3D FractalNet: Dense Volumetric Segmentation for Cardiovascular MRI Volumes

  • Lequan YuEmail author
  • Xin Yang
  • Jing Qin
  • Pheng-Ann Heng
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 10129)


Cardiac image segmentation plays a crucial role in various medical applications. However, differentiating branchy structures and slicing fuzzy boundaries from cardiovascular MRI volumes remain very challenging tasks. In this paper, we propose a novel deeply-supervised 3D fractal network for efficient automated whole heart and great vessel segmentation in MRI volumes. The proposed 3D fractal network takes advantage of fully convolutional architecture to perform efficient, precise and volume-to-volume prediction. Notably, by recursively applying a single expansion rule, we construct our network in a novel self-similar fractal scheme and thus promote it in combining hierarchical clues for accurate segmentation. More importantly, we employ deep supervision mechanism to alleviate the vanishing gradients problem and improve the training efficiency of our network on small medical image dataset. We evaluated our method on the HVSMR 2016 Challenge dataset. Extensive experimental results demonstrated the superior performance of our method, ranking top in both two phases.


Cardiovascular Magnetic Resonance Receptive Field Convolutional Neural Network Deep Neural Network Convolutional Layer 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.



The work described in this paper was supported by a grant from the Research Grants Council of the Hong Kong Special Administrative Region (Project no. CUHK 412513).


  1. 1.
    Chen, H., Dou, Q., Yu, L., Heng, P.A.: Voxresnet: deep voxelwise residual networks for volumetric brain segmentation. arXiv preprint arXiv:1608.05895 (2016)
  2. 2.
    Çiçek, Ö., Abdulkadir, A., Lienkamp, S.S., Brox, T., Ronneberger, O.: 3d u-net: learning dense volumetric segmentation from sparse annotation. arXiv preprint arXiv:1606.06650 (2016)
  3. 3.
    Dou, Q., Chen, H., Jin, Y., Yu, L., Qin, J., Heng, P.A.: 3d deeply supervised network for automatic liver segmentation from CT volumes. arXiv preprint arXiv:1607.00582 (2016)
  4. 4.
    Glorot, X., Bengio, Y.: Understanding the difficulty of training deep feedforward neural networks. Aistats 9, 249–256 (2010)Google Scholar
  5. 5.
    Jia, Y., Shelhamer, E., Donahue, J., Karayev, S., Long, J., Girshick, R., Guadarrama, S., Darrell, T.: Caffe: convolutional architecture for fast feature embedding. arXiv preprint arXiv:1408.5093 (2014)
  6. 6.
    Larsson, G., Maire, M., Shakhnarovich, G.: Fractalnet: ultra-deep neural networks without residuals. arXiv preprint arXiv:1605.07648 (2016)
  7. 7.
    Lee, C.Y., Xie, S., Gallagher, P., Zhang, Z., Tu, Z.: Deeply-supervised nets (2015)Google Scholar
  8. 8.
    Long, J., Shelhamer, E., 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
  9. 9.
    Merkow, J., Kriegman, D., Marsden, A., Tu, Z.: Dense volume-to-volume vascular boundary detection. arXiv preprint arXiv:1605.08401 (2016)
  10. 10.
    Pace, D.F., Dalca, A.V., Geva, T., Powell, A.J., Moghari, M.H., Golland, P.: Interactive whole-heart segmentation in congenital heart disease. In: Navab, N., Hornegger, J., Wells, W.M., Frangi, A.F. (eds.) MICCAI 2015. LNCS, vol. 9351, pp. 80–88. Springer, Heidelberg (2015). doi: 10.1007/978-3-319-24574-4_10 CrossRefGoogle Scholar
  11. 11.
    Peters, J., Ecabert, O., Meyer, C., Schramm, H., Kneser, R., Groth, A., Weese, J.: Automatic whole heart segmentation in static magnetic resonance image volumes. In: Ayache, N., Ourselin, S., Maeder, A. (eds.) MICCAI 2007. LNCS, vol. 4792, pp. 402–410. Springer, Heidelberg (2007). doi: 10.1007/978-3-540-75759-7_49 CrossRefGoogle Scholar
  12. 12.
    Ronneberger, O., Fischer, P., Brox, T.: U-net: convolutional networks for biomedical image segmentation. In: Navab, N., Hornegger, J., Wells, W.M., Frangi, A.F. (eds.) MICCAI 2015. LNCS, vol. 9351, pp. 234–241. Springer, Heidelberg (2015). doi: 10.1007/978-3-319-24574-4_28 CrossRefGoogle Scholar
  13. 13.
    Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)
  14. 14.
    Tran, P.V.: A fully convolutional neural network for cardiac segmentation in short-axis MRI. arXiv preprint arXiv:1604.00494 (2016)
  15. 15.
    Xie, S., Tu, Z.: Holistically-nested edge detection. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1395–1403 (2015)Google Scholar
  16. 16.
    Zhuang, X., Rhode, K.S., Razavi, R.S., Hawkes, D.J., Ourselin, S.: A registration-based propagation framework for automatic whole heart segmentation of cardiac MRI. IEEE Trans. Med. Imag. 29(9), 1612–1625 (2010)CrossRefGoogle Scholar

Copyright information

© Springer International Publishing AG 2017

Authors and Affiliations

  1. 1.Department of Computer Science and EngineeringThe Chinese University of Hong KongSha TinHong Kong
  2. 2.Centre for Smart Health, School of NursingThe Hong Kong Polytechnic UniversityKowloonHong Kong

Personalised recommendations