Research Article| Volume 29, ISSUE 5, 104715, May 2020

Computational Image Analysis of Nonenhanced Computed Tomography for Acute Ischaemic Stroke: A Systematic Review



      Noncontrast enhanced computed tomography (NCCT) remains the most common method for brain imaging patients who present acutely with ischaemic stroke. Computational methods may improve NCCT analysis in this context. We systematically reviewed current research.


      We searched 7 medical and computer engineering databases for studies testing computational methods for analysing NCCT in acute ischaemic stroke. Two independent reviewers extracted the following data; computational method, imaging features investigated, test dataset, ground truth comparison, and performance. We critically evaluated studies for risk of bias and applicability using the Quality Assessment of Diagnostic Accuracy Studies tool (QUADAS-2).


      From 11,235 nonduplicated articles, we full-text reviewed 200 and selected 68 for inclusion. We identified three dominant study types testing a large range of computational methods for: (1) identifying acute ischaemic stroke (n = 42); (2) ischaemic lesion segmentation (n = 6); and (3) automated Alberta Stroke Program Early CT Score (n = 20). Most articles presented small test datasets, poorly documented patient populations, and did not specify the acuity of the CT scans used in development. There was limited validation or clinical testing of computational methods. Automated Alberta Stroke Program Early CT Score methods were the only software systems presented in multiple publications. Critical evaluation was often limited by lack of data.


      Computational techniques for analysing NCCT in patients with acute ischaemic stroke have not been adequately clinically validated. Further research with larger and more relevant datasets, in addition to better collaboration between clinicians and researchers, is needed to aid more widespread clinical adoption and implementation.

      Key Words

      To read this article in full you will need to make a payment

      Purchase one-time access:

      Academic & Personal: 24 hour online accessCorporate R&D Professionals: 24 hour online access
      One-time access price info
      • For academic or personal research use, select 'Academic and Personal'
      • For corporate R&D use, select 'Corporate R&D Professionals'


      Subscribe to Journal of Stroke and Cerebrovascular Diseases
      Already a print subscriber? Claim online access
      Already an online subscriber? Sign in
      Institutional Access: Sign in to ScienceDirect


        • Wintermark M.
        • Luby M.
        • Bornstein N.M.
        • et al.
        International survey of acute stroke imaging used to make revascularization treatment decisions.
        Int J Stroke. 2015; 5: 759-762
        • Nogueira R.G.
        • Jadhav A.P.
        • Haussen D.C.
        • et al.
        Thrombectomy 6-24 hours after stroke with a mismatch between deficit and infarct.
        N Engl J Med. 2018; 378: 11-21
        • Ma H.
        • Campbell B.C.V.
        • Parsons M.W.
        • et al.
        Thrombolysis guided by perfusion imaging up to 9 hours after onset of stroke.
        N Engl J Med. 2019; 380: 1795-1803
        • Thomalla G.
        • Simonsen C.Z.
        • Boutitie F.
        • et al.
        MRi-guided thrombolysis for stroke with unknown time of onset.
        N Engl J Med. 2018; 379: 611-622
        • Emberson J.
        • Lees K.R.
        • Lyden P.
        • et al.
        Effect of treatment delay, age and stroke severity on the effects of intravenous thrombolysis with alteplase for acute ischaemic stroke: a meta-analysis of individual patient data from randomised trials.
        Lancet. 2014; 384: 1929-1935
        • Saver J.L.
        • Goyal M.
        • van der Lugt A.
        • et al.
        Time to treatment with endovascular thrombectomy and outcomes from ishemic stroke: a meta-analysis.
        JAMA. 2016; 316: 1279-1288
        • Wardlaw J.M.
        • von Kummer R.
        • Farrall A.J.
        • et al.
        A large web-based observer reliability study of early ischaemic signs on computer tomography. The acute cerebral CT evaluation of stroke study (ACCESS).
        PLoS One. 2010; 5: e15757
        • Mair G.
        • Boyd E.V.
        • Chappell F.M.
        • et al.
        Sensitivity and specificity of the hyperdense artery sign for arterial obstruction in acute ischaemic stroke.
        Stroke. 2015; 46: 102-107
        • Feng R.
        • Badgeley M.
        • Mocco J.
        • et al.
        Deep learning guided stroke management: A review of clinical applications.
        J NeuroInterv Surg. 2018; 10: 358-361
        • Babu M.S.
        • Vijayalakshmi V.
        A review on acute/sub-acute ischemic stroke lesion segmentation and registration challenges.
        Multimed Tools Appl. 2019; 78: 2481-2506
        • Rekik I.
        • Allassonniere S.
        • Carpenter T.K.
        • et al.
        Medical image analysis methods in MR/CT-imaged acute-subacute ischemic stroke lesion: segmentation, prediction and insights into dynamic evolution simulation models. A critical appraisal.
        Neuroimage. 2012; 1: 124-178
        • Karthik R.
        • Menaka R.
        Computer-aided detection and characterization of stroke lesion - a short review on the current state-of-the art methods.
        Imaging Sci J. 2018; 66: 1-22
        • Kamal H.
        • Lopez V.
        • Sheth S.A.
        Machine learning in acute ischemic stroke neuroimaging.
        Front Neurol. 2018; 9: 945
        • Lee E.J.
        • Kim Y.H.
        • Kim N.
        • et al.
        Deep into the brain: artificial intelligence in stroke imaging.
        J Stroke. 2017; 19: 277-285
        • Barber P.A.
        • Demchuk A.M.
        • Zhang J.
        • et al.
        Validity and reliability of a quantitative computed tomography score in predicting outcome of hyperacute stroke before thrombolytic therapy. ASPECTS Study Group. Alberta stroke programme early CT score.
        Lancet. 2000; 355: 1670-1674
        • Takahashi N.
        • Lee Y.
        • Tsai D.Y.
        • et al.
        An automated detection method for the MCA dot sign of acute stroke in unenhanced CT.
        Radiol Phys Technol. 2014; 7: 79-88
        • Kettenberger P.
        • Jansen O.
        • Riedel C.
        Automatic clot detection in NECT images of acute ischemic stroke patients using a convolutional neural network.
        Clin Neuroradiol. 2018; 28: S94
        • Takahashi N.
        • Lee Y.
        • Tsai D.Y.
        • et al.
        Computer-aided detection scheme for identification of hypoattenuation of acute stroke in unenhanced CT.
        Radiol Phys Technol. 2012; 5: 98-104
        • Mokil Y.
        • Pfaff J.
        • Pinto dos Santos D.
        • et al.
        Computer-aided imaging analysis in acute ischemic stroke – background and clinical applications.
        Neurol Res Pract. 2019; : 23
        • Austein F.
        • Riedel C.
        • Kerby T.
        • et al.
        Comparison of perfusion CT software to predict the final infarct volume after thrombectomy.
        Stroke. 2016; : 2311-2317
        • Ali A.
        • Imad Abdulsalam S.
        • Nema I.
        Detection and segmentation of ischemic stroke using textural analysis on brain CT images.
        Int J Sci Eng Res. 2015; : 369-400
        • Beecy A.N.
        • Chang Q.
        • Anchouche K.
        • et al.
        A novel deep learning approach for automated diagnosis of acute ischemic infarction on computed tomography.
        JACC. 2018; 11: 1723-1725
        • Chawla M.
        • Sharma S.
        • Sivaswamy J.
        • et al.
        A method for automatic detection and classification of stroke from brain CT images.
        in: 2009 Annual international conference of the IEEE engineering in medicine and biology society. 2009
      1. Chin C, Lin B, Wu G, et al., editors. An automated early ischemic stroke detection system using CNN deep learning algorithm. 2017 IEEE 8th International conference on awareness science and technology (iCAST). 2017.

        • Davis A.
        • Gordillo N.
        • Montseny E.
        • et al.
        Automated detection of parenchymal changes of ischemic stroke in non-contrast computer tomography: a fuzzy approach.
        Biomed Signal Process Control. 2018; 45: 117-127
        • de Haan B.
        • Clas P.
        • Juenger H.
        • et al.
        Fast semi-automated lesion demarcation in stroke.
        NeuroImage Clin. 2015; 9: 69-74
        • Gillebert C.R.
        • Humphreys G.W.
        • Mantini D.
        Automated delineation of stroke lesions using brain CT images.
        Neuroimage. 2014; 4: 540-548
        • Goebel J.
        • Stenzel E.
        • Guberina N.
        • et al.
        Automated ASPECT rating: comparison between the Frontier ASPECT Score software and the Brainomix software.
        Neuroradiology. 2018; 60: 1267-1272
        • Goebel J.
        • Stenzel E.
        • Wanke I.
        • et al.
        Computer aided diagnosis for ASPECT rating: initial experiences with the Frontier ASPECT score software.
        Clin Neuroradiol. 2018; 28: S5
        • Gomolka R.S.
        • Chrzan R.M.
        • Urbanik A.
        • et al.
        A quantitative method using head noncontrast CT scans to detect hyperacute nonvisible ischemic changes in patients with stroke.
        J Neuroimaging. 2016; 26: 581-587
        • Gordillo-Castillo N.
        • Davis A.
        • Felipe G.
        • et al.
        Hyperdense middle cerebral artery segmentation in non contrast computed tomography.
        World Congr Med Phys Biomed Eng. 2018; 1: 227-231
        • Grigaitis D.
        • Bartkute V.
        • Sakalauskas L.
        • et al.
        An optimization of system for automatic recognition of ischemic stroke areas in computed tomography images.
        Informatica. 2007; 18: 603-614
        • Grunwald I.Q.
        • Ragoschke-Schumm A.
        • Kettner M.
        • et al.
        First automated stroke imaging evaluation via electronic Alberta Stroke Program Early CT score in a mobile stroke unit.
        Cerebrovasc Dis. 2016; 42: 332-338
        • Guberina N.
        • Dietrich U.
        • Radbruch A.
        • et al.
        Detection of early infarction signs with machine learning-based diagnosis by means of the Alberta Stroke Program Early CT score (ASPECTS) in the clinical routine.
        Neuroradiology. 2018; 60: 889-901
        • Hajimani E.
        • Ruano M.G.
        • Ruano A.E.
        An intelligent support system for automatic detection of cerebral vascular accidents from brain CT images.
        Comput Methods Programs Biomed. 2017; 146: 109-123
        • Herweh C.
        • Ringleb P.A.
        • Rauch G.
        • et al.
        Performance of e-ASPECTS software in comparison to that of stroke physicians on assessing CT scans of acute ischemic stroke patients.
        Int J Stroke. 2016; 11: 438-445
        • Hoyte L.C.
        • Al Sultan A.S.
        • Finkelstein S.
        • et al.
        Reliability of automated software to assign e-ASPECTS to CT scans for acute ischemic changes.
        in: Neurology conference: 69th American academy of neurology annual meeting, AAN.88. 2017: 16
        • Hudyma E.
        • Terlikowski G.
        Computer-aided detecting of early strokes and its evaluation on the base of CT images.
        in: 2008 International multiconference on computer science and information technology. 2008
        • Jeena R.S.
        • Kumar S.
        Analysis of Stroke using texture features.
        in: 2015 International conference on control communication & computing India (ICCC). 2015
      2. Jung S., Whangbo T. Evaluating a deep-learning system for automatically calculating the stroke ASPECT score. 2018 International conference on information and communication technology convergence (ICTC). 2018.

        • Jurgensen N.
        • Lindner T.
        • Jansen O.
        • et al.
        A closer look behind the ASPECTS assessment-is the agreement based on identical subregions?.
        Clin Neuroradiol. 2018; 28: S6-S7
        • Kanchana R.
        • Menaka R.
        A novel approach for characterisation of ischaemic stroke lesion using histogram bin-based segmentation and gray level co-occurrence matrix features.
        Imaging Sci J. 2017; 65: 124-136
        • Kelavkar S.
        • Grunwald Q.
        • Shah S.
        In how far can the CE-marked e-ASPECTS software (Brainomix, Oxford) assist clinicians?.
        Cerebrovasc Dis. 2017; 43: 66
        • Kuang H.
        • Najm M.
        • Chakraborty D.
        • et al.
        Automated aspects on noncontrast CT scans in patients with acute ischemic stroke using machine learning.
        Am J Neuroradiol. 2019; 40: 33-38
      3. Kumar D.V., Krishniah V.V.J.R. An automated framework for stroke and hemorrhage detection using decision tree classifier. 2016 International conference on communication and electronics systems (ICCES). 2016.

        • Lisowska A.
        • Beveridge E.
        • Muir K.
        • et al.
        Thrombus detection in CT brain scans using a convolutional neural network. 2017; : 24-33
        • Maegerlein C.
        • Fischer J.
        • Mönch S.
        • et al.
        Automated Calculation of the Alberta Stroke Program Early CT Score: Feasibility and Reliability.
        Radiology. 2019; 291: 141-148
        • Maldjian J.A.
        • Chalela J.
        • Kasner S.E.
        • et al.
        Automated CT segmentation and analysis for acute middle cerebral artery stroke.
        Am J Neuroradiol. 2001; 22: 1050-1055
        • Classification of stroke disease using convolutional neural network
        2nd international conference on computing and applied informatics 2017. Journal of physics conference series. 978, Bristol Iop Publishing Ltd, 2018
        • Maya B.S.
        • Asha T.
        Automatic detection of brain strokes in CT images using soft computing techniques.
        in: Hemanth J. Balas V.E. Biologically rationalized computing techniques for image processing applications. Lecture notes in computational vision and biomechanics. 25. Springer International Publishing Ag, Cham2018: 85-109
        • Merkow J.
        • Luftkin R.
        • Nguyen K.
        • et al.
        DeepRadiologyNet: radiologist level pathology detection in CT head images.
        • Nag M.
        • Koley S.
        • Das D.
        • et al.
        Computer assisted identification of acute ischemic infarct using CT number and wavelet features from CT images.
        Int J Comput Assist Radiol Surg. 2017; 12: S155-S1S7
        • Nagashima H.
        • Harakawa T.
        Computer-aided diagnostic (CAD) scheme by use of contralateral subtraction technique. Application to detection of acute cerebral infarctions in brain computed tomography (CT).
        Electron Commun Japan. 2011; 94: 32-41
        • Nagel S.
        • Sinha D.
        • Day D.
        • et al.
        e-ASPECTS software is non-inferior to neuroradiologists in applying the ASPECT score to computed tomography scans of acute ischemic stroke patients.
        Int J Stroke. 2017; 12: 615-622
        • Nagel S.
        • Wang X.
        • Carcel C.
        • et al.
        Clinical utility of electronic Alberta Stroke Program early computed tomography score software in the ENCHANTED trial database.
        Stroke. 2018; 49: 1407-1411
        • Neethu S.
        • Venkataraman D.
        Stroke detection in brain using CT images.
        in: Suresh L.P. Dash S.S. Panigrahi B.K. Artificial intelligence and evolutionary algorithms in engineering systems, Vol 1. Advances in intelligent systems and computing. 324. Springer-Verlag Berlin, Berlin2015: 379-386
        • Nowinski W.L.
        • Gupta V.
        • Qian G.
        • et al.
        Automatic detection, localization, and volume estimation of ischemic infarcts in noncontrast computed tomographic scans: Method and preliminary results.
        Invest Radiol. 2013; 48: 661-670
        • Nurhayati O.D.
        • Windasari I.P.
        Isnanto R.R. Facta M. Widianto E.D. Eridani D. Ieee, New York2015: 113-116
        • Olive-Gadea M.
        • Martins N.
        • Boned S.
        • et al.
        Baseline ASPECTS and e-ASPECTS correlation with infarct volume and functional outcome in patients undergoing mechanical thrombectomy.
        J Neuroimaging. 2019; 29: 198-202
        • Oliveira M.S.
        • Fernandes P.T.
        • Avelar W.M.
        • et al.
        Texture analysis of computed tomography images of acute ischemic stroke patients.
        Braz J Med Biol Res. 2009; 42: 1076-1079
        • Ostrek G.
        • Przelaskowski A.
        Automatic early stroke recognition algorithm in CT Images.
        in: Pietka E. Kawa J. Information technologies in biomedicine, Itib 2012. Lecture notes in bioinformatics. 7339. Springer-Verlag Berlin, Berlin2012: 101-109
        • Peixoto S.A.
        • Reboucas P.P.
        Neurologist-level classification of stroke using a Structural Co-Occurrence Matrix based on the frequency domain.
        Comput Electr Eng. 2018; 71: 398-407
      4. Pereira D.R., Filho P.P.R., Rosa G.H.d., et al. Stroke lesion detection using convolutional neural networks. 2018 International joint conference on neural networks (IJCNN); 2018.

        • Peter R.
        • Korfiatis P.
        • Blezek D.
        • et al.
        A quantitative symmetry-based analysis of hyperacute ischemic stroke lesions in noncontrast computed tomography.
        Med Phys. 2017; 44: 192-199
        • Pfaff J.
        • Herweh C.
        • Schieber S.
        • et al.
        e-ASPECTS correlates with and is predictive of outcome after mechanical thrombectomy.
        AJNR. 2017; 38: 1594-1599
        • Przelaskowski A.
        • Ostrek G.
        • Sklinda K.
        Multiscale extraction of diagnostic content applied for CT brain examinations.
        Biocybern Biomed Eng. 2009; 29: 25-40
        • Przelaskowski A.
        • Ostrek G.
        • Sklinda K.
        • et al.
        Stroke slicer for CT-based automatic detection of acute ischemia.
        in: Kurzynski M. Wozniak M. Computer recognition systems 3. Advances in intelligent and soft computing. 57. Springer-Verlag Berlin, Berlin2009: 447-454
        • Przelaskowski A.
        • Walecki J.
        • Sklinda K.
        • et al.
        Improving diagnostic value of CT examinations in hyperacute ischemic stroke.
        in: Czernicki Z. Baethmann A. Ito U. Katayama Y. Kuroiwa T. Mendelow D. Brain edema Xiv. Acta neurochirurgica supplementum. 106. Springer-Verlag Wien, Vienna2010: 165
        • Racoceanu D.
        • Dalle J.
        • Huang C.
        StrokePrediCT - A Traceable Knowledge-Based System for Hyperacute Middle Cerebral Artery Stroke Early Diagnosis.
        Assistance using Brain Computed Tomography. 2015;
        • Rajini N.H.
        • Bhavani R.
        Computer aided detection of ischemic stroke using segmentation and texture features.
        Measurement. 2013; 46: 1865-1874
        • Reboucas Filho P.P.
        • Sarmento R.M.
        • Holanda G.B.
        • et al.
        New approach to detect and classify stroke in skull CT images via analysis of brain tissue densities.
        Comput Methods Programs Biomed. 2017; 148: 27-43
        • Ribeiro L.
        • Ruano A.E.
        • Ruano M.G.
        • et al.
        Neural networks assisted diagnosis of ischemic CVA's through CT scan.
        in: 2007 IEEE International symposium on intelligent signal processing. 2007
        • Saito H.
        • Katsuragawa S.
        • Hirai T.
        • et al.
        A computerized method for detection of acute cerebral infarction on CT images.
        Nippon Hoshasen Gijutsu Gakkai Zasshi. 2010; 66: 1169-1177
        • Seker F.
        • Pfaff J.
        • Nagel S.
        • et al.
        CT Reconstruction levels affect automated and reader-based ASPECTS ratings in acute ischemic stroke.
        J Neuroimaging. 2019; 29: 62-64
        • Shieh Y.
        • Chang C.H.
        • Shieh M.
        • et al.
        Computer-aided diagnosis of hyperacute stroke with thrombolysis decision support using a contralateral comparative method of CT image analysis.
        J Digit Imaging. 2014; 27: 392-406
        • Srivatsan A.
        • Christensen S.
        • Lansberg M.G.
        A relative noncontrast CT map to detect early ischemic changes in acute stroke.
        J Neuroimaging. 2019; 29: 182-186
        • Stoel B.C.
        • Marquering H.A.
        • Staring M.
        • et al.
        Automated brain computed tomographic densitometry of early ischemic changes in acute stroke.
        J Med Imaging (Bellingham). 2015; : 2
        • Takahashi N.
        • Lee Y.
        • Tsai D.Y.
        • et al.
        Development of an algorithm for the detection of early signs of cerebral ischemia on CT images.
        Nippon Hoshasen Gijutsu Gakkai Zasshi. 2007; 63: 835-842
        • Tang F.H.
        • Ng D.K.S.
        • Chow D.H.K.
        An image feature approach for computer-aided detection of ischemic stroke.
        Comput Biol Med. 2011; 4: 529-536
        • Thomson Q.P.
        • Modi J.
        • Coutts S.B.
        • et al.
        Computational texture analysis: Finding ischemic brain tissue in early ct images of acute ischemic stroke.
        Stroke. 2012; 43: e126
        • Tyan Y.S.
        • Wu M.C.
        • Chin C.L.
        • et al.
        Ischemic stroke detection system with a computer-aided diagnostic ability using an unsupervised feature perception enhancement method.
        Int J Biomed Imaging. 2014;
        • Usinskas A.
        • Gleizniene R.
        Ischemic stroke region recognition based on ray tracing.
        in: 2006 International biennial baltic electronics conference. 2006
        • Vos P.C.
        • Biesbroek J.M.
        • Weaver N.A.
        • et al.
        Automatic detection and segmentation of ischemic lesions in computed tomography images of stroke patients.
        in: Novak C.L. Aylward S. Medical imaging 2013: computer-aided diagnosis. Proceedings of SPIE. 8670. Spie-Int Soc Optical Engineering, Bellingham2013
        • Wolff L.
        • Berkhemer O.
        • Van Es A.
        • et al.
        Validation of automated aspects software for detection of early ischemic changes on non contrast brain computed tomography scans a MR clean sub study.
        Neuroradiology. 2018; 60: S444-S4S5
        • Yahiaoui A.F.Z.
        • Bessaid A.
        Segmentation of ischemic stroke area from CT brain images.
        Ieee, New York2016: 13-17