Advertisement

Dilated Convolutional Neural Networks for Cardiovascular MR Segmentation in Congenital Heart Disease

  • Jelmer M. Wolterink
  • Tim Leiner
  • Max A. Viergever
  • Ivana Išgum
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 10129)

Abstract

We propose an automatic method using dilated convolutional neural networks (CNNs) for segmentation of the myocardium and blood pool in cardiovascular MR (CMR) of patients with congenital heart disease (CHD).

Ten training and ten test CMR scans cropped to an ROI around the heart were provided in the MICCAI 2016 HVSMR challenge. A dilated CNN with a receptive field of \(131\times 131\) voxels was trained for myocardium and blood pool segmentation in axial, sagittal and coronal image slices. Performance was evaluated within the HVSMR challenge.

Automatic segmentation of the test scans resulted in Dice indices of \(0.80\,\pm \,0.06\) and \(0.93\,\pm \,0.02\), average distances to boundaries of \(0.96\,\pm \,0.31\) and \(0.89\,\pm \,0.24\) mm, and Hausdorff distances of \(6.13\,\pm \,3.76\) and \(7.07\,\pm \,3.01\) mm for the myocardium and blood pool, respectively. Segmentation took \(41.5\,\pm \,14.7\) s per scan.

In conclusion, dilated CNNs trained on a small set of CMR images of CHD patients showing large anatomical variability provide accurate myocardium and blood pool segmentations.

Keywords

Deep learning Dilated convolutional neural networks Medical image segmentation Cardiovascular MR Congenital heart disease 

Notes

Acknowledgments

We gratefully acknowledge the support of NVIDIA Corporation with the donation of the Tesla K40 GPU used for this research.

References

  1. 1.
    Clevert, D.A., Unterthiner, T., Hochreiter, S.: Fast and accurate deep network learning by exponential linear units (ELUs). In: ICLR (2016)Google Scholar
  2. 2.
    Gilboa, S.M., Devine, O.J., Kucik, J.E., Oster, M.E., Riehle-Colarusso, T., Nembhard, W.N., Xu, P., Correa, A., Jenkins, K., Marelli, A.J.: Congenital heart defects in the United States: Estimating the magnitude of the affected population in 2010. Circulation 134(2), 101–109 (2016)Google Scholar
  3. 3.
    Havaei, M., Davy, A., Warde-Farley, D., Biard, A., Courville, A., Bengio, Y., Pal, C., Jodoin, P.M., Larochelle, H.: Brain tumor segmentation with deep neural networks. Med. Imag. Anal. 35, 18–31 (2017)CrossRefGoogle Scholar
  4. 4.
    Ioffe, S., Szegedy, C.: Batch normalization: accelerating deep network training by reducing internal covariate shift. In: ICML (2015)Google Scholar
  5. 5.
    Kingma, D., Ba, J.: Adam: a method for stochastic optimization. In: ICLR (2015)Google Scholar
  6. 6.
    Moeskops, P., Viergever, M.A., Mendrik, A.M., de Vries, L.S., Benders, M.J., Išgum, I.: Automatic segmentation of MR brain images with a convolutional neural network. IEEE Trans. Med. Imag. 35(5), 1252–1261 (2016)CrossRefGoogle Scholar
  7. 7.
    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
  8. 8.
    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
  9. 9.
    Schmauss, D., Haeberle, S., Hagl, C., Sodian, R.: Three-dimensional printing in cardiac surgery and interventional cardiology: a single-centre experience. Eur. J. Cardiothorac. Surg. 47(6), 1044–1052 (2015)CrossRefGoogle Scholar
  10. 10.
    Srivastava, N., Hinton, G., Krizhevsky, A., Sutskever, I., Salakhutdinov, R.: Dropout: a simple way to prevent neural networks from overfitting. J. Mach. Learn. Res. 15(1), 1929–1958 (2014)MathSciNetzbMATHGoogle Scholar
  11. 11.
    Valverde, I., Gomez, G., Gonzalez, A., Suarez-Mejias, C., Adsuar, A., Coserria, J.F., Uribe, S., Gomez-Cia, T., Hosseinpour, A.R.: Three-dimensional patient-specific cardiac model for surgical planning in Nikaidoh procedure. Cardiol. Young 25(04), 698–704 (2015)CrossRefGoogle Scholar
  12. 12.
    Wolterink, J.M., Leiner, T., de Vos, B.D., van Hamersvelt, R.W., Viergever, M.A., Išgum, I.: Automatic coronary artery calcium scoring in cardiac CT angiography using paired convolutional neural networks. Med. Imag. Anal. 34, 123–136 (2016)CrossRefGoogle Scholar
  13. 13.
    Yu, F., Koltun, V.: Multi-scale context aggregation by dilated convolutions. In: ICLR (2016)Google Scholar
  14. 14.
    Zhuang, X., Shen, J.: Multi-scale patch and multi-modality atlases for whole heart segmentation of MRI. Med. Imag. Anal. 31, 77–87 (2016)CrossRefGoogle Scholar

Copyright information

© Springer International Publishing AG 2017

Authors and Affiliations

  • Jelmer M. Wolterink
    • 1
  • Tim Leiner
    • 2
  • Max A. Viergever
    • 1
  • Ivana Išgum
    • 1
  1. 1.Image Sciences InstituteUniversity Medical Center UtrechtUtrechtThe Netherlands
  2. 2.Department of RadiologyUniversity Medical Center UtrechtUtrechtThe Netherlands

Personalised recommendations