Characteristics for Machine Learning Detection of Large Vessel Occlusion on Computed Tomography Angiography

Detection of large vessel occlusion (LVO) using machine learning on computed tomography angiography (CTA) may help stroke triage, yet applicability across varied patient and image characteristics has not been examined. The study will examine which characteristics are important when using a convolutional neural network to identify LVO on CTA. A retrospective cohort study (November 2017 through May 2019) at a comprehensive stroke center evaluated 677 stroke-alerted patients with an LVO of the internal carotid artery, M1, or M2 (n=150), and a matching number without LVO was included. An Inception module-based network was trained for binary classification of LVO presence. Results were examined by LVO location, window settings, non-LVO findings, demographics, risk factors, presentation status, and times, interventions, and outcomes. Three hundred patients were included (48% women; median age 65). Mean+/-95% CI for cross-validation test and external validation, respectively, are area under precision-recall curve 0.871+/-0.094 and 0.742+/-0.018 and area under receiver operating characteristic curve 0.920+/-0.051 and 0.852+/-0.004. 145 true positive (TP), 5 false negative (FN), 39 false positive (FP), and 111 true negative (TN) patients were identified. Significant comparisons (P<0.05) were identified: lower window settings for misclassifications, smoking history for all FN versus 33% TP (P=0.005), and tissue plasminogen activator treatment for 41% FP versus 20% TN (P=0.017). Our LVO detection tool had high performance across patient characteristics with few exceptions. FP had pathology warranting detection, including distal occlusions. Lower window settings among misclassifications highlight the need for image quality when using machine learning for decision support.

[1]  M. Lansberg,et al.  High-Performance Automated Anterior Circulation CT Angiographic Clot Detection in Acute Stroke: A Multireader Comparison. , 2021, Radiology.

[2]  A. Demchuk,et al.  Clinical Course of Acute Ischemic Stroke Due to Medium Vessel Occlusion With and Without Intravenous Alteplase Treatment , 2020, Stroke.

[3]  U. Çetintemel,et al.  Detecting Large Vessel Occlusion at Multiphase CT Angiography by Using a Deep Convolutional Neural Network. , 2020, Radiology.

[4]  J. Grotta,et al.  Impact of Initial Imaging Protocol on Likelihood of Endovascular Stroke Therapy , 2020, Stroke.

[5]  J. Arrazola,et al.  Mechanical Thrombectomy in Medium Vessel Occlusions , 2020, Stroke.

[6]  M. Okawa,et al.  Deep Learning–Derived High-Level Neuroimaging Features Predict Clinical Outcomes for Large Vessel Occlusion , 2020, Stroke.

[7]  J. Boxerman,et al.  Detection of emergent large vessel occlusion stroke with CT angiography is high across all levels of radiology training and grayscale viewing methods , 2020, European Radiology.

[8]  R. Bammer,et al.  Fast Automatic Detection of Large Vessel Occlusions on CT Angiography. , 2019, Stroke.

[9]  W. Powers,et al.  Guidelines for the Early Management of Patients With Acute Ischemic Stroke: 2019 Update to the 2018 Guidelines for the Early Management of Acute Ischemic Stroke: A Guideline for Healthcare Professionals From the American Heart Association/American Stroke Association. , 2019, Stroke.

[10]  Aeilko H. Zwinderman,et al.  Data-efficient deep learning of radiological image data for outcome prediction after endovascular treatment of patients with acute ischemic stroke , 2019, Comput. Biol. Medicine.

[11]  M. Unberath,et al.  Artificial intelligence to diagnose ischemic stroke and identify large vessel occlusions: a systematic review , 2019, Journal of NeuroInterventional Surgery.

[12]  J. Grotta,et al.  Machine Learning-Enabled Automated Determination of Acute Ischemic Core From Computed Tomography Angiography. , 2019, Stroke.

[13]  R. Bammer,et al.  Automated Detection of Intracranial Large Vessel Occlusions on Computed Tomography Angiography. , 2019, Stroke.

[14]  Paul A. Harris,et al.  The REDCap consortium: Building an international community of software platform partners , 2019, J. Biomed. Informatics.

[15]  Quoc V. Le,et al.  EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks , 2019, ICML.

[16]  Kilian Q. Weinberger,et al.  Convolutional Networks with Dense Connectivity , 2019, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[17]  M. Jayaraman,et al.  Dismantling the ability of CT and MRI to identify the target mismatch profile in patients with anterior circulation large vessel occlusion beyond six hours from symptom onset , 2019, Emergency Radiology.

[18]  A. Chatterjee,et al.  Abstract WMP16: Artificial Intelligence Detection of Cerebrovascular Large Vessel Occlusion - Nine Month, 650 Patient Evaluation of the Diagnostic Accuracy and Performance of the Viz.ai LVO Algorithm , 2019, Stroke.

[19]  M. Howell,et al.  Ensuring Fairness in Machine Learning to Advance Health Equity , 2018, Annals of Internal Medicine.

[20]  S. Tamang,et al.  Potential Biases in Machine Learning Algorithms Using Electronic Health Record Data , 2018, JAMA internal medicine.

[21]  Michael Frankel,et al.  E-108 Aladin study: automated large artery occlusion detection in stroke imaging study – a multicenter analysis , 2018, Electronic Poster Abstracts.

[22]  Snehashis Roy,et al.  Classifying magnetic resonance image modalities with convolutional neural networks , 2018, Medical Imaging.

[23]  J. Gornbein,et al.  Ischemic Strokes Due to Large-Vessel Occlusions Contribute Disproportionately to Stroke-Related Dependence and Death: A Review , 2017, Front. Neurol..

[24]  Nigel S. George,et al.  Analysis of Workflow and Time to Treatment on Thrombectomy Outcome in the Endovascular Treatment for Small Core and Proximal Occlusion Ischemic Stroke (ESCAPE) Randomized, Controlled Trial , 2016 .

[25]  Kilian Q. Weinberger,et al.  Densely Connected Convolutional Networks , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[26]  Christopher Rorden,et al.  The first step for neuroimaging data analysis: DICOM to NIfTI conversion , 2016, Journal of Neuroscience Methods.

[27]  A. Demchuk,et al.  Analysis of Workflow and Time to Treatment on Thrombectomy Outcome in the Endovascular Treatment for Small Core and Proximal Occlusion Ischemic Stroke (ESCAPE) Randomized, Controlled Trial , 2016, Circulation.

[28]  Martín Abadi,et al.  TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems , 2016, ArXiv.

[29]  Benjamin N. Conrad,et al.  Vanderbilt University Institute of Imaging Science Center for Computational Imaging XNAT: A multimodal data archive and processing environment , 2016, NeuroImage.

[30]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[31]  Elad I Levy,et al.  Time to endovascular reperfusion and degree of disability in acute stroke , 2015, Annals of neurology.

[32]  M. Chen,et al.  Initial hospital management of patients with emergent large vessel occlusion (ELVO): report of the standards and guidelines committee of the Society of NeuroInterventional Surgery , 2015, Journal of NeuroInterventional Surgery.

[33]  Ciprian M. Crainiceanu,et al.  Validated automatic brain extraction of head CT images , 2015, NeuroImage.

[34]  Dumitru Erhan,et al.  Going deeper with convolutions , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[35]  J. Broderick,et al.  Impact of Onset-to-Reperfusion Time on Stroke Mortality: A Collaborative Pooled Analysis , 2013, Circulation.

[36]  H. Nam,et al.  Effects of cumulative smoking exposure and duration of smoking cessation on carotid artery structure. , 2012, Circulation journal : official journal of the Japanese Circulation Society.

[37]  K. Bae,et al.  Intravenous contrast medium administration and scan timing at CT: considerations and approaches. , 2010, Radiology.

[38]  P. Harris,et al.  Research electronic data capture (REDCap) - A metadata-driven methodology and workflow process for providing translational research informatics support , 2009, J. Biomed. Informatics.

[39]  G. Duckwiler,et al.  Intracranial vascular stenosis and occlusive disease: evaluation with CT angiography, MR angiography, and digital subtraction angiography. , 2005, AJNR. American journal of neuroradiology.

[40]  Michael Brady,et al.  Improved Optimization for the Robust and Accurate Linear Registration and Motion Correction of Brain Images , 2002, NeuroImage.

[41]  Stephen M. Smith,et al.  A global optimisation method for robust affine registration of brain images , 2001, Medical Image Anal..

[42]  K D Hopper,et al.  CT angiographic measurement of the carotid artery: optimizing visualization by manipulating window and level settings and contrast material attenuation. , 2000, Radiology.

[43]  J. Dichgans,et al.  Changes of cerebrovascular CO2 reactivity during normal aging. , 1998, Stroke.

[44]  J. Patterson,et al.  Responses of cerebral arteries and arterioles to acute hypotension and hypertension. , 1978, The American journal of physiology.

[45]  Scott Hamilton,et al.  Utilization of Emergent Neuroimaging for Thrombolysis‐Eligible Stroke Patients , 2017, Journal of neuroimaging : official journal of the American Society of Neuroimaging.