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
Clinical Collections
Advances in Alzheimer’s

At a glance: The STEP trials

A round-up of the STEP phase 3 clinical trials evaluating semaglutide for weight loss in people with overweight or obesity.
ADVANCED SEARCH
Log in
Top
European Journal of Nuclear Medicine and Molecular Imaging
Published in: European Journal of Nuclear Medicine and Molecular Imaging 13/2022

Open Access 29-07-2022 | Artificial Intelligence | Original Article

Artificial intelligence guided enhancement of digital PET: scans as fast as CT?

Authors: René Hosch, Manuel Weber, Miriam Sraieb, Nils Flaschel, Johannes Haubold, Moon-Sung Kim, Lale Umutlu, Jens Kleesiek, Ken Herrmann, Felix Nensa, Christoph Rischpler, Sven Koitka, Robert Seifert, David Kersting

Published in: European Journal of Nuclear Medicine and Molecular Imaging | Issue 13/2022

Login to get access

Abstract

Purpose

Both digital positron emission tomography (PET) detector technologies and artificial intelligence based image post-reconstruction methods allow to reduce the PET acquisition time while maintaining diagnostic quality. The aim of this study was to acquire ultra-low-count fluorodeoxyglucose (FDG) ExtremePET images on a digital PET/computed tomography (CT) scanner at an acquisition time comparable to a CT scan and to generate synthetic full-dose PET images using an artificial neural network.

Methods

This is a prospective, single-arm, single-center phase I/II imaging study. A total of 587 patients were included. For each patient, a standard and an ultra-low-count FDG PET/CT scan (whole-body acquisition time about 30 s) were acquired. A modified pix2pixHD deep-learning network was trained employing 387 data sets as training and 200 as test cohort. Three models (PET-only and PET/CT with or without group convolution) were compared. Detectability and quantification were evaluated.

Results

The PET/CT input model with group convolution performed best regarding lesion signal recovery and was selected for detailed evaluation. Synthetic PET images were of high visual image quality; mean absolute lesion SUVmax (maximum standardized uptake value) difference was 1.5. Patient-based sensitivity and specificity for lesion detection were 79% and 100%, respectively. Not-detected lesions were of lower tracer uptake and lesion volume. In a matched-pair comparison, patient-based (lesion-based) detection rate was 89% (78%) for PERCIST (PET response criteria in solid tumors)-measurable and 36% (22%) for non PERCIST-measurable lesions.

Conclusion

Lesion detectability and lesion quantification were promising in the context of extremely fast acquisition times. Possible application scenarios might include re-staging of late-stage cancer patients, in whom assessment of total tumor burden can be of higher relevance than detailed evaluation of small and low-uptake lesions.
Appendix
Available only for authorised users
Literature
1.
Boellaard R, Delgado-Bolton R, Oyen WJG, Giammarile F, Tatsch K, Eschner W, et al. FDG PET/CT: EANM procedure guidelines for tumour imaging: version 2.0. Eur J Nucl Med Mol Imaging. 2015;42:328–54.CrossRef
2.
Lasnon C, Coudrais N, Houdu B, Nganoa C, Salomon T, Enilorac B, et al. How fast can we scan patients with modern (digital) PET/CT systems? Eur J Radiol. 2020;129:109144.CrossRef
3.
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. J Nucl Med Off Publ Soc Nucl Med United States. 2019;60:1031–6.
4.
Surti S, Viswanath V, Daube-Witherspoon ME, Conti M, Casey ME, Karp JS. Benefit of improved performance with state-of-the art digital PET/CT for lesion detection in oncology. J Nucl Med Off Publ Soc Nucl Med United States. 2020;61:1684–90.
5.
Koopman D, van Dalen JA, Stevens H, Slump CH, Knollema S, Jager PL. Performance of digital PET compared with high-resolution conventional PET in patients with cancer. J Nucl Med Off Publ Soc Nucl Med United States. 2020;61:1448–54.
6.
van Sluis J, Boellaard R, Somasundaram A, van Snick PH, Borra RJH, Dierckx RAJO, et al. Image quality and semiquantitative measurements on the biograph vision PET/CT system: initial experiences and comparison with the biograph mCT. J Nucl Med Off Publ Soc Nucl Med United States. 2020;61:129–35.
7.
Kersting D, Jentzen W, Sraieb M, Costa PF, Conti M, Umutlu L, et al. Comparing lesion detection efficacy and image quality across different PET system generations to optimize the iodine-124 PET protocol for recurrent thyroid cancer. EJNMMI Phys. 2021;8:14.CrossRef
8.
López-Mora DA, Flotats A, Fuentes-Ocampo F, Camacho V, Fernández A, Ruiz A, et al. Comparison of image quality and lesion detection between digital and analog PET/CT. Eur J Nucl Med Mol Imaging. 2019;46:1383–90.CrossRef
9.
Alberts I, Prenosil G, Sachpekidis C, Weitzel T, Shi K, Rominger A, et al. Digital versus analogue PET in [(68)Ga]Ga-PSMA-11 PET/CT for recurrent prostate cancer: a matched-pair comparison. Eur J Nucl Med Mol Imaging Germany. 2020;47:614–23.CrossRef
10.
Kersting D, Jentzen W, Fragoso Costa P, Sraieb M, Sandach P, Umutlu L, et al. Silicon-photomultiplier-based PET/CT reduces the minimum detectable activity of iodine-124. Sci Rep. 2021;11:17477.CrossRef
11.
Conti M, Bendriem B. The new opportunities for high time resolution clinical TOF PET. Clin Transl Imaging. 2019;7:139–47.CrossRef
12.
Hatami S, Frye S, McMunn A, Botkin C, Muzaffar R, Christopher K, et al. Added value of digital over analog PET/CT: more significant as image field of view and body mass index increase. J Nucl Med Technol United States. 2020;48(354):360.
13.
Weber M, Jentzen W, Hofferber R, Herrmann K, Fendler WP, Rischpler C, et al. Evaluation of (18)F-FDG PET/CT images acquired with a reduced scan time duration in lymphoma patients using the digital biograph vision. BMC Cancer. 2021;21:62.CrossRef
14.
15.
Weber M, Jentzen W, Hofferber R, Herrmann K, Fendler WP, Conti M, et al. Evaluation of [(68)Ga]Ga-PSMA PET/CT images acquired with a reduced scan time duration in prostate cancer patients using the digital biograph vision. EJNMMI Res. 2021;11:21.CrossRef
16.
van Sluis J, Boellaard R, Dierckx RAJO, Stormezand GN, Glaudemans AWJM, Noordzij W. Image quality and activity optimization in oncologic (18)F-FDG PET using the digital biograph vision PET/CT system. J Nucl Med Off Publ Soc Nucl Med United States. 2020;61:764–71.
17.
Armanious K, Jiang C, Fischer M, Küstner T, Hepp T, Nikolaou K, et al. MedGAN: Medical image translation using GANs. Comput Med Imaging Graph. 2019;79:101684.CrossRef
18.
Cao H, Wang Y, Chen J, Jiang D, Zhang X, Tian Q, et al. Swin-Unet: Unet-like pure transformer for medical image segmentation. ArXiv210505537 Cs Eess [Internet]. 2021 [cited 2021 Jun 15]; Available from: http://​arxiv.​org/​abs/​2105.​05537
19.
Gong E, Pauly JM, Wintermark M, Zaharchuk G. Deep learning enables reduced gadolinium dose for contrast-enhanced brain MRI. J Magn Reson Imaging JMRI. 2018;48:330–40.CrossRef
20.
Haubold J, Hosch R, Umutlu L, Wetter A, Haubold P, Radbruch A, et al. Contrast agent dose reduction in computed tomography with deep learning using a conditional generative adversarial network. Eur Radiol. 2021;31:6087–95.CrossRef
21.
Zhao J, Li D, Kassam Z, Howey J, Chong J, Chen B, et al. Tripartite-GAN: Synthesizing liver contrast-enhanced MRI to improve tumor detection. Med Image Anal. 2020;63:101667.CrossRef
22.
Kaji S, Kida S. Overview of image-to-image translation by use of deep neural networks: denoising, super-resolution, modality conversion, and reconstruction in medical imaging. Radiol Phys Technol. 2019;12:235–48.CrossRef
23.
24.
Seibold C, Fink MA, Goos C, Kauczor H-U, Schlemmer H-P, Stiefelhagen R, et al. Prediction of low-kev monochromatic images from polyenergetic CT scans for improved automatic detection of pulmonary embolism. 2021 IEEE 18th Int Symp Biomed Imaging ISBI. 2021. p. 1017–20.
25.
Isola P, Zhu J-Y, Zhou T, Efros AA. Image-to-image translation with conditional adversarial networks. IEEE Conf Comput Vis Pattern Recognit CVPR. 2017. p. 5967–76.
26.
Wang T-C, Liu M-Y, Zhu J-Y, Tao A, Kautz J, Catanzaro B. High-resolution image synthesis and semantic manipulation with conditional gans. Proc IEEE Conf Comput Vis Pattern Recognit. 2018. p. 8798–807.
27.
Sanaat A, Shiri I, Arabi H, Mainta I, Nkoulou R, Zaidi H. Deep learning-assisted ultra-fast/low-dose whole-body PET/CT imaging. Eur J Nucl Med Mol Imaging. 2021;48:2405–15.CrossRef
28.
Chaudhari AS, Mittra E, Davidzon GA, Gulaka P, Gandhi H, Brown A, et al. Low-count whole-body PET with deep learning in a multicenter and externally validated study. NPJ Digit Med England. 2021;4:127.CrossRef
29.
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 England. 2019;64:165019.CrossRef
30.
Gong K, Guan J, Kim K, Zhang X, Yang J, Seo Y, et al. Iterative PET image reconstruction using convolutional neural network representation. IEEE Trans Med Imaging. 2019;38:675–85.CrossRef
31.
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.CrossRef
32.
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.CrossRef
33.
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 Off Publ Soc Nucl Med. 2020;61:1388–96.
34.
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.CrossRef
35.
Wang Y-RJ, Baratto L, Hawk KE, Theruvath AJ, Pribnow A, Thakor AS, et al. Artificial intelligence enables whole-body positron emission tomography scans with minimal radiation exposure. Eur J Nucl Med Mol Imaging. 2021;48:2771–81.
36.
Nguyen NC, Kaushik A, Wolverson MK, Osman MM. Is there a common SUV threshold in oncological FDG PET/CT, at least for some common indications? A retrospective study. Acta Oncol Taylor & Francis. 2011;50:670–7.CrossRef
37.
Horé A, Ziou D. Image quality metrics: PSNR vs. SSIM. 2010 20th Int Conf Pattern Recognit. 2010. 2366–9.
38.
39.
40.
Ma L, Jia X, Sun Q, Schiele B, Tuytelaars T, Van Gool L. Pose guided person image generation. Adv Neural Inf Process Syst. 2017;30.
41.
Sibille L, Seifert R, Avramovic N, Vehren T, Spottiswoode B, Zuehlsdorff S, et al. 18F-FDG PET/CT uptake classification in lymphoma and lung cancer by using deep convolutional neural networks. Radiology Radiological Society of North America. 2020;294:445–52.
42.
Weber M, Kersting D, Umutlu L, Schäfers M, Rischpler C, Fendler WP, et al. Just another “Clever Hans”? Neural networks and FDG PET-CT to predict the outcome of patients with breast cancer. Eur J Nucl Med Mol Imaging. 2021;48:3141–50.CrossRef
43.
O JH, Lodge MA, Wahl RL. Practical PERCIST: a simplified guide to PET response criteria in solid tumors 1.0. Radiology. Radiological Society of North America; 2016;280:576–84.
44.
45.
Virtanen P, Gommers R, Oliphant TE, Haberland M, Reddy T, Cournapeau D, et al. SciPy 1.0: fundamental algorithms for scientific computing in Python. Nat Methods. 2020;17:261–72.CrossRef
46.
Lei Y, Dong X, Wang T, Higgins K, Liu T, Curran WJ, et al. Whole-body PET estimation from low count statistics using cycle-consistent generative adversarial networks. Phys Med Biol. 2019;64:215017.CrossRef
47.
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.CrossRef
48.
Wang X, Zhou L, Wang Y, Jiang H, Ye H. Improved low-dose positron emission tomography image reconstruction using deep learned prior. Phys Med Biol IOP Publishing. 2021;66:115001.CrossRef
49.
Kaplan S, Zhu Y-M. Full-dose PET image estimation from low-dose PET image using deep learning: a pilot study. J Digit Imaging. 2019;32:773–8.CrossRef
50.
de Langen AJ, Vincent A, Velasquez LM, van Tinteren H, Boellaard R, Shankar LK, et al. Repeatability of 18F-FDG uptake measurements in tumors: a metaanalysis. J Nucl Med Off Publ Soc Nucl Med United States. 2012;53:701–8.
51.
Schaefferkoetter J, Nai Y-H, Reilhac A, Townsend DW, Eriksson L, Conti M. Low dose positron emission tomography emulation from decimated high statistics: a clinical validation study. Med Phys John & Sons Wiley Ltd. 2019;46:2638–45.
52.
Zhu J-Y, Park T, Isola P, Efros AA. Unpaired image-to-image translation using cycle-consistent adversarial networks. IEEE Int Conf Comput Vis ICCV. 2017. p. 2242–51.
Metadata
Title
Artificial intelligence guided enhancement of digital PET: scans as fast as CT?
Authors
René Hosch
Manuel Weber
Miriam Sraieb
Nils Flaschel
Johannes Haubold
Moon-Sung Kim
Lale Umutlu
Jens Kleesiek
Ken Herrmann
Felix Nensa
Christoph Rischpler
Sven Koitka
Robert Seifert
David Kersting
Publication date
29-07-2022
Publisher
Springer Berlin Heidelberg
Published in
European Journal of Nuclear Medicine and Molecular Imaging / Issue 13/2022
Print ISSN: 1619-7070
Electronic ISSN: 1619-7089
DOI
https://doi.org/10.1007/s00259-022-05901-x

Other articles of this Issue 13/2022

European Journal of Nuclear Medicine and Molecular Imaging 13/2022 Go to the issue

Original Article

[89Zr]Zr-PSMA-617 PET/CT in biochemical recurrence of prostate cancer: first clinical experience from a pilot study including biodistribution and dose estimates

Original Article

Anti-GD2 antibody for radiopharmaceutical imaging of osteosarcoma

Original Article

Presence of non-Newtonian fluid in invasive pulmonary mucinous adenocarcinomas impacts fluorescence during intraoperative molecular imaging of lung cancer

Image of the Month

Use of [11C]choline PET/CT for visualization of four hyperactive parathyroid glands in a patient with renal hyperparathyroidism

Original Article

Intraprocedural MRI-based dosimetry during transarterial radioembolization of liver tumours with holmium-166 microspheres (EMERITUS-1): a phase I trial towards adaptive, image-controlled treatment delivery

Original Article

Hetero-bivalent agents targeting FAP and PSMA