Abstract P321: The Cerebral Collateral Cascade: Rethinking the Assessment of Vascular Pathways in Acute Ischemic Stroke Patients

Stroke ◽  
2021 ◽  
Vol 52 (Suppl_1) ◽  
Author(s):  
Tobias D Faizy ◽  
Michael Mlynash ◽  
Reza Kabiri ◽  
Soren Christensen ◽  
Gabriella Kuraitis ◽  
...  
Keyword(s):  
Blood Flow ◽  
Ischemic Stroke ◽  
Acute Ischemic Stroke ◽  
Ct Perfusion ◽  
Infarct Volume ◽  
Strong Predictor ◽  
Secondary Outcome ◽  
Collateral Blood Flow ◽  
Vessel Occlusion ◽  
Cortical Vein

Background and Purpose: Robust collateral blood flow in patients with acute ischemic stroke due to large vessel occlusion (AIS-LVO) has been correlated with favorable outcomes. Collaterals are commonly assessed by the number of arteries present on non-invasive CT angiography (CTA) overlying ischemic brain, but blood transit from these arteries through the brain tissue and the venous drainage is not assessed by this technique. We hypothesized that a comprehensive imaging analysis of the cerebral collateral cascade (CCC) would predict clinical and radiological outcomes in patients with AIS-LVO patients. Materials and Methods: Multicenter retrospective cohort study of AIS-LVO patients undergoing thrombectomy triage. CCC was determined on pre-treatment imaging by scoring for pial arterial collaterals, tissue-level collaterals (TLC), and venous outflow. Pial arterial collaterals were determined by CTA (Tan scale), TLC were assessed on CT perfusion data using the Hypoperfusion Intensity Ratio, and venous egress was assessed on CTA using the cortical vein opacification score system. 3 groups were defined: CCC+ (good pial collaterals, TLC, and venous perfusion), CCC- (poor pial collaterals, TLC, and venous perfusion) and CCCmixed (reminder of patients). Primary outcome was a good functional outcome (modified Rankin Scale [mRS] 0-2 at 90 days). Secondary outcome was final infarct volume. Results: 647 patients met inclusion criteria: 176 CCC+, 345 CCCmixed and 126 CCC-. Multivariate ordinal logistic regression showed that CCC+ predicted good functional outcomes (mRS 0-2: OR=20.8 [95% CI 9.3-46.8]; p<0.001) compared to CCC- and CCCmixed. CCCmixed (β: 27.1, SE: 7.7; p<0.001) and CCC- (β: 86.6, SE: 9.9; p<0.001) profiles were associated with higher final infarct volumes after treatment compared to CCC+. Conclusion: Comprehensive assessment of the collateral blood flow cascade in AIS-LVO patients is a strong predictor of clinical and radiological outcomes in AIS-LVO patients.

Infarct growth despite full reperfusion in endovascular therapy for acute ischemic stroke

2014 ◽  
Vol 8 (2) ◽  
pp. 117-121 ◽  
Author(s):  
Diogo C Haussen ◽  
Raul G Nogueira ◽  
Mohamed Samy Elhammady ◽  
Dileep R Yavagal ◽  
Mohammad Ali Aziz-Sultan ◽  
...  
Keyword(s):  
Ischemic Stroke ◽  
Acute Ischemic Stroke ◽  
Ct Perfusion ◽  
Infarct Volume ◽  
Infarct Core ◽  
Anterior Circulation ◽  
Vessel Occlusion ◽  
Intravenous Tissue Plasminogen Activator ◽  
Stent Retrievers ◽  
Grade 3

AimTo explore the predictors of infarct core expansion despite full reperfusion after intra-arterial therapy (IAT).MethodsWe retrospectively reviewed 604 consecutive patients who underwent IAT for anterior circulation large vessel occlusion acute ischemic stroke in two tertiary centers (2008–2013/2010–2013). Sixty patients selected by MRI or CT perfusion presenting within <24 h of onset with modified Thrombolysis In Cerebral Infarction (mTICI) grade 3 or 2c reperfusion were included. Significant infarct growth (SIG) was defined as infarct expansion >11.6 mL.ResultsMean age was 67.0±13.7 years, 56% were men. Mean National Institute of Health Stroke Scale (NIHSS) score was 16.2±6.1, time from onset to puncture was 6.8±3.1 h, and procedure length was 1.3±0.6 h. MRI was used for baseline core analysis in 43% of patients. Mean baseline infarct volume was 17.1±19.1 mL, absolute infarct growth was 30.6±74.5 mL, and final infarct volume was 47.7±77.7 mL. Overall, 35% of patients had SIG. Three of 21 patients (14%) treated with stent-retrievers had SIG compared with 14 of 39 (36%) with first-generation devices. Eight of 21 patients (38%) with intravenous tissue plasminogen activator (IV t-PA) had infarct growth compared with 25/39 (64%) without. 23% of patients with SIG had a modified Rankin Scale score ≤2 at 3 months compared with 48% of those without SIG. Multivariate logistic regression indicated that race affected infarct growth. Use of IV t-PA (p=0.03) and stent-retrievers (p=0.03) were independently and inversely correlated with SIG.ConclusionsDespite full reperfusion, infarct growth is relatively frequent and may explain poor clinical outcomes in this setting. Ethnicity was found to influence SIG. Use of IV t-PA and stent-retrievers were associated with less infarct core expansion.

scholarly journals Cerebral endothelial cell-derived small extracellular vesicles enhance neurovascular function and neurological recovery in rat acute ischemic stroke models of mechanical thrombectomy and embolic stroke treatment with tPA

2021 ◽  
pp. 0271678X2199298
Author(s):  
Chao Li ◽  
Chunyang Wang ◽  
Yi Zhang ◽  
Owais K Alsrouji ◽  
Alex B Chebl ◽  
...  
Keyword(s):  
Ischemic Stroke ◽  
Acute Ischemic Stroke ◽  
Extracellular Vesicles ◽  
Mechanical Thrombectomy ◽  
Infarct Volume ◽  
Artery Occlusion ◽  
Therapeutic Effects ◽  
Vessel Occlusion ◽  
Healthy Human ◽  
Stroke Treatment

Treatment of patients with cerebral large vessel occlusion with thrombectomy and tissue plasminogen activator (tPA) leads to incomplete reperfusion. Using rat models of embolic and transient middle cerebral artery occlusion (eMCAO and tMCAO), we investigated the effect on stroke outcomes of small extracellular vesicles (sEVs) derived from rat cerebral endothelial cells (CEC-sEVs) in combination with tPA (CEC-sEVs/tPA) as a treatment of eMCAO and tMCAO in rat. The effect of sEVs derived from clots acquired from patients who had undergone mechanical thrombectomy on healthy human CEC permeability was also evaluated. CEC-sEVs/tPA administered 4 h after eMCAO reduced infarct volume by ∼36%, increased recanalization of the occluded MCA, enhanced cerebral blood flow (CBF), and reduced blood-brain barrier (BBB) leakage. Treatment with CEC-sEVs given upon reperfusion after 2 h tMCAO significantly reduced infarct volume by ∼43%, and neurological outcomes were improved in both CEC-sEVs treated models. CEC-sEVs/tPA reduced a network of microRNAs (miRs) and proteins that mediate thrombosis, coagulation, and inflammation. Patient-clot derived sEVs increased CEC permeability, which was reduced by CEC-sEVs. CEC-sEV mediated suppression of a network of pro-thrombotic, -coagulant, and -inflammatory miRs and proteins likely contribute to therapeutic effects. Thus, CEC-sEVs have a therapeutic effect on acute ischemic stroke by reducing neurovascular damage.

Abstract P538: A Detailed Analysis of Intracranial Hemorrhage After Endovascular Treatment in Acute Ischemic Stroke Due to Large Vessel Occlusion in the Escape-NA1 Trial

Stroke ◽  
2021 ◽  
Vol 52 (Suppl_1) ◽  
Author(s):  
Johanna Ospel ◽  
Michael D Hill ◽  
Nima Kashani ◽  
Arnuv Mayank ◽  
Nishita Singh ◽  
...  
Keyword(s):  
Ischemic Stroke ◽  
Acute Ischemic Stroke ◽  
Intracranial Hemorrhage ◽  
Intraventricular Hemorrhage ◽  
Infarct Volume ◽  
Prognostic Impact ◽  
Vessel Occlusion ◽  
Good Outcome

Purpose: We investigated the prevalence and prognostic impact on outcome of any intracranial hemorrhage, hemorrhage morphology, type and volume in acute ischemic stroke patients undergoing mechanical thrombectomy. Methods: Prevalence of intracranial hemorrhage, hemorrhage type, morphology and volume was determined on 24h follow-up imaging (non contrast head CT or gradient-echo/susceptibility-weighted MRI). Proportions of good outcome (mRS 0-2 at 90 days) were reported for patients with vs. without any intracranial hemorrhage. Multivariable logistic regression with adjustment for key minimization variables and total infarct volume was performed to obtain adjusted effect size estimates for hemorrhage type and volume on good outcome. Results: Hemorrhage on follow up-imaging was seen in 372/1097 (33.9%) patients, among them 126 (33.9%) with hemorrhagic infarction (HI) type 1, 108 (29.0%) with HI-2, 72 /19.4%) with parenchymal hematoma (PH) type 1, 37 (10.0) with PH2, 8 (2.2%) with remote PH and 21 (5.7%) with extra-parenchymal/intraventricular hemorrhage. Good outcomes were less often achieved by patients with hemorrhage on follow-up imaging (164/369 [44.4%] vs. 500/720 [69.4%]). Any type of intracranial hemorrhage was strongly associated with decreased chances of good outcome ( adj OR 0.62 [CI 95 0.44 - 0.87]). The effect of hemorrhage was driven by both PH hemorrhage sub-type [PH-1 ( adj OR 0.39 [CI 95 0.21 - 0.72]), PH-2 ( adj OR 0.15 [CI 95 0.05 - 0.50])] and extra-parenchymal/intraventricular hemorrhage ( adj OR 0.60 (0.20-1.78) Petechial hemorrhages (HI-1 and HI-2) were not associated with poorer outcomes. Hemorrhage volume ( adj OR 0.97 [CI 95 0.05 - 0.99] per ml increase) was significantly associated with decreased chances of good outcome. Conclusion: Presence of any hemorrhage on follow-up imaging was seen in one third of patients and strongly associated with decreased chances of good outcome.

Abstract WMP15: Automated Volumetric Assessment of Infarct Core in Non-Contrast Computed Tomography in Patients With Acute Ischemic Stroke Secondary to Large Vessel Occlusion

Stroke ◽  
2020 ◽  
Vol 51 (Suppl_1) ◽  
Author(s):  
Alvaro Garcia-Tornel ◽  
Matias Deck ◽  
Marc Ribo ◽  
David Rodriguez-Luna ◽  
Jorge Pagola ◽  
...  
Keyword(s):  
Computed Tomography ◽  
Ischemic Stroke ◽  
Acute Ischemic Stroke ◽  
Functional Outcome ◽  
Infarct Volume ◽  
Large Vessel Occlusion ◽  
Infarct Core ◽  
Vessel Occlusion ◽  
Good Functional Outcome ◽  
Volumetric Assessment

Introduction: Perfusion imaging has emerged as an imaging tool to select patients with acute ischemic stroke (AIS) secondary to large vessel occlusion (LVO) for endovascular treatment (EVT). We aim to compare an automated method to assess the infarct ischemic core (IC) in Non-Contrast Computed Tomography (NCCT) with Computed Tomography Perfusion (CTP) imaging and its ability to predict functional outcome and final infarct volume (FIV). Methods: 494 patients with anterior circulation stroke treated with EVT were included. Volumetric assessment of IC in NCCT (eA-IC) was calculated using eASPECTS™ (Brainomix, Oxford). CTP was processed using availaible software considering CTP-IC as volume of Cerebral Blood Flow (CBF) <30% comparing with the contralateral hemisphere. FIV was calculated in patients with complete recanalization using a semiautomated method with a NCCT performed 48-72 hours after EVT. Complete recanalization was considered as modified Thrombolysis In Cerebral Ischemia (mTICI) ≥2B after EVT. Good functional outcome was defined as modified Rankin score (mRs) ≤2 at 90 days. Statistical analysis was performed to assess the correlation between EA-IC and CTP-IC and its ability to predict prognosis and FIV. Results: Median eA-IC and CTP-IC were 16 (IQR 7-31) and 8 (IQR 0-28), respectively. 419 patients (85%) achieved complete recanalization, and their median FIV was 17.5cc (IQR 5-52). Good functional outcome was achieved in 230 patients (47%). EA-IC and CTP-IC had moderate correlation between them (r=0.52, p<0.01) and similar correlation with FIV (r=0.52 and 0.51, respectively, p<0.01). Using ROC curves, both methods had similar performance in its ability to predict good functional outcome (EA-IC AUC 0.68 p<0.01, CTP-IC AUC 0.66 p<0.01). Multivariate analysis adjusted by confounding factors showed that eA-IC and CTP-IC predicted good functional outcome (for every 10cc and >40cc, OR 1.5, IC1.3-1.8, p<0.01 and OR 1.3, IC1.1-1.5, p<0.01, respectively). Conclusion: Automated volumetric assessment of infarct core in NCCT has similar performance predicting prognosis and final infarct volume than CTP. Prospective studies should evaluate a NCCT-core / vessel occlusion penumbra missmatch as an alternative method to select patients for EVT.

Abstract WMP17: Computerized Tomography Perfusion to Characterize Lack of Clinical Improvement After Recanalization in Acute Ischemic Stroke

Stroke ◽  
2020 ◽  
Vol 51 (Suppl_1) ◽  
Author(s):  
Alvaro Garcia-Tornel ◽  
Marta Olive-Gadea ◽  
Marc Ribo ◽  
David Rodriguez-Luna ◽  
Jorge Pagola ◽  
...  
Keyword(s):  
Ischemic Stroke ◽  
Acute Ischemic Stroke ◽  
Functional Outcome ◽  
Infarct Volume ◽  
Significant Proportion ◽  
Hemorrhagic Transformation ◽  
Vessel Occlusion ◽  
Clinical Recovery ◽  
Good Functional Outcome ◽  
Significant Difference

A significant proportion of patients with acute ischemic stroke (AIS) treated with endovascular thrombectomy (EVT) present poor functional outcome despite recanalization. We aim to investigate computed tomography perfusion (CTP) patterns after EVT and their association with outcome Methods: Prospective study of anterior large vessel occlusion AIS patients who achieved complete recanalization (defined as modified Thrombolysis in Cerebral Ischemia (TICI) 2b - 3) after EVT. CTP was performed within 30 minutes post-EVT recanalization (POST-CTP): hypoperfusion was defined as volume of time to maximal arrival of contrast (Tmax) delay ≥6 seconds in the affected territory. Hyperperfusion was defined as visual increase in cerebral blood flow (CBF) and volume (CBV) with advanced Tmax compared with the unaffected hemisphere. Dramatic clinical recovery (DCR) was defined as a decrease of ≥8 points in NIHSS score at 24h or NIHSS≤2 and good functional outcome by mRS ≤2 at 3 months. Results: One-hundred and forty-one patients were included. 49 (34.7%) patients did not have any perfusion abnormality on POST-CTP, 60 (42.5%) showed hypoperfusion (median volume Tmax≥6s 17.5cc, IQR 6-45cc) and 32 (22.8%) hyperperfusion. DCR appeared in 56% of patients and good functional outcome in 55.3%. Post-EVT hypoperfusion was related with worse final TICI, and associated worse early clinical evolution, larger final infarct volume (p<0.01 for all) and was an independent predictor of functional outcome (OR 0.98, CI 0.97-0.99, p=0.01). Furthermore, POST-CTP identified patients with delayed improvement: in patients without DCR (n=62, 44%), there was a significant difference in post-EVT hypoperfusion volume according to functional outcome (hypoperfusion volume of 2cc in good outcome vs 11cc in poor outcome, OR 0.97 CI 0.93-0.99, p=0.04), adjusted by confounding factors. Hyperperfusion was not associated with worse outcome (p=0.45) nor symptomatic hemorrhagic transformation (p=0.55). Conclusion: Hypoperfusion volume after EVT is an accurate predictor of functional outcome. In patients without dramatic clinical recovery, hypoperfusion predicts good functional outcome and defines a “stunned-brain” pattern. POST-CTP may help to select EVT patients for additional therapies.

Abstract 1122‐000181: Collateral Circulation in Ischemic Stroke is Not Determined by Anatomical Variants of the Cerebral Arteries

2021 ◽  
Vol 1 (S1) ◽  
Author(s):  
Karolina Brzegowy ◽  
Bernard Solewski ◽  
Paweł Brzegowy ◽  
Agata Musiał ◽  
Tadeusz Popiela ◽  
...  
Keyword(s):  
Blood Flow ◽  
Ischemic Stroke ◽  
Collateral Circulation ◽  
Cerebral Arteries ◽  
Anatomical Variations ◽  
Detailed Knowledge ◽  
Collateral Blood Flow ◽  
Posterior Portion ◽  
Cortical Vein ◽  
Anatomical Variants

Introduction : In acute ischemic stroke, collateral circulation determines tissue fate and treatment results. The aim of this study was to evaluate the role of anatomical variations of the Circle of Willis (CoW) in formation of cerebral collateral blood flow in patients with acute M1 occlusion. Methods : This study was a retrospective assessment of radiological examinations of patients with stroke due to middle cerebral artery M1 segment occlusion. All patients underwent mechanical thrombectomy from January 2015 until March 2021. The anatomy of the CoW was assessed on initial CT‐angiography and DSA. CTA was utilized to grade cranial collateral vasculature status and cortical vein opacification score (COVES). Non‐contrast CT scans and ASPECTS scores (using RAPID software) were used to determine the ischemic area. Results : A total of 100 patients were included in the analysis (58 females and 42 males, mean age: 71.6 +/‐ 13.9). We classified the anatomy of the CoW according to its continuity as a full circle. Patients with fully continuous CoW (n = 19) had worse COVES scores than those with CoW incomplete at both anterior and posterior portion (n = 9) (89% vs 68% with COVES 0–2, p = 0.179). No statistically significant results were found when comparing the enhancement of collaterals between these two groups (p = 0.390). The COVES scores were similar for patients with complete and incomplete anterior portions of CoW (77% vs 80% with COVES 0–2, p = 0.812). Patients with incomplete posterior portions of CoW had lower COVES scores than those with complete (80% vs 67% with COVES 0–2, p = 0.206). No statistically significant differences were discovered when comparing different types of the posterior communicating artery (adult, transitional and fetal). Analysis of ischemic areas determined as ASPECTS scores pre‐ and post‐thrombectomy yielded no significant differences between any of the groups. Conclusions : Although certain variants of the CoW have been reported to increase the risk of ischemic stroke, our results show that the anatomy of CoW has no large effect on collateral blood flow during acute M1 occlusion. We presume that the greater role is played by pial arterioles than anatomical variants of major cerebral arteries in cerebral collateral circulation formation. Detailed knowledge about the factors that influence collateral blood flow is crucial as it may aid in identification of patients prone to worse outcomes of ischemic stroke. Anatomical variants of CoW do not play a major role in formation of cerebral collaterals.

Abstract T P26: Combining Clinical and Imaging Data to Develop a Highly Predictive Model of Outcomes in the MR RESCUE Trial

Stroke ◽  
2015 ◽  
Vol 46 (suppl_1) ◽  
Author(s):  
Chelsea S Kidwell ◽  
Reza Jahan ◽  
Jeffrey Gornbein ◽  
Jeffry R Alger ◽  
Val Nenov ◽  
...  
Keyword(s):  
Ischemic Stroke ◽  
Acute Ischemic Stroke ◽  
Infarct Volume ◽  
Patient Characteristics ◽  
Hemorrhagic Transformation ◽  
Imaging Data ◽  
Vascular Events ◽  
Vessel Occlusion ◽  
Intermediate Variables ◽  
Core Volume

Background: Identifying patient characteristics that predict outcomes in acute ischemic stroke may assist in triaging those who are candidates for endovascular therapies. We sought to identify predictors of outcome in the overall Mechanical Retrieval and Recanalization of Stroke Clots Using Embolectomy (MR RESCUE) cohort and compare results to the previously validated Totaled Health Risks in Vascular Events (THRIVE) score. Methods: MR RESCUE randomized 118 acute ischemic stroke patients with multimodal imaging to embolectomy or standard care within 8 hours of onset. For this analysis, we investigated 17 baseline variables (e.g. age, predicted core volume, time to enrollment) and 8 intermediate variables (e.g. hemorrhagic transformation, day 7 recanalization, final infarct volume) with the potential to impact outcomes (day 90 mRS). The baseline variables were analyzed employing bivariate and multivariate methods (random forest and logistic regression). Two models were developed, one including only significant baseline variables, and the second also incorporating significant intermediate variables. Results: A multivariate model (Table) employing only baseline covariates achieved an overall accuracy (C statistic) of 85% in predicting poor outcome (day 90 mRS 3-6) compared to 80.5% for the THRIVE score. A second model (Table) adding significant intermediate variables achieved 89% accuracy in predicting day 90 mRS. Conclusions: In the MR RESCUE trial, advanced imaging variables, including predicted core volume and site of vessel occlusion, contributed to a highly accurate multivariable model of outcome. In the development phase, this model achieved higher accuracy than the THRIVE score. Future studies are needed to validate this model in an independent cohort.

Association of collateral status and ischemic core growth in patients with acute ischemic stroke

Neurology ◽  
2020 ◽  
pp. 10.1212/WNL.0000000000011258
Author(s):  
Longting Lin ◽  
Jianhong Yang ◽  
Chushuang Chen ◽  
Huiqiao Tian ◽  
Andrew Bivard ◽  
...  
Keyword(s):  
Growth Rate ◽  
Ischemic Stroke ◽  
Acute Ischemic Stroke ◽  
Ct Perfusion ◽  
Study Cohort ◽  
Vessel Occlusion ◽  
Ischemic Core ◽  
Relationship Of ◽  
The Relationship ◽  
Linear Regressions

ObjectiveTo test the hypothesis that acute ischemic patients with poorer collaterals would have faster ischemic core growth, we included 2 cohorts in the study, cohort 1 of 342 patients for derivation and cohort 2 of 414 patients for validation purpose.MethodsAcute ischemic stroke patients with large vessel occlusion were included. Core growth rate was calculated by the following equation: Core growth rate = Acute core volume on CTP/Time from stroke onset to CTP. Collateral status was assessed by the ratio of severe hypoperfusion volume within the hypoperfusion region of CTP. The CTP collateral index was categorized in tertiles; for each tertile, core growth rate was summarized as median and inter-quartile range. Simple linear regressions were then performed to measure the predictive power of CTP collateral index in core growth rate.ResultsFor patients allocated to good collateral on CT perfusion (tertile 1 of collateral index), moderate collateral (tertile 2), and poor collateral (tertile 3), the median core growth rate was 2.93 mL/h (1.10–7.94), 8.65 mL/h (4.53–18.13), and 25.41 mL/h (12.83–45.07) respectively. Increments in the collateral index by 1% resulted in an increase of core growth by 0.57 mL/h (coefficient = 0.57, 95% confidence interval = [0.46, 0.68], p < 0.001). The relationship of core growth and CTP collateral index was validated in cohort 2. An increment in collateral index by 1% resulted in an increase of core growth by 0.59 mL/h (coefficient = 0.59 [0.48–0.71], p < 0.001) in cohort 2.ConclusionCollateral status is a major determinant of ischemic core growth.

scholarly journals Computed Tomography Perfusion–Based Machine Learning Model Better Predicts Follow-Up Infarction in Patients With Acute Ischemic Stroke

Stroke ◽  
2021 ◽  
Vol 52 (1) ◽  
pp. 223-231
Author(s):  
Hulin Kuang ◽  
Wu Qiu ◽  
Anna M. Boers ◽  
Scott Brown ◽  
Keith Muir ◽  
...  
Keyword(s):  
Computed Tomography ◽  
Blood Flow ◽  
Cerebral Blood Flow ◽  
Ischemic Stroke ◽  
Acute Ischemic Stroke ◽  
Infarct Volume ◽  
Interquartile Range ◽  
Time Dependent ◽  
Computed Tomography Perfusion

Background and Purpose: Prediction of infarct extent among patients with acute ischemic stroke using computed tomography perfusion is defined by predefined discrete computed tomography perfusion thresholds. Our objective is to develop a threshold-free computed tomography perfusion–based machine learning (ML) model to predict follow-up infarct in patients with acute ischemic stroke. Methods: Sixty-eight patients from the PRoveIT study (Measuring Collaterals With Multi-Phase CT Angiography in Patients With Ischemic Stroke) were used to derive a ML model using random forest to predict follow-up infarction voxel by voxel, and 137 patients from the HERMES study (Highly Effective Reperfusion Evaluated in Multiple Endovascular Stroke Trials) were used to test the derived ML model. Average map, T max , cerebral blood flow, cerebral blood volume, and time variables including stroke onset-to-imaging and imaging-to-reperfusion time, were used as features to train the ML model. Spatial and volumetric agreement between the ML model predicted follow-up infarct and actual follow-up infarct were assessed. Relative cerebral blood flow <0.3 threshold using RAPID software and time-dependent T max thresholds were compared with the ML model. Results: In the test cohort (137 patients), median follow-up infarct volume predicted by the ML model was 30.9 mL (interquartile range, 16.4–54.3 mL), compared with a median 29.6 mL (interquartile range, 11.1–70.9 mL) of actual follow-up infarct volume. The Pearson correlation coefficient between 2 measurements was 0.80 (95% CI, 0.74–0.86, P <0.001) while the volumetric difference was −3.2 mL (interquartile range, −16.7 to 6.1 mL). Volumetric difference with the ML model was smaller versus the relative cerebral blood flow <0.3 threshold and the time-dependent T max threshold ( P <0.001). Conclusions: A ML using computed tomography perfusion data and time estimates follow-up infarction in patients with acute ischemic stroke better than current methods.

Sign in / Sign up

Export Citation Format

Share Document