Left Atrium Segmentation in CT Volumes with Fully Convolutional Networks

  • Honghui Liu
  • Jianjiang Feng
  • Zishun Feng
  • Jiwen Lu
  • Jie Zhou
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 10553)

Abstract

Automatic segmentation of the left atrium (LA) is a fundamental task for atrial fibrillation diagnosis and computer-aided ablation operation support systems. This paper presents an approach to automatically segmenting left atrium in 3D CT volumes using fully convolutional neural networks (FCNs). We train FCN for automatic segmentation of the left atrium, and then refine the segmentation results of the FCN using the knowledge of the left ventricle segmented using ASM based method. The proposed FCN models were trained on the STACOM’13 CT dataset. The results show that FCN-based left atrium segmentation achieves Dice coefficient scores over 93% with computation time below 35s per volume, despite of the high variation of LA.

Notes

Acknowledgements

This work is supported by the National Natural Science Foundation of China under Grants 61622207, 61373074, 61225008, and 61572271.

References

  1. 1.
    Christ, P.F., Elshaer, M.E.A., et al.: Automatic liver and lesion segmentation in CT using cascaded fully convolutional neural networks and 3D conditional random fields. In: Proceedings of International Conference on Medical Image Computing and Computer-Assisted Intervention, pp. 415–423 (2016)Google Scholar
  2. 2.
    Cootes, T.F., Taylor, C.J., Cooper, D.H., Graham, J.: Active shape models-their training and application. Comput. Vis. Image Underst. 61(1), 38–59 (1995)CrossRefGoogle Scholar
  3. 3.
    Daoudi, A., Mahmoudi, S., Chikh, M.A.: Automatic segmentation of the left atrium on CT images. In: Proceedings of International Workshop on Statistical Atlases and Computational Models of the Heart, pp. 14–23 (2013)Google Scholar
  4. 4.
    Everingham, M., Eslami, S.M.A., Gool, L.V., Williams, C.K.I., Winn, J., Zisserman, A.: The PASCAL visual object classes challenge: a retrospective. Int. J. Comput. Vis. 111(1), 98–136 (2015)CrossRefGoogle Scholar
  5. 5.
    Heimann, T., Meinzer, H.: Statistical shape models for 3D medical image segmentation: a review. Med. Image Anal. 13(4), 543–563 (2009)CrossRefGoogle Scholar
  6. 6.
    Iglesias, J.E., Sabuncu, M.R.: Multi-atlas segmentation of biomedical images: a survey. Med. Image Anal. 24(1), 205–219 (2015)CrossRefGoogle Scholar
  7. 7.
    Koltun, V.: Efficient inference in fully connected CRFs with Gaussian edge potentials. Adv. Neural Inf. Proc. Syst. 2(3), 4 (2011)Google Scholar
  8. 8.
    Margeta, J., McLeod, K., Criminisi, A., Ayache, N.: Decision forests for segmentation of the left atrium from 3D MRI. In: Proceedings of International Workshop on Statistical Atlases and Computational Models of the Heart, pp. 49–56 (2013)Google Scholar
  9. 9.
    Marrouche, N.F., Wilber, D.J., Hindricks, G., et al.: Association of atrial tissue fibrosis identified by delayed enhancement MRI and atrial fibrillation catheter ablation: The DECAAF study. J. Am. Med. Assoc. 311(5), 498–506 (2014)CrossRefGoogle Scholar
  10. 10.
    Noh, H., Hong, S., Han, B.: Learning deconvolution network for semantic segmentation. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1520–1528 (2015)Google Scholar
  11. 11.
    Patti, G., Pengo, V., Marcucci, R., et al.: The left atrial appendage: from embryology to prevention of thromboembolism. Eur. Heart J. (2016). doi: 10.1093/eurheartj/ehw159
  12. 12.
    Shelhamer, E., Long, J., Darrell, T.: Fully convolutional networks for semantic segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3431–3440 (2015)Google Scholar
  13. 13.
    Tobongomez, C., Geers, A.J., Peters, J., et al.: Benchmark for algorithms segmenting the left atrium from 3D CT and MRI datasets. IEEE Trans. Med. Imaging 34(7), 1460–1473 (2015)CrossRefGoogle Scholar
  14. 14.
    Zheng, Y., Wang, T., John, M., Zhou, S.K., Boese, J., Comaniciu, D.: Multi-part left atrium modeling and segmentation in C-arm CT volumes for atrial fibrillation ablation. In: Proceedings of International Conference on Medical Image Computing and Computer-Assisted Intervention, pp. 487–495. Springer, New York (2011)Google Scholar
  15. 15.
    Zuluaga, M., Cardoso, M.J., Modat, M., et al.: Multi-atlas propagation whole heart segmentation from MRI and CTA using a local normalised correlation coefficient criterion. In: Proceedings of International Conference on Functional Imaging and Modeling of the Heart, pp. 174–181 (2013)Google Scholar

Copyright information

© Springer International Publishing AG 2017

Authors and Affiliations

  • Honghui Liu
    • 1
  • Jianjiang Feng
    • 1
  • Zishun Feng
    • 1
  • Jiwen Lu
    • 1
  • Jie Zhou
    • 1
  1. 1.Department of AutomationTsinghua UniversityBeijingChina

Personalised recommendations