Deep Learning Using K-Space Based Data Augmentation for Automated Cardiac MR Motion Artefact Detection

Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11070)


Quality assessment of medical images is essential for complete automation of image processing pipelines. For large population studies such as the UK Biobank, artefacts such as those caused by heart motion are problematic and manual identification is tedious and time-consuming. Therefore, there is an urgent need for automatic image quality assessment techniques. In this paper, we propose a method to automatically detect the presence of motion-related artefacts in cardiac magnetic resonance (CMR) images. As this is a highly imbalanced classification problem (due to the high number of good quality images compared to the low number of images with motion artefacts), we propose a novel k-space based training data augmentation approach in order to address this problem. Our method is based on 3D spatio-temporal Convolutional Neural Networks, and is able to detect 2D+time short axis images with motion artefacts in less than 1 ms. We test our algorithm on a subset of the UK Biobank dataset consisting of 3465 CMR images and achieve not only high accuracy in detection of motion artefacts, but also high precision and recall. We compare our approach to a range of state-of-the-art quality assessment methods.


Cardiac MR Image quality assessment Motion artefacts UK Biobank Convolutional Neural Networks 



This work was supported by an EPSRC programme Grant (EP/P001009/1) and the Wellcome EPSRC Centre for Medical Engineering at the School of Biomedical Engineering and Imaging Sciences, King’s College London (WT 203148/Z/16/Z). This research has been conducted using the UK Biobank Resource under Application Number 17806. The GPU used in this research was generously donated by the NVIDIA Corporation.

Supplementary material

473972_1_En_29_MOESM1_ESM.avi (318 kb)
Supplementary material 1 (avi 317 KB)
473972_1_En_29_MOESM2_ESM.avi (318 kb)
Supplementary material 2 (avi 317 KB)
473972_1_En_29_MOESM3_ESM.avi (318 kb)
Supplementary material 3 (avi 317 KB)


  1. 1.
    Abdi, A.H., et al.: Quality assessment of echocardiographic cine using recurrent neural networks: feasibility on five standard view planes. In: Descoteaux, M., Maier-Hein, L., Franz, A., Jannin, P., Collins, D.L., Duchesne, S. (eds.) MICCAI 2017, Part III. LNCS, vol. 10435, pp. 302–310. Springer, Cham (2017). Scholar
  2. 2.
    Baumgartner, C.F., Kamnitsas, K., Matthew, J., Smith, S., Kainz, B., Rueckert, D.: Real-time standard scan plane detection and localisation in fetal ultrasound using fully convolutional neural networks. In: Ourselin, S., Joskowicz, L., Sabuncu, M.R., Unal, G., Wells, W. (eds.) MICCAI 2016, Part II. LNCS, vol. 9901, pp. 203–211. Springer, Cham (2016). Scholar
  3. 3.
    Ferreira, P.F.: Cardiovascular magnetic resonance artefacts. JCMR 15(1), 1–41 (2013)MathSciNetGoogle Scholar
  4. 4.
    Kang, L., et al.: Convolutional neural networks for no reference image quality assessment. In: CVPR, vol. 18, pp. 1733–1740 (2014)Google Scholar
  5. 5.
    Korshunova, F.N., et al.: Diagnosing heart diseases with deep neural networks (2016).
  6. 6.
    Kustner, T., et al.: Automated reference-free detection of motion artifacts in magnetic resonance images. MR Mater. Phys. Biol. Med. 31(2), 1–14 (2017)Google Scholar
  7. 7.
    Lorch, B.: Automated detection of motion artefacts in MR imaging using decision forests. J. Med. Eng. 2017, 9 (2017)CrossRefGoogle Scholar
  8. 8.
    Meding, K., et al.: Automatic detection of motion artifacts in MR images using CNNS. In: ICASSP, pp. 811–815 (2017)Google Scholar
  9. 9.
    Mittal, A.: Making a completely blind image quality analyzer. IEEE Signal Process. Lett. 22(3), 209–212 (2013)CrossRefGoogle Scholar
  10. 10.
    Oksuz, I., et al.: Automatic left ventricular outflow tract classification for accurate cardiac MR planning. In: ISBI (2018)Google Scholar
  11. 11.
    Petersen, S.E.: UK biobank’s cardiovascular magnetic resonance protocol. JCMR 18(1), 1–8 (2016)Google Scholar
  12. 12.
    Robinson, R., et al.: Automatic quality control of cardiac MRI segmentation in large-scale population imaging. In: Descoteaux, M., Maier-Hein, L., Franz, A., Jannin, P., Collins, D.L., Duchesne, S. (eds.) MICCAI 2017, Part I. LNCS, vol. 10433, pp. 720–727. Springer, Cham (2017). Scholar
  13. 13.
    Tarroni, G., et al.: Learning-based heart coverage estimation for short-axis cine cardiac MR images. In: Pop, M., Wright, G.A. (eds.) FIMH 2017. LNCS, vol. 10263, pp. 73–82. Springer, Cham (2017). Scholar
  14. 14.
    Tran, D., et al.: Learning spatiotemporal features with 3D convolutional networks. In: ICCV, pp. 4489–4497 (2015)Google Scholar
  15. 15.
    Wu, L.: FUIQA: fetal ultrasound image quality assessment with deep convolutional networks. IEEE Trans. Cybern. 47(5), 1336–1349 (2016)CrossRefGoogle Scholar
  16. 16.
    Zhang, L., Gooya, A., Frangi, A.F.: Semi-supervised assessment of incomplete LV coverage in cardiac MRI using generative adversarial nets. In: Tsaftaris, S.A., Gooya, A., Frangi, A.F., Prince, J.L. (eds.) SASHIMI 2017. LNCS, vol. 10557, pp. 61–68. Springer, Cham (2017). Scholar

Copyright information

© Springer Nature Switzerland AG 2018

Authors and Affiliations

  1. 1.School of Biomedical Engineering and Imaging SciencesKing’s College LondonLondonUK
  2. 2.Guy’s and St Thomas’ Hospital NHS Foundation TrustLondonUK
  3. 3.Biomedical Image Analysis GroupImperial College LondonLondonUK

Personalised recommendations