Top

European Journal of Nuclear Medicine and Molecular Imaging

Published in:

01-08-2021 | Artificial Intelligence | Original Article

Artificial intelligence enables whole-body positron emission tomography scans with minimal radiation exposure

Authors: Yan-Ran (Joyce) Wang, Lucia Baratto, K. Elizabeth Hawk, Ashok J. Theruvath, Allison Pribnow, Avnesh S. Thakor, Sergios Gatidis, Rong Lu, Santosh E. Gummidipundi, Jordi Garcia-Diaz, Daniel Rubin, Heike E. Daldrup-Link

Published in: European Journal of Nuclear Medicine and Molecular Imaging | Issue 9/2021

Abstract

Purpose

To generate diagnostic ¹⁸F-FDG PET images of pediatric cancer patients from ultra-low-dose ¹⁸F-FDG PET input images, using a novel artificial intelligence (AI) algorithm.

Methods

We used whole-body ¹⁸F-FDG-PET/MRI scans of 33 children and young adults with lymphoma (3–30 years) to develop a convolutional neural network (CNN), which combines inputs from simulated 6.25% ultra-low-dose ¹⁸F-FDG PET scans and simultaneously acquired MRI scans to produce a standard-dose ¹⁸F-FDG PET scan. The image quality of ultra-low-dose PET scans, AI-augmented PET scans, and clinical standard PET scans was evaluated by traditional metrics in computer vision and by expert radiologists and nuclear medicine physicians, using Wilcoxon signed-rank tests and weighted kappa statistics.

Results

The peak signal-to-noise ratio and structural similarity index were significantly higher, and the normalized root-mean-square error was significantly lower on the AI-reconstructed PET images compared to simulated 6.25% dose images (p < 0.001). Compared to the ground-truth standard-dose PET, SUV_max values of tumors and reference tissues were significantly higher on the simulated 6.25% ultra-low-dose PET scans as a result of image noise. After the CNN augmentation, the SUV_max values were recovered to values similar to the standard-dose PET. Quantitative measures of the readers’ diagnostic confidence demonstrated significantly higher agreement between standard clinical scans and AI-reconstructed PET scans (kappa = 0.942) than 6.25% dose scans (kappa = 0.650).

Conclusions

Our CNN model could generate simulated clinical standard ¹⁸F-FDG PET images from ultra-low-dose inputs, while maintaining clinically relevant information in terms of diagnostic accuracy and quantitative SUV measurements.

Available only for authorised users

Baum SH, Fruhwald M, Rahbar K, Wessling J, Schober O, Weckesser M. Contribution of PET/CT to prediction of outcome in children and young adults with rhabdomyosarcoma. J Nucl Med. 2011;52:1535–40. https://doi.org/10.2967/jnumed.110.082511.CrossRefPubMed

Cheng G, Chen W, Chamroonrat W, Torigian DA, Zhuang H, Alavi A. Biopsy versus FDG PET/CT in the initial evaluation of bone marrow involvement in pediatric lymphoma patients. Eur J Nucl Med Mol Imaging. 2011;38:1469–76. https://doi.org/10.1007/s00259-011-1815-z.CrossRefPubMed

Kleis M, Daldrup-Link H, Matthay K, Goldsby R, Lu Y, Schuster T, et al. Diagnostic value of PET/CT for the staging and restaging of pediatric tumors. Eur J Nucl Med Mol Imaging. 2009;36:23–36. https://doi.org/10.1007/s00259-008-0911-1.CrossRefPubMed

Huang B, Law MW, Khong PL. Whole-body PET/CT scanning: estimation of radiation dose and cancer risk. Radiology. 2009;251:166–74. https://doi.org/10.1148/radiol.2511081300.CrossRefPubMed

Brenner DJ, Hall EJ. Computed tomography--an increasing source of radiation exposure. N Engl J Med. 2007;357:2277–84. https://doi.org/10.1056/NEJMra072149.CrossRefPubMed

Meulepas JM, Ronckers CM, Smets A, Nievelstein RAJ, Gradowska P, Lee C, et al. Radiation exposure from pediatric CT scans and subsequent cancer risk in the Netherlands. J Natl Cancer Inst. 2018. https://doi.org/10.1093/jnci/djy104.

Pearce MS, Salotti JA, Little MP, McHugh K, Lee C, Kim KP, et al. Radiation exposure from CT scans in childhood and subsequent risk of leukaemia and brain tumours: a retrospective cohort study. Lancet. 2012;380:499–505. https://doi.org/10.1016/S0140-6736(12)60815-0.CrossRefPubMedPubMedCentral

Mathews JD, Forsythe AV, Brady Z, Butler MW, Goergen SK, Byrnes GB, et al. Cancer risk in 680,000 people exposed to computed tomography scans in childhood or adolescence: data linkage study of 11 million Australians. Bmj. 2013;346:f2360. https://doi.org/10.1136/bmj.f2360.CrossRefPubMedPubMedCentral

Brenner DJ, Doll R, Goodhead DT, Hall EJ, Land CE, Little JB, et al. Cancer risks attributable to low doses of ionizing radiation: assessing what we really know. Proc Natl Acad Sci U S A. 2003;100:13761–6. https://doi.org/10.1073/pnas.2235592100.CrossRefPubMedPubMedCentral

10.

Klenk C, Gawande R, Uslu L, Khurana A, Qiu D, Quon A, et al. Ionising radiation-free whole-body MRI versus (18)F-fluorodeoxyglucose PET/CT scans for children and young adults with cancer: a prospective, non-randomised, single-centre study. Lancet Oncol. 2014;15:275–85. https://doi.org/10.1016/S1470-2045(14)70021-X.CrossRefPubMed

11.

Robbins E. Radiation risks from imaging studies in children with cancer. Pediatr Blood Cancer. 2008;51:453–7. https://doi.org/10.1002/pbc.21599.CrossRefPubMed

12.

Chawla SC, Federman N, Zhang D, Nagata K, Nuthakki S, McNitt-Gray M, et al. Estimated cumulative radiation dose from PET/CT in children with malignancies: a 5-year retrospective review. Pediatr Radiol. 2010;40:681–6. https://doi.org/10.1007/s00247-009-1434-z.CrossRefPubMed

13.

Applegate KE, Frush DP. Image gently: a decade of international collaborations to promote appropriate imaging for children. J Am Coll Radiol. 2017;14:956–7. https://doi.org/10.1016/j.jacr.2017.04.039.CrossRefPubMed

14.

Muehe AM, Theruvath AJ, Lai L, Aghighi M, Quon A, Holdsworth SJ, et al. How to provide gadolinium-free PET/MR cancer staging of children and young adults in less than 1 h: the Stanford approach. Mol Imaging Biol. 2018;20:324–35. https://doi.org/10.1007/s11307-017-1105-7.CrossRefPubMedPubMedCentral

15.

Theruvath AJ, Siedek F, Muehe AM, Garcia-Diaz J, Kirchner J, Martin O, et al. Therapy response assessment of pediatric tumors with whole-body diffusion-weighted MRI and FDG PET/MRI. Radiology. 2020;192508. https://doi.org/10.1148/radiol.2020192508.

16.

Karakatsanis NA, Fokou E, Tsoumpas C. Dosage optimization in positron emission tomography: state-of-the-art methods and future prospects. Am J Nucl Med Mol Imaging. 2015;5:527–47.PubMedPubMedCentral

17.

Kim SM, Alessio AM, De Man B, Asma E, Kinahan PE. Direct reconstruction of CT-based attenuation correction images for PET with cluster-based penalties. IEEE Nucl Sci Symp Conf Rec (1997). 2013;2013. https://doi.org/10.1109/NSSMIC.2013.6829245.

18.

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

19.

Kang J, Gao Y, Shi F, Lalush DS, Lin W, Shen D. Prediction of standard-dose brain PET image by using MRI and low-dose brain [18F]FDG PET images. Med Phys. 2015;42:5301–9. https://doi.org/10.1118/1.4928400.CrossRefPubMedPubMedCentral

20.

Wang Y, Zhang P, An L, Ma G, Kang J, Shi F, et al. Predicting standard-dose PET image from low-dose PET and multimodal MR images using mapping-based sparse representation. Phys Med Biol. 2016;61:791–812. https://doi.org/10.1088/0031-9155/61/2/791.CrossRefPubMed

21.

Cui J, Gong K, Guo N, Wu C, Meng X, Kim K, et al. PET image denoising using unsupervised deep learning. Eur J Nucl Med Mol Imaging. 2019;46:2780–9. https://doi.org/10.1007/s00259-019-04468-4.CrossRefPubMedPubMedCentral

22.

Xiang L, Qiao Y, Nie D, An L, Wang Q, Shen D. Deep auto-context convolutional neural networks for standard-dose PET image estimation from low-dose PET/MRI. Neurocomputing. 2017;267:406–16. https://doi.org/10.1016/j.neucom.2017.06.048.CrossRefPubMedPubMedCentral

23.

Ouyang J, Chen KT, Gong E, Pauly J, Zaharchuk G. Ultra-low-dose PET reconstruction using generative adversarial network with feature matching and task-specific perceptual loss. Med Phys. 2019;46:3555–64. https://doi.org/10.1002/mp.13626.CrossRefPubMed

24.

Sekine T, Delso G, Zeimpekis KG, de Galiza Barbosa F, Ter Voert E, Huellner M, et al. Reduction of (18)F-FDG dose in clinical PET/MR imaging by using silicon photomultiplier detectors. Radiology. 2018;286:249–59. https://doi.org/10.1148/radiol.2017162305.CrossRefPubMed

25.

Lim B, Son S, Kim H, Nah S, Mu Lee K. Enhanced deep residual networks for single image super-resolution. Proc IEEE Conf Comput Vis Pattern Recognit. 2017;136–44.

26.

Banerjee I, Crawley A, Bhethanabotla M, Daldrup-Link HE, Rubin DL. Transfer learning on fused multiparametric MR images for classifying histopathological subtypes of rhabdomyosarcoma. Comput Med Imaging Graph. 2018;65:167–75. https://doi.org/10.1016/j.compmedimag.2017.05.002.CrossRefPubMed

27.

Zaharchuk G. Next generation research applications for hybrid PET/MR and PET/CT imaging using deep learning. Eur J Nucl Med Mol Imaging. 2019;46:2700–7. https://doi.org/10.1007/s00259-019-04374-9.CrossRefPubMedPubMedCentral

28.

Wang Y, Yu B, Wang L, Zu C, Lalush DS, Lin W, et al. 3D conditional generative adversarial networks for high-quality PET image estimation at low dose. Neuroimage. 2018;174:550–62. https://doi.org/10.1016/j.neuroimage.2018.03.045.CrossRefPubMed

29.

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 Trans Med Imaging. 2019;38:1328–39. https://doi.org/10.1109/TMI.2018.2884053.CrossRefPubMed

30.

Sanaat A, Arabi H, Mainta I, Garibotto V, Zaidi H. Projection space implementation of deep learning-guided low-dose brain PET imaging improves performance over implementation in image space. J Nucl Med. 2020;61:1388–96. https://doi.org/10.2967/jnumed.119.239327.CrossRefPubMedPubMedCentral

31.

Xu J, Gong E, Pauly JM, Zaharchuk G. 200x low-dose PET reconstruction using deep learning. Computer Vision and Pattern Recognition. Cornell University Library. 2018;arXiv:1712.04119.

32.

Chen KT, Gong E, de Carvalho Macruz FB, Xu J, Boumis A, Khalighi M, et al. Ultra-low-dose (18)F-florbetaben amyloid PET imaging using deep learning with multi-contrast MRI inputs. Radiology. 2019;290:649–56. https://doi.org/10.1148/radiol.2018180940.CrossRefPubMed

33.

Kaplan S, Zhu YM. Full-dose PET image estimation from low-dose PET image using deep learning: a pilot study. J Digit Imaging. 2019;32:773–8. https://doi.org/10.1007/s10278-018-0150-3.CrossRefPubMed

34.

Whiteley W, Luk WK, Gregor J. DirectPET: full-size neural network PET reconstruction from sinogram data. J Med Imaging (Bellingham). 2020;7:032503. https://doi.org/10.1117/1.JMI.7.3.032503.CrossRef

Title: Artificial intelligence enables whole-body positron emission tomography scans with minimal radiation exposure
Authors: Yan-Ran (Joyce) Wang
Lucia Baratto
K. Elizabeth Hawk
Ashok J. Theruvath
Allison Pribnow
Avnesh S. Thakor
Sergios Gatidis
Rong Lu
Santosh E. Gummidipundi
Jordi Garcia-Diaz
Daniel Rubin
Heike E. Daldrup-Link
Publication date: 01-08-2021
Publisher: Springer Berlin Heidelberg
Keywords: Artificial Intelligence
Pediatric Cancer
Published in: European Journal of Nuclear Medicine and Molecular Imaging / Issue 9/2021
Print ISSN: 1619-7070
Electronic ISSN: 1619-7089
DOI: https://doi.org/10.1007/s00259-021-05197-3

At a glance: The ONWARDS insulin icodec trials

Springer Medicine

Artificial intelligence enables whole-body positron emission tomography scans with minimal radiation exposure

Abstract

Purpose

Methods

Results

Conclusions

At a glance: The ONWARDS insulin icodec trials

Springer Medicine

Abstract

Purpose

Methods

Results

Conclusions

Please log in to get access to this content

Other articles of this Issue 9/2021

Give to Fryback what is Fryback’s, and to new PET technologies what is new PET technologies’

Impact of EBUS-TBNA in addition to [18F]FDG-PET/CT imaging on target volume definition for radiochemotherapy in stage III NSCLC

New PET technologies – embracing progress and pushing the limits

α-Particle-induced DNA damage tracks in peripheral blood mononuclear cells of [223Ra]RaCl2-treated prostate cancer patients

Deep learning-based auto-delineation of gross tumour volumes and involved nodes in PET/CT images of head and neck cancer patients

Diagnostic accuracy of stress-only myocardial perfusion SPECT improved by deep learning