Advertisement

Investigating Image Registration Impact on Preterm Birth Classification: An Interpretable Deep Learning Approach

  • Irina GrigorescuEmail author
  • Lucilio Cordero-Grande
  • A. David Edwards
  • Joseph V. Hajnal
  • Marc Modat
  • Maria Deprez
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11798)

Abstract

Deep learning algorithms have recently become the dominant trend in medical image classification. However, the decision-making rationale of convolutional neural network (CNN) classifiers can be obscure. Interpretable machine learning techniques, such as layer-wise relevance propagation (LRP), can provide a visual interpretation of these decisions. In this work, we build a 3D CNN model to classify neonatal \(T_2\)-weighted magnetic resonance (MR) scans into term or preterm. Additionally, we investigate the impact of different registration techniques applied to the image dataset on the classifier’s predictions. Finally, we compute LRP ‘relevance maps’, which indicate each voxel’s importance to the outcome of the decision. Our resulting LRP heatmaps show no visually striking differences between the different registration techniques, while also revealing anatomically plausible features for term and preterm birth.

Keywords

Preterm birth Classification Layer-wise relevance propagation 

References

  1. 1.
    Arbabzadah, F., Montavon, G., Müller, K., Samek, W.: Identifying individual facial expressions by deconstructing a neural network. CoRR (2016). http://arxiv.org/abs/1606.07285
  2. 2.
    Bach, S., Binder, A., Montavon, G., Klauschen, F., Müller, K.R., Samek, W.: On pixel-wise explanations for non-linear classifier decisions by layer-wise relevance propagation. PLoS ONE 10(7), e0130140 (2015)CrossRefGoogle Scholar
  3. 3.
    Bach, S., Binder, A., Montavon, G., Müller, K., Samek, W.: Analyzing classifiers: Fisher vectors and deep neural networks. CoRR (2015). http://arxiv.org/abs/1512.00172
  4. 4.
    Cordero-Grande, L., Hughes, E.J., Hutter, J., Price, A.N., Hajnal, J.V.: Three-dimensional motion corrected sensitivity encoding reconstruction for multi-shot multi-slice MRI: application to neonatal brain imaging. Magn. Reson. Med. 79(3), 1365–1376 (2018). https://onlinelibrary.wiley.com/doi/abs/10.1002/mrm.26796CrossRefGoogle Scholar
  5. 5.
    Georgios, A., Hugo, L., Ulrika, A., Nelly, P., Mats, B.: Brain growth gains and losses in extremely preterm infants at term. Cereb. Cortex 25(7), 1897–1905 (2014).  https://doi.org/10.1093/cercor/bht431CrossRefGoogle Scholar
  6. 6.
    Grigorescu, I., Cordero-Grande, L., Edwards, A.D., Hajnal, J., Modat, M., Deprez, M.: Interpretable convolutional neural networks for preterm birth classification. In: International Conference on Medical Imaging with Deep Learning - Extended Abstract Track, London, United Kingdom, 08–10 July 2019. https://openreview.net/pdf?id=SyevkEaEcE
  7. 7.
    Hughes, E.J., et al.: A dedicated neonatal brain imaging system. Magn. Reson. Med. 78(2), 794–804 (2017). https://onlinelibrary.wiley.com/doi/abs/10.1002/mrm.26462CrossRefGoogle Scholar
  8. 8.
    Ioffe, S., Szegedy, C.: Batch normalization: accelerating deep network training by reducing internal covariate shift. CoRR (2015). http://arxiv.org/abs/1502.03167
  9. 9.
    Montavon, G., Samek, W., Müller, K.R.: Methods for interpreting and understanding deep neural networks. Digit. Sig. Process. Rev. J. 73, 1–15 (2018).  https://doi.org/10.1016/j.dsp.2017.10.011MathSciNetCrossRefGoogle Scholar
  10. 10.
    Rueckert, D., Sonoda, L.I., Hayes, C., Hill, D.L.G., Leach, M.O., Hawkes, D.J.: Nonrigid registration using free-form deformations: application to breast MR images. IEEE Trans. Med. Imaging 18(8), 712–721 (1999). http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=796284&isnumber=17288CrossRefGoogle Scholar
  11. 11.
    Schuh, A., et al.: Unbiased construction of a temporally consistent morphological atlas of neonatal brain development. bioRxiv (2018).  https://doi.org/10.1101/251512
  12. 12.
    Smith, L.N.: No more pesky learning rate guessing games. CoRR (2015). http://arxiv.org/abs/1506.01186
  13. 13.
    Sturm, I., Bach, S., Samek, W., Müller, K.: Interpretable deep neural networks for single-trial EEG classification. CoRR (2016). http://arxiv.org/abs/1604.08201

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  1. 1.School of Biomedical Engineering and Imaging SciencesKing’s College LondonLondonUK

Personalised recommendations