Share：
Share this content in WeChat
X
[Chinese][PDF]4545
• Special Focus •
Prediction of mixed ischemic stroke mechanism based on HR-MRI radiomics of intracranial arterial plaque
LI Hongxia  LIU Jia  CHENG Xiaoqing  LI Yingle  ZHI Beibei  YANG Jialuo  ZHANG Longjiang  LU Guangming 

Cite this article as: LI H X, LIU J, CHENG X Q, et al. Prediction of mixed ischemic stroke mechanism based on HR-MRI radiomics of intracranial arterial plaque[J]. Chin J Magn Reson Imaging, 2023, 14(3): 6-11, 27. DOI:10.12015/issn.1674-8034.2023.03.002.


[Abstract] Objective To establish and verify the radiomics model of intracranial arterial plaque based on three dimensional (3D) high-resolution magnetic resonance imaging (HR-MRI) to predict the mechanism of mixed infarction.Materials and Methods The HR-MRI and diffusion weight imaging (DWI) data of 137 patients with acute/subacute intracranial atherosclerotic ischemic stroke from November 2016 to January 2022 were retrospectively analyzed. According to the lesion distribution pattern on DWI, the patients were divided into mixed mechanism group and non-mixed mechanism group. Univariate and multivariate analysis were used to analyze the imaging characteristics of responsible plaques in these two groups, and the traditional prediction model was constructed using logistic regression model. The radiomics features of intracranial plaques were extracted based on 3D HR-MRI sequences, and were divided into training set (n=95) and test set (n=42) with a ratio of 7∶3 by random sampling. Linear correlation threshold and ANOVA were used for feature selection. The selected radiomics features were used to build a machine learning model. A combined model was built using both the traditional and radiomics features. Receiver operating characteristic (ROC) curve was used to evaluate the diagnostic performance of the model. Delong test was used to compare the prediction performance of each model.Results Multivariate logistic analysis showed that the enhancement ratio was an independent predictor of mixed infarction mechanism (OR=2.77, P=0.002). The area under the curve (AUC) of the training set and the test set were 0.676 and 0.568, respectively. The machine learning model composed of radiomics features showed good discrimination ability, with an AUC of 0.906 (95% CI: 0.849-0.964) in the training set and 0.828 (95% CI: 0.704-0.951) in the test set. The prediction performance of the combined model was the best, with the AUC of 0.917 (95% CI: 0.864-0.969) and 0.837 (95% CI: 0.708-0.966) in the training and test sets, respectively.Conclusions The radiomics model of intracranial arterial plaque based on 3D HR-MRI can effectively predict the mixed stroke mechanism, which is helpful to take targeted clinical treatment measures.
[Keywords] ischemic stroke；atherosclerosis；stroke mechanism；radiomics；high resolution magnetic resonance imaging；magnetic resonance imaging

LI Hongxia1   LIU Jia1   CHENG Xiaoqing2   LI Yingle3   ZHI Beibei2   YANG Jialuo4   ZHANG Longjiang2   LU Guangming1*  

1 Department of Diagnostic Radiology, Jinling Hospital, the First School of Clinical Medicine, Southern Medical University, Nanjing 210002, China

2 Department of Diagnostic Radiology, Jinling Hospital, Nanjing University School of Medicine, Nanjing 210002, China

3 Department of Neurology, Jinling Hospital, the First School of Clinical Medicine, Southern Medical University, Nanjing 210002, China

4 Department of Diagnostic Radiology, Jinling School of Clinical Medicine, Nanjing University of Chinese Medicine, Nanjing 210002, China

Corresponding author: Lu GM, E-mail: cjr.luguangming@vip.163.com

Conflicts of interest   None.

ACKNOWLEDGMENTS National Natural Scientific Foundation of China (No. 82271983).
Received  2022-12-02
Accepted  2023-02-28
DOI: 10.12015/issn.1674-8034.2023.03.002
Cite this article as: LI H X, LIU J, CHENG X Q, et al. Prediction of mixed ischemic stroke mechanism based on HR-MRI radiomics of intracranial arterial plaque[J]. Chin J Magn Reson Imaging, 2023, 14(3): 6-11, 27. DOI:10.12015/issn.1674-8034.2023.03.002.

[1]
GUTIERREZ J, TURAN T N, HOH B L, et al. Intracranial atherosclerotic stenosis: risk factors, diagnosis, and treatment[J]. Lancet Neurol, 2022, 21(4): 355-368. DOI: 10.1016/S1474-4422(21)00376-8.
[2]
KIM W J, KO Y, YANG M H, et al. Differential effect of previous antiplatelet use on stroke severity according to stroke mechanism[J]. Stroke, 2010, 41(6): 1200-1204. DOI: 10.1161/STROKEAHA.110.580225.
[3]
HA S H, CHANG J Y, LEE S H, et al. Mechanism of stroke according to the severity and location of atherosclerotic middle cerebral artery disease[J/OL]. J Stroke Cerebrovasc Dis, 2021, 30(2): 105503 [2022-11-23]. https://doi.org/10.1016/j.jstrokecerebrovasdis.2020.105503. DOI: 10.1016/j.jstrokecerebrovasdis.2020.105503.
[4]
TEKLE W G, HASSAN A E. Intracranial atherosclerotic disease: current concepts in medical and surgical management[J]. Neurology, 2021, 97(20Suppl 2): S145-S157. DOI: 10.1212/WNL.0000000000012805.
[5]
FENG X Y, CHAN K L, LAN L F, et al. Stroke mechanisms in symptomatic intracranial atherosclerotic disease: classification and clinical implications[J]. Stroke, 2019, 50(10): 2692-2699. DOI: 10.1161/STROKEAHA.119.025732.
[6]
PAN Y S, MENG X, JING J, et al. Association of multiple infarctions and ICAS with outcomes of minor stroke and TIA[J]. Neurology, 2017, 88(11): 1081-1088. DOI: 10.1212/WNL.0000000000003719.
[7]
BRUNSER A M, HOPPE A, ILLANES S, et al. Accuracy of diffusion-weighted imaging in the diagnosis of stroke in patients with suspected cerebral infarct[J]. Stroke, 2013, 44(4): 1169-1171. DOI: 10.1161/STROKEAHA.111.000527.
[8]
HUANG H T, LI X, LIANG B, et al. Diffusion weighted imaging and arterial spin labeling for prediction of cerebral infarct volume in acute atherothrombotic stroke[J/OL]. Curr Med Imaging, 2022 [2022-11-23]. https://doi.org/10.2174/1573405618666220509205920. DOI: 10.2174/1573405618666220509205920.
[9]
BRUNSER A M, MANSILLA E, NAVIA V, et al. Diffusion-weighted imaging as predictor of acute ischemic stroke etiology[J]. Arq Neuropsiquiatr, 2022, 80(4): 353-359. DOI: 10.1590/0004-282X-ANP-2021-0080.
[10]
CHEN C H, LEE M, WENG H H, et al. Identification of magnetic resonance imaging features for the prediction of unrecognized atrial fibrillation in acute ischemic stroke[J/OL]. Front Neurol, 2022, 13: 952462 [2022-11-23]. https://doi.org/10.3389/fneur.2022.952462. DOI: 10.3389/fneur.2022.952462.
[11]
LEE D K, KIM J S, KWON S U, et al. Lesion patterns and stroke mechanism in atherosclerotic middle cerebral artery disease: early diffusion-weighted imaging study[J]. Stroke, 2005, 36(12): 2583-2588. DOI: 10.1161/01.STR.0000189999.19948.14.
[12]
ZHU T T, REN L J, ZHANG L, et al. Comparison of plaque characteristics of small and large subcortical infarctions in the middle cerebral artery territory using high-resolution magnetic resonance vessel wall imaging[J]. Quant Imaging Med Surg, 2021, 11(1): 57-66. DOI: 10.21037/qims-20-310.
[13]
LIU S, TANG R W, XIE W W, et al. Plaque characteristics and hemodynamics contribute to neurological impairment in patients with ischemic stroke and transient ischemic attack[J]. Eur Radiol, 2021, 31(4): 2062-2072. DOI: 10.1007/s00330-020-07327-1.
[14]
WON S Y, CHA J, CHOI H S, et al. High-resolution intracranial vessel wall MRI findings among different middle cerebral artery territory infarction types[J]. Korean J Radiol, 2022, 23(3): 333-342. DOI: 10.3348/kjr.2021.0615.
[15]
SONG X Y, LI S, DU H, et al. Association of plaque morphology with stroke mechanism in patients with symptomatic posterior circulation ICAD[J/OL]. Neurology, 2022, 99(24): e2708-e2717 [2022-11-23]. https://doi.org/10.1212/WNL.0000000000201299. DOI: 10.1212/WNL.0000000000201299.
[16]
SHI Z, ZHU C C, DEGNAN A J, et al. Identification of high-risk plaque features in intracranial atherosclerosis: initial experience using a radiomic approach[J]. Eur Radiol, 2018, 28(9): 3912-3921. DOI: 10.1007/s00330-018-5395-1.
[17]
SHI Z, LI J, ZHAO M, et al. Progression of plaque burden of intracranial atherosclerotic plaque predicts recurrent stroke/transient ischemic attack: a pilot follow-up study using higher-resolution MRI[J]. J Magn Reson Imaging, 2021, 54(2): 560-570. DOI: 10.1002/jmri.27561.
[18]
CHIMOWITZ M I, KOKKINOS J, STRONG J, et al. The warfarin-aspirin symptomatic intracranial disease study[J]. Neurology, 1995, 45(8): 1488-1493. DOI: 10.1212/wnl.45.8.1488.
[19]
LIN G H, SONG J X, FU N X, et al. Quantitative and qualitative analysis of atherosclerotic Stenosis in the middle cerebral artery using high-resolution magnetic resonance imaging[J]. J L'association Can Des Radiol, 2021, 72(4): 783-788. DOI: 10.1177/0846537120961312.
[20]
QIAO Y, ZEILER S R, MIRBAGHERI S, et al. Intracranial plaque enhancement in patients with cerebrovascular events on high-spatial-resolution MR images[J]. Radiology, 2014, 271(2): 534-542. DOI: 10.1148/radiol.13122812.
[21]
QIAO Y, ANWAR Z, INTRAPIROMKUL J, et al. Patterns and implications of intracranial arterial remodeling in stroke patients[J]. Stroke, 2016, 47(2): 434-440. DOI: 10.1161/STROKEAHA.115.009955.
[22]
MANDELL D M, MOSSA-BASHA M, QIAO Y, et al. Intracranial vessel wall MRI: principles and expert consensus recommendations of the American society of neuroradiology[J]. AJNR Am J Neuroradiol, 2017, 38(2): 218-229. DOI: 10.3174/ajnr.A4893.
[23]
CHUNG G H, KWAK H S, HWANG S B, et al. High resolution MR imaging in patients with symptomatic middle cerebral artery stenosis[J]. Eur J Radiol, 2012, 81(12): 4069-4074. DOI: 10.1016/j.ejrad.2012.07.001.
[24]
SONG J W, PAVLOU A, XIAO J Y, et al. Vessel wall magnetic resonance imaging biomarkers of symptomatic intracranial atherosclerosis: a meta-analysis[J]. Stroke, 2021, 52(1): 193-202. DOI: 10.1161/STROKEAHA.120.031480.
[25]
YANG D H, LIU J, YAO W H, et al. The MRI enhancement ratio and plaque steepness may be more accurate for predicting recurrent ischemic cerebrovascular events in patients with intracranial atherosclerosis[J]. Eur Radiol, 2022, 32(10): 7004-7013. DOI: 10.1007/s00330-022-08893-2.
[26]
KIM J M, JUNG K H, SOHN C H, et al. Middle cerebral artery plaque and prediction of the infarction pattern[J]. Arch Neurol, 2012, 69(11): 1470-1475. DOI: 10.1001/archneurol.2012.1018.
[27]
BALLOUT A A, LIBMAN R B, SCHNEIDER J R, et al. Vertebrobasilar stroke: association between infarction patterns and quantitative magnetic resonance angiography flow state[J/OL]. J Am Heart Assoc, 2022, 11(5): e023991 [2022-11-23]. https://doi.org/10.1161/JAHA.121.023991. DOI: 10.1161/JAHA.121.023991.
[28]
JUNG J M, KANG D W, YU K H, et al. Predictors of recurrent stroke in patients with symptomatic intracranial arterial stenosis[J]. Stroke, 2012, 43(10): 2785-2787. DOI: 10.1161/STROKEAHA.112.659185.
[29]
JING J, MENG X, ZHAO X Q, et al. Dual antiplatelet therapy in transient ischemic attack and minor stroke with different infarction patterns: subgroup analysis of the CHANCE randomized clinical trial[J]. JAMA Neurol, 2018, 75(6): 711-719. DOI: 10.1001/jamaneurol.2018.0247.
[30]
MAYERHOEFER M E, MATERKA A, LANGS G, et al. Introduction to radiomics[J]. J Nucl Med, 2020, 61(4): 488-495. DOI: 10.2967/jnumed.118.222893.
[31]
ZHANG R Y, ZHANG Q W, JI A H, et al. Identification of high-risk carotid plaque with MRI-based radiomics and machine learning[J]. Eur Radiol, 2021, 31(5): 3116-3126. DOI: 10.1007/s00330-020-07361-z.
[32]
CHENG X Q, DONG Z, LIU J, et al. Prediction of carotid In-stent restenosis by computed tomography angiography carotid plaque-based radiomics[J/OL]. J Clin Med, 2022, 11(11): 3234 [2022-11-23]. https://doi.org/10.3390/jcm11113234. DOI: 10.3390/jcm11113234.
[33]
KOLOSSVÁRY M, GERSTENBLITH G, BLUEMKE D A, et al. Contribution of risk factors to the development of coronary atherosclerosis as confirmed via coronary CT angiography: a longitudinal radiomics-based study[J]. Radiology, 2021, 299(1): 97-106. DOI: 10.1148/radiol.2021203179.
[34]
HATT M, LE REST C C, TIXIER F, et al. Radiomics: data are also images[J]. J Nucl Med, 2019, 60(suppl 2): 38S-44S. DOI: 10.2967/jnumed.118.220582.
[35]
LIN A, KOLOSSVÁRY M, CADET S, et al. Radiomics-based precision phenotyping identifies unstable coronary plaques from computed tomography angiography[J]. JACC Cardiovasc Imaging, 2022, 15(5): 859-871. DOI: 10.1016/j.jcmg.2021.11.016.
[36]
HUANG Z, CHENG X Q, LIU H Y, et al. Relation of carotid plaque features detected with ultrasonography-based radiomics to clinical symptoms[J]. Transl Stroke Res, 2022, 13(6): 970-982. DOI: 10.1007/s12975-021-00963-9.

PREV Research status and development prospect of magnetic resonance imaging artificial intelligence
NEXT Application of 3D convolutional neural network based on fusion of multiple sequence MRI to evaluate the survival prediction of patients with glioma
  


LINK


Tel & Fax: +8610-67113815    E-mail: editor@cjmri.cn