Evaluation of an Automatic ASPECT Scoring System for Acute Stroke in Non-Contrast CT

  • Matt DaykinEmail author
  • Erin Beveridge
  • Vismantas Dilys
  • Aneta Lisowska
  • Keith Muir
  • Mathini Sellathurai
  • Ian Poole
Conference paper
Part of the Communications in Computer and Information Science book series (CCIS, volume 723)


Determining the severity of ischemic stroke in non-contrast CT is a difficult problem due to a low signal to noise ratio. This leads to variable interpretation of ischemic stroke severity. We investigate the level of agreement between four methods including the use of an automated system with the aim of identifying early ischemic changes within the brain. For the evaluation we divide the middle cerebral artery territory of each hemisphere into ten regions defined according to the Alberta Stroke Programme Early CT Score (ASPECTS). The automatic system uses a specialised Convolutional Neural Network (CNN) based regressor to produce voxel-level confidence masks of which voxels are suspected as showing early ischemic change and from this we compute the score. Additionally, we obtain the score from three other methods that involved trained human graders. We compare the level of agreement between these methods at both a patient level and a territory level through Simultaneous Truth and Performance Level Estimation (STAPLE) and Cohen’s kappa coefficient. We analyse possible causes of disagreement between the methods and statistically validate the performance of the CNN model against the performance of clinical staff. We find that the CNN produces scores that correlate the greatest with its training data at the patient level, but the training data could be improved to strengthen the correlation with the professional standard.


Non-contrast CT (NCCT) Alberta Stroke Program Early CT Score (ASPECTS) Simultaneous Truth And Performance Level Estimation (STAPLE) Early Ischemic Changes Middle Cerebral Artery Territory 
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.


  1. 1.
    Barber, P.A., Demchuk, A.M., Zhang, J., Buchan, A.M., ASPECTS Study Group, et al.: Validity and reliability of a quantitative computed tomography score in predicting outcome of hyperacute stroke before thrombolytic therapy. Lancet 355(9216), 1670–1674 (2000)Google Scholar
  2. 2.
    Cohen, J.: A coefficient of agreement for nominal scales. Educ. Psychol. Meas. 20(1), 37–46 (1960)CrossRefGoogle Scholar
  3. 3.
    Dabbah, M.A., Murphy, S., Pello, H., Courbon, R., Beveridge, E., Wiseman, S., Wyeth, D., Poole, I.: Detection and location of 127 anatomical landmarks in diverse CT datasets. In: SPIE Medical Imaging, p. 903415. International Society for Optics and Photonics (2014)Google Scholar
  4. 4.
    Fedorov, A., Beichel, R., Kalpathy-Cramer, J., Finet, J., Fillion-Robin, J.C., Pujol, S., Bauer, C., Jennings, D., Fennessy, F., Sonka, M., et al.: 3D slicer as an image computing platform for the quantitative imaging network. Magn. Reson. Imaging 30(9), 1323–1341 (2012)CrossRefGoogle Scholar
  5. 5.
    Grotta, J.C., Chiu, D., Lu, M., Patel, S., Levine, S.R., Tilley, B.C., Brott, T.G., Haley, E.C., Lyden, P.D., Kothari, R., et al.: Agreement and variability in the interpretation of early CT changes in stroke patients qualifying for intravenous rtPA therapy. Stroke 30(8), 1528–1533 (1999)CrossRefGoogle Scholar
  6. 6.
    Grunwald, I., Reith, W.: Non-traumatic neurological emergencies: imaging of cerebral ischemia. Eur. Radiol. 12(7), 1632–1647 (2002)CrossRefGoogle Scholar
  7. 7.
    Hill, M.D., Buchan, A.M., The Canadian Alteplase for Stroke Effectiveness Study (CASES) Investigators: Thrombolysis for acute ischemic stroke: results of the Canadian Alteplase for stroke effectiveness study. Can. Med. Assoc. J. 172(10), 1307–1312 (2005)CrossRefGoogle Scholar
  8. 8.
    Huang, X., Cheripelli, B.K., Lloyd, S.M., Kalladka, D., Moreton, F.C., Siddiqui, A., Ford, I., Muir, K.W.: Alteplase versus tenecteplase for thrombolysis after ischaemic stroke (ATTEST): a phase 2, randomised, open-label, blinded endpoint study. Lancet Neurol. 14(4), 368–376 (2015)CrossRefGoogle Scholar
  9. 9.
    Kosior, R.K., Lauzon, M.L., Steffenhagen, N., Kosior, J.C., Demchuk, A., Frayne, R.: Atlas-based topographical scoring for magnetic resonance imaging of acute stroke. Stroke 41, 455–460 (2010)CrossRefGoogle Scholar
  10. 10.
    Kunst, M.M., Schaefer, P.W.: Ischemic stroke. Radiol. Clin. N. Am. 49(1), 1–26 (2011)CrossRefGoogle Scholar
  11. 11.
    Larrue, V., von Kummer, R., Müller, A., Bluhmki, E.: Risk factors for severe hemorrhagic transformation in ischemic stroke patients treated with recombinant tissue plasminogen activator. Stroke 32(2), 438–441 (2001)CrossRefGoogle Scholar
  12. 12.
    Lisowska, A., Beveridge, E., Muir, K., Poole, I.: Thrombus detection in CT brain scans using a convolutional neural network. In: Proceedings of the 10th International Joint Conference on Biomedical Engineering Systems and Technologies (BIOSTEC), BIOIMAGING, vol. 2, pp. 24–33 (2017). ISBN 978-989-758-215-8Google Scholar
  13. 13.
    Lisowska, A., O’Neil, A., Dilys, V., Daykin, M., Beveridge, E., Muir, K., Mclaughlin, S., Poole, I.: Context-aware convolutional neural networks for stroke sign detection in non-contrast CT scans. J. Imaging (2017, in press)Google Scholar
  14. 14.
    MacDougall, N., McVerry, F., Huang, X., Welch, A., Fulton, R., Muir, K.: Post-stroke hyperglycaemia is associated with adverse evolution of acute ischaemic injury. In: Cerebrovascular Diseases, vol. 37, pp. 267–267. Karger, Basel (2014)Google Scholar
  15. 15.
    Pexman, J.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(8), 1534–1542 (2001)Google Scholar
  16. 16.
    Wardlaw, J., Dorman, P., Lewis, S., Sandercock, P.: Can stroke physicians and neuroradiologists identify signs of early cerebral infarction on CT? J. Neurol. Neurosurg. Psychiatry 67(5), 651–653 (1999)CrossRefGoogle Scholar
  17. 17.
    Wardlaw, J.M., Muir, K.W., Macleod, M.J., Weir, C., McVerry, F., Carpenter, T., Shuler, K., Thomas, R., Acheampong, P., Dani, K., Murray, A.: Clinical relevance and practical implications of trials of perfusion and angiographic imaging in patients with acute ischaemic stroke: a multicentre cohort imaging study. J. Neurol. Neurosurg. Psychiatry 84(9), 1001–1007 (2013). CrossRefGoogle Scholar
  18. 18.
    Wardlaw, J.M., Von Kummer, R., Farrall, A.J., Chappell, F.M., Hill, M., Perry, D.: A large web-based observer reliability study of early ischaemic signs on computed tomography. the acute cerebral CT evaluation of stroke study (ACCESS). PLoS ONE 5(12), e15757 (2010)CrossRefGoogle Scholar
  19. 19.
    Warfield, S.K., Zou, K.H., Wells, W.M.: Simultaneous truth and performance level estimation (STAPLE): an algorithm for the validation of image segmentation. IEEE Trans. Med. Imaging 23(7), 903–921 (2004)CrossRefGoogle Scholar

Copyright information

© Springer International Publishing AG 2017

Authors and Affiliations

  • Matt Daykin
    • 1
    • 2
    Email author
  • Erin Beveridge
    • 1
  • Vismantas Dilys
    • 1
  • Aneta Lisowska
    • 1
    • 2
  • Keith Muir
    • 3
  • Mathini Sellathurai
    • 2
  • Ian Poole
    • 1
  1. 1.Toshiba Medical Visualization Systems Europe Ltd.EdinburghUK
  2. 2.School of Engineering and Physical SciencesHeriot-Watt UniversityEdinburghUK
  3. 3.Institute of Neuroscience and PsychologyUniversity of GlasgowGlasgowUK

Personalised recommendations