Response by Kauw et al to Letter Regarding Article, "Intracranial Cerebrospinal Fluid Volume as a Predictor of Malignant Middle Cerebral Artery Infarction"

CSF-Based Volumetric Imaging Biomarkers Highlight Incidence and Risk Factors for Cerebral Edema After Ischemic Stroke

BACKGROUND

Cerebral edema has primarily been studied using midline shift or clinical deterioration as end points, which only captures the severe and delayed manifestations of a process affecting many patients with stroke. Quantitative imaging biomarkers that measure edema severity across the entire spectrum could improve its early detection, as well as identify relevant mediators of this important stroke complication.

METHODS

We applied an automated image analysis pipeline to measure the displacement of cerebrospinal fluid (ΔCSF) and the ratio of lesional versus contralateral hemispheric cerebrospinal fluid (CSF) volume (CSF ratio) in a cohort of 935 patients with hemispheric stroke with follow-up computed tomography scans taken a median of 26 h (interquartile range 24-31) after stroke onset. We determined diagnostic thresholds based on comparison to those without any visible edema. We modeled baseline clinical and radiographic variables against each edema biomarker and assessed how each biomarker was associated with stroke outcome (modified Rankin Scale at 90 days).

RESULTS

The displacement of CSF and CSF ratio were correlated with midline shift (r = 0.52 and - 0.74, p < 0.0001) but exhibited broader ranges. A ΔCSF of greater than 14% or a CSF ratio below 0.90 identified those with visible edema: more than half of the patients with stroke met these criteria, compared with only 14% who had midline shift at 24 h. Predictors of edema across all biomarkers included a higher National Institutes of Health Stroke Scale score, a lower Alberta Stroke Program Early CT score, and lower baseline CSF volume. A history of hypertension and diabetes (but not acute hyperglycemia) predicted greater ΔCSF but not midline shift. Both ΔCSF and a lower CSF ratio were associated with worse outcome, adjusting for age, National Institutes of Health Stroke Scale score, and Alberta Stroke Program Early CT score (odds ratio 1.7, 95% confidence interval 1.3-2.2 per 21% ΔCSF).

CONCLUSIONS

Cerebral edema can be measured in a majority of patients with stroke on follow-up computed tomography using volumetric biomarkers evaluating CSF shifts, including in many without visible midline shift. Edema formation is influenced by clinical and radiographic stroke severity but also by chronic vascular risk factors and contributes to worse stroke outcomes.

Predictors of malignant middle cerebral artery infarction after endovascular thrombectomy: results of DIRECT-MT trial

OBJECTIVES

Predictors of malignant middle cerebral artery infarction (mMCAi) in patients after intravenous thrombolysis were well documented, but the risk factors of mMCAi after endovascular thrombectomy (EVT) were not fully explored. Therefore, the present study aimed to investigate the predictors of mMCAi after EVT in stroke patients.

METHODS

This was a secondary analysis of the DIRECT-MT trial. Patients who underwent EVT for the occlusions of MCA and/or intracranial internal carotid artery were analyzed. Primary outcome was the occurrence of mMCAi after EVT. Demographic, clinical, imaging, and treatment data were recorded, and multivariate logistic regression analysis was used to identify independent predictors. All of the candidate predictors were included, and forward elimination was applied to establish the most effective predictive model. Predictive ability and calibration of the model were assessed using the area under the receiver operating characteristic curve (AUC) and Hosmer-Lemeshow test, respectively.

RESULTS

Of 559 enrolled patients, 74 (13.2%) patients developed mMCAi. Predictors of mMCAi included unsuccessful reperfusion, higher serum glucose, lower Alberta Stroke Project Early Computed Tomography Change Score (ASPECTS), higher clot burden score (CBS), lower collateral score, and higher pass number of thrombectomy device. AUC of predictive model integrating all independent variables was 0.836. The Hosmer-Lemeshow test showed appropriate calibration (p = 0.859).

CONCLUSIONS

Reperfusion, serum glucose, ASPECTS, CBS, collateral, and pass number of thrombectomy device were associated with the occurrence of mMCAi in stroke patients after EVT, while alteplase treatment was not. Our findings might facilitate the early identification and management of stroke patients at a high risk of mMCAi.

KEY POINTS

• A total of 13.2% of stroke patients with large vessel occlusion of anterior circulation developed mMCAi after EVT. • The occurrence of mMCAi had a definite negative impact on the outcome for stroke patients. • Reperfusion, serum glucose, ASPECTS, CBS, collateral score, and the pass number of thrombectomy device were associated with the occurrence of mMCAi after EVT in stroke patients.

Evaluation and Prediction of Post-stroke Cerebral Edema Based on Neuroimaging

Cerebral edema is a common complication of acute ischemic stroke that leads to poorer functional outcomes and substantially increases the mortality rate. Given that its negative effects can be reduced by more intensive monitoring and evidence-based interventions, the early identification of patients with a high risk of severe edema is crucial. Neuroimaging is essential for the assessment and prediction of edema. Simple markers, such as midline shift and hypodensity volume on computed tomography, have been used to evaluate edema in clinical trials; however, advanced techniques can be applied to examine the underlying mechanisms. In this study, we aimed to review current imaging tools in the assessment and prediction of cerebral edema to provide guidance for using these methods in clinical practice.

Accelerating Prediction of Malignant Cerebral Edema After Ischemic Stroke with Automated Image Analysis and Explainable Neural Networks

BACKGROUND

Malignant cerebral edema is a devastating complication of stroke, resulting in deterioration and death if hemicraniectomy is not performed prior to herniation. Current approaches for predicting this relatively rare complication often require advanced imaging and still suffer from suboptimal performance. We performed a pilot study to evaluate whether neural networks incorporating data extracted from routine computed tomography (CT) imaging could enhance prediction of edema in a large diverse stroke cohort.

METHODS

An automated imaging pipeline retrospectively extracted volumetric data, including cerebrospinal fluid (CSF) volumes and the hemispheric CSF volume ratio, from baseline and 24 h CT scans performed in participants of an international stroke cohort study. Fully connected and long short-term memory (LSTM) neural networks were trained using serial clinical and imaging data to predict those who would require hemicraniectomy or die with midline shift. The performance of these models was tested, in comparison with regression models and the Enhanced Detection of Edema in Malignant Anterior Circulation Stroke (EDEMA) score, using cross-validation to construct precision-recall curves.

RESULTS

Twenty of 598 patients developed malignant edema (12 required surgery, 8 died). The regression model provided 95% recall but only 32% precision (area under the precision-recall curve [AUPRC] 0.74), similar to the EDEMA score (precision 28%, AUPRC 0.66). The fully connected network did not perform better (precision 33%, AUPRC 0.71), but the LSTM model provided 100% recall and 87% precision (AUPRC 0.97) in the overall cohort and the subgroup with a National Institutes of Health Stroke Scale (NIHSS) score ≥ 8 (p = 0.0001 vs. regression and fully connected models). Features providing the most predictive importance were the hemispheric CSF ratio and NIHSS score measured at 24 h.

CONCLUSIONS

An LSTM neural network incorporating volumetric data extracted from routine CT scans identified all cases of malignant cerebral edema by 24 h after stroke, with significantly fewer false positives than a fully connected neural network, regression model, and the validated EDEMA score. This preliminary work requires prospective validation but provides proof of principle that a deep learning framework could assist in selecting patients for surgery prior to deterioration.

Cerebral Edema in Patients With Large Hemispheric Infarct Undergoing Reperfusion Treatment: A HERMES Meta-Analysis

BACKGROUND AND PURPOSE

Whether reperfusion into infarcted tissue exacerbates cerebral edema has treatment implications in patients presenting with extensive irreversible injury. We investigated the effects of endovascular thrombectomy and reperfusion on cerebral edema in patients presenting with radiological evidence of large hemispheric infarction at baseline.

METHODS

In a systematic review and individual patient-level meta-analysis of 7 randomized controlled trials comparing thrombectomy versus medical therapy in anterior circulation ischemic stroke published between January 1, 2010, and May 31, 2017 (Highly Effective Reperfusion Using Multiple Endovascular Devices collaboration), we analyzed the association between thrombectomy and reperfusion with maximal midline shift (MLS) on follow-up imaging as a measure of the space-occupying effect of cerebral edema in patients with large hemispheric infarction on pretreatment imaging, defined as diffusion-magnetic resonance imaging or computed tomography (CT)-perfusion ischemic core 80 to 300 mL or noncontrast CT-Alberta Stroke Program Early CT Score ≤5. Risk of bias was assessed using the Cochrane tool.

RESULTS

Among 1764 patients, 177 presented with large hemispheric infarction. Thrombectomy and reperfusion were associated with functional improvement (thrombectomy common odds ratio =2.30 [95% CI, 1.32-4.00]; reperfusion common odds ratio =4.73 [95% CI, 1.66-13.52]) but not MLS (thrombectomy β=-0.27 [95% CI, -1.52 to 0.98]; reperfusion β=-0.78 [95% CI, -3.07 to 1.50]) when adjusting for age, National Institutes of Health Stroke Score, glucose, and time-to-follow-up imaging. In an exploratory analysis of patients presenting with core volume >130 mL or CT-Alberta Stroke Program Early CT Score ≤3 (n=76), thrombectomy was associated with greater MLS after adjusting for age and National Institutes of Health Stroke Score (β=2.76 [95% CI, 0.33-5.20]) but not functional improvement (odds ratio, 1.71 [95% CI, 0.24-12.08]).

CONCLUSIONS

In patients presenting with large hemispheric infarction, thrombectomy and reperfusion were not associated with MLS, except in the subgroup with very large core volume (>130 mL) in whom thrombectomy was associated with increased MLS due to space-occupying ischemic edema. Mitigating cerebral edema-mediated secondary injury in patients with very large infarcts may further improve outcomes after reperfusion therapies.

Malignant infarction after endovascular treatment: Incidence and prediction

BACKGROUND

Early prediction of malignant infarction may guide treatment decisions. For patients who received endovascular treatment, the risk of malignant infarction is unknown and risk factors are unrevealed.

AIMS

The objective of this study is to estimate the incidence of malignant infarction after endovascular treatment in patients with an occlusion of the anterior circulation, to identify independent risk factors, and to establish a model for prediction.

METHODS

We analyzed patients who received endovascular treatment for a large vessel occlusion in the anterior circulation within 6.5 h after symptom onset, included in the Dutch MR CLEAN Registry between March 2014 and June 2016. We compared patients with and without malignant infarction. Candidate predictors were incorporated in a multivariable binary logistic regression model. The final prediction model was established using backward elimination. Discrimination and calibration were evaluated with the area under the receiver operating characteristic curve (AUROC) and the Hosmer-Lemeshow test.

RESULTS

Of 1445 patients, 82 (6%) developed malignant infarction. Independent predictors were lower age, higher National Institutes of Health Stroke Scale (NIHSS), lower alberta stroke program early CT score (ASPECTS), internal carotid artery occlusion, lower collateral score, longer times from onset to groin puncture, and unsuccessful reperfusion. The AUROC of a prediction model combining these features was 0.83 (95% confidence interval (CI): 0.79-0.88) and the Hosmer-Lemeshow test indicated appropriate calibration (P = 0.937).

CONCLUSION

The risk of malignant infarction after endovascular treatment started within 6.5 h of stroke onset is approximately 6%. Successful reperfusion decreases the risk. A prediction model combining easily retrievable measures of age, ASPECTS, collateral status, and reperfusion shows good discrimination between patients who will develop malignant infarction and those who will not.

Net Water Uptake Calculated in Standardized and Blindly Outlined Regions of the Middle Cerebral Artery Territory Predicts the Development of Malignant Edema in Patients With Acute Large Hemispheric Infarction

Background and purpose: Previous studies have demonstrated that Net Water Uptake (NWU) is associated with the development of malignant edema (ME). The current study aimed to investigate whether NWU calculated in standardized and blindly outlined regions of the middle cerebral artery can predict the development of ME. Methods: We retrospectively included 119 patients suffering from large hemispheric infarction within onset of 24 h. The region of the middle cerebral artery territory was blindly outlined in a standard manner to calculate NWU. Patients were divided into two groups according to the occurrence of ME, which is defined as space-occupying infarct requiring decompressive craniotomy or death due to cerebral hernia in 7 days from onset. The clinical characteristics were analyzed, and the receiver operating characteristic curve (ROC curve) was used to assess the predictive ability of NWU and other factors for ME. Results: Multivariable analysis showed that NWU was an independent predictor of ME (OR 1.168, 95% CI 1.041-1.310). According to the ROC curve, NWU≥8.127% identified ME with good predictive power (AUC 0.734, sensitivity 0.656, specificity 0.862). Conclusions: NWU calculated in standardized and blindly outlined regions of the middle cerebral artery territory is also a good predictor for the development of ME in patients with large hemispheric infarction.

Fully Automated Segmentation of Head CT Neuroanatomy Using Deep Learning

Purpose

To develop a deep learning model that segments intracranial structures on head CT scans.

Materials and Methods

In this retrospective study, a primary dataset containing 62 normal noncontrast head CT scans from 62 patients (mean age, 73 years; age range, 27-95 years) acquired between August and December 2018 was used for model development. Eleven intracranial structures were manually annotated on the axial oblique series. The dataset was split into 40 scans for training, 10 for validation, and 12 for testing. After initial training, eight model configurations were evaluated on the validation dataset and the highest performing model was evaluated on the test dataset. Interobserver variability was reported using multirater consensus labels obtained from the test dataset. To ensure that the model learned generalizable features, it was further evaluated on two secondary datasets containing 12 volumes with idiopathic normal pressure hydrocephalus (iNPH) and 30 normal volumes from a publicly available source. Statistical significance was determined using categorical linear regression with P < .05.

Results

Overall Dice coefficient on the primary test dataset was 0.84 ± 0.05 (standard deviation). Performance ranged from 0.96 ± 0.01 (brainstem and cerebrum) to 0.74 ± 0.06 (internal capsule). Dice coefficients were comparable to expert annotations and exceeded those of existing segmentation methods. The model remained robust on external CT scans and scans demonstrating ventricular enlargement. The use of within-network normalization and class weighting facilitated learning of underrepresented classes.

Conclusion

Automated segmentation of CT neuroanatomy is feasible with a high degree of accuracy. The model generalized to external CT scans as well as scans demonstrating iNPH.Supplemental material is available for this article.© RSNA, 2020.

A web based dynamic MANA Nomogram for predicting the malignant cerebral edema in patients with large hemispheric infarction

Background

For large hemispheric infarction (LHI), malignant cerebral edema (MCE) is a life-threatening complication with a mortality rate approaching 80%. Establishing a convenient prediction model of MCE after LHI is vital for the rapid identification of high-risk patients as well as for a better understanding of the potential mechanism underlying MCE.

Methods

One hundred forty-two consecutive patients with LHI within 24 h of onset between January 1, 2016 and August 31, 2019 were retrospectively reviewed. MCE was defined as patient death or received decompressive hemicraniectomy (DHC) with obvious mass effect (≥ 5 mm midline shift or Basal cistern effacement). Binary logistic regression was performed to identify independent predictors of MCE. Independent prognostic factors were incorporated to build a dynamic nomogram for MCE prediction.

Results

After adjusting for confounders, four independent factors were identified, including previously known atrial fibrillation (KAF), midline shift (MLS), National Institutes of Health Stroke Scale (NIHSS) and anterior cerebral artery (ACA) territory involvement. To facilitate the nomogram use for clinicians, we used the “Dynnom” package to build a dynamic MANA (acronym for MLS, ACA territory involvement, NIHSS and KAF) nomogram on web (http://www.MANA-nom.com) to calculate the exact probability of developing MCE. The MANA nomogram’s C-statistic was up to 0.887 ± 0.041 and the AUC-ROC value in this cohort was 0.887 (95%CI, 0.828 ~ 0.934).

Conclusions

Independent MCE predictors included KAF, MLS, NIHSS, and ACA territory involvement. The dynamic MANA nomogram is a convenient, practical and effective clinical decision-making tool for predicting MCE after LHI in Chinese patients.