Using Deep-Learning-Based Artificial Intelligence Technique to Automatically Evaluate the Collateral Status of Multiphase CTA in Acute Ischemic Stroke

被引:6
作者
Huang, Chun-Chao [1 ,2 ]
Chiang, Hsin-Fan [1 ,2 ,3 ]
Hsieh, Cheng-Chih [1 ,2 ,3 ]
Chou, Chao-Liang [2 ,4 ]
Jhou, Zong-Yi [5 ]
Hou, Ting-Yi [5 ]
Shaw, Jin-Siang [5 ]
机构
[1] MacKay Mem Hosp, Dept Radiol, Taipei 104217, Taiwan
[2] MacKay Med Coll, Dept Med, New Taipei City 252005, Taiwan
[3] Mackay Jr Coll Med Nursing & Management, Taipei 112021, Taiwan
[4] MacKay Mem Hosp, Dept Neurol, Taipei 104217, Taiwan
[5] Natl Taipei Univ Technol, Inst Mechatron Engn, Taipei 106344, Taiwan
关键词
multiphase CTA; collateral status; artificial intelligence; convolutional neural network; acute ischemic stroke; COMPUTED-TOMOGRAPHY; ANGIOGRAPHY;
D O I
10.3390/tomography9020052
中图分类号
R8 [特种医学]; R445 [影像诊断学];
学科分类号
1002 ; 100207 ; 1009 ;
摘要
Background: Collateral status is an important predictor for the outcome of acute ischemic stroke with large vessel occlusion. Multiphase computed-tomography angiography (mCTA) is useful to evaluate the collateral status, but visual evaluation of this examination is time-consuming. This study aims to use an artificial intelligence (AI) technique to develop an automatic AI prediction model for the collateral status of mCTA. Methods: This retrospective study enrolled subjects with acute ischemic stroke receiving endovascular thrombectomy between January 2015 and June 2020 in a tertiary referral hospital. The demographic data and images of mCTA were collected. The collateral status of all mCTA was visually evaluated. Images at the basal ganglion and supraganglion levels of mCTA were selected to produce AI models using the convolutional neural network (CNN) technique to automatically predict the collateral status of mCTA. Results: A total of 82 subjects were enrolled. There were 57 cases randomly selected for the training group and 25 cases for the validation group. In the training group, there were 40 cases with a positive collateral result (good or intermediate) and 17 cases with a negative collateral result (poor). In the validation group, there were 21 cases with a positive collateral result and 4 cases with a negative collateral result. During training for the CNN prediction model, the accuracy of the training group could reach 0.999 +/- 0.015, whereas the prediction model had a performance of 0.746 +/- 0.008 accuracy on the validation group. The area under the ROC curve was 0.7. Conclusions: This study suggests that the application of the AI model derived from mCTA images to automatically evaluate the collateral status is feasible.
引用
收藏
页码:647 / 656
页数:10
相关论文
共 28 条
  • [1] Automatic collateral circulation scoring in ischemic stroke using 4D CT angiography with low-rank and sparse matrix decomposition
    Aktar, Mumu
    Tampieri, Donatella
    Rivaz, Hassan
    Kersten-Oertel, Marta
    Xiao, Yiming
    [J]. INTERNATIONAL JOURNAL OF COMPUTER ASSISTED RADIOLOGY AND SURGERY, 2020, 15 (09) : 1501 - 1511
  • [2] Effects of Collateral Status on Infarct Distribution Following Endovascular Therapy in Large Vessel Occlusion Stroke
    Al-Dasuqi, Khalid
    Payabvash, Seyedmehdi
    Torres-Flores, Gerardo A.
    Strander, Sumita M.
    Nguyen, Cindy Khanh
    Peshwe, Krithika U.
    Kodali, Sreeja
    Silverman, Andrew
    Malhotra, Ajay
    Johnson, Michele H.
    Matouk, Charles C.
    Schindler, Joseph L.
    Sansing, Lauren H.
    Falcone, Guido J.
    Sheth, Kevin N.
    Petersen, Nils H.
    [J]. STROKE, 2020, 51 (09) : E193 - E202
  • [3] Arenillas JF, 2018, J CEREBR BLOOD F MET, V38, P1839, DOI 10.1177/0271678X17740293
  • [4] Artificial Neural Networks in Mammography Interpretation and Diagnostic Decision Making
    Ayer, Turgay
    Chen, Qiushi
    Burnside, Elizabeth S.
    [J]. COMPUTATIONAL AND MATHEMATICAL METHODS IN MEDICINE, 2013, 2013
  • [5] Collateral Flow Averts Hemorrhagic Transformation After Endovascular Therapy for Acute Ischemic Stroke
    Bang, Oh Young
    Saver, Jeffrey L.
    Kim, Suk Jae
    Kim, Gyeong-Moon
    Chung, Chin-Sang
    Ovbiagele, Bruce
    Lee, Kwang Ho
    Liebeskind, David S.
    [J]. STROKE, 2011, 42 (08) : 2235 - U329
  • [6] The importance of comorbidities in ischemic stroke: Impact of hypertension on the cerebral circulation
    Cipolla, Marilyn J.
    Liebeskind, David S.
    Chan, Siu-Lung
    [J]. JOURNAL OF CEREBRAL BLOOD FLOW AND METABOLISM, 2018, 38 (12) : 2129 - 2149
  • [7] Multiphase CT Angiography: A Useful Technique in Acute Stroke Imaging?Collaterals and Beyond
    Dundamadappa, S.
    Iyer, K.
    Agrawal, A.
    Choi, D. J.
    [J]. AMERICAN JOURNAL OF NEURORADIOLOGY, 2021, 42 (02) : 221 - 227
  • [8] Automated Detection of White Matter and Cortical Lesions in Early Stages of Multiple Sclerosis
    Fartaria, Mario Joao
    Bonnier, Guillaume
    Roche, Alexis
    Kober, Tobias
    Meuli, Reto
    Rotzinger, David
    Frackowiak, Richard
    Schluep, Myriam
    Du Pasquier, Renaud
    Thiran, Jean-Philippe
    Krueger, Gunnar
    Cuadra, Meritxell Bach
    Granziera, Cristina
    [J]. JOURNAL OF MAGNETIC RESONANCE IMAGING, 2016, 43 (06) : 1445 - 1454
  • [10] Hypoperfusion intensity ratio correlates with angiographic collaterals in acute ischaemic stroke with M1 occlusion
    Guenego, A.
    Fahed, R.
    Albers, G. W.
    Kuraitis, G.
    Sussman, E. S.
    Martin, B. W.
    Marcellus, D. G.
    Olivot, J. -M.
    Marks, M. P.
    Lansberg, M. G.
    Wintermark, M.
    Heit, J. J.
    [J]. EUROPEAN JOURNAL OF NEUROLOGY, 2020, 27 (05) : 864 - 870