Advertisement

Deep Nested Level Sets: Fully Automated Segmentation of Cardiac MR Images in Patients with Pulmonary Hypertension

  • Jinming DuanEmail author
  • Jo Schlemper
  • Wenjia Bai
  • Timothy J. W. Dawes
  • Ghalib Bello
  • Georgia Doumou
  • Antonio De Marvao
  • Declan P. O’Regan
  • Daniel Rueckert
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11073)

Abstract

In this paper we introduce a novel and accurate optimisation method for segmentation of cardiac MR (CMR) images in patients with pulmonary hypertension (PH). The proposed method explicitly takes into account the image features learned from a deep neural network. To this end, we estimate simultaneous probability maps over region and edge locations in CMR images using a fully convolutional network. Due to the distinct morphology of the heart in patients with PH, these probability maps can then be incorporated in a single nested level set optimisation framework to achieve multi-region segmentation with high efficiency. The proposed method uses an automatic way for level set initialisation and thus the whole optimisation is fully automated. We demonstrate that the proposed deep nested level set (DNLS) method outperforms existing state-of-the-art methods for CMR segmentation in PH patients.

Notes

Acknowledgements

The research was supported by the British Heart Foundation (NH/17/1/32725, RE/13/4/30184); National Institute for Health Research (NIHR) Biomedical Research Centre based at Imperial College Healthcare NHS Trust and Imperial College London; and the Medical Research Council, UK. We would like to thank Dr Simon Gibbs, Dr Luke Howard and Prof Martin Wilkins for providing the CMR image data. The TITAN Xp GPU used for this research was kindly donated by the NVIDIA Corporation.

References

  1. 1.
    Feng, C., Li, C., Zhao, D., Davatzikos, C., Litt, H.: Segmentation of the left ventricle using distance regularized two-layer level set approach. In: Mori, K., Sakuma, I., Sato, Y., Barillot, C., Navab, N. (eds.) MICCAI 2013. LNCS, vol. 8149, pp. 477–484. Springer, Heidelberg (2013).  https://doi.org/10.1007/978-3-642-40811-3_60CrossRefGoogle Scholar
  2. 2.
    Bai, W., Shi, W., O’Regan, D.P., Tong, T., Wang, H., Jamil-Copley, S., Peters, N.S., Rueckert, D.: A probabilistic patch-based label fusion model for multi-atlas segmentation with registration refinement: application to cardiac MR images. IEEE Trans. Med. Imaging 32(7), 1302–1315 (2013)CrossRefGoogle Scholar
  3. 3.
    Albà, X., Pereañez, M., Hoogendoorn, C.: An algorithm for the segmentation of highly abnormal hearts using a generic statistical shape model. IEEE Trans. Med. Imaging 35(3), 845–859 (2016)CrossRefGoogle Scholar
  4. 4.
    Bai, W., Sinclair, M., Tarroni, G., et al.: Human-level CMR image analysis with deep fully convolutional networks. J. Cardiovasc. Magn. (2018)Google Scholar
  5. 5.
    Duan, J., Pan, Z., Yin, X., Wei, W., Wang, G.: Some fast projection methods based on Chan-Vese model for image segmentation. EURASIP J. Image Video Process. 7, 1–16 (2014)Google Scholar
  6. 6.
    Tan, L., Pan, Z., Liu, W., Duan, J., Wei, W., Wang, G.: Image segmentation with depth information via simplified variational level set formulation. J. Math. Imaging Vis. 60(1), 1–17 (2018)MathSciNetCrossRefGoogle Scholar
  7. 7.
    Chung, G., Vese, L.A.: Image segmentation using a multilayer level-set approach. Comput. Vis. Sci. 12(6), 267–285 (2009)MathSciNetCrossRefGoogle Scholar
  8. 8.
    Xie, S., Tu, Z.: Holistically-nested edge detection. In: ECCV, pp. 1395–1403 (2015)Google Scholar
  9. 9.
    Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. CoRR abs/1409.1556 (2014)Google Scholar
  10. 10.
    Duan, J., Haines, B., Ward, W.O.C., Bai, L.: Surface reconstruction from point clouds using a novel variational model. In: Bramer, M., Petridis, M. (eds.) Research and Development in Intelligent Systems XXXII, pp. 135–146. Springer, Cham (2015).  https://doi.org/10.1007/978-3-319-25032-8_9CrossRefGoogle Scholar
  11. 11.
    Krähenbühl, P., Koltun, V.: Efficient inference in fully connected CRFs with Gaussian edge potentials. In: NIPS, pp. 109–117 (2011)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2018

Authors and Affiliations

  • Jinming Duan
    • 1
    • 2
    Email author
  • Jo Schlemper
    • 1
  • Wenjia Bai
    • 1
  • Timothy J. W. Dawes
    • 2
  • Ghalib Bello
    • 2
  • Georgia Doumou
    • 2
  • Antonio De Marvao
    • 2
  • Declan P. O’Regan
    • 2
  • Daniel Rueckert
    • 1
  1. 1.Biomedical Image Analysis GroupImperial College LondonLondonUK
  2. 2.MRC London Institute of Medical SciencesImperial College LondonLondonUK

Personalised recommendations