Image Based Automated ASPECT Score for Acute Ischemic Stroke Patients

The Alberta Stroke Program Early Computed Tomography Score (ASPECTS) is a tool to assess early ischemic changes in acute stroke patients and found to be superior when applied to contrast-based image modalities. We hypothesized that automated ASPECTS scores have no differences with the manual scoring. We generated time-invariant CTA (tiCTA) from CT Perfusion dataset and measured the ASPECTS score automatically and manually. Statistical analysis was performed to see the differences. The association of both measurements with patient outcome was measured using NIH stroke scale at admission, final infarct size, and 3-month modified Rank Scale (mRS) determined using the Spearman correlation coefficient. As a result, the difference between automated and manual ASPECT scores was statistically not significant (p=0.18). Both automated ASPECTS scores were identical in 40% of the patients for the total score. While all ASPECTS scores have limited association with outcome, our study illustrates the usability of automated ASPECTS applied on tiCTA, allowing simplification of CT workflow for acute ischemic stroke patients and promoting faster analysis.

[1]  Geert J. Streekstra,et al.  3D movement correction of CT brain perfusion image data of patients with acute ischemic stroke , 2014, Neuroradiology.

[2]  Fahmi Fahmi,et al.  Sequential — Storage of differences approach in medical image data compression for brain image dataset , 2016, 2016 International Seminar on Application for Technology of Information and Communication (ISemantic).

[3]  Max A. Viergever,et al.  elastix: A Toolbox for Intensity-Based Medical Image Registration , 2010, IEEE Transactions on Medical Imaging.

[4]  A. Demchuk,et al.  Use of the Alberta Stroke Program Early CT Score (ASPECTS) for assessing CT scans in patients with acute stroke. , 2001, AJNR. American journal of neuroradiology.

[5]  A. Vagal,et al.  Role of Imaging in Acute Ischemic Stroke. , 2018, Seminars in ultrasound, CT, and MR.

[6]  A. Demchuk,et al.  ASPECTS on CTA Source Images Versus Unenhanced CT: Added Value in Predicting Final Infarct Extent and Clinical Outcome , 2004, Stroke.

[7]  Eric E. Smith,et al.  CT Angiographic Source Images Predict Outcome and Final Infarct Volume Better Than Noncontrast CT in Proximal Vascular Occlusions , 2011, Stroke.

[8]  Hester F. Lingsma,et al.  MR CLEAN, a multicenter randomized clinical trial of endovascular treatment for acute ischemic stroke in the Netherlands: study protocol for a randomized controlled trial , 2014, Trials.

[9]  L. Beenen,et al.  Head movement during CT brain perfusion acquisition of patients with suspected acute ischemic stroke. , 2013, European journal of radiology.

[10]  Fahmi Fahmi,et al.  Automatic detection of CT perfusion datasets unsuitable for analysis due to head movement of acute ischemic stroke patients. , 2014, Journal of healthcare engineering.

[11]  Scott E Kasner,et al.  Utility of the NIH Stroke Scale as a Predictor of Hospital Disposition , 2003, Stroke.

[12]  Fahmi Fahmi,et al.  Smart cloud system with image processing server in diagnosing brain diseases dedicated for hospitals with limited resources. , 2017, Technology and health care : official journal of the European Society for Engineering and Medicine.

[13]  D. Gladstone,et al.  Alberta Stroke Program Early CT Scoring of CT Perfusion in Early Stroke Visualization and Assessment , 2007, American Journal of Neuroradiology.

[14]  F. Fahmi,et al.  Image based water gauge reading developed with ANN Kohonen , 2014, 2014 International Conference on Electrical Engineering and Computer Science (ICEECS).

[15]  Geert J. Streekstra,et al.  The effect of head movement on CT perfusion summary maps: simulations with CT hybrid phantom data , 2013, Medical & Biological Engineering & Computing.