Towards Automatic Collateral Circulation Score Evaluation in Ischemic Stroke Using Image Decompositions and Support Vector Machines

Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 10555)


Stroke is the second leading cause of disability worldwide. Thrombectomy has been shown to offer fast and efficient reperfusion with high recanalization rates and thus improved patient outcomes. One of the most important indicators to identify patients amenable to thrombectomy is evidence of good collateral circulation. Currently, methods for evaluating collateral circulation are generally limited to visual inspection with potentially high inter- and intra-rater variability. In this work, we present an automatic technique to evaluate collateral circulation. This is achieved via low-rank decomposition of the target subject’s 4D CT angiography, and using principal component analysis (PCA) and support vector machines (SVMs) to automatically generate a collateral circulation score. With the proposed automatic score evaluation technique, we have achieved an overall scoring accuracy of 82.2% to identify patients with poor, intermediate, and good/normal collateral circulation.


CTA Collateral score Stroke Machine learning 


  1. 1.
    Sharma, V.K., Teoh, H.L., Wong, L.Y., Su, J., Ong, B.K., Chan, B.P.: Recanalization therapies in acute ischemic stroke: pharmacological agents, devices, and combinations. Stroke Res. Treat. 2010 (2010)Google Scholar
  2. 2.
    Sung, S.M., Lee, T.H., Cho, H.J., Kang, T.H., Jung, D.S., Park, K.P., Park, M.K., Lee, J.I., Ko, J.K.: Functional outcome after recanalization for acute pure M1 occlusion of the middle cerebral artery as assessed by collateral CTA flow. Clin. Neurol. Neurosur. 131, 72–76 (2015)CrossRefGoogle Scholar
  3. 3.
    Ramaiah, S.S., Mitchell, P., Dowling, R., Yan, B.: Assessment of arterial collateralization and its relevance to intra-arterial therapy for acute ischemic stroke. J. Stroke Cerebrovasc. 23, 399–407 (2014)CrossRefGoogle Scholar
  4. 4.
    Cuccione, E., Padovano, G., Versace, A., Ferrarese, C., Beretta, S.: Cerebral collateral circulation in experimental ischemic stroke. Exp. Transl. Stroke Med. 8, 2 (2016)CrossRefGoogle Scholar
  5. 5.
    Pexman, J.H.W., Barber, P.A., Hill, M.D., Sevick, R.J., Demchuk, A.M., Hudon, M.E., Hu, W.Y., Buchan, A.M.: Use of the alberta stroke program early CT score (ASPECTS) for assessing CT scans in patients with acute stroke. Am. J. Neuroradiol. 22, 1534–1542 (2001)Google Scholar
  6. 6.
    Fonov, V., Evans, A.C., Botteron, K., Almli, C.R., McKinstry, R.C., Collins, D.L., Brain Development Cooperative Group: Unbiased average age-appropriate atlases for pediatric studies. Neuroimage 54, 313–327 (2011)Google Scholar
  7. 7.
    Cui, X., Huang, J., Zhang, S., Metaxas, Dimitris N.: Background subtraction using low rank and group sparsity constraints. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012. LNCS, vol. 7572, pp. 612–625. Springer, Heidelberg (2012). doi: 10.1007/978-3-642-33718-5_44 CrossRefGoogle Scholar
  8. 8.
    Lin, Z., Chen, M., Ma, Y.: The augmented Lagrange multiplier method for exact recovery of corrupted low-rank matrices.
  9. 9.
    Turk, M., Pentland, A.: Eigenfaces for recognition. J. Cogn. Neurosci. 3, 71–86 (1991)CrossRefGoogle Scholar
  10. 10.
    Faruqe, M.O., Hasan, M.A.: Face recognition using PCA and SVM. In: Proceedings of the 3rd International Conference on Anti-Counterfeiting, Security, and Identification in Communication, pp. 97–101 (2009)Google Scholar

Copyright information

© Springer International Publishing AG 2017

Authors and Affiliations

  1. 1.PERFORM CentreConcordia UniversityMontrealCanada
  2. 2.Department of Electrical and Computer EngineeringConcordia UniversityMontrealCanada
  3. 3.Diagnostic and Interventional NeuroradiologyMontreal Neurological HospitalMontrealCanada
  4. 4.McConnell Brain Imaging CentreMontreal Neurological InstituteMontrealCanada
  5. 5.Department of Neurology and NeurosurgeryMontreal Neurological HospitalMontrealCanada
  6. 6.Department of Computer Science and Software EngineeringConcordia UniversityMontrealCanada

Personalised recommendations