Prediction of final infarct volume from native CT perfusion and treatment parameters using deep learning

David Robben*, Anna M. M. Boers, Henk A. Marquering, Lucianne L. C. M. Langezaal, Yvo B. W. E. M. Roos, Robert J. van Oostenbrugge, Wim H. van Zwam, Diederik W. J. Dippel, Charles B. L. M. Majoie, Aad van der Lugt, Robin Lemmens, Paul Suetens

*Corresponding author for this work

Research output: Contribution to journalArticleAcademicpeer-review

53 Downloads (Pure)

Abstract

CT Perfusion (CTP) imaging has gained importance in the diagnosis of acute stroke. Conventional perfusion analysis performs a deconvolution of the measurements and thresholds the perfusion parameters to determine the tissue status. We pursue a data-driven and deconvolution-free approach, where a deep neural network learns to predict the final infarct volume directly from the native CTP images and meta data such as the time parameters and treatment. This would allow clinicians to simulate various treatments and gain insight into predicted tissue status over time. We demonstrate on a multicenter dataset that our approach is able to predict the final infarct and effectively uses the metadata. An ablation study shows that using the native CTP measurements instead of the deconvolved measurements improves the prediction. (C) 2019 Published by Elsevier B.V.

Original languageEnglish
Article number101589
Number of pages9
JournalMedical Image Analysis
Volume59
DOIs
Publication statusPublished - Jan 2020

Keywords

  • Stroke
  • CT Perfusion
  • Final infarct prediction
  • Deep learning
  • STROKE
  • SALVAGE
  • TIME
  • MRI

Cite this