Share：
Share this content in WeChat
X
[Chinese][PDF]102974
• Technical Article •
Combining machine learning with imaging omics characteristics based on DWI in predicting outcome after mechanical thrombectomy of acute stroke
GUO Qun  WU Han  PENG Mingyang  CHEN Guozhong  YIN Xindao  SUN Jun 

Cite this article as: Citation:Guo Q, Wu H, Peng MY, et al. Combining machine learning with imaging omics characteristics based on DWI in predicting outcome after mechanical thrombectomy of acute stroke[J]. Chin J Magn Reson Imaging, 2021, 12(10): 32-35, 48. DOI:10.12015/issn.1674-8034.2021.10.007.


[Abstract] Objective To construct a prediction model of outcome after mechanical thrombectomy in acute stroke by machine learning based on imaging omics characteristics of diffusion weighted imaging (DWI). Materials andMethods Acute stroke patients in our hospital were retrospectively collected. These patients were divided into a training set (n=252) and a test set (n=108) according to random number table method. The imaging omics characteristics were extracted from lesions on DWI using A.K. software, and Least absolute shrinkage and selection operator regression model was used to screen the characteristics, and then, the selected characteristics were used to construct the prediction model by support vector machine classifier. Receiver operating characteristic (ROC) curve was used to evaluate the predictive efficacy of the model.Results One thousand one hundred and thirty-six imaging omics characteristics of each patient were extracted from DWI, and 21 characteristics highly related to outcome after mechanical thrombectomy in acute stroke were screened after dimension reduction. ROC analysis showed that the area under curve (AUC) of DWI model in predicting outcome was 0.956 based on training set, the sensitivity and specificity were 0.965, 0.948 respectively, and the accuracy was 0.954; the AUC of DWI model in predicting outcome was 0.801 based on test set, the sensitivity and specificity were 0.818, 0.816 respectively, and the accuracy was 0.828.Conclusion The imaging omics characteristics and machine learning model based on DWI before therapy can effectively predict outcome after mechanical thrombectomy in acute stroke.
[Keywords] stroke；diffusion weighted imaging；imaging omics；machine learning；outcome

GUO Qun   WU Han   PENG Mingyang   CHEN Guozhong   YIN Xindao   SUN Jun*  

Department of Radiology, Nanjing First Hospital, Nanjing Medical University, Nanjing, 21006

Sun J, E-mail: 13505194324@163.com

Conflicts of interest   None.

ACKNOWLEDGMENTS National Natural Science Foundation of China (No. 82001811); Natural Science Foundation of Jiangsu Province (No. BK20201118).
Received  2021-04-12
Accepted  2021-06-29
DOI: 10.12015/issn.1674-8034.2021.10.007
Cite this article as: Citation:Guo Q, Wu H, Peng MY, et al. Combining machine learning with imaging omics characteristics based on DWI in predicting outcome after mechanical thrombectomy of acute stroke[J]. Chin J Magn Reson Imaging, 2021, 12(10): 32-35, 48. DOI:10.12015/issn.1674-8034.2021.10.007.

[1]
van den Berg LA, Dijkgraaf MG, Berkhemer OA, et al. Two-Year Outcome after Endovascular Treatment for Acute Ischemic Stroke[J]. N Engl J Med, 2017, 376(14): 1341-1349. DOI: 10.1056/NEJMoa1612136.
[2]
Martins SO, Mont'Alverne F, Rebello LC, et al. Thrombectomy for Stroke in the Public Health Care System of Brazil[J]. N Engl J Med, 2020, 382(24): 2316-2326. DOI: 10.1056/NEJMoa2000120.
[3]
Shi ZJ, Guo SY, Zheng SJ, et al. Number of Stent Retriever Passes Associated with Clinical Outcome After Mechanical Thrombectomy in Acute Ischemic Stroke[J]. J Stroke Cerebrovasc Dis, 2020, 29(11): 105199. DOI: 10.1016/j.jstrokecerebrovasdis.2020.105199.
[4]
Jiang L, Peng MY, Chen HY, et al. Diffusion-weighted imaging (DWI) ischemic volume is related to FLAIR hyperintensity-DWI mismatch and functional outcome after endovascular therapy[J]. Quant Imaging Med Surg, 2020, 10(2): 356-367. DOI: 10.21037/qims.2019.12.05.
[5]
Nezu T, Koga M, Kimura K, et al. Pretreatment ASPECTS on DWI predicts 3-month outcome following rt-PA: SAMURAI rt-PA Registry[J]. Neurology, 2010, 75(6): 555-561. DOI: 10.1212/WNL.0b013e3181eccf78.
[6]
Wang W, Zhao J, Peng MY, et al. To explore the outcome differences in acute ischemic stroke with different time windows after mechanical thrombectomy[J]. Chin J Magn Reson Imaging, 2021, 12(3): 39-43. DOI: 10.12015/issn.1674-8034.2021.03.009.
[7]
Maïer B, Fahed R, Khoury N, et al. Association of Blood Pressure During Thrombectomy for Acute Ischemic Stroke With Functional Outcome: A Systematic Review[J]. Stroke, 2019, 50(10): 2805-2812. DOI: 10.1161/STROKEAHA.119.024915.
[8]
Zivanovic Z, Ostojic Z, Rajic S, et al. Outcome after intravenous thrombolysis in embolic stroke of undetermined source compared to cardioembolic stroke[J]. Wien Klin Wochenschr, 2020, 132(17-18): 515-520. DOI: 10.1007/s00508-020-01727-5.
[9]
Navis A, Garcia-Santibanez R, Skliut M. Epidemiology and Outcomes of Ischemic Stroke and Transient Ischemic Attack in the Adult and Geriatric Population[J]. J Stroke Cerebrovasc Dis, 2019, 28(1): 84-89. DOI: 10.1016/j.jstrokecerebrovasdis.
[10]
Majidi S, Luby M, Lynch JK, et al. MRI-based thrombolytic therapy in patients with acute ischemic stroke presenting with a low NIHSS[J]. Neurology, 2019, 93(16): e1507-e1513. DOI: 10.1212/WNL.0000000000008312.
[11]
Provost C, Soudant M, Legrand L, et al. Magnetic Resonance Imaging or Computed Tomography Before Treatment in Acute Ischemic Stroke[J]. Stroke, 2019, 50(3): 659-664. DOI: 10.1161/STROKEAHA.118.023882.
[12]
Ospel JM, Jaffray A, Schulze-Zachau V, et al. Spatial Resolution and the Magnitude of Infarct Volume Measurement Error in DWI in Acute Ischemic Stroke[J]. AJNR Am J Neuroradiol, 2020, 41(5): 792-797. DOI: 10.3174/ajnr.A6520.
[13]
Simonsen CZ, Madsen MH, Schmitz ML, et al. Sensitivity of diffusion- and perfusion-weighted imaging for diagnosing acute ischemic stroke is 97.5%[J]. Stroke, 2015, 46(1): 98-101. DOI: 10.1161/STROKEAHA.114.007107.
[14]
Qiu JB, Chen GH, Huang HT, et al. The Predict Value of DWI Infarct Volume and Volume Growth in the Functional Outcome of Stroke After Endovascular Therapy[J]. China Medical Devices, 2020, 35(4): 55-59. DOI: 10.3969/j.issn.1674-1633.2020.04.015.
[15]
Ribo M, Tomasello A, Lemus M, et al. Maximal Admission Core Lesion Compatible With Favorable Outcome in Acute Stroke Patients Undergoing Endovascular Procedures[J]. Stroke, 2015, 46(10): 2849-2852. DOI: 10.1161/STROKEAHA.115.010707.
[16]
Raoult H, Lassalle MV, Parat B, et al. Dwi-based algorithm to predict disability in patients treated with thrombectomy for acute stroke. AJNR[J]. American journal of neuroradiology, 2020, 41(2): 274-279. DOI: 10.3174/ajnr.A6379.
[17]
Giger ML. Machine Learning in Medical Imaging[J]. J Am Coll Radiol, 2018, 15(3Pt B): 512-520. DOI: 10.1016/j.jacr.2017.12.028.
[18]
Goecks J, Jalili V, Heiser LM, et al. How Machine Learning Will Transform Biomedicine[J]. Cell, 2020, 181(1): 92-101. DOI: 10.1016/j.cell.2020.03.022.
[19]
Kamal H, Lopez V, Sheth SA. Machine Learning in Acute Ischemic Stroke Neuroimaging[J]. Front Neurol, 2018, 9: 945. DOI: 10.3389/fneur.2018.00945.
[20]
Cheng C, Hua ZC. Lasso Peptides: Heterologous Production and Potential Medical Application[J]. Front Bioeng Biotechnol, 2020, 8: 571165. DOI: 10.3389/fbioe.2020.571165.
[21]
Heo J, Yoon JG, Park H, et al. Machine Learning-Based Model for Prediction of Outcomes in Acute Stroke[J]. Stroke, 2019, 50(5): 1263-1265. DOI: 10.1161/STROKEAHA.118.024293.
[22]
Hamann J, Herzog L, Wehrli C, et al. Machine-learning-based outcome prediction in stroke patients with middle cerebral artery-M1 occlusions and early thrombectomy[J]. Eur J Neurol, 2021, 28(4): 1234-1243. DOI: 10.1111/ene.14651.
[23]
Xie Y, Jiang B, Gong EH, et al. JOURNAL CLUB: Use of Gradient Boosting Machine Learning to Predict Patient Outcome in Acute Ischemic Stroke on the Basis of Imaging, Demographic, and Clinical Information[J]. AJR Am J Roentgenol, 2019, 212(1): 44-51. DOI: 10.2214/AJR.18.20260.

PREV The study of multi-nuclide 1H/19F-MR lung ventilation imaging based on atomized perfluorocarbon nanoprobe
NEXT Gd-EOB-DTPA-enhanced MRI for evaluation of hepatic reserve function: The value of hepatic signal intensity and histogram in hepatobiliary phase
  


LINK


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