Skip to main content
Key Specialties
Cardiology Diabetology Endocrinology Gastroenterology Geriatrics and Gerontology Gynecology and Obstetrics Hematology Infectious Disease Internal Medicine Nephrology Neurology Oncology Pediatrics Respiratory Medicine Rheumatology Surgery
Congress Coverage
2024 ACC Congress 2023 ESMO Congress 2023 EASD Congress 2023 ERS Congress 2023 ESC Congress 2023 EHA Congress 2023 ASCO Annual Meeting
Clinical Collections
Advances in Alzheimer’s

Keynote webinar | Spotlight on sleep in brain health

LIVE: Thursday 2nd May 2024, 18:00-19:30 (CEST)

Quality sleep is essential for health. But what happens to our brains when sleep patterns are disturbed? Join our experts to explore the interplay between sleep disruption and neurological diseases, and the questions that you need to be asking your patients to help you prevent the harmful effects of sleep deprivation.
ADVANCED SEARCH
Log in
Top
European Journal of Nuclear Medicine and Molecular Imaging
Published in: European Journal of Nuclear Medicine and Molecular Imaging 6/2022

Open Access 01-05-2022 | Artificial Intelligence | Original Article

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

Authors: Song Xue, Rui Guo, Karl Peter Bohn, Jared Matzke, Marco Viscione, Ian Alberts, Hongping Meng, Chenwei Sun, Miao Zhang, Min Zhang, Raphael Sznitman, Georges El Fakhri, Axel Rominger, Biao Li, Kuangyu Shi

Published in: European Journal of Nuclear Medicine and Molecular Imaging | Issue 6/2022

Login to get access

Abstract

Purpose

A critical bottleneck for the credibility of artificial intelligence (AI) is replicating the results in the diversity of clinical practice. We aimed to develop an AI that can be independently applied to recover high-quality imaging from low-dose scans on different scanners and tracers.

Methods

Brain [18F]FDG PET imaging of 237 patients scanned with one scanner was used for the development of AI technology. The developed algorithm was then tested on [18F]FDG PET images of 45 patients scanned with three different scanners, [18F]FET PET images of 18 patients scanned with two different scanners, as well as [18F]Florbetapir images of 10 patients. A conditional generative adversarial network (GAN) was customized for cross-scanner and cross-tracer optimization. Three nuclear medicine physicians independently assessed the utility of the results in a clinical setting.

Results

The improvement achieved by AI recovery significantly correlated with the baseline image quality indicated by structural similarity index measurement (SSIM) (r = −0.71, p < 0.05) and normalized dose acquisition (r = −0.60, p < 0.05). Our cross-scanner and cross-tracer AI methodology showed utility based on both physical and clinical image assessment (p < 0.05).

Conclusion

The deep learning development for extensible application on unknown scanners and tracers may improve the trustworthiness and clinical acceptability of AI-based dose reduction.
Appendix
Available only for authorised users
Literature
1.
2.
Moskowitz AJ, Schoder H, Yahalom J, McCall SJ, Fox SY, Gerecitano J, et al. PET-adapted sequential salvage therapy with brentuximab vedotin followed by augmented ifosamide, carboplatin, and etoposide for patients with relapsed and refractory Hodgkin's lymphoma: a non-randomised, open-label, single-centre, phase 2 study. The lancet oncology. 2015;16:284–92. https://​doi.​org/​10.​1016/​S1470-2045(15)70013-6.CrossRefPubMed
3.
4.
5.
Voss SD, Reaman GH, Kaste SC, Slovis TL. The ALARA concept in pediatric oncology. Pediatric radiology. 2009;39:1142.CrossRefPubMed
6.
Martí-Climent JM, Prieto E, Morán V, Sancho L, Rodríguez-Fraile M, Arbizu J, et al. Effective dose estimation for oncological and neurological PET/CT procedures. EJNMMI research. 2017;7:37.CrossRefPubMedPubMedCentral
7.
Cherry SR, Jones T, Karp JS, Qi J, Moses WW, Badawi RD. Total-body PET: maximizing sensitivity to create new opportunities for clinical research and patient care. Journal of Nuclear Medicine. 2018;59:3–12.CrossRefPubMedPubMedCentral
8.
9.
Lecoq P, Morel C, Prior JO, Visvikis D, Gundacker S, Auffray E, et al. Roadmap toward the 10 ps time-of-flight PET challenge. Physics in Medicine & Biology. 2020;65:21RM01.
10.
11.
Lecoq P. Pushing the limits in time-of-flight PET imaging. IEEE Transactions on radiation and plasma medical sciences. 2017;1:473–85.CrossRef
12.
Hsu DF, Ilan E, Peterson WT, Uribe J, Lubberink M, Levin CS. Studies of a next-generation silicon-photomultiplier–based time-of-flight PET/CT system. Journal of Nuclear Medicine. 2017;58:1511–8.CrossRefPubMed
13.
Van Sluis J, De Jong J, Schaar J, Noordzij W, Van Snick P, Dierckx R, et al. Performance characteristics of the digital Biograph Vision PET/CT system. Journal of Nuclear Medicine. 2019;60:1031–6.CrossRefPubMed
14.
Chen S, Hu P, Gu Y, Yu H, Shi H. Performance characteristics of the digital uMI550 PET/CT system according to the NEMA NU2-2018 standard. EJNMMI physics. 2020;7:1–14.CrossRef
15.
Zhang J, Maniawski P, Knopp MV. Performance evaluation of the next generation solid-state digital photon counting PET/CT system. EJNMMI research. 2018;8:97.CrossRefPubMedPubMedCentral
16.
17.
18.
Nguyen NC, Vercher-Conejero JL, Sattar A, Miller MA, Maniawski PJ, Jordan DW, et al. Image quality and diagnostic performance of a digital PET prototype in patients with oncologic diseases: initial experience and comparison with analog PET. Journal of nuclear medicine : official publication, Society of Nuclear Medicine. 2015;56:1378–85. https://​doi.​org/​10.​2967/​jnumed.​114.​148338.CrossRef
19.
20.
21.
Alberts I, Sachpekidis C, Prenosil G, Viscione M, Bohn KP, Mingels C, et al. Digital PET/CT allows for shorter acquisition protocols or reduced radiopharmaceutical dose in [18 F]-FDG PET/CT. Annals of Nuclear Medicine. 2021;35:485–92.CrossRefPubMedPubMedCentral
22.
23.
Berg E, Gill H, Marik J, Ogasawara A, Williams S, van Dongen G, et al. Total-body PET and highly stable chelators together enable meaningful (89)Zr-antibody PET studies up to 30 days after injection. Journal of nuclear medicine : official publication, Society of Nuclear Medicine. 2020;61:453–60. https://​doi.​org/​10.​2967/​jnumed.​119.​230961.CrossRef
24.
25.
Alberts I, Hünermund J-N, Prenosil G, Mingels C, Bohn KP, Viscione M, et al. Clinical performance of long axial field of view PET/CT: a head-to-head intra-individual comparison of the Biograph Vision Quadra with the Biograph Vision PET/CT. European Journal of Nuclear Medicine and Molecular Imaging. 2021;1-10.
26.
Dutta J, Leahy RM, Li Q. Non-local means denoising of dynamic PET images. PloS one. 2013;8.
27.
Le Pogam A, Hanzouli H, Hatt M, Le Rest CC, Visvikis D. Denoising of PET images by combining wavelets and curvelets for improved preservation of resolution and quantitation. Medical image analysis. 2013;17:877–91.CrossRefPubMed
28.
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. Medical physics. 2015;42:5301–9.CrossRefPubMedPubMedCentral
29.
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. Physics in Medicine & Biology. 2016;61:791.CrossRef
30.
Wang Y, Ma G, An L, Shi F, Zhang P, Lalush DS, et al. Semisupervised tripled dictionary learning for standard-dose PET image prediction using low-dose PET and multimodal MRI. IEEE Transactions on Biomedical Engineering. 2016;64:569–79.CrossRefPubMed
31.
An L, Zhang P, Adeli E, Wang Y, Ma G, Shi F, et al. Multi-level canonical correlation analysis for standard-dose PET image estimation. IEEE Transactions on Image Processing. 2016;25:3303–15.CrossRefPubMedPubMedCentral
32.
Xiang L, Qiao Y, Nie D, An L, Lin W, Wang Q, et al. Deep auto-context convolutional neural networks for standard-dose PET image estimation from low-dose PET/MRI. Neurocomputing. 2017;267:406–16.CrossRefPubMedPubMedCentral
33.
Goodfellow I, Pouget-Abadie J, Mirza M, Xu B, Warde-Farley D, Ozair S, et al. Generative adversarial nets. Advances in neural information processing systems; 2014. p. 2672-80.
34.
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.CrossRefPubMed
35.
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 transactions on medical imaging. 2018;38:1328–39.CrossRefPubMedPubMedCentral
36.
Galavis PE, Hollensen C, Jallow N, Paliwal B, Jeraj R. Variability of textural features in FDG PET images due to different acquisition modes and reconstruction parameters. Acta oncologica. 2010;49:1012–6.CrossRefPubMed
37.
Yan J, Chu-Shern JL, Loi HY, Khor LK, Sinha AK, Quek ST, et al. Impact of image reconstruction settings on texture features in 18F-FDG PET. Journal of nuclear medicine. 2015;56:1667–73.CrossRefPubMed
38.
Moses W. Time of flight in PET revisited. IEEE Transactions on Nuclear Science. 2003;50:1325–30.CrossRef
39.
Ohi J, Tonami H. Investigation of a whole-body DOI-PET system. Nuclear instruments and methods in physics research section a: accelerators, spectrometers, detectors and associated equipment. 2007;571:223–6.CrossRef
40.
Ronneberger O, Fischer P, Brox T. U-net: convolutional networks for biomedical image segmentation. International Conference on Medical image computing and computer-assisted intervention: Springer; 2015. p. 234-41.
41.
Ioffe S, Szegedy C. Batch normalization: accelerating deep network training by reducing internal covariate shift. arXiv preprint arXiv:150203167. 2015.
42.
Wang Z, Bovik AC, Sheikh HR, Simoncelli EP. Image quality assessment: from error visibility to structural similarity. IEEE transactions on image processing. 2004;13:600–12.CrossRefPubMed
43.
Minoshima S, Frey KA, Koeppe RA, Foster NL, Kuhl DE. A diagnostic approach in Alzheimer's disease using three-dimensional stereotactic surface projections of fluorine-18-FDG PET. Journal of Nuclear Medicine. 1995;36:1238–48.PubMed
44.
Pascoal TA, Mathotaarachchi S, Shin M, Park AY, Mohades S, Benedet AL, et al. Amyloid and tau signatures of brain metabolic decline in preclinical Alzheimer’s disease. European journal of nuclear medicine and molecular imaging. 2018;45:1021–30.CrossRefPubMedPubMedCentral
45.
Ha S, Choi H, Paeng JC. Cheon GJJNm, imaging m. Radiomics in oncological PET/CT: a methodological overview. 2019;53:14–29.
46.
Brooks FJ. Grigsby PWJJoNM. The effect of small tumor volumes on studies of intratumoral heterogeneity of tracer uptake. 2014;55:37–42.
47.
Hatt M, Majdoub M, Vallières M, Tixier F, Le Rest CC, Groheux D, et al. 18F-FDG PET uptake characterization through texture analysis: investigating the complementary nature of heterogeneity and functional tumor volume in a multi–cancer site patient cohort. 2015;56:38–44.
48.
Hatt M, Tixier F, Pierce L, Kinahan PE, Le Rest CC, DJEjonm V, et al. Characterization of PET/CT images using texture analysis: the past, the present… any future? 2017;44:151–65.
49.
Presotto L, Bettinardi V, De Bernardi E, Belli M, Cattaneo G, Broggi S, et al. PET textural features stability and pattern discrimination power for radiomics analysis: an “ad-hoc” phantoms study. 2018;50:66–74.
50.
Kim BH, Kim S-J, Kim K, Kim H, Kim SJ, Kim WJ, et al. High metabolic tumor volume and total lesion glycolysis are associated with lateral lymph node metastasis in patients with incidentally detected thyroid carcinoma. 2015;29:721–9.
51.
Kong Z, Lin Y, Jiang C, Li L, Liu Z, Wang Y, et al. 18 F-FDG-PET-based radiomics signature predicts MGMT promoter methylation status in primary diffuse glioma. 2019;19:58.
52.
Li L, Mu W, LIU Z, Liu Z, Wang Y, Ma W, et al. A non-invasive radiomic method us 18F-FDG PET predicts isocitrate dehydrogenase genotype and prognosis in patients with glioma. 2019;9:1183.
53.
Wu Y, Jiang J-H, Chen L, Lu J-Y, Ge J-J, Liu F-T, et al. Use of radiomic features and support vector machine to distinguish Parkinson’s disease cases from normal controls. 2019;7.
54.
Lohmann P, Kocher M, Ceccon G, Bauer EK, Stoffels G, Viswanathan S, et al. Combined FET PET/MRI radiomics differentiates radiation injury from recurrent brain metastasis. 2018;20:537–42.
55.
Lohmann P, Stoffels G, Ceccon G, Rapp M, Sabel M, Filss CP, et al. Radiation injury vs. recurrent brain metastasis: combining textural feature radiomics analysis and standard parameters may increase 18 F-FET PET accuracy without dynamic scans. 2017;27:2916–27.
56.
Roberts M, Driggs D, Thorpe M, Gilbey J, Yeung M, Ursprung S, et al. Common pitfalls and recommendations for using machine learning to detect and prognosticate for COVID-19 using chest radiographs and CT scans. Nature Machine Intelligence. 2021;3:199–217.CrossRef
57.
Maier-Hein L, Eisenmann M, Reinke A, Onogur S, Stankovic M, Scholz P, et al. Why rankings of biomedical image analysis competitions should be interpreted with care. Nat Commun. 2018;9:1–13.CrossRef
58.
Degenhardt C, Rodrigues P, Trindade A, Zwaans B, Mülhens O, Dorscheid R, et al. Performance evaluation of a prototype positron emission tomography scanner using digital photon counters (DPC). 2012 IEEE Nuclear Science Symposium and Medical Imaging Conference Record (NSS/MIC): IEEE; 2012. p. 2820-4.
59.
Nguyen NC, Vercher-Conejero JL, Sattar A, Miller MA, Maniawski PJ, Jordan DW, et al. Image quality and diagnostic performance of a digital PET prototype in patients with oncologic diseases: initial experience and comparison with analog PET. Journal of Nuclear Medicine. 2015;56:1378–85.CrossRefPubMed
60.
Hudson HM, Larkin RS. Accelerated image reconstruction using ordered subsets of projection data. IEEE transactions on medical imaging. 1994;13:601–9.CrossRefPubMed
61.
Cohen JP, Luck M, Honari S. Distribution matching losses can hallucinate features in medical image translation. International conference on medical image computing and computer-assisted intervention: Springer; 2018. p. 529–36.
62.
Martí-Climent JM, Prieto E, Morán V, Sancho L, Rodríguez-Fraile M, Arbizu J, et al. Effective dose estimation for oncological and neurological PET/CT procedures. EJNMMI research. 2017;7:1–8.CrossRef
Metadata
Title
A cross-scanner and cross-tracer deep learning method for the recovery of standard-dose imaging quality from low-dose PET
Authors
Song Xue
Rui Guo
Karl Peter Bohn
Jared Matzke
Marco Viscione
Ian Alberts
Hongping Meng
Chenwei Sun
Miao Zhang
Min Zhang
Raphael Sznitman
Georges El Fakhri
Axel Rominger
Biao Li
Kuangyu Shi
Publication date
01-05-2022
Publisher
Springer Berlin Heidelberg
Published in
European Journal of Nuclear Medicine and Molecular Imaging / Issue 6/2022
Print ISSN: 1619-7070
Electronic ISSN: 1619-7089
DOI
https://doi.org/10.1007/s00259-021-05644-1

Other articles of this Issue 6/2022

European Journal of Nuclear Medicine and Molecular Imaging 6/2022 Go to the issue

Correction

Correction to: Imaging of neuroinflammation due to repetitive head injury in currently active kickboxers

Original Article

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

Original Article

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

Original Article

13 N-ammonia PET-derived right ventricular longitudinal strain and myocardial flow reserve in right coronary artery disease

Guidelines

EANM dosimetry committee recommendations for dosimetry of 177Lu-labelled somatostatin-receptor- and PSMA-targeting ligands

Original Article

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