Learning a Single Step of Streamline Tractography Based on Neural Networks

Conference paper
Part of the Mathematics and Visualization book series (MATHVISUAL)

Abstract

This paper focuses on predicting a single step of streamline tractography from diffusion magnetic resonance imaging data by using different predictors based on neural networks. We train 18 different classifiers in order to assess the effect of including neighbourhood information in the learning step or as a post processing step. Moreover, the performance using four different post processing approaches as well as the variation of the number of classes resulting in a total of 60 experimental configurations are assessed. Further, a comparison to 12 regression-based networks is performed and the effect of including several streamline steps in the network input is investigated. All networks are trained and tested on the ISMRM 2015 tractography challenge data. Our results do not indicate a clear improvement when using neighbouring data (regardless if it used as an input or as a post processing). Also, the linear interpolation of the diffusion data does not outperform the less expensive nearest neighbour approach. As opposed to that, using a linear model on top of the output of the classifiers is beneficial and—in combination with at least 200 classes—resulted in a similar performance as the regression approach. Finally, providing the networks with additional curvature information led to a clear improvement of prediction performance. Our analysis of accuracy based on average angular errors suggests that also considering spatial location in the learning step might further improve machine learning-based streamline tractography algorithms.

References

  1. 1.
    Chollet, F., et al.: Keras (2015). https://github.com/fchollet/keras
  2. 2.
    Cote, M.A., Girard, G., Bore, A., Garyfallidis, E., Houde, J.C., Descoteaux, M.: Tractometer: towards validation of tractography pipelines. Med. Image Anal. 17, 884–857 (2013)CrossRefGoogle Scholar
  3. 3.
    Golkov, V., Dosovitskiy, A., Sperl, J.I., Menzel, M.I., Czisch, M., Smann, P., Brox, T., Cremers, D.: q-Space deep learning: twelve-fold shorter and model-free diffusion MRI scans. IEEE Trans. Med. Imaging 35(5), 1344–1351 (2016)Google Scholar
  4. 4.
    Kingma, D., Ba, J.: Adam: a method for stochastic optimization (2014). arXiv preprint arXiv:1412.6980Google Scholar
  5. 5.
    Koppers, S., Merhof, D.: Direct estimation of fiber orientations using deep learning in diffusion imaging. In: Machine Learning in Medical Imaging, pp. 53–60. Springer, New York (2016)Google Scholar
  6. 6.
    Koppers, S., Haarburger, C., Merhof, D.: Diffusion mri signal augmentation: from single shell to multi shell with deep learning. In: Computational Diffusion MRI, pp. 61–70. Springer, New York (2017)Google Scholar
  7. 7.
    Maier-Hein, K.H., et al.: The challenge of mapping the human connectome based on diffusion tractography. Nat. Commun. 8(1349) (2017)Google Scholar
  8. 8.
    Neher, P.F., Laun, F.B., Stieltjes, B., Maier-Hein, K.H.: Fiberfox: an extensible system for generating realistic white matter software phantoms. In: Computational Diffusion MRI and Brain Connectivity, pp. 105–113. Springer, New York (2014)Google Scholar
  9. 9.
    Neher, P.F., Götz, M., Norajitra, T., Weber, C., Maier-Hein, K.H.: A machine learning based approach to fiber tractography using classifier voting. In: International Conference on Medical Image Computing and Computer-Assisted Intervention – MICCAI 2015, pp. 45–52. Springer, New York (2015)Google Scholar
  10. 10.
    Neher, P.F., Côté, M.-A., Houde, J.-C., Descoteaux, M., Maier-Hein, K.H.: Fiber tractography using machine learning. NeuroImage 158, 417–429 (2017)CrossRefGoogle Scholar
  11. 11.
    Srivastava, N., Hinton, G.E., 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)MathSciNetMATHGoogle Scholar
  12. 12.
    Ye, C.: Estimation of tissue microstructure using a deep network inspired by a sparse reconstruction framework. In: Information Processing in Medical Imaging, pp. 466–477. Springer, New York (2017)Google Scholar

Copyright information

© Springer International Publishing AG, part of Springer Nature 2018

Authors and Affiliations

  • Daniel Jörgens
    • 1
  • Örjan Smedby
    • 1
  • Rodrigo Moreno
    • 1
  1. 1.Department of Biomedical Engineering and Health SystemsKTH Royal Institute of TechnologyStockholmSweden

Personalised recommendations