Skip to main content
Top
Published in: Magnetic Resonance Materials in Physics, Biology and Medicine 2/2018

01-04-2018 | Research Article

Automated reference-free detection of motion artifacts in magnetic resonance images

Authors: Thomas Küstner, Annika Liebgott, Lukas Mauch, Petros Martirosian, Fabian Bamberg, Konstantin Nikolaou, Bin Yang, Fritz Schick, Sergios Gatidis

Published in: Magnetic Resonance Materials in Physics, Biology and Medicine | Issue 2/2018

Login to get access

Abstract

Objectives

Our objectives were to provide an automated method for spatially resolved detection and quantification of motion artifacts in MR images of the head and abdomen as well as a quality control of the trained architecture.

Materials and methods

T1-weighted MR images of the head and the upper abdomen were acquired in 16 healthy volunteers under rest and under motion. Images were divided into overlapping patches of different sizes achieving spatial separation. Using these patches as input data, a convolutional neural network (CNN) was trained to derive probability maps for the presence of motion artifacts. A deep visualization offers a human-interpretable quality control of the trained CNN. Results were visually assessed on probability maps and as classification accuracy on a per-patch, per-slice and per-volunteer basis.

Results

On visual assessment, a clear difference of probability maps was observed between data sets with and without motion. The overall accuracy of motion detection on a per-patch/per-volunteer basis reached 97%/100% in the head and 75%/100% in the abdomen, respectively.

Conclusion

Automated detection of motion artifacts in MRI is feasible with good accuracy in the head and abdomen. The proposed method provides quantification and localization of artifacts as well as a visualization of the learned content. It may be extended to other anatomic areas and used for quality assurance of MR images.
Appendix
Available only for authorised users
Literature
1.
go back to reference Ollier W, Sprosen T, Peakman T (2005) UK Biobank: from concept to reality. Pharmacogenomics 6(6):639–646CrossRefPubMed Ollier W, Sprosen T, Peakman T (2005) UK Biobank: from concept to reality. Pharmacogenomics 6(6):639–646CrossRefPubMed
2.
go back to reference Bamberg F, Kauczor HU, Weckbach S, Schlett CL, Forsting M, Ladd SC, Greiser KH, Weber MA, Schulz-Menger J, Niendorf T, Pischon T, Caspers S, Amunts K, Berger K, Bulow R, Hosten N, Hegenscheid K, Kroncke T, Linseisen J, Gunther M, Hirsch JG, Kohn A, Hendel T, Wichmann HE, Schmidt B, Jockel KH, Hoffmann W, Kaaks R, Reiser MF, Volzke H (2015) Whole-body MR imaging in the German National Cohort: rationale, design, and technical background. Radiology 277(1):206–220CrossRefPubMed Bamberg F, Kauczor HU, Weckbach S, Schlett CL, Forsting M, Ladd SC, Greiser KH, Weber MA, Schulz-Menger J, Niendorf T, Pischon T, Caspers S, Amunts K, Berger K, Bulow R, Hosten N, Hegenscheid K, Kroncke T, Linseisen J, Gunther M, Hirsch JG, Kohn A, Hendel T, Wichmann HE, Schmidt B, Jockel KH, Hoffmann W, Kaaks R, Reiser MF, Volzke H (2015) Whole-body MR imaging in the German National Cohort: rationale, design, and technical background. Radiology 277(1):206–220CrossRefPubMed
3.
go back to reference De Wilde JP, Lunt JA, Straughan K (1997) Information in magnetic resonance images: evaluation of signal, noise and contrast. Med Biol Eng Comput 35(3):259–265CrossRefPubMed De Wilde JP, Lunt JA, Straughan K (1997) Information in magnetic resonance images: evaluation of signal, noise and contrast. Med Biol Eng Comput 35(3):259–265CrossRefPubMed
4.
go back to reference Eck BL, Fahmi R, Brown KM, Zabic S, Raihani N, Miao J, Wilson DL (2015) Computational and human observer image quality evaluation of low dose, knowledge-based CT iterative reconstruction. Med Phys 42(10):6098CrossRefPubMedPubMedCentral Eck BL, Fahmi R, Brown KM, Zabic S, Raihani N, Miao J, Wilson DL (2015) Computational and human observer image quality evaluation of low dose, knowledge-based CT iterative reconstruction. Med Phys 42(10):6098CrossRefPubMedPubMedCentral
5.
go back to reference Sinha N, Ramakrishnan AG (2010) Quality assessment in magnetic resonance images. Crit Rev Biomed Eng 38(2):127–141CrossRefPubMed Sinha N, Ramakrishnan AG (2010) Quality assessment in magnetic resonance images. Crit Rev Biomed Eng 38(2):127–141CrossRefPubMed
6.
go back to reference Pizarro RA, Cheng X, Barnett A, Lemaitre H, Verchinski BA, Goldman AL, Xiao E, Luo Q, Berman KF, Callicott JH, Weinberger DR, Mattay VS (2016) Automated quality assessment of structural magnetic resonance brain images based on a supervised machine learning algorithm. Front Neurosci 10:52 Pizarro RA, Cheng X, Barnett A, Lemaitre H, Verchinski BA, Goldman AL, Xiao E, Luo Q, Berman KF, Callicott JH, Weinberger DR, Mattay VS (2016) Automated quality assessment of structural magnetic resonance brain images based on a supervised machine learning algorithm. Front Neurosci 10:52
7.
go back to reference Küstner T, Bahar P, Würslin C, Gatidis S, Martirosian P, Schwenzer NF, Yang B, Schmidt H (2015)A new approach for automatic image quality assessment. In: Proceedings of the 23rd scientific meeting, International Society for Magnetic Resonance in Medicine, Toronto, Canada. p 4735 Küstner T, Bahar P, Würslin C, Gatidis S, Martirosian P, Schwenzer NF, Yang B, Schmidt H (2015)A new approach for automatic image quality assessment. In: Proceedings of the 23rd scientific meeting, International Society for Magnetic Resonance in Medicine, Toronto, Canada. p 4735
8.
go back to reference Deng L, Yu D (2014) Deep learning: methods and applications. Found Trend Signal Process 7(3–4):197–387CrossRef Deng L, Yu D (2014) Deep learning: methods and applications. Found Trend Signal Process 7(3–4):197–387CrossRef
9.
go back to reference Cheng JY, Zhang T, Ruangwattanapaisarn N, Alley MT, Uecker M, Pauly JM, Lustig M, Vasanawala SS (2015) Free-breathing pediatric MRI with nonrigid motion correction and acceleration. J Magn Reson Imaging 42(2):407–420CrossRefPubMed Cheng JY, Zhang T, Ruangwattanapaisarn N, Alley MT, Uecker M, Pauly JM, Lustig M, Vasanawala SS (2015) Free-breathing pediatric MRI with nonrigid motion correction and acceleration. J Magn Reson Imaging 42(2):407–420CrossRefPubMed
10.
go back to reference Cruz G, Atkinson D, Buerger C, Schaeffter T, Prieto C (2016) Accelerated motion corrected three-dimensional abdominal MRI using total variation regularized SENSE reconstruction. Magn Reson Med 75(4):1484–1498CrossRefPubMed Cruz G, Atkinson D, Buerger C, Schaeffter T, Prieto C (2016) Accelerated motion corrected three-dimensional abdominal MRI using total variation regularized SENSE reconstruction. Magn Reson Med 75(4):1484–1498CrossRefPubMed
11.
go back to reference Feng L, Grimm R, Block KT, Chandarana H, Kim S, Xu J, Axel L, Sodickson DK, Otazo R (2014) Golden-angle radial sparse parallel MRI: combination of compressed sensing, parallel imaging, and golden-angle radial sampling for fast and flexible dynamic volumetric MRI. Magn Reson Med 72(3):707–717CrossRefPubMed Feng L, Grimm R, Block KT, Chandarana H, Kim S, Xu J, Axel L, Sodickson DK, Otazo R (2014) Golden-angle radial sparse parallel MRI: combination of compressed sensing, parallel imaging, and golden-angle radial sampling for fast and flexible dynamic volumetric MRI. Magn Reson Med 72(3):707–717CrossRefPubMed
12.
go back to reference Küstner T, Würslin C, Schwartz M, Martirosian P, Gatidis S, Brendle C, Seith F, Schick F, Schwenzer NF, Yang B, Schmidt H (2016) Self-navigated 4D cartesian imaging of periodic motion in the body trunk using partial k-space compressed sensing. Magn Reson Med. doi:10.1002/mrm.26406 PubMed Küstner T, Würslin C, Schwartz M, Martirosian P, Gatidis S, Brendle C, Seith F, Schick F, Schwenzer NF, Yang B, Schmidt H (2016) Self-navigated 4D cartesian imaging of periodic motion in the body trunk using partial k-space compressed sensing. Magn Reson Med. doi:10.​1002/​mrm.​26406 PubMed
13.
go back to reference Rank CM, Heusser T, Buzan MT, Wetscherek A, Freitag MT, Dinkel J, Kachelriess M (2016) 4D respiratory motion-compensated image reconstruction of free-breathing radial MR data with very high undersampling. Magn Reson Med 77(3):1170–1183CrossRefPubMed Rank CM, Heusser T, Buzan MT, Wetscherek A, Freitag MT, Dinkel J, Kachelriess M (2016) 4D respiratory motion-compensated image reconstruction of free-breathing radial MR data with very high undersampling. Magn Reson Med 77(3):1170–1183CrossRefPubMed
14.
go back to reference Zhu Y, Guo Y, Lingala SG, Marc Lebel R, Law M, Nayak KS (2015) GOCART: GOlden-angle CArtesian randomized time-resolved 3D MRI. J Magn Reson Imaging 34(7):940–950CrossRef Zhu Y, Guo Y, Lingala SG, Marc Lebel R, Law M, Nayak KS (2015) GOCART: GOlden-angle CArtesian randomized time-resolved 3D MRI. J Magn Reson Imaging 34(7):940–950CrossRef
15.
go back to reference Godenschweger F, Kagebein U, Stucht D, Yarach U, Sciarra A, Yakupov R, Lusebrink F, Schulze P, Speck O (2016) Motion correction in MRI of the brain. Phys Med Biol 61(5):R32–R56CrossRefPubMedPubMedCentral Godenschweger F, Kagebein U, Stucht D, Yarach U, Sciarra A, Yakupov R, Lusebrink F, Schulze P, Speck O (2016) Motion correction in MRI of the brain. Phys Med Biol 61(5):R32–R56CrossRefPubMedPubMedCentral
16.
go back to reference Maclaren J, Herbst M, Speck O, Zaitsev M (2013) Prospective motion correction in brain imaging: a review. Magn Reson Med 69(3):621–636CrossRefPubMed Maclaren J, Herbst M, Speck O, Zaitsev M (2013) Prospective motion correction in brain imaging: a review. Magn Reson Med 69(3):621–636CrossRefPubMed
17.
18.
go back to reference Baum EB, Haussler D (1989) What size net gives valid generalization? Neural Comput 1(1):151–160CrossRef Baum EB, Haussler D (1989) What size net gives valid generalization? Neural Comput 1(1):151–160CrossRef
19.
go back to reference Kingma DP, Ba J (2014) Adam: a Method for stochastic optimization. Comput Res Repos 1412.6980 Kingma DP, Ba J (2014) Adam: a Method for stochastic optimization. Comput Res Repos 1412.6980
21.
go back to reference Atkinson D, Hill DL, Stoyle PN, Summers PE, Keevil SF (1997) Automatic correction of motion artifacts in magnetic resonance images using an entropy focus criterion. IEEE Trans Med Imaging 16(6):903–910CrossRefPubMed Atkinson D, Hill DL, Stoyle PN, Summers PE, Keevil SF (1997) Automatic correction of motion artifacts in magnetic resonance images using an entropy focus criterion. IEEE Trans Med Imaging 16(6):903–910CrossRefPubMed
22.
go back to reference Yosinski J, Clune J, Nguyen A, Fuchs T, Lipson H (2015) Understanding neural networks through deep visualization. In: Proceedings of the 31st International conference on machine learning, Deep Learning Workshop. Lille, pp 1–12 Yosinski J, Clune J, Nguyen A, Fuchs T, Lipson H (2015) Understanding neural networks through deep visualization. In: Proceedings of the 31st International conference on machine learning, Deep Learning Workshop. Lille, pp 1–12
23.
go back to reference Parikh N, Boyd S (2014) Proximal algorithms. Found Trend Optim 1(3):127–239CrossRef Parikh N, Boyd S (2014) Proximal algorithms. Found Trend Optim 1(3):127–239CrossRef
24.
go back to reference Krizhevsky A, Sutskever I, Hinton GE (2012) Imagenet classification with deep convolutional neural networks. In: Pereira F, Burges CJC, Bottou L, Weinberger KQ (eds) Advances in neural information processing systems 25. Curran Associates, Red Hook, pp 1097–1105 Krizhevsky A, Sutskever I, Hinton GE (2012) Imagenet classification with deep convolutional neural networks. In: Pereira F, Burges CJC, Bottou L, Weinberger KQ (eds) Advances in neural information processing systems 25. Curran Associates, Red Hook, pp 1097–1105
25.
go back to reference Ruder S (2016) An overview of gradient descent optimization algorithms. CoRR abs/1609.04747 Ruder S (2016) An overview of gradient descent optimization algorithms. CoRR abs/1609.04747
26.
go back to reference Aksoy M, Forman C, Straka M, Cukur T, Hornegger J, Bammer R (2012) Hybrid prospective and retrospective head motion correction to mitigate cross-calibration errors. Magn Reson Med 67(5):1237–1251CrossRefPubMed Aksoy M, Forman C, Straka M, Cukur T, Hornegger J, Bammer R (2012) Hybrid prospective and retrospective head motion correction to mitigate cross-calibration errors. Magn Reson Med 67(5):1237–1251CrossRefPubMed
27.
go back to reference McGee KP, Manduca A, Felmlee JP, Riederer SJ, Ehman RL (2000) Image metric-based correction (autocorrection) of motion effects: analysis of image metrics. J Magn Reson Imaging 11(2):174–181CrossRefPubMed McGee KP, Manduca A, Felmlee JP, Riederer SJ, Ehman RL (2000) Image metric-based correction (autocorrection) of motion effects: analysis of image metrics. J Magn Reson Imaging 11(2):174–181CrossRefPubMed
28.
go back to reference Gilliam C, Küstner T, Blu T (2016) 3D motion flow estimation using local all-pass filters. In: Proceedings of the 13th IEEE International Symposium on Biomedical Imaging, 13–16. pp 282–285 Gilliam C, Küstner T, Blu T (2016) 3D motion flow estimation using local all-pass filters. In: Proceedings of the 13th IEEE International Symposium on Biomedical Imaging, 13–16. pp 282–285
29.
30.
go back to reference Oh J, Woolley SI, Arvanitis TN, Townend JN (2001) A multistage perceptual quality assessment for compressed digital angiogram images. IEEE Trans Med Imaging 20(12):1352–1361CrossRefPubMed Oh J, Woolley SI, Arvanitis TN, Townend JN (2001) A multistage perceptual quality assessment for compressed digital angiogram images. IEEE Trans Med Imaging 20(12):1352–1361CrossRefPubMed
31.
go back to reference Ouled Zaid A, Fradj BB (2010) Coronary angiogram video compression for remote browsing and archiving applications. Comput Med Imaging Graph 34(8):632–641CrossRefPubMed Ouled Zaid A, Fradj BB (2010) Coronary angiogram video compression for remote browsing and archiving applications. Comput Med Imaging Graph 34(8):632–641CrossRefPubMed
32.
go back to reference Flask CA, Salem KA, Moriguchi H, Lewin JS, Wilson DL, Duerk JL (2003) Keyhole Dixon method for faster, perceptually equivalent fat suppression. J Magn Reson Imaging 18(1):103–112CrossRefPubMed Flask CA, Salem KA, Moriguchi H, Lewin JS, Wilson DL, Duerk JL (2003) Keyhole Dixon method for faster, perceptually equivalent fat suppression. J Magn Reson Imaging 18(1):103–112CrossRefPubMed
33.
go back to reference Mortamet B, Bernstein MA, Jack CR Jr, Gunter JL, Ward C, Britson PJ, Meuli R, Thiran JP, Krueger G (2009) Automatic quality assessment in structural brain magnetic resonance imaging. Magn Reson Med 62(2):365–372CrossRefPubMedPubMedCentral Mortamet B, Bernstein MA, Jack CR Jr, Gunter JL, Ward C, Britson PJ, Meuli R, Thiran JP, Krueger G (2009) Automatic quality assessment in structural brain magnetic resonance imaging. Magn Reson Med 62(2):365–372CrossRefPubMedPubMedCentral
34.
go back to reference Woodard JP, Carley-Spencer MP (2006) No-reference image quality metrics for structural MRI. Neuroinformatics 4(3):243–262CrossRefPubMed Woodard JP, Carley-Spencer MP (2006) No-reference image quality metrics for structural MRI. Neuroinformatics 4(3):243–262CrossRefPubMed
35.
go back to reference Tisdall MD, Atkins MS (2006) Using human and model performance to compare MRI reconstructions. IEEE Trans Med Imaging 25(11):1510–1517CrossRefPubMed Tisdall MD, Atkins MS (2006) Using human and model performance to compare MRI reconstructions. IEEE Trans Med Imaging 25(11):1510–1517CrossRefPubMed
Metadata
Title
Automated reference-free detection of motion artifacts in magnetic resonance images
Authors
Thomas Küstner
Annika Liebgott
Lukas Mauch
Petros Martirosian
Fabian Bamberg
Konstantin Nikolaou
Bin Yang
Fritz Schick
Sergios Gatidis
Publication date
01-04-2018
Publisher
Springer Berlin Heidelberg
Published in
Magnetic Resonance Materials in Physics, Biology and Medicine / Issue 2/2018
Print ISSN: 0968-5243
Electronic ISSN: 1352-8661
DOI
https://doi.org/10.1007/s10334-017-0650-z

Other articles of this Issue 2/2018

Magnetic Resonance Materials in Physics, Biology and Medicine 2/2018 Go to the issue