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


Journal

European journal of nuclear medicine and molecular imaging
ISSN: 1619-7089
Titre abrégé: Eur J Nucl Med Mol Imaging
Pays: Germany
ID NLM: 101140988

Informations de publication

Date de publication:
Nov 2022
Historique:
received: 15 02 2022
accepted: 30 06 2022
pubmed: 30 7 2022
medline: 29 10 2022
entrez: 29 7 2022
Statut: ppublish

Résumé

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. 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. 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 SUV 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.

Identifiants

pubmed: 35904589
doi: 10.1007/s00259-022-05901-x
pii: 10.1007/s00259-022-05901-x
pmc: PMC9606065
doi:

Substances chimiques

Fluorodeoxyglucose F18 0Z5B2CJX4D

Types de publication

Journal Article

Langues

eng

Sous-ensembles de citation

IM

Pagination

4503-4515

Informations de copyright

© 2022. The Author(s).

Références

IEEE Trans Med Imaging. 2019 Jun;38(6):1328-1339
pubmed: 30507527
Eur J Nucl Med Mol Imaging. 2019 Jun;46(6):1383-1390
pubmed: 30631910
J Digit Imaging. 2019 Oct;32(5):773-778
pubmed: 30402670
Eur Radiol. 2021 Aug;31(8):6087-6095
pubmed: 33630160
J Magn Reson Imaging. 2018 Aug;48(2):330-340
pubmed: 29437269
Radiology. 2020 Feb;294(2):445-452
pubmed: 31821122
Q J Nucl Med Mol Imaging. 2021 Jul 26;:
pubmed: 34309334
Med Phys. 2019 Jun;46(6):2638-2645
pubmed: 30929270
BMC Cancer. 2021 Jan 14;21(1):62
pubmed: 33446147
Eur J Nucl Med Mol Imaging. 2021 Aug;48(9):2771-2781
pubmed: 33527176
Phys Med Biol. 2019 Nov 04;64(21):215017
pubmed: 31561244
Neuroimage. 2018 Jul 1;174:550-562
pubmed: 29571715
J Nucl Med Technol. 2020 Dec;48(4):354-360
pubmed: 32887763
J Nucl Med. 2019 Jul;60(7):1031-1036
pubmed: 30630944
Eur J Nucl Med Mol Imaging. 2020 Mar;47(3):614-623
pubmed: 31792572
EJNMMI Phys. 2021 Feb 15;8(1):14
pubmed: 33587222
Med Image Anal. 2020 Jul;63:101667
pubmed: 32375101
J Nucl Med. 2020 Jan;61(1):129-135
pubmed: 31253742
Eur J Radiol. 2020 Aug;129:109144
pubmed: 32593080
J Nucl Med. 2020 Oct;61(10):1448-1454
pubmed: 32060217
IEEE Trans Med Imaging. 2019 Mar;38(3):675-685
pubmed: 30222554
Sci Rep. 2021 Sep 1;11(1):17477
pubmed: 34471170
Phys Med Biol. 2019 Aug 21;64(16):165019
pubmed: 31307019
EJNMMI Res. 2021 Feb 28;11(1):21
pubmed: 33641046
Eur J Nucl Med Mol Imaging. 2021 Jul;48(8):2405-2415
pubmed: 33495927
Nat Methods. 2020 Mar;17(3):261-272
pubmed: 32015543
Eur J Nucl Med Mol Imaging. 2021 Sep;48(10):3141-3150
pubmed: 33674891
J Nucl Med. 2020 Nov;61(11):1684-1690
pubmed: 32198313
J Nucl Med. 2020 May;61(5):764-771
pubmed: 31628214
Med Phys. 2015 Sep;42(9):5301-9
pubmed: 26328979
Med Phys. 2019 Aug;46(8):3555-3564
pubmed: 31131901
Phys Med Biol. 2021 May 20;66(11):
pubmed: 33882466
Radiology. 2016 Aug;280(2):576-84
pubmed: 26909647
NPJ Digit Med. 2021 Aug 23;4(1):127
pubmed: 34426629
J Nucl Med. 2020 Sep;61(9):1388-1396
pubmed: 31924718
Comput Med Imaging Graph. 2020 Jan;79:101684
pubmed: 31812132
J Nucl Med. 2012 May;53(5):701-8
pubmed: 22496583
Radiol Phys Technol. 2019 Sep;12(3):235-248
pubmed: 31222562
Acta Oncol. 2011 Jun;50(5):670-7
pubmed: 21247262
Eur J Nucl Med Mol Imaging. 2015 Feb;42(2):328-54
pubmed: 25452219

Auteurs

René Hosch (R)

Institute of Diagnostic and Interventional Radiology and Neuroradiology, University Hospital Essen, Hufelandstraße 55, 45147, Essen, Germany. rene.hosch@uk-essen.de.
Institute for Artificial Intelligence in Medicine (IKIM), University Hospital Essen, Girardetstraße 2, 45131, Essen, Germany. rene.hosch@uk-essen.de.

Manuel Weber (M)

Department of Nuclear Medicine and German Cancer Consortium (DKTK), University Hospital Essen, University of Duisburg-Essen, Hufelandstraße 55, 45147, Essen, Germany.

Miriam Sraieb (M)

Department of Nuclear Medicine and German Cancer Consortium (DKTK), University Hospital Essen, University of Duisburg-Essen, Hufelandstraße 55, 45147, Essen, Germany.

Nils Flaschel (N)

Institute of Diagnostic and Interventional Radiology and Neuroradiology, University Hospital Essen, Hufelandstraße 55, 45147, Essen, Germany.
Institute for Artificial Intelligence in Medicine (IKIM), University Hospital Essen, Girardetstraße 2, 45131, Essen, Germany.

Johannes Haubold (J)

Institute of Diagnostic and Interventional Radiology and Neuroradiology, University Hospital Essen, Hufelandstraße 55, 45147, Essen, Germany.

Moon-Sung Kim (MS)

Institute of Diagnostic and Interventional Radiology and Neuroradiology, University Hospital Essen, Hufelandstraße 55, 45147, Essen, Germany.
Institute for Artificial Intelligence in Medicine (IKIM), University Hospital Essen, Girardetstraße 2, 45131, Essen, Germany.

Lale Umutlu (L)

Institute of Diagnostic and Interventional Radiology and Neuroradiology, University Hospital Essen, Hufelandstraße 55, 45147, Essen, Germany.

Jens Kleesiek (J)

Institute for Artificial Intelligence in Medicine (IKIM), University Hospital Essen, Girardetstraße 2, 45131, Essen, Germany.

Ken Herrmann (K)

Department of Nuclear Medicine and German Cancer Consortium (DKTK), University Hospital Essen, University of Duisburg-Essen, Hufelandstraße 55, 45147, Essen, Germany.

Felix Nensa (F)

Institute of Diagnostic and Interventional Radiology and Neuroradiology, University Hospital Essen, Hufelandstraße 55, 45147, Essen, Germany.
Institute for Artificial Intelligence in Medicine (IKIM), University Hospital Essen, Girardetstraße 2, 45131, Essen, Germany.

Christoph Rischpler (C)

Department of Nuclear Medicine and German Cancer Consortium (DKTK), University Hospital Essen, University of Duisburg-Essen, Hufelandstraße 55, 45147, Essen, Germany.

Sven Koitka (S)

Institute of Diagnostic and Interventional Radiology and Neuroradiology, University Hospital Essen, Hufelandstraße 55, 45147, Essen, Germany.
Institute for Artificial Intelligence in Medicine (IKIM), University Hospital Essen, Girardetstraße 2, 45131, Essen, Germany.

Robert Seifert (R)

Department of Nuclear Medicine and German Cancer Consortium (DKTK), University Hospital Essen, University of Duisburg-Essen, Hufelandstraße 55, 45147, Essen, Germany.
Department of Nuclear Medicine, University Hospital Münster, University of Münster, Albert-Schweitzer-Campus 1, 48149, Münster, Germany.

David Kersting (D)

Department of Nuclear Medicine and German Cancer Consortium (DKTK), University Hospital Essen, University of Duisburg-Essen, Hufelandstraße 55, 45147, Essen, Germany.

Articles similaires

[Redispensing of expensive oral anticancer medicines: a practical application].

Lisanne N van Merendonk, Kübra Akgöl, Bastiaan Nuijen
1.00
Humans Antineoplastic Agents Administration, Oral Drug Costs Counterfeit Drugs

Smoking Cessation and Incident Cardiovascular Disease.

Jun Hwan Cho, Seung Yong Shin, Hoseob Kim et al.
1.00
Humans Male Smoking Cessation Cardiovascular Diseases Female
Humans United States Aged Cross-Sectional Studies Medicare Part C
1.00
Humans Yoga Low Back Pain Female Male

Classifications MeSH