Deep Learning Detection of Penumbral Tissue on Arterial Spin Labeling in Stroke

Supplemental Digital Content is available in the text. Background and Purpose— Selection of patients with acute ischemic stroke for endovascular treatment generally relies on dynamic susceptibility contrast magnetic resonance imaging or computed tomography perfusion. Dynamic susceptibility contrast magnetic resonance imaging requires injection of contrast, whereas computed tomography perfusion requires high doses of ionizing radiation. The purpose of this work was to develop and evaluate a deep learning (DL)–based algorithm for assisting the selection of suitable patients with acute ischemic stroke for endovascular treatment based on 3-dimensional pseudo-continuous arterial spin labeling (pCASL). Methods— A total of 167 image sets of 3-dimensional pCASL data from 137 patients with acute ischemic stroke scanned on 1.5T and 3.0T Siemens MR systems were included for neural network training. The concurrently acquired dynamic susceptibility contrast magnetic resonance imaging was used to produce labels of hypoperfused brain regions, analyzed using commercial software. The DL and 6 machine learning (ML) algorithms were trained with 10-fold cross-validation. The eligibility for endovascular treatment was determined retrospectively based on the criteria of perfusion/diffusion mismatch in the DEFUSE 3 trial (Endovascular Therapy Following Imaging Evaluation for Ischemic Stroke). The trained DL algorithm was further applied on twelve 3-dimensional pCASL data sets acquired on 1.5T and 3T General Electric MR systems, without fine-tuning of parameters. Results— The DL algorithm can predict the dynamic susceptibility contrast–defined hypoperfusion region in pCASL with a voxel-wise area under the curve of 0.958, while the 6 ML algorithms ranged from 0.897 to 0.933. For retrospective determination for subject-level endovascular treatment eligibility, the DL algorithm achieved an accuracy of 92%, with a sensitivity of 0.89 and specificity of 0.95. When applied to the GE pCASL data, the DL algorithm achieved a voxel-wise area under the curve of 0.94 and a subject-level accuracy of 92% for endovascular treatment eligibility. Conclusions— pCASL perfusion magnetic resonance imaging in conjunction with the DL algorithm provides a promising approach for assisting decision-making for endovascular treatment in patients with acute ischemic stroke.

[1]  M. Bouslama,et al.  Computed Tomographic Perfusion Selection and Clinical Outcomes After Endovascular Therapy in Large Vessel Occlusion Stroke , 2017, Stroke.

[2]  S. Choi,et al.  Improving Arterial Spin Labeling by Using Deep Learning. , 2017, Radiology.

[3]  Whitney B. Pope,et al.  The Value of Arterial Spin-Labeled Perfusion Imaging in Acute Ischemic Stroke: Comparison With Dynamic Susceptibility Contrast-Enhanced MRI , 2012, Stroke.

[4]  Leif Østergaard,et al.  How Reliable Is Perfusion MR in Acute Stroke?: Validation and Determination of the Penumbra Threshold Against Quantitative PET , 2008, Stroke.

[5]  R. Gonzalez,et al.  In patients with suspected acute stroke, CT perfusion-based cerebral blood flow maps cannot substitute for DWI in measuring the ischemic core , 2017, PloS one.

[6]  Hester F. Lingsma,et al.  Predicting Outcome of Endovascular Treatment for Acute Ischemic Stroke: Potential Value of Machine Learning Algorithms , 2018, Front. Neurol..

[7]  Nancy J Fischbein,et al.  Comparison of Arterial Spin Labeling and Bolus Perfusion-Weighted Imaging for Detecting Mismatch in Acute Stroke , 2012, Stroke.

[8]  Seyed-Ahmad Ahmadi,et al.  V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentation , 2016, 2016 Fourth International Conference on 3D Vision (3DV).

[9]  H. Asadi,et al.  Machine Learning for Outcome Prediction of Acute Ischemic Stroke Post Intra-Arterial Therapy , 2014, PloS one.

[10]  R. Bammer,et al.  Real‐time diffusion‐perfusion mismatch analysis in acute stroke , 2010, Journal of magnetic resonance imaging : JMRI.

[11]  Sébastien Ourselin,et al.  On the Compactness, Efficiency, and Representation of 3D Convolutional Networks: Brain Parcellation as a Pretext Task , 2017, IPMI.

[12]  Parashkev Nachev,et al.  Computer Methods and Programs in Biomedicine NiftyNet: a deep-learning platform for medical imaging , 2022 .

[13]  Fabien Scalzo,et al.  Postischemic Hyperperfusion on Arterial Spin Labeled Perfusion MRI is Linked to Hemorrhagic Transformation in Stroke , 2015, Journal of cerebral blood flow and metabolism : official journal of the International Society of Cerebral Blood Flow and Metabolism.

[14]  Greg Zaharchuk,et al.  Arterial Spin-Labeling MRI Can Identify the Presence and Intensity of Collateral Perfusion in Patients With Moyamoya Disease , 2011, Stroke.

[15]  Heung-Il Suk,et al.  Deep Learning in Medical Image Analysis. , 2017, Annual review of biomedical engineering.

[16]  Fabien Scalzo,et al.  A Machine Learning Approach to Perfusion Imaging With Dynamic Susceptibility Contrast MR , 2018, Front. Neurol..

[17]  Stephen M. Smith,et al.  Segmentation of brain MR images through a hidden Markov random field model and the expectation-maximization algorithm , 2001, IEEE Transactions on Medical Imaging.

[18]  R. Bammer,et al.  Apparent Diffusion Coefficient Threshold for Delineation of Ischemic Core , 2015, International journal of stroke : official journal of the International Stroke Society.

[19]  Keith Muir,et al.  Effects of alteplase beyond 3 h after stroke in the Echoplanar Imaging Thrombolytic Evaluation Trial (EPITHET): a placebo-controlled randomised trial , 2008, The Lancet Neurology.

[20]  Stephen M Smith,et al.  Fast robust automated brain extraction , 2002, Human brain mapping.

[21]  Fabien Scalzo,et al.  Predictive analytics and machine learning in stroke and neurovascular medicine , 2019, Neurological research.

[22]  M. Krause,et al.  Endovascular therapy for ischemic stroke with perfusion-imaging selection. , 2015, The New England journal of medicine.

[23]  D. Zafeiriou,et al.  Stroke and Hypertension in Children and Adolescents , 2017, Journal of child neurology.

[24]  Geoffrey E. Hinton,et al.  Deep Learning , 2015, Nature.

[25]  C. Langlotz,et al.  Deep Learning in Neuroradiology , 2018, American Journal of Neuroradiology.

[26]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[27]  Whitney B. Pope,et al.  Multi-delay multi-parametric arterial spin-labeled perfusion MRI in acute ischemic stroke — Comparison with dynamic susceptibility contrast enhanced perfusion imaging☆ , 2013, NeuroImage: Clinical.

[28]  Samantha J. Ma,et al.  ASPECTS-based reperfusion status on arterial spin labeling is associated with clinical outcome in acute ischemic stroke patients , 2017, Journal of cerebral blood flow and metabolism : official journal of the International Society of Cerebral Blood Flow and Metabolism.

[29]  Eric E. Smith,et al.  Randomized assessment of rapid endovascular treatment of ischemic stroke. , 2015, The New England journal of medicine.

[30]  Lee H. Schwamm,et al.  In Acute Stroke, Can CT Perfusion-Derived Cerebral Blood Volume Maps Substitute for Diffusion-Weighted Imaging in Identifying the Ischemic Core? , 2015, PloS one.

[31]  I. Jovin,et al.  Adverse Reactions to Iodinated Contrast Media , 2013, International Journal of Angiology.

[32]  Manish Gupta,et al.  A review of stroke and pregnancy: incidence, management and prevention. , 2014, European journal of obstetrics, gynecology, and reproductive biology.

[33]  B. Campbell,et al.  Imaging selection for acute stroke intervention , 2018, International journal of stroke : official journal of the International Stroke Society.

[34]  R. Gonzalez,et al.  Limited Reliability of Computed Tomographic Perfusion Acute Infarct Volume Measurements Compared With Diffusion-Weighted Imaging in Anterior Circulation Stroke , 2015, Stroke.

[35]  R. Bammer,et al.  Optimal Tmax Threshold for Predicting Penumbral Tissue in Acute Stroke , 2009, Stroke.

[36]  H. Diener,et al.  Stent-retriever thrombectomy after intravenous t-PA vs. t-PA alone in stroke. , 2015, The New England journal of medicine.

[37]  A. Demchuk,et al.  Thrombectomy for Stroke at 6 to 16 Hours with Selection by Perfusion Imaging , 2018, The New England journal of medicine.

[38]  Stephen V. Stehman,et al.  Selecting and interpreting measures of thematic classification accuracy , 1997 .