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. Proc Med Image Comput Comput Assist Interv. 2019:723–31.

22.

Bauer CE, Brefczynski-Lewis J, Marano G, Mandich MB, Stolin A, Martone P, et al. Concept of an upright wearable positron emission tomography imager in humans. Brain Behav. 2016;6:e00530.CrossRefPubMedPubMedCentral

23.

Tashima H, Yoshida E, Iwao Y, Wakizaka H, Maeda T, Seki C, et al. First prototyping of a dedicated PET system with the hemisphere detector arrangement. Phys Med Biol. 2019;64:065004. https://doi.org/10.1088/1361-6560/ab012c.CrossRefPubMed

24.

Armanious K, Kustner T, Reimold M, Nikolaou K, La Fougere C, Yang B, et al. Independent brain (18)F-FDG PET attenuation correction using a deep learning approach with Generative Adversarial Networks. Hell J Nucl Med. 2019;22:179–86. https://doi.org/10.1967/s002449911053.CrossRefPubMed

25.

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.CrossRefPubMedPubMedCentral

26.

Arabi H, Bortolin K, Ginovart N, Garibotto V, Zaidi H. Deep learning-guided joint attenuation and scatter correction in multitracer neuroimaging studies. Hum Brain Mapp. 2020;41:3667–79. https://doi.org/10.1002/hbm.25039.CrossRefPubMedPubMedCentral

27.

Dong X, Lei Y, Wang T, Higgins K, Liu T, Curran WJ, et al. Deep learning-based attenuation correction in the absence of structural information for whole-body PET imaging. Phys Med Biol. 2019. https://doi.org/10.1088/1361-6560/ab652c.CrossRefPubMedPubMedCentral

28.

Shiri I, Arabi H, Geramifar P, Hajianfar G, Ghafarian P, Rahmim A, et al. Deep-JASC: joint attenuation and scatter correction in whole-body (18)F-FDG PET using a deep residual network. Eur J Nucl Med Mol Imaging. 2020;47:2533–48. https://doi.org/10.1007/s00259-020-04852-5.CrossRefPubMed

29.

Yang J, Park D, Gullberg GT, Seo Y. Joint correction of attenuation and scatter in image space using deep convolutional neural networks for dedicated brain (18)F-FDG PET. Phys Med Biol. 2019;64:075019. https://doi.org/10.1088/1361-6560/ab0606.CrossRefPubMedPubMedCentral

30.

Hu Z, Li Y, Zou S, Xue H, Sang Z, Liu X, et al. Obtaining PET/CT images from non-attenuation corrected PET images in a single PET system using Wasserstein generative adversarial networks. Phys Med Biol. 2020;65:215010. https://doi.org/10.1088/1361-6560/aba5e9.CrossRefPubMed

31.

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 18F-FDG PET/MRI using a deep neural network trained with simultaneously reconstructed activity and attenuation maps. J Nucl Med. 2019;60:1183–9.CrossRefPubMedPubMedCentral

32.

Hwang D, Kim KY, Kang SK, Seo S, Paeng JC, Lee DS, et al. Improving the accuracy of simultaneously reconstructed activity and attenuation maps using deep learning. J Nucl Med. 2018;59:1624–9. https://doi.org/10.2967/jnumed.117.202317.CrossRefPubMed

33.

Hwang D, Kim KY, Kang SK, Choi H, Seo S, Paeng JC, et al. Accurate attenuation correction for whole-body Ga-68-DOTATOC PET studies using deep learning. J Nucl Med. 2019;60:568.CrossRef

34.

Hwang D, Kang SK, Kim KY, Choi H, Seo S, Lee JS. Data-driven respiratory phase-matched PET attenuation correction without CT. Phys Med Biol. 2021;66:115009.CrossRef

35.

Chun SY, Kim KY, Lee JS, Fessier JA. Joint estimation of activity distribution and attenuation map for TOF-PET using alternating direction method of multiplier. Proc IEEE Int Symp Biomed Imaging. 2016:86–9.

36.

Defrise M, Rezaei A, Nuyts J. Time-of-flight PET data determine the attenuation sinogram up to a constant. Phys Med Biol. 2012;57:885–99. https://doi.org/10.1088/0031-9155/57/4/885.CrossRefPubMed

37.

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.CrossRefPubMed

38.

Salomon A, Goedicke A, Schweizer B, Aach T, Schulz V. Simultaneous reconstruction of activity and attenuation for PET/MR. IEEE Trans Med Imaging. 2011;30:804–13. https://doi.org/10.1109/tmi.2010.2095464.CrossRefPubMed

39.

Rezaei A, Schramm G, Willekens SMA, Delso G, Van Laere K, Nuyts J. A Quantitative evaluation of joint activity and attenuation reconstruction in TOF PET/MR brain imaging. J Nucl Med. 2019;60:1649–55. https://doi.org/10.2967/jnumed.118.220871.CrossRefPubMedPubMedCentral

40.

Ronneberger O, Fischer P, Brox T. U-net: Convolutional networks for biomedical image segmentation. Proc Med Image Comput Comput Assist Interv. 2015:234–41.

41.

Hegazy MAA, Cho MH, Cho MH, Lee SY. U-net based metal segmentation on projection domain for metal artifact reduction in dental CT. Biomed Eng Lett. 2019;9:375–85. https://doi.org/10.1007/s13534-019-00110-2.CrossRefPubMedPubMedCentral

42.

Lee MS, Hwang D, Kim JH, Lee JS. Deep-dose: a voxel dose estimation method using deep convolutional neural network for personalized internal dosimetry. Sci Rep. 2019;9:10308. https://doi.org/10.1038/s41598-019-46620-y.CrossRefPubMedPubMedCentral

43.

Park J, Bae S, Seo S, Park S, Bang JI, Han JH, et al. Measurement of glomerular filtration rate using quantitative SPECT/CT and deep-learning-based kidney segmentation. Sci Rep. 2019;9:4223. https://doi.org/10.1038/s41598-019-40710-7.CrossRefPubMedPubMedCentral

44.

Park J, Hwang D, Kim KY, Kang SK, Kim YK, Lee JS. Computed tomography super-resolution using deep convolutional neural network. Phys Med Biol. 2018;63:145011. https://doi.org/10.1088/1361-6560/aacdd4.CrossRefPubMed

45.

Arabi H, Zaidi H. Whole-body bone segmentation from MRI for PET/MRI attenuation correction using shape-based averaging. Med Phys. 2016;43:5848–61. https://doi.org/10.1118/1.4963809.CrossRefPubMed

Titel: Comparison of deep learning-based emission-only attenuation correction methods for positron emission tomography
verfasst von: Donghwi Hwang
Seung Kwan Kang
Kyeong Yun Kim
Hongyoon Choi
Jae Sung Lee
Publikationsdatum: 09.12.2021
Verlag: Springer Berlin Heidelberg
Schlagwort: COVID-19
Erschienen in: European Journal of Nuclear Medicine and Molecular Imaging / Ausgabe 6/2022
Print ISSN: 1619-7070
Elektronische ISSN: 1619-7089
DOI: https://doi.org/10.1007/s00259-021-05637-0

Springer Medizin

Abstract

Purpose

Methods

Results

Conclusion

Bitte loggen Sie sich ein, um Zugang zu diesem Inhalt zu erhalten

Weitere Artikel der Ausgabe 6/2022

Determination of optimal 68 Ga-PSMA PET/CT imaging time in prostate cancers by total-body dynamic PET/CT

Usefulness of the 2-year iodine-123 metaiodobenzylguanidine-based risk model for post-discharge risk stratification of patients with acute decompensated heart failure

Prediction of myocardial blood flow under stress conditions by means of a computational model

A cross-scanner and cross-tracer deep learning method for the recovery of standard-dose imaging quality from low-dose PET

Morphometric analysis program and quantitative positron emission tomography in presurgical localization in MRI-negative epilepsies: a simultaneous PET/MRI study

[18F]FDG-PET/CT to prevent futile surgery in indeterminate thyroid nodules: a blinded, randomised controlled multicentre trial