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 Radiology
Published in: European Radiology 11/2020

Open Access 01-11-2020 | Magnetic Resonance Imaging | Contrast Media

Reduction of respiratory motion artifacts in gadoxetate-enhanced MR with a deep learning–based filter using convolutional neural network

Authors: M.-L. Kromrey, D. Tamada, H. Johno, S. Funayama, N. Nagata, S. Ichikawa, J.-P. Kühn, H. Onishi, U. Motosugi

Published in: European Radiology | Issue 11/2020

Login to get access

Abstract

Objectives

To reveal the utility of motion artifact reduction with convolutional neural network (MARC) in gadoxetate disodium–enhanced multi-arterial phase MRI of the liver.

Methods

This retrospective study included 192 patients (131 men, 68.7 ± 10.3 years) receiving gadoxetate disodium–enhanced liver MRI in 2017. Datasets were submitted to a newly developed filter (MARC), consisting of 7 convolutional layers, and trained on 14,190 cropped images generated from abdominal MR images. Motion artifact for training was simulated by adding periodic k-space domain noise to the images. Original and filtered images of pre-contrast and 6 arterial phases (7 image sets per patient resulting in 1344 sets in total) were evaluated regarding motion artifacts on a 4-point scale. Lesion conspicuity in original and filtered images was ranked by side-by-side comparison.

Results

Of the 1344 original image sets, motion artifact score was 2 in 597, 3 in 165, and 4 in 54 sets. MARC significantly improved image quality over all phases showing an average motion artifact score of 1.97 ± 0.72 compared to 2.53 ± 0.71 in original MR images (p < 0.001). MARC improved motion scores from 2 to 1 in 177/596 (29.65%), from 3 to 2 in 119/165 (72.12%), and from 4 to 3 in 34/54 sets (62.96%). Lesion conspicuity was significantly improved (p < 0.001) without removing anatomical details.

Conclusions

Motion artifacts and lesion conspicuity of gadoxetate disodium–enhanced arterial phase liver MRI were significantly improved by the MARC filter, especially in cases with substantial artifacts. This method can be of high clinical value in subjects with failing breath-hold in the scan.

Key Points

• This study presents a newly developed deep learning–based filter for artifact reduction using convolutional neural network (motion artifact reduction with convolutional neural network, MARC).
• MARC significantly improved MR image quality after gadoxetate disodium administration by reducing motion artifacts, especially in cases with severely degraded images.
• Postprocessing with MARC led to better lesion conspicuity without removing anatomical details.
Literature
1.
Davenport MS, Viglianti BL, Al-Hawary MM et al (2013) Comparison of acute transient dyspnea after intravenous administration of gadoxetate disodium and gadobenate dimeglumine: effect on arterial phase image quality. Radiology 266:452–461CrossRef
2.
Pietryga JA, Burke LM, Marin D, Jaffe TA, Bashir MR (2014) Respiratory motion artifact affecting hepatic arterial phase imaging with gadoxetate disodium: examination recovery with a multiple arterial phase acquisition. Radiology 271:426–434CrossRef
3.
Davenport MS, Caoili EM, Kaza RK, Hussain HK (2014) Matched within-patient cohort study of transient arterial phase respiratory motion-related artifact in MR imaging of the liver: gadoxetate disodium versus gadobenate dimeglumine. Radiology 272:123–131CrossRef
4.
Motosugi U, Bannas P, Bookwalter CA, Sano K, Reeder SB (2016) An investigation of transient severe motion related to gadoxetic acid-enhanced MR imaging. Radiology 279:93–102CrossRef
5.
Kim SY, Park SH, Wu EH et al (2015) Transient respiratory motion artifact during arterial phase MRI with gadoxetate disodium: risk factor analyses. AJR Am J Roentgenol 204:1220–1227CrossRef
6.
Bruix J, Sherman M, American Association for the Study of Liver Diseases (2011) Management of hepatocellular carcinoma: an update. Hepatology 53:1020–1022CrossRef
7.
Motosugi U, Ichikawa T, Araki T (2013) Rules, roles, and room for discussion in gadoxetic acid-enhanced magnetic resonance liver imaging: current knowledge and future challenges. Magn Reson Med Sci 12:161–175CrossRef
8.
Song JS, Choi EJ, Park EH, Lee JH (2018) Comparison of transient severe motion in gadoxetate disodium and gadopentetate dimeglumine-enhanced MRI: effect of modified breath-holding method. Eur Radiol 28:1132–1139CrossRef
9.
Kim YK, Lin WC, Sung K et al (2017) Reducing artifacts during arterial phase of gadoxetate disodium-enhanced MR imaging: dilution method versus reduced injection rate. Radiology 283:429–437CrossRef
10.
Polanec SH, Bickel H, Baltzer PAT et al (2017) Respiratory motion artifacts during arterial phase imaging with gadoxetic acid: can the injection protocol minimize this drawback? J Magn Reson Imaging 46:1107–1114CrossRef
11.
Hollingsworth KG (2015) Reducing acquisition time in clinical MRI by data undersampling and compressed sensing reconstruction. Phys Med Biol 60:R297–R322CrossRef
12.
Zhang T, Chowdhury S, Lustig M et al (2014) Clinical performance of contrast enhanced abdominal pediatric MRI with fast combined parallel imaging compressed sensing reconstruction. J Magn Reson Imaging 40:13–25CrossRef
13.
Vasanawala SS, Iwadate Y, Church DG, Herfkens RJ, Brau AC (2010) Navigated abdominal T1-W MRI permits free-breathing image acquisition with less motion artifact. Pediatr Radiol 40:340–344CrossRef
14.
Grazioli L, Faletti R, Frittoli B et al (2018) Evaluation of incidence of acute transient dyspnea and related artifacts after administration of gadoxetate disodium: a prospective observational study. Radiol Med 123:910–917CrossRef
15.
Gruber L, Rainer V, Plaikner M, Kremser C, Jaschke W, Henninger B (2018) CAIPIRINHA-Dixon-TWIST (CDT)-VIBE MR imaging of the liver at 3.0T with gadoxetate disodium: a solution for transient arterial-phase respiratory motion-related artifacts? Eur Radiol 28:2013–2021CrossRef
16.
Min JH, Kim YK, Kang TW et al (2018) Artifacts during the arterial phase of gadoxetate disodium-enhanced MRI: multiple arterial phases using view-sharing from two different vendors versus single arterial phase imaging. Eur Radiol 28:3335–3346CrossRef
17.
Hyun CM, Kim HP, Lee SM, Lee S, Seo JK (2018) Deep learning for undersampled MRI reconstruction. Phys Med Biol 63:135007CrossRef
18.
Yang G, Yu S, Dong H et al (2018) DAGAN: deep de-aliasing generative adversarial networks for fast compressed sensing MRI reconstruction. IEEE Trans Med Imaging 37:1310–1321CrossRef
19.
Han Y, Yoo J, Kim HH, Shin HJ, Sung K, Ye JC (2018) Deep learning with domain adaptation for accelerated projection-reconstruction MR. Magn Reson Med 80:1189–1205CrossRef
20.
Hauptmann A, Arridge S, Lucka F, Muthurangu V, Steeden JA (2019) Real-time cardiovascular MR with spatio-temporal artifact suppression using deep learning-proof of concept in congenital heart disease. Magn Reson Med 81:1143–1156CrossRef
21.
Sommer K, Brosch T, Wiemker R et al (2018) Correction of motion artifacts using a multi-resolution fully convolutional neural network. In Proceedings of the 26th Annual Meeting of ISMRM, Paris, France Abstract 1175
22.
Pawar K, Chen ZE, Shah NJ, Egan GF (2018) Motion correction in MRI using deep convolutional neural network. In Proceedings of the 26th Annual Meeting of ISMRM, Paris, France, 2018 Abstract 1174
23.
24.
Rodriguez-Molinero A, Narvaiza L, Ruiz J, Galvez-Barron C (2013) Normal respiratory rate and peripheral blood oxygen saturation in the elderly population. J Am Geriatr Soc 61:2238–2240CrossRef
25.
26.
Girshick R, Donahue J, Darrell T, Malik J (2016) Region-based convolutional networks for accurate object detection and segmentation. IEEE Trans Pattern Anal Mach Intell 38:142–158CrossRef
27.
Zhang K, Zuo W, Chen Y, Meng D, Zhang L (2017) Beyond a Gaussian denoiser: residual learning of deep CNN for image denoising. IEEE Trans Image Process 26:3142–3155CrossRef
28.
Shi J, Liu QP, Wang CF, Zhang Q, Ying SH, Xu HY (2018) Super-resolution reconstruction of MR image with a novel residual learning network algorithm. Phys Med Biol 63
29.
Jin KH, McCann MT, Froustey E, Unser M (2017) Deep convolutional neural network for inverse problems in imaging. IEEE Trans Image Process 26:4509–4522CrossRef
30.
Lee D, Yoo J, Ye JC (2017) Deep artifact learning for compressed sensing and parallel MRI. arXiv arXiv:1703.01120
31.
Goodfellow IJ, Pouget-Abadie J, Mirza M et al (2014) Generative adversarial nets. Advances in Neural Information Processing Systems 27 (Nips 2014) 27
32.
Jiang W, Liu Z, Lee KH et al (2019) Respiratory motion correction in abdominal MRI using a densely connected U-net with GAN-guided training. arXiv arXiv:1906.09745
33.
Armanious K, Gatidis S, Nikolaou K, Yang B, Kustner T (2019) Retrospective correction of rigid and non-rigid Mr motion artifacts using GANs. 2019 IEEE 16th International Symposium on Biomedical Imaging (Isbi 2019):1550–1554
34.
Uricar M, Krizek P, Hurych D, Sobh I, Yogamani S, Denny P (2019) Yes, we GAN: applying adversarial techniques for autonomous driving. arXiv arXiv:1902.03442
Metadata
Title
Reduction of respiratory motion artifacts in gadoxetate-enhanced MR with a deep learning–based filter using convolutional neural network
Authors
M.-L. Kromrey
D. Tamada
H. Johno
S. Funayama
N. Nagata
S. Ichikawa
J.-P. Kühn
H. Onishi
U. Motosugi
Publication date
01-11-2020
Publisher
Springer Berlin Heidelberg
Published in
European Radiology / Issue 11/2020
Print ISSN: 0938-7994
Electronic ISSN: 1432-1084
DOI
https://doi.org/10.1007/s00330-020-07006-1

Other articles of this Issue 11/2020

European Radiology 11/2020 Go to the issue

Ultrasound

Impact of focused ultrasound on the ethanol ablation of VX2 liver tumours in rabbits

Cardiac

Influence of contrast agent and spatial resolution on myocardial strain results using feature tracking MRI

Breast

Breast-specific gamma imaging or ultrasonography as adjunct imaging diagnostics in women with mammographically dense breasts

Imaging Informatics and Artificial Intelligence

Clinico-radiological characteristic-based machine learning in reducing unnecessary prostate biopsies of PI-RADS 3 lesions with dual validation

Imaging Informatics and Artificial Intelligence

Current status and quality of radiomics studies in lymphoma: a systematic review

Chest

Association of “initial CT” findings with mortality in older patients with coronavirus disease 2019 (COVID-19)