End to end stroke triage using cerebrovascular morphology and machine learning

被引:0
作者
Deshpande, Aditi [1 ,2 ]
Elliott, Jordan [1 ]
Jiang, Bin [3 ]
Tahsili-Fahadan, Pouya [4 ,5 ]
Kidwell, Chelsea [6 ]
Wintermark, Max [7 ]
Laksari, Kaveh [1 ,2 ,8 ]
机构
[1] Univ Arizona, Dept Biomed Engn, Tucson, AZ 85721 USA
[2] Univ Calif Riverside, Dept Mech Engn, Riverside, CA 92521 USA
[3] Stanford Univ, Dept Radiol, Stanford, CA USA
[4] Univ Virginia, Dept Med Educ, Inova Campus, Falls Church, VA USA
[5] Johns Hopkins Univ, Sch Med, Dept Neurol, Baltimore, MD USA
[6] Univ Arizona, Dept Neurol, Tucson, AZ USA
[7] Univ Texas MD Anderson Ctr, Dept Neuroradiol, Houston, TX USA
[8] Univ Arizona, Dept Aerosp & Mech Engn, Tucson, AZ 85721 USA
来源
FRONTIERS IN NEUROLOGY | 2023年 / 14卷
基金
美国国家卫生研究院;
关键词
stroke; CNN-convolutional neural network; stroke outcome; collateral circulation; segmentation (image processing); machine learning; cerebrovascular disease; ACUTE ISCHEMIC-STROKE; ENDOVASCULAR THROMBECTOMY; BLOOD-VESSELS; OUTCOMES; TORTUOSITY; THERAPY; SCORE; TIME;
D O I
10.3389/fneur.2023.1217796
中图分类号
R74 [神经病学与精神病学];
学科分类号
摘要
BackgroundRapid and accurate triage of acute ischemic stroke (AIS) is essential for early revascularization and improved patient outcomes. Response to acute reperfusion therapies varies significantly based on patient-specific cerebrovascular anatomy that governs cerebral blood flow. We present an end-to-end machine learning approach for automatic stroke triage.MethodsEmploying a validated convolutional neural network (CNN) segmentation model for image processing, we extract each patient's cerebrovasculature and its morphological features from baseline non-invasive angiography scans. These features are used to detect occlusion's presence and the site automatically, and for the first time, to estimate collateral circulation without manual intervention. We then use the extracted cerebrovascular features along with commonly used clinical and imaging parameters to predict the 90 days functional outcome for each patient.ResultsThe CNN model achieved a segmentation accuracy of 94% based on the Dice similarity coefficient (DSC). The automatic stroke detection algorithm had a sensitivity and specificity of 92% and 94%, respectively. The models for occlusion site detection and automatic collateral grading reached 96% and 87.2% accuracy, respectively. Incorporating the automatically extracted cerebrovascular features significantly improved the 90 days outcome prediction accuracy from 0.63 to 0.83.ConclusionThe fast, automatic, and comprehensive model presented here can improve stroke diagnosis, aid collateral assessment, and enhance prognostication for treatment decisions, using cerebrovascular morphology.
引用
收藏
页数:12
相关论文
共 56 条
[1]   Automatic detection of ischemic stroke using higher order spectra features in brain MRI images [J].
Acharya, U. Rajendra ;
Meiburger, Kristen M. ;
Faust, Oliver ;
Koh, Joel En Wei ;
Oh, Shu Lih ;
Ciaccio, Edward J. ;
Subudhi, Asit ;
Jahmunah, V ;
Sabut, Sukanta .
COGNITIVE SYSTEMS RESEARCH, 2019, 58 :134-142
[2]   Functional Outcome Prediction in Ischemic Stroke: A Comparison of Machine Learning Algorithms and Regression Models [J].
Alaka, Shakiru A. ;
Menon, Bijoy K. ;
Brobbey, Anita ;
Williamson, Tyler ;
Goyal, Mayank ;
Demchuk, Andrew M. ;
Hill, Michael D. ;
Sajobi, Tolulope T. .
FRONTIERS IN NEUROLOGY, 2020, 11
[3]   Modelling the circle of Willis to assess the effects of anatomical variations and occlusions on cerebral flows [J].
Alastruey, J. ;
Parker, K. H. ;
Peiro, J. ;
Byrd, S. M. ;
Sherwin, S. J. .
JOURNAL OF BIOMECHANICS, 2007, 40 (08) :1794-1805
[4]   Thrombectomy for Stroke at 6 to 16 Hours with Selection by Perfusion Imaging [J].
Albers, G. W. ;
Marks, M. P. ;
Kemp, S. ;
Christensen, S. ;
Tsai, J. P. ;
Ortega-Gutierrez, S. ;
McTaggart, R. A. ;
Torbey, M. T. ;
Kim-Tenser, M. ;
Leslie-Mazwi, T. ;
Sarraj, A. ;
Kasner, S. E. ;
Ansari, S. A. ;
Yeatts, S. D. ;
Hamilton, S. ;
Mlynash, M. ;
Heit, J. J. ;
Zaharchuk, G. ;
Kim, S. ;
Carrozzella, J. ;
Palesch, Y. Y. ;
Demchuk, A. M. ;
Bammer, R. ;
Lavori, P. W. ;
Broderick, J. P. ;
Lansberg, M. G. .
NEW ENGLAND JOURNAL OF MEDICINE, 2018, 378 (08) :708-718
[5]   A multicenter randomized controlled trial of endovascular therapy following imaging evaluation for ischemic stroke (DEFUSE 3) [J].
Albers, Gregory W. ;
Lansberg, Maarten G. ;
Kemp, Stephanie ;
Tsai, Jenny P. ;
Lavori, Phil ;
Christensen, Soren ;
Mlynash, Michael ;
Kim, Sun ;
Hamilton, Scott ;
Yeatts, Sharon D. ;
Palesch, Yuko ;
Bammer, Roland ;
Broderick, Joe ;
Marks, Michael P. .
INTERNATIONAL JOURNAL OF STROKE, 2017, 12 (08) :896-905
[6]   Automated Detection of Intracranial Large Vessel Occlusions on Computed Tomography Angiography: A Single Center Experience [J].
Amukotuwa, Shalini A. ;
Straka, Matus ;
Smith, Heather ;
Chandra, Ronil V. ;
Dehkharghani, Seena ;
Fischbein, Nancy J. ;
Bammer, Roland .
STROKE, 2019, 50 (10) :2790-2798
[7]   Machine Learning for Outcome Prediction of Acute Ischemic Stroke Post Intra-Arterial Therapy [J].
Asadi, Hamed ;
Dowling, Richard ;
Yan, Bernard ;
Mitchell, Peter .
PLOS ONE, 2014, 9 (02)
[8]  
Azad R., 2022, arXiv
[9]   Outcomes validity and reliability of the modified Rankin scale: Implications for stroke clinical trials - A literature review and synthesis [J].
Banks, Jamie L. ;
Marotta, Charles A. .
STROKE, 2007, 38 (03) :1091-1096
[10]   Measuring tortuosity of the intracerebral vasculature from MRA images [J].
Bullitt, E ;
Gerig, G ;
Pizer, SM ;
Lin, WL ;
Aylward, SR .
IEEE TRANSACTIONS ON MEDICAL IMAGING, 2003, 22 (09) :1163-1171