Utilization of Emergent Neuroimaging for Thrombolysis-Eligible Stroke Patients

Large vessel occlusion detection by non-contrast CT using artificial ıntelligence

INTRODUCTION

Computer vision models have been used to diagnose some disorders using computer tomography (CT) and magnetic resonance (MR) images. In this work, our objective is to detect large and small brain vessel occlusion using a deep feature engineering model in acute of ischemic stroke.

METHODS

We use our dataset. which contains 324 patient's CT images with two classes; these classes are large and small brain vessel occlusion. We divided the collected image into horizontal and vertical patches. Then, pretrained AlexNet was utilized to extract deep features. Here, fc6 and fc7 (sixth and seventh fully connected layers) layers have been used to extract deep features from the created patches. The generated features from patches have been concatenated/merged to generate the final feature vector. In order to select the best combination from the generated final feature vector, an iterative selector (iterative neighborhood component analysis-INCA) has been used, and this selector has chosen 43 features. These 43 features have been used for classification. In the last phase, we used a kNN classifier with tenfold cross-validation.

RESULTS

By using 43 features and a kNN classifier, our AlexNet-based deep feature engineering model surprisingly attained 100% classification accuracy.

CONCLUSION

The obtained perfect classification performance clearly demonstrated that our proposal could separate large and small brain vessel occlusion detection in non-contrast CT images. In this aspect, this model can assist neurology experts with the early recanalization chance.

Combining Early Ischemic Change and Collateral Extent for Functional Outcomes After Endovascular Therapy: An Analysis From AcT Trial

BACKGROUND

Early ischemic change and collateral extent are colinear with ischemic core volume (ICV). We investigated the relationship between a combined score using the Alberta Stroke Program Early Computed Tomography Score and multiphase computed tomography angiography (mCTA) collateral extent, named mCTA-ACE score, on functional outcomes in endovascular therapy-treated patients.

METHODS

We performed a post hoc analysis of a subset of endovascular therapy-treated patients from the Alteplase Compared to Tenecteplase trial which was conducted between December 2019 and January 2022 at 22 centers across Canada. Ten-point mCTA collateral corresponding to M2 to M6 regions of the Alberta Stroke Program Early Computed Tomography Score grid was evaluated as 0 (poor), 1 (moderate), or 2 (normal) and additively combined with the 10-point Alberta Stroke Program Early Computed Tomography Score to produce a 20-point mCTA-ACE score. We investigated the association of mCTA-ACE score with modified Rankin Scale score ≤2 and return to prestroke level of function at 90 to 120 days using mixed-effects logistic regression. In the subset of patients who underwent baseline computed tomography perfusion imaging, we compared the mCTA-ACE score and ICV for outcome prediction.

RESULTS

Among 1577 intention-to-treat population in the trial, 368 (23%; 179 men; median age, 73 years) were included, with Alberta Stroke Program Early Computed Tomography Score, mCTA collateral, and combination of both (mCTA-ACE score: median [interquartile range], 8 [7-10], 9 [8-10], and 17 [16-19], respectively). The probability of modified Rankin Scale score ≤2 and return to prestroke level of function increased for each 1-point increase in mCTA-ACE score (odds ratio, 1.16 [95% CI, 1.06-1.28] and 1.22 [95% CI, 1.06-1.40], respectively). Among 173 patients in whom computed tomography perfusion data was assessable, the mCTA-ACE score was inversely correlated with ICV (ρ=-0.46; P<0.01). The mCTA-ACE score was comparable to ICV to predict a modified Rankin Scale score ≤2 and return to prestroke level of function (C statistics 0.71 versus 0.69 and 0.68 versus 0.64, respectively).

CONCLUSIONS

The mCTA-ACE score had a significant positive association with functional outcomes after endovascular therapy and had a similar predictive performance as ICV.

Viz LVO versus Rapid LVO in detection of large vessel occlusion on CT angiography for acute stroke

BACKGROUND

Endovascular thrombectomy improves outcomes and reduces mortality for large vessel occlusion (LVO) and is time-sensitive. Computer automation may aid in the early detection of LVOs, but false values may lead to alarm desensitization. We compared Viz LVO and Rapid LVO for automated LVO detection.

METHODS

Data were retrospectively extracted from Rapid LVO and Viz LVO running concurrently from January 2022 to January 2023 on CT angiography (CTA) images compared with a radiologist interpretation. We calculated diagnostic accuracy measures and performed a McNemar test to look for a difference between the algorithms' errors. We collected demographic data, comorbidities, ejection fraction (EF), and imaging features and performed a multiple logistic regression to determine if any of these variables predicted the incorrect classification of LVO on CTA.

RESULTS

360 participants were included, with 47 large vessel occlusions. Viz LVO and Rapid LVO had a specificity of 0.96 and 0.85, a sensitivity of 0.87 and 0.87, a positive predictive value of 0.75 and 0.46, and a negative predictive value of 0.98 and 0.97, respectively. A McNemar test on correct and incorrect classifications showed a statistically significant difference between the two algorithms' errors (P=0.00000031). A multiple logistic regression showed that low EF (Viz P=0.00125, Rapid P=0.0286) and Modified Woodcock Score >1 (Viz P=0.000198, Rapid P=0.000000975) were significant predictors of incorrect classification.

CONCLUSION

Rapid LVO produced a significantly larger number of false positive values that may contribute to alarm desensitization, leading to missed alarms or delayed responses. EF and intracranial atherosclerosis were significant predictors of incorrect predictions.

Stroke mimics: incidence, aetiology, clinical features and treatment

Mimics account for almost half of hospital admissions for suspected stroke. Stroke mimics may present as a functional (conversion) disorder or may be part of the symptomatology of a neurological or medical disorder. While many underlying conditions can be recognized rapidly by careful assessment, a significant proportion of patients unfortunately still receive thrombolysis and admission to a high-intensity stroke unit with inherent risks and unnecessary costs. Accurate diagnosis is important as recurrent presentations may be common in many disorders. A non-contrast CT is not sufficient to make a diagnosis of acute stroke as the test may be normal very early following an acute stroke. Multi-modal CT or magnetic resonance imaging (MRI) may be helpful to confirm an acute ischaemic stroke and are necessary if stroke mimics are suspected. Treatment in neurological and medical mimics results in prompt resolution of the symptoms. Treatment of functional disorders can be challenging and is often incomplete and requires early psychiatric intervention.

Effect of different thresholds for CT perfusion volumetric analysis on estimated ischemic core and penumbral volumes

Purpose

This single-center study compared three threshold settings for automated analysis of the ischemic core (IC) and penumbral volumes using computed tomographic perfusion, and their accuracy for predicting final infarct volume (FIV) in patients with anterior circulation acute ischemic stroke (AIS).

Methods

Fifty-two consecutive AIS patients undergoing mechanical thrombectomy (November 2015–March 2018) were included. Perfusion images were retrospectively analyzed using a single CT Neuro perfusion application (syngo.via 4.1, Siemens Healthcare GmbH). Three threshold values (S1–S3) were derived from another commercial package (RAPID; iSchema View) (S1), up-to-date syngo.via default values (S2), and adapted values for syngo.via from a reference study (S3). The results were compared with FIV determined by non-contrast CT.

Results

The median IC volume (mL) was 24.6 (interquartile range: 13.7–58.1) with S1 and 30.1 (20.1–53.1) with S2/S3. After removing the contralateral hemisphere from the analysis, the median IC volume decreased by 1.33(0–3.14) with S1 versus 9.13 (6.24–14.82) with S2/S3. The median penumbral volume (mL) was 74.52 (49.64–131.91), 77.86 (46.56–99.23), and 173.23 (125.86–200.64) for S1, S2, and S3, respectively. Limiting analysis to the affected hemisphere, the penumbral volume decreased by 1.6 (0.13–9.02), 19.29 (12.59–26.52), and 58.33 mL (45.53–74.84) for S1, S2, and S3, respectively. The correlation between IC and FIV was highest in patients with successful recanalization (n = 34, r = 0.784 for S1; r = 0.797 for S2/S3).

Conclusion

Optimizing thresholds significantly improves the accuracy of estimated IC and penumbral volumes. Current recommended values produce diversified results. International guidelines based on larger multicenter studies should be established to support the standardization of volumetric analysis in clinical decision-making.

Utilization and Availability of Advanced Imaging in Patients With Acute Ischemic Stroke

BACKGROUND

Recent clinical trials have established the efficacy of endovascular stroke therapy and intravenous thrombolysis using advanced imaging, particularly computed tomography perfusion (CTP). The availability and utilization of CTP for patients and hospitals that treat acute ischemic stroke (AIS), however, is uncertain.

METHODS

We performed a retrospective cross-sectional analysis using 2 complementary Medicare datasets, full sample Texas and 5% national fee-for-service data from 2014 to 2017. AIS cases were identified using International Classification of Diseases, Ninth Revision and International Classification of Diseases, Tenth Revision coding criteria. Imaging utilization performed in the initial evaluation of patients with AIS was derived using Current Procedural Terminology codes from professional claims. Primary outcomes were utilization of imaging in AIS cases and the change in utilization over time. Hospitals were defined as imaging modality-performing if they submitted at least 1 claim for that modality per calendar year. The National Medicare dataset was used to validate state-level findings, and a local hospital-level cohort was used to validate the claims-based approach.

RESULTS

Among 50 797 AIS cases in the Texas Medicare fee-for-service cohort, 64% were evaluated with noncontrast head CT, 17% with CT angiography, 3% with CTP, and 33% with magnetic resonance imaging. CTP utilization was greater in patients treated with endovascular stroke therapy (17%) and intravenous thrombolysis (9%). CT angiography (4%/y) and CTP (1%/y) utilization increased over the study period. These findings were validated in the National dataset. Among hospitals in the Texas cohort, 100% were noncontrast head CT-performing, 77% CT angiography-performing, and 14% CTP-performing in 2017. Most AIS cases (69%) were evaluated at non-CTP-performing hospitals. CTP-performing hospitals were clustered in urban areas, whereas large regions of the state lacked immediate access.

CONCLUSIONS

In state-wide and national Medicare fee-for-service cohorts, CTP utilization in patients with AIS was low, and most patients were evaluated at non-CTP-performing hospitals. These findings support the need for alternative means of screening for AIS recanalization therapies.

High-Performance Automated Anterior Circulation CT Angiographic Clot Detection in Acute Stroke: A Multireader Comparison

Background Identification of large vessel occlusion (LVO) is critical to the management of acute ischemic stroke and prerequisite to endovascular therapy in recent trials. Increasing volumes and data complexity compel the development of fast, reliable, and automated tools for LVO detection to facilitate acute imaging triage. Purpose To investigate the performance of an anterior circulation LVO detection platform in a large mixed sample of individuals with and without LVO at cerebrovascular CT angiography (CTA). Materials and Methods In this retrospective analysis, CTA data from recent cerebrovascular trials (CRISP [ClinicalTrials.gov NCT01622517] and DASH) were enriched with local repositories from 11 worldwide sites to balance demographic and technical variables in LVO-positive and LVO-negative examinations. CTA findings were reviewed independently by two neuroradiologists from different institutions for intracranial internal carotid artery (ICA) or middle cerebral artery (MCA) M1 LVO; these observers were blinded to all clinical variables and outcomes. An automated analysis platform was developed and tested for prediction of LVO presence and location relative to reader consensus. Discordance between readers with respect to LVO presence or location was adjudicated by a blinded tertiary reader at a third institution. Sensitivity, specificity, and receiver operating characteristics were assessed by an independent statistician, and subgroup analyses were conducted. Prespecified performance thresholds were set at a lower bound of the 95% CI of sensitivity and specificity of 0.8 or greater at mean times to notification of less than 3.5 minutes. Results A total of 217 study participants (mean age, 64 years ± 16 [standard deviation]; 116 men; 109 with positive findings of LVO) were evaluated. Prespecified performance thresholds were exceeded (sensitivity, 105 of 109 [96%; 95% CI: 91, 99]; specificity, 106 of 108 [98%; 95% CI: 94, 100]). Sensitivity and specificity estimates across age, sex, location, and vendor subgroups exceeded 90%. The area under the receiver operating characteristic curve was 99% (95% CI: 97, 100). Mean processing and notification time was 3 minutes 18 seconds. Conclusion The results confirm the feasibility of fast automated high-performance detection of intracranial internal carotid artery and middle cerebral artery M1 occlusions. © RSNA, 2021 See also the editorial by Kloska in this issue.

Deep Learning Based Software to Identify Large Vessel Occlusion on Noncontrast Computed Tomography

Background and Purpose:

Reliable recognition of large vessel occlusion (LVO) on noncontrast computed tomography (NCCT) may accelerate identification of endovascular treatment candidates. We aim to validate a machine learning algorithm (MethinksLVO) to identify LVO on NCCT.

Methods:

Patients with suspected acute stroke who underwent NCCT and computed tomography angiography (CTA) were included. Software detection of LVO (MethinksLVO) on NCCT was tested against the CTA readings of 2 experienced radiologists (NR-CTA). We used a deep learning algorithm to identify clot signs on NCCT. The software image output trained a binary classifier to determine LVO on NCCT. We studied software accuracy when adding National Institutes of Health Stroke Scale and time from onset to the model (MethinksLVO+).

Results:

From 1453 patients, 823 (57%) had LVO by NR-CTA. The area under the curve for the identification of LVO with MethinksLVO was 0.87 (sensitivity: 83%, specificity: 71%, positive predictive value: 79%, negative predictive value: 76%) and improved to 0.91 with MethinksLVO+ (sensitivity: 83%, specificity: 85%, positive predictive value: 88%, negative predictive value: 79%).

Conclusions:

In patients with suspected acute stroke, MethinksLVO software can rapidly and reliably predict LVO. MethinksLVO could reduce the need to perform CTA, generate alarms, and increase the efficiency of patient transfers in stroke networks.

Evaluating severity of white matter lesions from computed tomography images with convolutional neural network

PURPOSE

Severity of white matter lesion (WML) is typically evaluated on magnetic resonance images (MRI), yet the more accessible, faster, and less expensive method is computed tomography (CT). Our objective was to study whether WML can be automatically segmented from CT images using a convolutional neural network (CNN). The second aim was to compare CT segmentation with MRI segmentation.

METHODS

The brain images from the Helsinki University Hospital clinical image archive were systematically screened to make CT-MRI image pairs. Selection criteria for the study were that both CT and MRI images were acquired within 6 weeks. In total, 147 image pairs were included. We used CNN to segment WML from CT images. Training and testing of CNN for CT was performed using 10-fold cross-validation, and the segmentation results were compared with the corresponding segmentations from MRI.

RESULTS

A Pearson correlation of 0.94 was obtained between the automatic WML volumes of MRI and CT segmentations. The average Dice similarity index validating the overlap between CT and FLAIR segmentations was 0.68 for the Fazekas 3 group.

CONCLUSION

CNN-based segmentation of CT images may provide a means to evaluate the severity of WML and establish a link between CT WML patterns and the current standard MRI-based visual rating scale.

Retrospective single-centre experience on the effect of the DAWN trial on the utilisation pattern, diagnostic yield and accuracy of CT perfusions performed for suspected acute stroke

INTRODUCTION

The recent DAWN trial created a paradigm shift in acute stroke treatment from 'time-based' criteria (within 6 hours) to 'tissue-based' criteria dependent on advanced neuroimaging such as CT perfusion (CTP). This has expanded the thrombectomy window from 6 to 24 hours and has major implications for healthcare providers involved in acute stroke management. Our aim is to characterise changes in the utilisation, diagnostic yield and accuracy of CTP in the diagnosis of acute stroke in the year following the DAWN trial.

METHODS

Four hundred and forty-three patients underwent CTP for investigation of suspected stroke between 1 January 2017 and 31 December 2018. Studies in 2017 were considered 'pre-DAWN' while studies in 2018 were considered 'post-DAWN trial'. Electronic medical records were reviewed to extract patient characteristics. Each patient was categorised as early presenter (within 6 hours) or late presenter (over 6 hours). Chi-squared tests were performed to assess for differences in proportions between the 2 years.

RESULTS

There was a 50% increase in CTP performed from 177 in 2017 to 266 in 2018. The proportion of all CT that were CTP increased by 40% while CTP in late presenters increased by 70% in 2018. The sensitivity, specificity and proportions of CTP with a final diagnosis of acute stroke, TIA or nonstroke did not demonstrate statistically significant differences between the 2 years.

CONCLUSIONS

The CTP utilisation, particularly in late presenters, has substantially increased since the DAWN trial. This contributes to increasing burden on healthcare services related to the diagnosis and management of stroke.

Retrospective single-centre experience on the effect of the DAWN trial on the utilisation pattern, diagnostic yield and accuracy of CT perfusions performed for suspected acute stroke

INTRODUCTION

The recent DAWN trial created a paradigm shift in acute stroke treatment from 'time-based' criteria (within 6 hours) to 'tissue-based' criteria dependent on advanced neuroimaging such as CT perfusion (CTP). This has expanded the thrombectomy window from 6 to 24 hours and has major implications for healthcare providers involved in acute stroke management. Our aim is to characterise changes in the utilisation, diagnostic yield and accuracy of CTP in the diagnosis of acute stroke in the year following the DAWN trial.

METHODS

Four hundred and forty-three patients underwent CTP for investigation of suspected stroke between 1 January 2017 and 31 December 2018. Studies in 2017 were considered 'pre-DAWN' while studies in 2018 were considered 'post-DAWN trial'. Electronic medical records were reviewed to extract patient characteristics. Each patient was categorised as early presenter (within 6 hours) or late presenter (over 6 hours). Chi-squared tests were performed to assess for differences in proportions between the 2 years.

RESULTS

There was a 50% increase in CTP performed from 177 in 2017 to 266 in 2018. The proportion of all CT that were CTP increased by 40% while CTP in late presenters increased by 70% in 2018. The sensitivity, specificity and proportions of CTP with a final diagnosis of acute stroke, TIA or nonstroke did not demonstrate statistically significant differences between the 2 years.

CONCLUSIONS

The CTP utilisation, particularly in late presenters, has substantially increased since the DAWN trial. This contributes to increasing burden on healthcare services related to the diagnosis and management of stroke.

The Continued Role and Value of Imaging for Acute Ischemic Stroke

Advances in neuroimaging in the last 2 decades have revolutionized the management of acute ischemic stroke (AIS). Here we review the development of computed tomography (CT) and magnetic resonance imaging (MRI) modalities used to guide treatment of patients with AIS characterized by large vessel occlusion. In particular, we highlight recent randomized trials and their patient selection methodologies to detail the progression of these selection paradigms. With advanced imaging, distinction between at-risk penumbra and ischemic core in AIS may be performed using either CT or MRI. While limitations exist for methodologies to quantify core and penumbra, commercially available fully automated software packages provide useful information to guide treatment decisions. Randomized controlled trials implementing perfusion imaging to patient selection algorithms have demonstrated marked success in improving functional outcomes in patients with large vessel occlusions. As such, imaging has become a vital aspect of AIS treatment in selecting patients who may benefit from mechanical thrombectomy.

Radiological Eye Deviation as a Predictor of Large Vessel Occlusion in Acute Ischaemic Stroke

BACKGROUND

Detection of large vessel occlusion (LVO) is required for endovascular therapy in acute ischemic stroke (AIS) but CT angiography (CTA) is not always performed at primary stroke centers. Eye deviation on CT brain has been associated with improved stroke detection, but comparisons with angiographic status have been limited. This study sought to determine if radiological eye deviation was associated with LVO.

METHODS

All AIS patients given intravenous thrombolysis who had acute CTA performed in 2 stroke units were reviewed over 2013-2015 for the presence of LVO. Eye deviation was determined by 2 clinicians blinded to LVO status. Logistic regression was performed to determine which factors predicated LVO.

RESULTS

Total 195 AIS patients with acute CTA were identified; 124 (64%) had LVO. Median age was 72 (IQR 64-82) years, median National Institutes of Health Stroke Scale (NIHSS) was 12 (IQR 7-14). LVO patients had a higher NIHSS (15 versus 7, p < .01) and were more likely to have eye deviation on CT brain (71% versus 22.5%, p < .01). Logistic regression confirmed NIHSS score and eye deviation were associated with LVO, with odds ratios of 1.15 (per point) and 5.13 respectively. NIHSS less than equal to 11 gave greatest sensitivity (78.5%) and specificity (76.1%) for LVO with a positive predictive value of 84.7%. Eye deviation was similar with sensitivity 71%, specificity 77.5%, and 84.6%.

CONCLUSIONS

Eye deviation on CT brain is strongly associated with LVO. Presence of eye deviation on CT should alert clinicians to probability of LVO and for formal angiographic testing if not already performed.

DRINet for Medical Image Segmentation

Convolutional neural networks (CNNs) have revolutionized medical image analysis over the past few years. The U-Net architecture is one of the most well-known CNN architectures for semantic segmentation and has achieved remarkable successes in many different medical image segmentation applications. The U-Net architecture consists of standard convolution layers, pooling layers, and upsampling layers. These convolution layers learn representative features of input images and construct segmentations based on the features. However, the features learned by standard convolution layers are not distinctive when the differences among different categories are subtle in terms of intensity, location, shape, and size. In this paper, we propose a novel CNN architecture, called Dense-Res-Inception Net (DRINet), which addresses this challenging problem. The proposed DRINet consists of three blocks, namely a convolutional block with dense connections, a deconvolutional block with residual inception modules, and an unpooling block. Our proposed architecture outperforms the U-Net in three different challenging applications, namely multi-class segmentation of cerebrospinal fluid on brain CT images, multi-organ segmentation on abdominal CT images, and multi-class brain tumor segmentation on MR images.

Rapid Automated Quantification of Cerebral Leukoaraiosis on CT Images: A Multicenter Validation Study

Purpose To validate a random forest method for segmenting cerebral white matter lesions (WMLs) on computed tomographic (CT) images in a multicenter cohort of patients with acute ischemic stroke, by comparison with fluid-attenuated recovery (FLAIR) magnetic resonance (MR) images and expert consensus. Materials and Methods A retrospective sample of 1082 acute ischemic stroke cases was obtained that was composed of unselected patients who were treated with thrombolysis or who were undergoing contemporaneous MR imaging and CT, and a subset of International Stroke Thrombolysis-3 trial participants. Automated delineations of WML on images were validated relative to experts' manual tracings on CT images, and co-registered FLAIR MR imaging, and ratings were performed by using two conventional ordinal scales. Analyses included correlations between CT and MR imaging volumes, and agreements between automated and expert ratings. Results Automated WML volumes correlated strongly with expert-delineated WML volumes at MR imaging and CT (r2 = 0.85 and 0.71 respectively; P < .001). Spatial-similarity of automated maps, relative to WML MR imaging, was not significantly different to that of expert WML tracings on CT images. Individual expert WML volumes at CT correlated well with each other (r2 = 0.85), but varied widely (range, 91% of mean estimate; median estimate, 11 mL; range of estimated ranges, 0.2-68 mL). Agreements (κ) between automated ratings and consensus ratings were 0.60 (Wahlund system) and 0.64 (van Swieten system) compared with agreements between individual pairs of experts of 0.51 and 0.67, respectively, for the two rating systems (P < .01 for Wahlund system comparison of agreements). Accuracy was unaffected by established infarction, acute ischemic changes, or atrophy (P > .05). Automated preprocessing failure rate was 4%; rating errors occurred in a further 4%. Total automated processing time averaged 109 seconds (range, 79-140 seconds). Conclusion An automated method for quantifying CT cerebral white matter lesions achieves a similar accuracy to experts in unselected and multicenter cohorts.

ASPECTS (Alberta Stroke Program Early CT Score) Measurement Using Hounsfield Unit Values When Selecting Patients for Stroke Thrombectomy

BACKGROUND AND PURPOSE

The ASPECTS (Alberta Stroke Program Early CT Score) is a quantitate score that measures the extent of early ischemic changes. Our aim was to investigate how measurement of ASPECTS using Hounsfield unit (HU) values on initial noncontrast head computerized tomography (CT) correlates with the extent of final infarct on follow-up imaging.

METHODS

Cases of acute stroke from the middle cerebral artery M1 occlusion in which complete recanalization (TICI [Thrombolysis in Cerebral Infarction] 3) was achieved were included for analysis. Using HU ratio (HU affected/HU control hemisphere) and HU difference (HU control-HU affected hemisphere) values, ASPECTS was measured on initial CT imaging and correlated with final ASPECTS at 24 hours. The study cohort consisted of 41 patients with acute stroke from the M1 occlusion. The mean time from stroke symptoms onset to baseline head CT imaging was 264 minutes and from CT to TICI 3 recanalization was 142 minutes.

RESULTS

HU ratio within the 0.94 to 0.96 ranges showed the highest correlation coefficient and lowest mean and median errors with the final ASPECTS. The difference of 2.0 HU between the 2 hemispheres demonstrated the higher correlation coefficient (r=0.71; P<0.0001) and the lowest mean and median absolute errors (1.4 and 1, respectively).

CONCLUSIONS

We established a simple algorithm for rapid and accurate assessment of ASPECTS on baseline CT imaging to predict the extent of final stroke in patients with emergent large vessel occlusion who undergo endovascular revascularization.