BACKGROUND: The presence of diffusion-weighted imaging (DWI) and fluid-attenuated inversion recovery (FLAIR) mismatch was used to determine eligibility for intravenous thrombolysis in clinical trials. However, due to the restricted availability of MRI and the ambiguity of image assessment, it is not widely implemented in clinical practice. METHODS: A total of 222 acute ischemic stroke patients underwent non-contrast computed tomography (NCCT), DWI, and FLAIR within 1 h of one another. Human experts manually segmented ischemic lesions on DWI and FLAIR images and independently graded the presence of DWI-FLAIR mismatch. Deep learning (DL) models based on the nnU-net architecture were developed to predict ischemic lesions visible on DWI and FLAIR images using NCCT images. Inexperienced neurologists evaluated the DWI-FLAIR mismatch on NCCT images without and with the model's results. RESULTS: The mean age of included subjects was 71.8 ± 12.8 years, 123 (55%) were male, and the baseline NIHSS score was a median of 11 [IQR, 6-18]. All images were taken in the following order: NCCT - DWI - FLAIR, starting after a median of 139 [81-326] min after the time of the last known well. Intravenous thrombolysis was administered in 120 patients (54%) after NCCT. The DL model's prediction on NCCT images revealed a Dice coefficient and volume correlation of 39.1% and 0.76 for DWI lesions and 18.9% and 0.61 for FLAIR lesions. In the subgroup with 15 mL or greater lesion volume, the evaluation of DWI-FLAIR mismatch from NCCT by inexperienced neurologists improved in accuracy (from 0.537 to 0.610) and AUC-ROC (from 0.493 to 0.613). CONCLUSION: The DWI-FLAIR mismatch may be reckoned using NCCT images through advanced artificial intelligence techniques.

College of Electronic Engineering Xi'an Shiyou University Xi'an Shaanxi China

Department of Clinical Neurosciences and Diagnostic Imaging University of Calgary Cumming School of Medicine Calgary AB Canada

Department of Medical Imaging St Anne's University Hospital Brno and Faculty of Medicine Masaryk University Brno Czechia

Department of Neurology College of Medicine Seoul National University Seoul Republic of Korea

Department of Neurology Nowon Eulji Medical Center Eulji University Seoul Republic of Korea

Department of Neurology Seoul National University Bundang Hospital Seongnam si Republic of Korea

Diagnostic and Interventional Neuroradiology Department University Hospital of Tours Tours France

Gyeonggi Regional Cerebrovascular Center Seoul National University Bundang Hospital Seongnam si Republic of Korea

Neurology Division Department of Internal Medicine Max Rady College of Medicine University of Manitoba Winnipeg MB Canada

School of Life Science and Technology Huazhong University of Science and Technology Wuhan Hubei China

See more in PubMed

Powers WJ, Rabinstein AA, Ackerson T, Adeoye OM, Bambakidis NC, Becker K, et al. . 2018 guidelines for the early Management of Patients with Acute Ischemic Stroke: a guideline for healthcare professionals from the American Heart Association/American Stroke Association. Stroke. (2018) 49:e46–e110. doi: 10.1161/STR.0000000000000158, PMID: PubMed DOI

Ko SB, Park HK, Kim BM, Heo JH, Rha JH, Kwon SU, et al. . 2019 update of the Korean clinical practice guidelines of stroke for endovascular recanalization therapy in patients with acute ischemic stroke. J Stroke. (2019) 21:231–40. doi: 10.5853/jos.2019.00024 PubMed DOI PMC

Emberson J, Lees KR, Lyden P, Blackwell L, Albers G, Bluhmki E, et al. . Effect of treatment delay, age, and stroke severity on the effects of intravenous thrombolysis with alteplase for acute ischaemic stroke: a meta-analysis of individual patient data from randomised trials. Lancet. (2014) 384:1929–35. doi: 10.1016/S0140-6736(14)60584-5, PMID: PubMed DOI PMC

Saver JL, Goyal M, van der Lugt A, Menon BK, Majoie CB, Dippel DW, et al. . Time to treatment with endovascular Thrombectomy and outcomes from ischemic stroke: a Meta-analysis. JAMA. (2016) 316:1279–88. doi: 10.1001/jama.2016.13647 PubMed DOI

Kim BJ, Kim H, Jeong HG, Yang MH, Jung CK, Han MK, et al. . Tenacity of collateral perfusion in proximal cerebral arterial occlusions 6-12 h after onset. Cerebrovasc Dis. (2018) 45:263–9. doi: 10.1159/000489894, PMID: PubMed DOI

Kim BJ, Menon BK, Kim JY, Shin DW, Baik SH, Jung C, et al. . Endovascular treatment after stroke due to large vessel occlusion for patients presenting very late from time last known well. JAMA Neurol. (2020) 78:21–9. doi: 10.1001/jamaneurol.2020.2804, PMID: PubMed DOI PMC

Kim BJ, Singh N, Menon BK. Hemodynamics of leptomeningeal collaterals after large vessel occlusion and blood pressure management with endovascular treatment. J Stroke. (2021) 23:343–57. doi: 10.5853/jos.2021.02446, PMID: PubMed DOI PMC

Thomalla G, Cheng B, Ebinger M, Hao Q, Tourdias T, Wu O, et al. . DWI-FLAIR mismatch for the identification of patients with acute ischaemic stroke within 4.5 h of symptom onset (PRE-FLAIR): a multicentre observational study. Lancet Neurol. (2011) 10:978–86. doi: 10.1016/S1474-4422(11)70192-2, PMID: PubMed DOI

Thomalla G, Rossbach P, Rosenkranz M, Siemonsen S, Krutzelmann A, Fiehler J, et al. . Negative fluid-attenuated inversion recovery imaging identifies acute ischemic stroke at 3 hours or less. Ann Neurol. (2009) 65:724–32. doi: 10.1002/ana.21651 PubMed DOI

Aoki J, Sakamoto Y, Suzuki K, Nishi Y, Kutsuna A, Takei Y, et al. . Fluid-attenuated inversion recovery may serve as a tissue clock in patients treated with endovascular Thrombectomy. Stroke. (2021) 52:2232–40. doi: 10.1161/STROKEAHA.120.033374, PMID: PubMed DOI

Campbell BCV, Ma H, Ringleb PA, Parsons MW, Churilov L, Bendszus M, et al. . Extending thrombolysis to 4.5-9 h and wake-up stroke using perfusion imaging: a systematic review and meta-analysis of individual patient data. Lancet. (2019) 394:139–47. doi: 10.1016/S0140-6736(19)31053-0, PMID: PubMed DOI

Toyoda K, Inoue M, Yoshimura S, Yamagami H, Sasaki M, Fukuda-Doi M, et al. . Magnetic resonance imaging-guided thrombolysis (0.6 mg/kg) was beneficial for unknown onset stroke above a certain Core size: THAWS RCT substudy. Stroke. (2021) 52:12–9. doi: 10.1161/STROKEAHA.120.030848 PubMed DOI

Abdalkader M, Siegler JE, Lee JS, Yaghi S, Qiu Z, Huo X, et al. . Neuroimaging of acute ischemic stroke: multimodal imaging approach for acute endovascular therapy. J Stroke. (2023) 25:55–71. doi: 10.5853/jos.2022.03286 PubMed DOI PMC

Fleet R, Bussieres S, Tounkara FK, Turcotte S, Legare F, Plant J, et al. . Rural versus urban academic hospital mortality following stroke in Canada. PLoS One. (2018) 13:e0191151. doi: 10.1371/journal.pone.0191151, PMID: PubMed DOI PMC

Lin E, Alessio A. What are the basic concepts of temporal, contrast, and spatial resolution in cardiac CT? J Cardiovasc Comput Tomogr. (2009) 3:403–8. doi: 10.1016/j.jcct.2009.07.003, PMID: PubMed DOI PMC

Qiu W, Kuang H, Teleg E, Ospel JM, Sohn SI, Almekhlafi M, et al. . Machine learning for detecting early infarction in acute stroke with non-contrast-enhanced CT. Radiology. (2020) 294:638–44. doi: 10.1148/radiol.2020191193, PMID: PubMed DOI

Kim BJ, Park JM, Kang K, Lee SJ, Ko Y, Kim JG, et al. . Case characteristics, hyperacute treatment, and outcome information from the clinical research center for stroke-fifth division registry in South Korea. J Stroke. (2015) 17:38–53. doi: 10.5853/jos.2015.17.1.38, PMID: PubMed DOI PMC

Hong KS, Ko SB, Yu KH, Jung C, Park SQ, Kim BM, et al. . Update of the Korean clinical practice guidelines for endovascular recanalization therapy in patients with acute ischemic stroke. J Stroke. (2016) 18:102–13. doi: 10.5853/jos.2015.01655, PMID: PubMed DOI PMC

Beare R, Lowekamp B, Yaniv Z. Image segmentation, registration and characterization in R with SimpleITK. J Stat Softw. (2018) 86:86. doi: 10.18637/jss.v086.i08, PMID: PubMed DOI PMC

Najm M, Kuang H, Federico A, Jogiat U, Goyal M, Hill MD, et al. . Automated brain extraction from head CT and CTA images using convex optimization with shape propagation. Comput Methods Prog Biomed. (2019) 176:1–8. doi: 10.1016/j.cmpb.2019.04.030, PMID: PubMed DOI

Yushkevich PA, Piven J, Hazlett HC, Smith RG, Ho S, Gee JC, et al. . User-guided 3D active contour segmentation of anatomical structures: significantly improved efficiency and reliability. NeuroImage. (2006) 31:1116–28. doi: 10.1016/j.neuroimage.2006.01.015, PMID: PubMed DOI

Barow E, Thomalla G. Acute treatment of ischemic stroke: current standards. Nervenarzt. (2019) 90:979–86. doi: 10.1007/s00115-019-0776-5, PMID: PubMed DOI

Rohl L, Ostergaard L, Simonsen CZ, Vestergaard-Poulsen P, Andersen G, Sakoh M, et al. . Viability thresholds of ischemic penumbra of hyperacute stroke defined by perfusion-weighted MRI and apparent diffusion coefficient. Stroke. (2001) 32:1140–6. doi: 10.1161/01.str.32.5.1140, PMID: PubMed DOI

Schwamm LH, Wu O, Song SS, Latour LL, Ford AL, Hsia AW, et al. . Intravenous thrombolysis in unwitnessed stroke onset: MR WITNESS trial results. Ann Neurol. (2018) 83:980–93. doi: 10.1002/ana.25235, PMID: PubMed DOI PMC

Isensee F, Jaeger PF, Kohl SAA, Petersen J, Maier-Hein KH. nnU-net: a self-configuring method for deep learning-based biomedical image segmentation. Nat Methods. (2021) 18:203–11. doi: 10.1038/s41592-020-01008-z PubMed DOI

Woo I, Lee A, Jung SC, Lee H, Kim N, Cho SJ, et al. . Fully automatic segmentation of acute ischemic lesions on diffusion-weighted imaging using convolutional neural networks: comparison with conventional algorithms. Korean J Radiol. (2019) 20:1275–84. doi: 10.3348/kjr.2018.0615, PMID: PubMed DOI PMC

Woo S, Park J, Lee J-Y, Kweon IS. CBAM: convolutional block attention module In: Paper/poster presented at: Computer vision – ECCV 2018. Cham: (2018)

Feng S, Zhao H, Shi F, Cheng X, Wang M, Ma Y, et al. . CPFNet: context pyramid fusion network for medical image segmentation. IEEE Trans Med Imaging. (2020) 39:3008–18. doi: 10.1109/TMI.2020.2983721, PMID: PubMed DOI

Ma J, Chen J, Ng M, Huang R, Li Y, Li C, et al. . Loss odyssey in medical image segmentation. Med Image Anal. (2021) 71:102035. doi: 10.1016/j.media.2021.102035, PMID: PubMed DOI

Wu JC, Martin AF, Kacker RN. Validation of nonparametric two-sample bootstrap in ROC analysis on large datasets. Commun Stat Simul Comput. (2016) 45:1689–703. doi: 10.1080/03610918.2015.1065327, PMID: PubMed DOI PMC

Menon BK. Neuroimaging in acute stroke. Continuum (Minneap Minn). (2020) 26:287–309. doi: 10.1212/CON.0000000000000839 PubMed DOI

Wardlaw JM, Mair G, von Kummer R, Williams MC, Li W, Storkey AJ, et al. . Accuracy of automated computer-aided diagnosis for stroke imaging: a critical evaluation of current evidence. Stroke. (2022) 53:2393–403. doi: 10.1161/STROKEAHA.121.036204, PMID: PubMed DOI

Saur D, Kucinski T, Grzyska U, Eckert B, Eggers C, Niesen W, et al. . Sensitivity and interrater agreement of CT and diffusion-weighted MR imaging in hyperacute stroke. AJNR Am J Neuroradiol. (2003) 24:878–85. PMID: PubMed PMC