Advertisement

Multi-Input and Dataset-Invariant Adversarial Learning (MDAL) for Left and Right-Ventricular Coverage Estimation in Cardiac MRI

  • Le ZhangEmail author
  • Marco Pereañez
  • Stefan K. Piechnik
  • Stefan Neubauer
  • Steffen E. Petersen
  • Alejandro F. Frangi
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11071)

Abstract

Cardiac functional parameters, such as, the Ejection Fraction (EF) and Cardiac Output (CO) of both ventricles, are most immediate indicators of normal/abnormal cardiac function. To compute these parameters, accurate measurement of ventricular volumes at end-diastole (ED) and end-systole (ES) are required. Accurate volume measurements depend on the correct identification of basal and apical slices in cardiac magnetic resonance (CMR) sequences that provide full coverage of both left (LV) and right (RV) ventricles. This paper proposes a novel adversarial learning (AL) approach based on convolutional neural networks (CNN) that detects and localizes the basal/apical slices in an image volume independently of image-acquisition parameters, such as, imaging device, magnetic field strength, variations in protocol execution, etc. The proposed model is trained on multiple cohorts of different provenance, and learns image features from different MRI viewing planes to learn the appearance and predict the position of the basal and apical planes. To the best of our knowledge, this is the first work tackling the fully automatic detection and position regression of basal/apical slices in CMR volumes in a dataset-invariant manner. We achieve this by maximizing the ability of a CNN to regress the position of basal/apical slices within a single dataset, while minimizing the ability of a classifier to discriminate image features between different data sources. Our results show superior performance over state-of-the-art methods.

Keywords

Deep learning Dataset invariance Adversarial learning Ventricular coverage assessment MRI 

References

  1. 1.
    Attili, A.K., Schuster, A., Nagel, E., Reiber, J.H., van der Geest, R.J.: Quantification in cardiac MRI: advances in image acquisition and processing. Int. J. Cardiovasc. Imaging 26(1), 27–40 (2010)CrossRefGoogle Scholar
  2. 2.
    Carapella, V.: Towards the semantic enrichment of free-text annotation of image quality assessment for UK Biobank cardiac cine MRI scans. In: Carneiro, G. (ed.) LABELS/DLMIA 2016. LNCS, vol. 10008, pp. 238–248. Springer, Cham (2016).  https://doi.org/10.1007/978-3-319-46976-8_25CrossRefGoogle Scholar
  3. 3.
    Demyanov, S.: ConvNet library for Matlab. https://github.com/sdemyanov/ConvNet. Accessed 15 Oct 2017
  4. 4.
    Ganin, Y., Ustinova, E., Ajakan, H., Germain, P., et al.: Domain-adversarial training of neural networks. J. Mach. Learn. Res. 17(1), 2096–2030 (2016)Google Scholar
  5. 5.
    García-Laencina, P.J., Sancho-Gómez, J.L., Figueiras-Vidal, A.R.: Pattern classification with missing data: a review. Neural Comput. Appl. 19(2), 263–282 (2010)CrossRefGoogle Scholar
  6. 6.
    Goodfellow, I., Pouget-Abadie, J., Mirza, M., Xu, B., Warde-Farley, D., et al.: Generative adversarial nets. In: Advances in Neural Information Processing Systems, pp. 2672–2680 (2014)Google Scholar
  7. 7.
    Huang, Y., Shao, L., Frangi, A.F.: Simultaneous super-resolution and cross-modality synthesis of 3D medical images using weakly-supervised joint convolutional sparse coding. In: IEEE Conference on CVPR, pp. 6070–6079 (2017)Google Scholar
  8. 8.
    Lisanti, G., Masi, I., Bagdanov, A.D., Del Bimbo, A.: Person re-identification by iterative re-weighted sparse ranking. IEEE TPAMI 37(8), 1629–1642 (2015)CrossRefGoogle Scholar
  9. 9.
    Ma, L., Yang, X., Tao, D.: Person re-identification over camera networks using multi-task distance metric learning. IEEE TIP 23(8), 3656–3670 (2014)MathSciNetzbMATHGoogle Scholar
  10. 10.
    Paknezhad, M., Marchesseau, S., Brown, M.S.: Automatic basal slice detection for cardiac analysis. J. Med. Imaging 3(3), 034004–034004 (2016)CrossRefGoogle Scholar
  11. 11.
    Petersen, S.E., Matthews, P.M., Francis, J.M.: UK Biobank’s cardiovascular magnetic resonance protocol. J. Cardiovasc. Magn. Reson. 18(1), 1 (2016)Google Scholar
  12. 12.
    Sharmanska, V., Quadrianto, N.: Learning from the mistakes of others: matching errors in cross-dataset learning. In: IEEE Conference on CVPR, pp. 3967–3975 (2016)Google Scholar
  13. 13.
    Wang, Z., Wu, G., Sheikh, H.R., Simoncelli, E.P., Yang, E.H., Bovik, A.C.: Quality-aware images. IEEE TIP 15(6), 1680–1689 (2006)Google Scholar
  14. 14.
    Zhang, L., et al.: Automated quality assessment of cardiac MR images using convolutional neural networks. In: Tsaftaris, S.A., Gooya, A., Frangi, A.F., Prince, J.L. (eds.) SASHIMI 2016. LNCS, vol. 9968, pp. 138–145. Springer, Cham (2016).  https://doi.org/10.1007/978-3-319-46630-9_14CrossRefGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2018

Authors and Affiliations

  • Le Zhang
    • 1
    Email author
  • Marco Pereañez
    • 1
  • Stefan K. Piechnik
    • 2
  • Stefan Neubauer
    • 2
  • Steffen E. Petersen
    • 3
  • Alejandro F. Frangi
    • 1
  1. 1.Centre for Computational Imaging and Simulation Technologies in Biomedicine, Department of Electronic and Electrical EngineeringUniversity of SheffieldSheffieldUK
  2. 2.Oxford Center for Clinical Magnetic Resonance Research (OCMR), Division of Cardiovascular Medicine, University of Oxford, John Radcliffe HospitalOxfordUK
  3. 3.Cardiovascular Medicine at the William Harvey Research Institute, Queen Mary University of London and Barts Heart Center, Barts Health NHS TrustLondonUK

Personalised recommendations