Advertisement

Applications of artificial intelligence for DWI and PWI data processing in acute ischemic stroke: Current practices and future directions

      Highlights

      • In this work, we draw an overview of several applications of Artificial Intelligence (AI) for the automation of diffusion-perfusion mismatch processing and their potential contributions in clinical practice.
      • We compare the current approaches among each others with respect to some key requirements.
      • We present future directions of research in the field of applying IA technics ti PWI-DWI data processing

      Abstract

      Multimodal Magnetic Resonance Imaging (MRI) techniques of Perfusion-Weighted Imaging (PWI) and Diffusion-Weighted Imaging (DWI) data are integral parts of the diagnostic workup in the acute stroke setting. The visual interpretation of PWI/DWI data is the most likely procedure to triage Acute Ischemic Stroke (AIS) patients who will access reperfusion therapy, especially in those exceeding 6 h of stroke onset. In fact, this process defines two classes of tissue: the ischemic core, which is presumed to be irreversibly damaged, visualized on DWI data and the penumbra which is the reversibly injured brain tissue around the ischemic tissue, visualized on PWI data. AIS patients with a large ischemic penumbra and limited infarction core have a high probability of benefiting from endovascular treatment.
      However, it is a tedious and time-consuming procedure. Consequently, it is subject to high inter- and intra-observer variability. Thus, the assessment of the potential risks and benefits of endovascular treatment is uncertain.
      Fast, accurate and automatic post-processing of PWI and DWI data is important for clinical diagnosis and is necessary to help the decision making for therapy. Therefore, an automated procedure that identifies stroke slices, stroke hemisphere, segments stroke regions in DWI, and measures hypoperfused tissue in PWI enhances considerably the reproducibility and the accuracy of stroke assessment.
      In this work, we draw an overview of several applications of Artificial Intelligence (AI) for the automation processing and their potential contributions in clinical practices. We compare the current approaches among each other's with respect to some key requirements.

      Abbreviations:

      MRI (Magnetic Resonance Imaging), CT (Computed Tomography), DWI (Diffusion Weighted Imaging), DSC (Dynamic Susceptibility Contrast), PWI (Perfusion Weighted Imaging), ADC (Apparent Diffusion Coefficient), Tmax (time-to-maximum), TTP (time to peak), AIF (Arterial Input Function), ROI (region of interest), TE (Echo Time), CBF (Cerebral Blood Flow), MTT (Mean Transit Time), CBV (Cerebral Blood Volume), SVD (Singular Value Decomposition), bSVD (block circulant singular value decomposition), oSVD (oscillation-index SVD), MCA (middle cerebral artery), ICA (internal carotid artery), DI (Dice Index), AI (artificial intelligence), CNN (Convolutional Neural Networks)

      Keywords

      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:

      Subscribe to Clinical Imaging
      Already a print subscriber? Claim online access
      Already an online subscriber? Sign in
      Institutional Access: Sign in to ScienceDirect

      References

        • Culebras A.
        • Sacco R.L.
        • Kasner S.E.
        • Broderick J.P.
        • Caplan L.R.
        • Connors J.J.
        • et al.
        An updated definition of stroke for the 21st century.
        Stroke. 2013; 44: 2064-2089
        • French B.R.
        • Boddepalli R.S.
        • Govindarajan R.
        Acute ischemic stroke: status and future directions.
        Mo Med. 2016; 113: 480-486
        • Saver J.L.
        • Goyal M.
        • Bonafe A.
        • et al.
        Stent-retriever thrombectomy after intravenous t-PA vs. t-PA alone in stroke.
        N Engl J Med. 2015; 372: 2285-2295
        • Gregory W.A.
        • Maarten G.L.
        • et al.
        A multicenter randomized controlled trial of endovascular therapy following imaging evaluation for ischemic stroke (DEFUSE 3).
        Int J Stroke. 2017; 12: 896-905
        • Albers G.W.
        • Marks M.P.
        • Kemp S.
        • et al.
        Thrombectomy for stroke at 6 to 16 hours with selection by perfusion imaging.
        N Engl J Med. 2018; 378: 708-718
        • Nogueira R.G.
        • Jadhav A.P.
        • Haussen D.C.
        • et al.
        Thrombectomy 6 to 24 hours after stroke with a mismatch between deficit and infarct.
        N Engl J Med. 2018; 378: 11-21
        • Sasaki M.
        • Kudo K.
        • Oikawa H.
        CT perfusion for acute stroke: current concepts on technical aspects and clinical applications.
        Int Congr Ser. 2006; 1290: 30-36
        • Hoeffner E.G.
        • Case I.
        • Jain R.
        • Gujar S.K.
        • Shah G.V.
        • Deveikis J.P.
        • Carlos R.C.
        • Thompson B.G.
        • Harrigan M.R.
        • Mukherji S.K.
        Cerebral perfusion CT: techniques and clinical applications.
        Radiology. 2004; 231: 632-644
        • Chalela J.A.
        • Kidwell C.S.
        • Nentwich L.M.
        • Luby M.
        • Butman J.A.
        • Demchuk A.M.
        • et al.
        Magnetic resonance imaging and computed tomography in emergency assessment of patients with suspected acute stroke: a prospective comparison.
        Lancet. 2007; 369: 293-298
        • Albers G.W.
        • Thijs V.N.
        • Wechsler L.
        • Kemp S.
        • et al.
        Magnetic resonance imaging profiles predict clinical response to early reperfusion: the diffusion and perfusion imaging evaluation for understanding stroke evolution (DEFUSE) study.
        Ann Neurol. 2006; 60: 508-517
        • Davis S.M.
        • Donnan G.A.
        • Parsons M.W.
        • et al.
        Effects of alteplase beyond 3 h after stroke in the echoplanar imaging thrombolytic evaluation trial (EPITHET): a placebo-controlled randomised trial.
        Lancet Neurol. 2008; 7: 299-309
        • Olivot J.M.
        • Mlynash M.
        • Thijs V.N.
        • Kemp S.
        • Lansberg M.G.
        • Wechsler L.
        • Schlaug G.
        • Bammer R.
        • Marks M.P.
        • Albers G.W.
        Relationships between infarct growth, clinical outcome, and early recanalization in diffusion and perfusion imaging for understanding stroke evolution (DEFUSE).
        Stroke. 2008; 39: 2491-2496
        • Mitra J.
        • Bourgeat P.
        • Fripp J.
        • Ghose S.
        • Rose S.
        • Salvado O.
        • Connelly A.
        • Campbell B.
        • Palmer S.
        • Sharma G.
        • et al.
        Lesion segmentation from multimodal MRI using random forest following ischemic stroke.
        NeuroImage. 2014; 98: 324-335
        • Guenego A.
        • Mosimann P.J.
        • Pereira V.M.
        • et al.
        Proposed achievable levels of dose and impact of dose-reduction systems for thrombectomy in acute ischemic stroke: an international, multicentric, retrospective study in 1096 patients.
        Eur Radiol. 2019; 29: 3506-3515
        • Lansberg M.G.
        • Lee J.
        • Christensen S.
        • et al.
        RAPID automated patient selection for reperfusion therapy: a pooled analysis of the echoplanar imaging thrombolytic evaluation trial (EPITHET) and the diffusion and perfusion imaging evaluation for understanding stroke evolution (DEFUSE) study.
        Stroke. 2011; 42: 1608-1614
        • Keir S.L.
        • Wardlaw J.M.
        Systematic review of diffusion and perfusion imaging in acute ischemic stroke.
        Stroke. 2000; 31: 2723-2731
        • Schaefer P.W.
        • Grant P.E.
        • Gonzalez R.G.
        Diffusion-weighted MR imaging of the brain.
        Radiology. 2000; 217: 331-345
        • Schlaug G.
        • Benfield A.
        • Baird A.E.
        • Siewert B.
        • Lovblad K.O.
        • Parker R.A.
        • Edelman R.R.
        • Warach S.
        The ischemic penumbra: operationally defined by diffusion and perfusion MRI.
        Neurology. 1999; 53: 1528-1537
        • Neumann-Haefelin T.
        • Wittsack H.J.
        • Wenserski F.
        • et al.
        Diffusion- and perfusion-weightedMRI. The DWI/PWI mismatch region in acute stroke.
        Stroke. 1999; 30: 1591-1597
        • Heiss W.-D.
        The ischemic penumbra: correlates in imaging and implications for treatment of ischemic stroke.
        Cerebrovasc Dis. 2011; 32: 307-320
        • Matus S.
        • Gregory W.A.
        • Roland B.
        Real-time diffusion-perfusion mismatch analysis in acute stroke.
        J Magn Reson Imaging. 2010; 32: 1024-1037
        • Harston G.W.
        • Minks D.
        • Sheerin F.
        • et al.
        Optimizing image registration and infarct definition in stroke research.
        Ann Clin Transl Neurol. 2017; 4: 166-174
        • Ashburner J.S.P.M.
        A history.
        Neuroimage. 2012; 62: 791-800
        • Grosser M.
        • Gellißen S.
        • Borchert P.
        • et al.
        Localized prediction of tissue outcome in acute ischemic stroke patients using diffusion- and perfusion-weighted MRI datasets.
        PLoS ONE. 2020; 15e0241917
        • Sorensen A.G.
        • Copen W.A.
        • Ostergaard L.
        • et al.
        Hyperacute stroke: simultaneous measurement of relative cerebral blood volume, relative cerebral blood flow, and mean tissue transit time.
        Radiology. 1999; 210: 519-527
        • Calamante F.
        • Willats L.
        • Gadian D.G.
        • et al.
        Bolus delay and dispersion in perfusion MRI: implications for tissue predictor models in stroke.
        Magn Reson Med. 2006; 55: 1180-1185
        • Fernando C.
        Arterial input function in perfusion MRI: a comprehensive review.
        Prog Nucl Magn Reson Spectrosc. 2013; 74: 1-32
        • Willats L.
        • Christensen S.
        • Henry K.M.
        • et al.
        Validating a local arterial input function method for improved perfusion quantification in stroke.
        J Cereb Blood Flow Metab. 2011; 31: 2189-2198
        • Olivier Zaro-Weber M.D.
        • Walter Moeller-Hartmann M.D.
        • Wolf-Dieter Heiss M.D.
        • Jan Sobesky M.D.
        Influence of the arterial input function on absolute and relative perfusion-weighted imaging penumbral flow detection a validation with 15O-water positron emission tomography.
        Stroke. 2012; 43: 378-385
        • Murase K.
        • Kikuchi K.
        • Miki H.
        • et al.
        Determination of arterial input function using fuzzy clustering for quantification of cerebral blood flow with dynamic susceptibility contrast-enhanced MR imaging.
        J Magn Reson Imaging. 2001; 13: 797-806
        • Mouridsen K.
        • Christensen S.
        • Gyldensted L.
        • et al.
        Automatic selection of arterial input function using cluster analysis.
        Magn Reson Med. 2006; 55: 524-531
        • Jiandong Y.
        • Jiawen Y.
        • Qiyong G.
        Evaluating the feasibility of an agglomerative hierarchy clustering algorithm for the automatic detection of the arterial input function using DSC-MRI.
        PLoS One. 2014; 9e100308
        • Jiandong Y.
        • Hongzan S.
        • Jiawen Y.
        • et al.
        Automated detection of the arterial input function using normalized cut clustering to determine cerebral perfusion by dynamic susceptibility contrast-magnetic resonance imaging.
        J Magn Reson Imaging. 2015; 41: 1071-1078
        • Jiandong Y.
        • Jiawen Y.
        • Qiyong G.
        Automatic determination of the arterial input function in dynamic susceptibility contrast MRI: comparison of different reproducible clustering algorithms.
        Neuroradiology. 2015; 57: 535-543
        • Calamante F.
        • Morup M.
        • Hansen L.K.
        Defining a local arterial input function for perfusion MRI using independent component analysis.
        Magn Reson Med. 2004; 52: 789-797
        • Willats L.
        • Christensen S.
        • Henry K.M.
        • et al.
        Validating a local arterial input function method for improved perfusion quantification in stroke.
        J Cereb Blood Flow Metab. 2011; 31: 2189-2198
        • Rahimzadeh H.
        • Fathi Kazerooni A.
        • Deevband M.R.
        • et al.
        An efficient framework for accurate arterial input selection in DSC-MRI of glioma brain tumors.
        J Biomed Phys Eng. 2019; 9: 1
        • Fieselmann A.
        • Kowarschik M.
        • Ganguly A.
        • et al.
        Deconvolution-based CT and MR brain perfusion measurement : theoretical model revisited and practical implementation details.
        Int J Biomed Imaging. 2011; 2011467563
        • Wu O.
        • Ostergaard L.
        • Weisskoff R.M.
        • et al.
        Tracer arrival timing-insensitive technique for estimating flow in mr perfusion-weighted imaging using singular value decomposition with a block circulant deconvolution matrix.
        Magn Reson Med. 2003; 50: 164-174
        • Zaro-Weber O.
        • Livne M.
        • Martin S.Z.
        • et al.
        Comparison of the 2 Most popular deconvolution techniques for the detection of penumbral flow in acute stroke.
        Stroke. 2015; 46: 2795-2799
        • Andersen I.K.
        • Szymkowiak A.
        • Rasmussen C.E.
        • et al.
        Perfusion quantification using gaussian process deconvolution.
        Magn Reson Med. 2002; 48: 351-361
        • Calamante F.
        • Gadian D.G.
        • et al.
        Quantification of bolus- tracking MRI: improved characterization of the tissue residue function using tikhonov regularization”.
        Magn Reson Med. 2003; 50: 1237-1247
        • Boutelier T.
        • Kudo K.
        • Pautot F.
        • et al.
        Bayesian hemodynamic parameter estimation by bolus tracking perfusion weighted imaging.
        IEEE Trans Med Imaging. 2012; 31: 1381-1395
        • Olivot J.M.
        • Michael Mlynash
        • Thijs V.N.
        • Kemp S.
        • et al.
        Optimal tmax threshold for predicting penumbral tissue in acute stroke.
        Stroke. 2009; 40: 469-475
        • Ben Alaya I.
        • Drissi C.
        The role of time to maximum parameter in the quantification of the ischemic penumbra for DSC-MRI imaging.
        J Int Res Med Pharm Sci. 2020; 15: 32-41
        • Hyunna L.
        • Kyesam J.
        • Dong-Wha K.
        • et al.
        Fully automated and real-time volumetric measurement of infarct Core and penumbra in diffusion- and perfusion-weighted MRI of patients with hyper-acute stroke.
        J Digit Imaging. 2020; 33: 262-272
        • Wouters A.
        • Christensen S.
        • Straka M.
        A comparison of relative time to peak and Tmax for mismatch-based patient selection.
        Front Neurol. 2017; 8: 539
        • McKinley R.
        • Hung F.
        • Wiest R.
        • Liebeskind D.S.
        • et al.
        A machine learning approach to perfusion imaging with dynamic susceptibility contrast MR.
        Front Neurol. 2018; 9: 717
      1. K Chung Ho F Scalzo KV Sarma et al., A temporal deep learning approach for MR perfusion parameter estimation in stroke 2016; 23rd international conference on pattern recognition (ICPR) Cancún Center, Cancún, México, December 4-8.

        • Hess A.
        • Meier R.
        • Kaesmacher J.
        Synthetic perfusion maps: imaging perfusion deficits in DSC-MRI with deep learning published in [email protected]
        Comput Sci. 2018; abs/1806.03848
        • Meier R.
        • Lux P.
        • Jung S.
        Neural network–derived perfusion maps for the assessment of lesions in patients with acute ischemic stroke.
        Radiology: Artificial Intelligence. 2019; 1e190019
        • Ostergaard L.
        • Weisskoff R.M.
        • Chesler D.A.
        • et al.
        High-resolution measurement of cerebral blood flow using intravascular tracer bolus passages. part I: mathematical approach and statistical analysis.
        Magn Reson Med. 1996; 36: 715-725
        • Muir K.W.
        • Buchan A.
        • von Kummer R.
        • Rother J.
        • Baron J.C.
        Imaging of acute stroke.
        Lancet Neurol. 2006; 5: 755-768
        • Hjort N.
        • Christensen S.
        • Solling C.
        • Ashkanian M.
        • Wu O.
        • Rohl L.
        • et al.
        Ischemic injury detected by diffusion imaging 11 minutes after stroke.
        Ann Neurol. 2005; 58: 462-465
        • Schaefer P.W.
        • Copen W.A.
        • Lev M.H.
        • et al.
        Diffusion weighted imaging in acute stroke.
        Neuroimaging Clin N Am. 2005; 15: 503-530
        • Purushotham A.
        • Campbell B.C.
        • Straka M.
        • et al.
        Apparent diffusion coefficient threshold for delineation of ischemic core.
        Int J Stroke. 2015; 10: 348-353
        • Oppenheim C.
        • Grandin C.
        • Samson Y.
        • et al.
        Is there an apparent diffusion coefficient threshold in predicting tissue viability in hyperacute stroke?.
        Stroke. 2001; 32: 2486-2491
        • Sener R.
        Diffusion MRI: apparent diffusion coefficient (ADC) values in the normal brain and a classification of brain disorders based on ADC values.
        Comput Med Imaging Graph. 2001; 25: 299-326
        • Straka M.
        • Albers G.W.
        • Bammer R.
        Real-time diffusion-perfusion mismatch analysis in acute stroke.
        J Magn Reson Imaging. 2010; 32: 1024-1037
        • Boldsen J.K.
        • Engedal T.S.
        • Pedraza S.
        • et al.
        Better diffusion segmentation in acute ischemic stroke through automatic tree learning anomaly segmentation.
        Front Neuroinform. 2018; 12: 21
        • Nag M.K.
        • Koley S.
        • China D.
        • Sadhu A.K.
        • Balaji R.
        • Ghosh S.
        • et al.
        Computer-assisted delineation of cerebral infarct from diffusion-weighted MRI using gaussian mixture model.
        Int J Comput Assist Radiol Surg. 2017; 12: 539-552
        • Charoensuk W.
        • Covavisaruch N.
        • Lerdlum S.
        • Likitjaroen Y.
        Acute stroke brain infarct segmentation in DWI images.
        Int J Pharm Med Biol Sci. 2015; 4: 115-122
        • Peng Y.
        • Zhang X.
        • Hu Q.
        Segmentation of hyper-acute ischemic infarcts from diffusion weighted imaging based on support vector machine.
        J Comput Commun. 2015; 3: 152-157
        • Maier O.
        • Wilms M.
        • Janina von der Gablentz
        Extra Tree forests for sub-acute ischemic stroke lesion segmentation in MR sequences.
        J Neurosci Methods. 2015; 240: 89-100
        • Meng L.
        • Lin A.
        • Huiguang H.
        Segmentation of infarct in acute ischemic stroke from MR apparent diffusion coefficient and trace-weighted images.
        in: MIPPR: medical imaging, parallel processing of images, and optimization techniques. 2009
        • Prakash K.N.B.
        • Gupta V.
        • Bilello M.
        • et al.
        Identification, segmentation, and image property study of acute infarcts in diffusion-weighted images by using a probabilistic neural network and adaptive gaussian mixture model.
        Acad Radiol. 2006; 13: 1474-1484
        • Liangliang L.
        • Shaowu C.
        • Fuhao Z.
        • et al.
        Deep convolutional neural network for automatically segmenting acute ischemic stroke lesion in multi-modality MRI.
        Neural Comput Applic. 2020; 32: 6545-6558
        • Yoon-Chul K.
        • Ji-Eun L.
        • Inwu Y.
        Evaluation of diffusion lesion volume measurements in acute ischemic stroke using encoder-decoder convolutional network.
        Stroke. 2019; 50: 1444-1451
        • Winzeck X.S.
        • Mocking X.S.J.T.
        • Bezerra X.R.
        • et al.
        Ensemble of convolutional neural networks improves automated segmentation of acute ischemic lesions using multiparametric diffusion-weighted MRI.
        AJNR Am J Neuroradiol. 2019; 40: 938-945
        • Ilsang W.
        • Areum L.
        • Seung Chai J.
        • et al.
        Fully automatic segmentation of acute ischemic lesions on diffusion-weighted imaging using convolutional neural networks: comparison with conventional algorithms.
        Korean J Radiol. 2019; 20: 1275-1284
        • Chen L.
        • Bentley P.
        • Rueckert D.
        Fully automatic acute ischemic lesion segmentation in DWI using convolutional neural networks.
        NeuroImage. 2017; 15: 633-643
        • Albers G.W.
        • Thijs V.N.
        • Wechsler L.
        • et al.
        Magnetic resonance imaging profiles predict clinical response to early reperfusion: the diffusion and perfusion imaging evaluation for understanding stroke evolution (defuse) study.
        Ann Neurol. 2006; 60: 508-517
        • Fiebach J.B.
        • Hopt A.
        • Vucic T.
        • Brunecker P.
        • Nolte C.H.
        • Doege C.
        • Villringer K.
        • Jungehulsing G.J.
        • Kunze C.
        • Wegener S.
        • Villringer A.
        Inverse mismatch and lesion growth in small subcortical ischaemic stroke.
        Eur Radiol. 2010; 20: 2983-2989
        • Kakuda W.
        • Lansberg M.G.
        • Thijs V.N.
        • Kemp S.M.
        • Bammer R.
        • Wechsler L.R.
        • Moseley M.E.
        • Marks M.P.
        • Albers G.W.
        Optimal definition for PWI/DWI mismatch in acute ischemic stroke patients.
        J Cereb Blood Flow Metab. 2008; 28: 887-891
        • Soares B.P.
        • Dankbaar J.W.
        • Bredno J.
        • et al.
        Automated versus manual post-processing of perfusion-CT data in patients with acute cerebral ischemia: influence on interobserver variability.
        Neuroradiology. 2009; 51: 445-451
        • Kima J.
        • Leirab E.C.
        • Callisona R.C.
        Toward fully automated processing of dynamic susceptibility contrast perfusion MRI for acute ischemic cerebral stroke.
        Comput Methods Prog Biomed. 2010; 98: 204-213
        • Bjørnerud A.
        • Emblem K.E.
        A fully automated method for quantitative cerebral hemodynamic analysis using DSC–MRI.
        J Cereb Blood Flow Metab. 2010; 30: 1066-1078
        • Schaafs L.A.
        • Porter D.
        • Audebert Heinrich J.
        • et al.
        Optimising MR perfusion imaging: comparison of different software-based approaches in acute ischaemic stroke.
        Eur Radiol. 2016; 26: 4204-4212
        • Lansberg M.G.
        • Straka M.
        • Kemp S.
        • et al.
        MRI profile and response to endovascular reperfusion after stroke (defuse 2): a prospective cohort study.
        Lancet Neurol. 2012; 11: 860-867
        • Lorenz C.
        • Benner T.
        • Lopez C.J.
        • et al.
        Effect of using local arterial input functions on cerebral blood flow estimation.
        J Magn Reson Imaging. 2006; 24: 57-65
        • Peruzzo D.
        • Bertoldo A.
        • Zanderigo F.
        • et al.
        Automatic selection of arterial input function on dynamic contrast-enhanced MR images.
        Comput Methods Programs Biomed. 2011; 104: e148-e157
        • Deutschmann H.
        • Hinteregger N.
        • Wießpeiner U.
        • et al.
        Automated MRI perfusion-diffusion mismatch estimation may be significantly different in individual patients when using different software packages.
        Eur Radiol. 2021; 31: 658-665
        • Zou K.H.
        • Warfield S.K.
        • Bharatha A.
        • et al.
        Statistical validation of image segmentation quality based on a spatial overlap index.
        Acad Radiol. 2004; 11: 178-189