Advertisement

Synthetic Perfusion Maps: Imaging Perfusion Deficits in DSC-MRI with Deep Learning

  • Andreas Hess
  • Raphael Meier
  • Johannes Kaesmacher
  • Simon Jung
  • Fabien Scalzo
  • David Liebeskind
  • Roland Wiest
  • Richard McKinleyEmail author
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11383)

Abstract

In this work, we present a novel convolutional neural network based method for perfusion map generation in dynamic susceptibility contrast-enhanced perfusion imaging. The proposed architecture is trained end-to-end and solely relies on raw perfusion data for inference. We used a dataset of 151 acute ischemic stroke cases for evaluation. Our method generates perfusion maps that are comparable to the target maps used for clinical routine, while being model-free, fast, and less noisy.

Supplementary material

479725_1_En_45_MOESM1_ESM.pdf (455 kb)
Supplementary material 1 (pdf 454 KB)

References

  1. 1.
    Kendall, A., Gal, Y.: What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision? (2017)Google Scholar
  2. 2.
    Kingma, D.P., Ba, J.: Adam: A Method for Stochastic Optimization (2014)Google Scholar
  3. 3.
    Klambauer, G., Unterthiner, T., et al.: Self-Normalizing Neural Networks (2017)Google Scholar
  4. 4.
    McKinley, R., Häni, L., et al.: Fully automated stroke tissue estimation using random forest classifiers (FASTER). JCBFM 37(8), 2728–2741 (2017)Google Scholar
  5. 5.
    McKinley, R., Hung, F., et al.: A machine learning approach to perfusion imaging with dynamic susceptibility contrast MR. Front. Neurol. 9, 717 (2018)CrossRefGoogle Scholar
  6. 6.
    Olivot, J.M., Mlynash, M., et al.: Geography, structure, and evolution of diffusion and perfusion lesions in Diffusion and perfusion imaging Evaluation For Understanding Stroke Evolution (DEFUSE). Stroke 40(10), 3245–3251 (2009)CrossRefGoogle Scholar
  7. 7.
    Song, S., et al.: Temporal similarity perfusion mapping: a standardized and model-free method for detecting perfusion deficits in stroke. PLoS ONE 12(10), e0185552 (2017)CrossRefGoogle Scholar
  8. 8.
    Ulas, C., Tetteh, G., et al.: Direct Estimation of Pharmacokinetic Parameters from DCE-MRI using Deep CNN with Forward Physical Model Loss (2018)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  • Andreas Hess
    • 1
  • Raphael Meier
    • 1
  • Johannes Kaesmacher
    • 1
    • 2
  • Simon Jung
    • 2
  • Fabien Scalzo
    • 3
  • David Liebeskind
    • 3
  • Roland Wiest
    • 1
  • Richard McKinley
    • 1
    Email author
  1. 1.Support Centre for Advanced Neuroimaging, University Institute of Diagnostic and Interventional NeuroradiologyInselspital, Bern University HospitalBernSwitzerland
  2. 2.Department of NeurologyInselspital, University of BernBernSwitzerland
  3. 3.Department of NeurologyUniversity of California Los Angeles (UCLA)Los AngelesUSA

Personalised recommendations