Accelerating Whole-Body Diffusion-weighted MRI with Deep Learning-based Denoising Image Filters.
Image Postprocessing
Lung
MR-Diffusion-weighted Imaging
MR-Functional Imaging
Metastases
Neural Networks
Oncology
Prostate
Supervised Learning
Whole-Body Imaging
Journal
Radiology. Artificial intelligence
ISSN: 2638-6100
Titre abrégé: Radiol Artif Intell
Pays: United States
ID NLM: 101746556
Informations de publication
Date de publication:
Sep 2021
Sep 2021
Historique:
received:
19
11
2020
revised:
11
05
2021
accepted:
04
06
2021
entrez:
7
10
2021
pubmed:
8
10
2021
medline:
8
10
2021
Statut:
epublish
Résumé
To use deep learning to improve the image quality of subsampled images (number of acquisitions = 1 [NOA Both retrospective and prospective patient groups were used to develop a deep learning-based denoising image filter (DNIF) model. For initial model training and validation, 17 patients with metastatic prostate cancer with acquired WBDWI NOA The model visually improved the quality of NOA Clinical-standard images were generated from subsampled images by using a DNIF.
Identifiants
pubmed: 34617028
doi: 10.1148/ryai.2021200279
pmc: PMC8489468
doi:
Types de publication
Journal Article
Langues
eng
Pagination
e200279Informations de copyright
2021 by the Radiological Society of North America, Inc.
Déclaration de conflit d'intérêts
Disclosures of Conflicts of Interest: K.Z.P. Activities related to the present article: disclosed no relevant relationships. Activities not related to the present article: disclosed no relevant relationships. Other relationships: a patent has been submitted to the UK Intellectual Property Office directly regarding the work described in this article. N.T. disclosed no relevant relationships. A.C. disclosed no relevant relationships. C.M. disclosed no relevant relationships. S.C. disclosed no relevant relationships. D.J.C. disclosed no relevant relationships. J.C.H. disclosed no relevant relationships. Y.J. disclosed no relevant relationships. D.M.K. Activities related to the present article: institution received grant from NIHR Clinical Research Facilities. Activities not related to the present article: disclosed no relevant relationships. Other relationships: disclosed no relevant relationships. M.D.B. Activities related to the present article: disclosed no relevant relationships. Activities not related to the present article: consultant for Bayer. Other relationships: a patent has been submitted to the UK Intellectual Property Office directly regarding the work described in this article; a patent has been granted for work in a broadly relevant field (US10885679B2). This patent is also pending in Japan and Europe (JP2019513515A/EP3443373A1).
Références
Radiology. 2011 Dec;261(3):700-18
pubmed: 22095994
Eur Urol. 2017 Jan;71(1):81-92
pubmed: 27317091
J Magn Reson Imaging. 2010 Jul;32(1):2-16
pubmed: 20575076
Nat Rev Clin Oncol. 2017 Mar;14(3):169-186
pubmed: 27725679
Front Oncol. 2020 May 08;10:704
pubmed: 32457842
Radiology. 2019 Apr;291(1):5-13
pubmed: 30806604
Radiology. 2018 Jul;288(1):177-185
pubmed: 29584598
Radiology. 2019 Dec;293(3):607-617
pubmed: 31592731
BMJ Open. 2017 Sep 6;7(9):e016391
pubmed: 28882915
Neuroimage. 2019 Jul 15;195:373-383
pubmed: 30935908
Radiology. 2017 Jul;284(1):88-99
pubmed: 28301311
Br J Radiol. 2018 Jun;91(1086):20170731
pubmed: 29528257
Lung Cancer. 2015 Dec;90(3):433-41
pubmed: 26443279
J Magn Reson Imaging. 2011 May;33(5):1160-70
pubmed: 21509875
AJR Am J Roentgenol. 2012 Aug;199(2):252-62
pubmed: 22826385
Br J Haematol. 2017 Aug;178(3):380-393
pubmed: 28677897
Nature. 2018 Mar 21;555(7697):487-492
pubmed: 29565357
Magn Reson Med. 2021 Jan;85(1):413-428
pubmed: 32662910
PLoS One. 2014 Apr 07;9(4):e91779
pubmed: 24710083
IEEE Trans Image Process. 2004 Apr;13(4):600-12
pubmed: 15376593
Phys Med Biol. 2018 Jun 25;63(13):135007
pubmed: 29787383
Med Image Anal. 2019 Jul;55:165-180
pubmed: 31085444