Skip to main content
SpringerLink
Log in

Combining Deep Learning Networks with Permutation Tests to Predict Traumatic Brain Injury Outcome

  • Conference paper
  • First Online:
Brainlesion: Glioma, Multiple Sclerosis, Stroke and Traumatic Brain Injuries (BrainLes 2016)

Part of the book series: Lecture Notes in Computer Science ((LNIP,volume 10154))

  • 2141 Accesses

Abstract

Reliable prediction of traumatic brain injury (TBI) outcome using neuroimaging is clinically important, yet, computationally challenging. To tackle this problem, we developed an injury prediction or classification pipeline based on diffusion tensor imaging (DTI) by combining a novel deep learning approach with statistical permutation tests. We first applied a multi-modal deep learning network to individually train a classification model for each DTI measure. Individual results were then combined to allow iterative refinement of the classification via Tract-Based Spatial Statistics (TBSS) permutation tests, where voxel sum of skeletonized significance values served as a classification performance feedback. Our technique combined a high-performance machine learning algorithm with a conventional statistical tool, which provided a flexible and intuitive approach to predict TBI outcome.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Log in via an institution
Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 39.99
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 54.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

References

  1. Mitra, J., Shen, K., Ghose, S., Bourgeat, P., Fripp, J., Salvado, O., Pannek, K., Taylor, D.J., Mathias, J.L., Rose, S.: Statistical machine learning to identify traumatic brain injury (TBI) from structural disconnections of white matter networks. Neuroimage 129, 247–259 (2016)

    Article  Google Scholar 

  2. Levin, H.S., Li, X., McCauley, S.R., Hanten, G., Wilde, E.A., Swank, P.: Neuropsychological outcome of mTBI: a principal component analysis approach. J. Neurotrauma 30, 625–632 (2013)

    Article  Google Scholar 

  3. Alexander, D.C., Barker, G.J., Arridge, S.R.: Detection and modeling of non-Gaussian apparent diffusion coefficient profiles in human brain data. Magn. Reson. Med. 48, 331–340 (2002)

    Article  Google Scholar 

  4. Smith, S.M., Jenkinson, M., Johansen-Berg, H., Rueckert, D., Nichols, T.E., Mackay, C.E., Watkins, K.E., Ciccarelli, O., Cader, M.Z., Matthews, P.M., Behrens, T.E.J.: Tract-based spatial statistics: voxelwise analysis of multi-subject diffusion data. Neuroimage 31, 1487–1505 (2006)

    Article  Google Scholar 

  5. Nichols, T., Holmes, A.: Nonparametric permutation tests for functional neuroimaging. In: Human Brain Function, 2nd edn., pp. 887–910 (2003)

    Google Scholar 

  6. Nichols, T.E., Holmes, A.P.: Nonparametric permutation tests for functional neuroimaging: a primer with examples. Hum. Brain Mapp. 15, 1–25 (2002)

    Article  Google Scholar 

  7. Arfanakis, K., Haughton, V.M., Carew, J.D., Rogers, B.P., Dempsey, R.J., Meyerand, M.E.: Diffusion tensor MR imaging in diffuse axonal injury. AJNR Am. J. Neuroradiol. 23, 794–802 (2002)

    Google Scholar 

  8. Rutgers, D.R., Toulgoat, F., Cazejust, J., Fillard, P., Lasjaunias, P., Ducreux, D.: White matter abnormalities in mild traumatic brain injury: a diffusion tensor imaging study. AJNR Am. J. Neuroradiol. 29, 514–519 (2008)

    Article  Google Scholar 

  9. Kraus, M.F., Susmaras, T., Caughlin, B.P., Walker, C.J., Sweeney, J.A., Little, D.M.: White matter integrity and cognition in chronic traumatic brain injury: a diffusion tensor imaging study. Brain 130, 2508–2519 (2007)

    Article  Google Scholar 

  10. Mayer, A.R., Ling, J., Mannell, M.V., Gasparovic, C., Phillips, J.P., Doezema, D., Reichard, R., Yeo, R.A.: A prospective diffusion tensor imaging study in mild traumatic brain injury. Neurology 74, 643–650 (2010)

    Article  Google Scholar 

  11. Ilvesmäki, T., Luoto, T.M., Hakulinen, U., Brander, A., Ryymin, P., Eskola, H., Iverson, G.L., Öhman, J.: Acute mild traumatic brain injury is not associated with white matter change on diffusion tensor imaging. Brain 137, 1876–1882 (2014)

    Article  Google Scholar 

  12. Niogi, S.N., Mukherjee, P., Ghajar, J., Johnson, C.E., Kolster, R., Lee, H., Suh, M., Zimmerman, R.D., Manley, G.T., McCandliss, B.D.: Structural dissociation of attentional control and memory in adults with and without mild traumatic brain injury. Brain 131, 3209–3221 (2008)

    Article  Google Scholar 

  13. Wang, J.Y., Abdi, H., Bakhadirov, K., Diaz-Arrastia, R., Devous, M.D.: A comprehensive reliability assessment of quantitative diffusion tensor tractography. Neuroimage 60, 1127–1138 (2012)

    Article  Google Scholar 

  14. Farquharson, S., Tournier, J.-D., Calamante, F., Fabinyi, G., Schneider-Kolsky, M., Jackson, G.D., Connelly, A.: White matter fiber tractography: why we need to move beyond DTI. J. Neurosurg. 118, 1367–1377 (2013)

    Article  Google Scholar 

  15. Jenkinson, M., Beckmann, C.F., Behrens, T.E.J., Woolrich, M.W., Smith, S.M.: FSL. Neuroimage 62, 782–790 (2012)

    Article  Google Scholar 

  16. Ngiam, J., Khosla, A., Kim, M., Nam, J., Lee, H., Ng, A.Y.: Multimodal deep learning. In: Proceedings of 28th International Conference on Machine Learning, pp. 689–696 (2011)

    Google Scholar 

  17. Wilde, E.A., McCauley, S.R., Hunter, J.V., Bigler, E.D., Chu, Z., Wang, Z.J., Hanten, G.R., Troyanskaya, M., Yallampalli, R., Li, X., Chia, J., Levin, H.S.: Diffusion tensor imaging of acute mild traumatic brain injury in adolescents. Neurology 70, 948–955 (2008)

    Article  Google Scholar 

  18. Andersson, J.L.R., Jenkinson, M., Smith, S.: Non-linear registration aka Spatial normalisation FMRIB Technical report TR07JA2. In Pract. 22 (2007)

    Google Scholar 

  19. Nowlan, S.J.: Maximum likelihood competitive learning. In: Advances in Neural Information Processing Systems, vol. 2, pp. 574–582 (1990)

    Google Scholar 

  20. Cotter, A., Shamir, O., Srebro, N., Sridharan, K.: Better mini-batch algorithms via accelerated gradient methods. In: NIPS, pp. 1–9 (2011)

    Google Scholar 

  21. Bengio, Y., Lamblin, P., Popovici, D., Larochelle, H.: Greedy layer-wise training of deep networks. Adv. Neural Inf. Process. Syst. 19, 153 (2007)

    Google Scholar 

  22. Kao, P., Rojas, E., Chen, J., Zhang, A., Manjunath, B.S.: Unsupervised 3-D feature learning for mild traumatic brain injury. In: MICCAI Workshop:mTOP Grand Challenge (2016)

    Google Scholar 

  23. Bellotti, R., Lombardi, A., Amoroso, N., Tateo, A., Tangaro, S.: Semi-unsupervised prediction for mild TBI based on both graph and K-nn methods. In: MICCAI Workshop:mTOP Grand Challenge (2016)

    Google Scholar 

Download references

Acknowledgement

Funding is provided by the NIH grants R01 NS092853 and R21 NS088781.

Author information

Authors and Affiliations

  1. Department of Biomedical Engineering, Worcester Polytechnic Institute, Worcester, Massachusetts, 01605, USA

    Y. Cai & S. Ji

  2. Thayer School of Engineering, Dartmouth College, Hanover, New Hampshire, 03755, USA

    S. Ji

Authors
  1. Y. Cai
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. S. Ji
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Y. Cai .

Editor information

Editors and Affiliations

  1. University of Zurich, Istituto Italiano di Tecnologia, Genoa, Italy

    Alessandro Crimi

  2. TU München, Computer Science, Munich, Germany

    Bjoern Menze

  3. Medical Informatics, University of Lübeck, Lübeck, Germany

    Oskar Maier

  4. Surgical Technology and Biomechanics, Universität Bern, Bern, Switzerland

    Mauricio Reyes

  5. Department of Medicine, University of Cambridge, Cambridge, United Kingdom

    Stefan Winzeck

  6. Institute of Medical Informatics, University of Lübeck, Lübeck, Germany

    Heinz Handels

Appendix

Appendix

Table 1. Summary of subject classifications along with the corresponding confidence (obtained by the Softmax function of the classifier) levels. Shaded entries represent leaked labels.
Full size table

Rights and permissions

Reprints and permissions

Copyright information

© 2016 Springer International Publishing AG

About this paper

Cite this paper

Cai, Y., Ji, S. (2016). Combining Deep Learning Networks with Permutation Tests to Predict Traumatic Brain Injury Outcome. In: Crimi, A., Menze, B., Maier, O., Reyes, M., Winzeck, S., Handels, H. (eds) Brainlesion: Glioma, Multiple Sclerosis, Stroke and Traumatic Brain Injuries. BrainLes 2016. Lecture Notes in Computer Science(), vol 10154. Springer, Cham. https://doi.org/10.1007/978-3-319-55524-9_24

Download citation

  • DOI: https://doi.org/10.1007/978-3-319-55524-9_24

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-319-55523-2

  • Online ISBN: 978-3-319-55524-9

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics

Search

Navigation