Tissue Fate Prediction in Acute Ischemic Stroke Using Cuboid Models

  • Fabien Scalzo
  • Qing Hao
  • Jeffrey R. Alger
  • Xiao Hu
  • David S. Liebeskind
Part of the Lecture Notes in Computer Science book series (LNCS, volume 6454)


Early and accurate prediction of tissue outcome is essential to the clinical decision-making process in acute ischemic stroke. We present a quantitative predictive model that combines tissue information available immediately after onset, measured using fluid attenuated inversion recovery (FLAIR), with multi-modal perfusion features (Tmax, MTT, and TTP) to infer the likely outcome of the tissue. A key component is the use of randomly extracted, overlapping, cuboids (i.e. rectangular volumes) whose size is automatically determined during learning. The prediction problem is formalized into a nonlinear spectral regression framework where the inputs are the local, multi-modal cuboids extracted from FLAIR and perfusion images at onset, and where the output is the local FLAIR intensity of the tissue 4 days after intervention. Experiments on 7 stroke patients demonstrate the effectiveness of our approach in predicting tissue fate and its superiority to linear models that are conventionally used.


Acute Ischemic Stroke Cerebral Blood Volume Mean Transit Time Flair Image Perfusion Weight Image 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Heiss, W., Sobesky, J.: Can the penumbra be detected: MR versus PET imaging. J. Cereb Blood Flow Metab 25, 702 (2005)CrossRefGoogle Scholar
  2. 2.
    Shen, Q., Ren, H., Fisher, M., Duong, T.: Statistical prediction of tissue fate in acute ischemic brain injury. J. Cereb Blood Flow Metab 25, 1336–1345 (2005)CrossRefGoogle Scholar
  3. 3.
    Shen, Q., Duong, T.: Quantitative Prediction of Ischemic Stroke Tissue Fate. NMR Biomedicine 21, 839–848 (2008)CrossRefGoogle Scholar
  4. 4.
    Wu, O., Koroshetz, W., Ostergaard, L., Buonanno, F., Copen, W., Gonzalez, R., Rordorf, G., Rosen, B., Schwamm, L., Weisskoff, R., Sorensen, A.: Predicting tissue outcome in acute human cerebral ischemia using combined diffusion- and perfusion-weighted MR imaging. Stroke 32, 933–942 (2001)CrossRefGoogle Scholar
  5. 5.
    Wu, O., Christensen, S., Hjort, N., Dijkhuizen, R., Kucinski, T., Fiehler, J., Thomalla, G., Rother, J., Ostergaard, L.: Characterizing physiological heterogeneity of infarction risk in acute human ischaemic stroke using MRI. Brain 129, 2384–2393 (2006)CrossRefGoogle Scholar
  6. 6.
    Rose, S., Chalk, J., Griffin, M., Janke, A., Chen, F., McLachan, G., Peel, D., Zelaya, F., Markus, H., Jones, D., Simmons, A., OSullivan, M., Jarosz, J., Strugnell, W., Doddrell, D., Semple, J.: MRI based diffusion and perfusion predictive model to estimate stroke evolution. Magnetic Resonance Imaging 19, 1043–1053 (2001)CrossRefGoogle Scholar
  7. 7.
    Nguyen, V., Pien, H., Menenzes, N., Lopez, C., Melinosky, C., Wu, O., Sorensen, A., Cooperman, G., Ay, H., Koroshetz, W., Liu, Y., Nuutinen, J., Aronen, H., Karonen, J.: Stroke Tissue Outcome Prediction Using A Spatially-Correlated Model. In: PPIC (2008)Google Scholar
  8. 8.
    Maree, R., Geurts, P., Piater, J., Wehenkel, L.: Random subwindows for robust image classification. In: CVPR, vol. 1, pp. 34–40 (2005)Google Scholar
  9. 9.
    Cai, D., He, X., Han, J.: Spectral Regression for Efficient Regularized Subspace Learning. In: ICCV (2007)Google Scholar
  10. 10.
    Liebeskind, D., Kidwell, C.: Advanced MR Imaging of Acute Stroke: The University of California at Los Angeles Endovascular Therapy Experience. Neuroimag. Clin. N. Am. 15, 455–466 (2005)CrossRefGoogle Scholar
  11. 11.
    Smith., S.: Fast robust automated brain extraction. Human Brain Mapping 17, 143–155 (2002)CrossRefGoogle Scholar
  12. 12.
    Jonsdottir, K., Ostergaard, L., Mouridsen, K.: Predicting Tissue Outcome From Acute Stroke Magnetic Resonance Imaging: Improving Model Performance by Optimal Sampling of Training Data. Stroke 40, 3006–3011 (2009)CrossRefGoogle Scholar
  13. 13.
    Chatterjee, S., Hadi, A.S.: Influential observations, high leverage points and outliers in linear regression. Statistical Science 1, 379–393 (1986)MathSciNetCrossRefzbMATHGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2010

Authors and Affiliations

  • Fabien Scalzo
    • 1
    • 2
  • Qing Hao
    • 1
  • Jeffrey R. Alger
    • 1
  • Xiao Hu
    • 2
  • David S. Liebeskind
    • 1
  1. 1.Dept. of NeurologyUniversity of CaliforniaLos AngelesUSA
  2. 2.Dept. of Neurosurgery, NSDLUniversity of CaliforniaLos AngelesUSA

Personalised recommendations