Automated quantitative assessment of cerebral edema after ischemic stroke using CSF volumetrics

Neuroimaging predictors of malignant brain oedema after thrombectomy in ischemic stroke: a systematic review and meta-analysis

BACKGROUND

We systematically reviewed neuroimaging predictors for malignant brain oedema (MBE) after thrombectomy in patients with ischemic stroke.

METHODS

We searched MEDLINE and EMBASE in November 2023 for studies of patients with ischemic stroke. We included studies investigating neuroimaging predictors or prediction models for MBE after thrombectomy. We estimated effect size for the association between predictors and MBE by odds ratios (ORs) or standardized mean differences (SMDs), and pooled results using random-effects modelling.

RESULTS

We included 19 studies (n = 6007) with 17 neuroimaging factors and 5 models. Lower Alberta Stroke Program Early CT scores (ASPECTS, n = 3052, SMD -1.84, 95% CI -2.52 - -1.16; df = 9) and longer extent of arterial occlusion at baseline were associated with higher risk of MBE. Post-thrombectomy ASPECTS was associated with MBE in general stroke patients (n = 453, SMD -2.91, -4.02 - -1.79; df = 1), but not in successfully reperfused patients (n = 110, SMD 0.24, -0.16 - 0.65). Successful reperfusion reduced risk of MBE (n = 4851, OR 0.39, 0.30-0.51; df = 13). Contrast enhancement on CT after thrombectomy was associated with higher risk of MBE (n = 998, OR 4.82, 2.53-9.20; df = 4). More reserved brain volume capacity (baseline: n = 683, OR 0.83, 0.77-0.91, p < .001; post-thrombectomy: n = 329, OR 0.53, 0.37-0.77, p < .001) and good collaterals (baseline: n = 2301, OR 0.14, 0.10-0.20, df = 3; post-thrombectomy: n = 1006, OR 0.28, 0.15-0.51; df = 2) were associated with lower risk of MBE.

CONCLUSION

Lower ASPECTS and longer arterial occlusion at baseline, and post-thrombectomy CT contrast enhancement increased risk of MBE. Reperfusion after thrombectomy, more reserved brain volume and good collaterals at baseline and post-thrombectomy reduced its risk.

Predictive Value of Machine Learning Models for Cerebral Edema Risk in Stroke Patients: A Meta-Analysis

INTRODUCTION

Stroke patients are at high risk of developing cerebral edema, which can have severe consequences. However, there are currently few effective tools for early identification or prediction of this risk. As machine learning (ML) is increasingly used in clinical practice, its effectiveness in predicting cerebral edema risk in stroke patients has been explored. Nonetheless, the lack of systematic evidence on its predictive value challenges the update of simple and user-friendly risk assessment tools. Therefore, we conducted a systematic review to evaluate the predictive utility of ML for cerebral edema in stroke patients.

METHODS

We searched PubMed, Embase, Web of Science, and the Cochrane Database up to February 21, 2024. The risk of bias in selected studies was assessed using a bias assessment tool for predictive models. Meta-analysis synthesized results from validation sets.

RESULTS

We included 22 studies with 25,096 stroke patients and 25 models, which were constructed using common and interpretable clinical features. In the validation cohort, the models achieved a concordance index (c-index) of 0.840 (95% CI: 0.810-0.871) for predicting poststroke cerebral edema, with a sensitivity of 0.76 (95% CI: 0.72-0.79) and a specificity of 0.87 (95% CI: 0.83-0.90).

CONCLUSION

ML models are significant in predicting poststroke cerebral edema, providing clinicians with a powerful prognostic tool. However, radiomics-based research was not included. We anticipate advancements in radiomics research to enhance the predictive power of ML for poststroke cerebral edema.

Evaluating the interaction between hemorrhagic transformation and cerebral edema on functional outcome after ischemic stroke

BACKGROUND

Hemorrhagic transformation (HT) and cerebral edema (CED) are both major complications following ischemic stroke, but few studies have evaluated their overlap. We evaluated the frequency and predictors of CED/HT overlap and whether their co-occurrence impacts functional outcome more than each in isolation.

METHODS

892 stroke patients enrolled in a prospective study had follow-up CT imaging evaluated for HT and CED; the latter was quantified using the ratio of hemispheric CSF volumes (with hemispheric CSF ratio < 0.90 used as the CED threshold). The interaction between HT and CED on functional outcome (using modified Rankin Scale at 3 months) was compared to that for each condition separately.

RESULTS

Among the 275 (31%) who developed HT, 233 (85%) manifested hemispheric CSF ratio < 0.9 (CED/HT), with this overlap group representing half of the 475 with measurable CED. Higher baseline NIHSS scores and larger infarct volumes were observed in the CED/HT group compared with those with CED or HT alone. Functional outcome was worse in those with CED/HT [median mRS 3 (IQR 2-5)] than those with CED [median 2 (IQR 1-4)] or HT alone [median 1 (IQR 0-2), p < 0.0001]. Overlap of CED/HT independently predicted worse outcome [OR 1.89 (95% CI: 1.12-3.18), p = 0.02] while HT did not; however, CED/HT was no longer associated with worse outcome after adjusting for severity of CED [adjusted OR 0.35 (95% CI: 0.23, 0.51) per 0.21 lower hemispheric CSF ratio, p < 0.001].

CONCLUSIONS

Most stroke patients with HT also have measurable CED. The co-occurrence of CED and HT occurs in larger and more severe strokes and is associated with worse functional outcome, although this is driven by greater severity of stroke-related edema in those with HT.

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.

Emerging frontiers of artificial intelligence and machine learning in ischemic stroke: a comprehensive investigation of state-of-the-art methodologies, clinical applications, and unraveling challenges

At present, stroke remains the second highest cause of death globally and a leading cause of disability. From 1990 to 2019, the absolute number of strokes worldwide increased by 70.0%, and the prevalence of stroke increased by 85.0%, causing millions of deaths and disability. Ischemic stroke accounts for the majority of strokes, which is caused by arterial occlusion. Effective primary prevention strategies, early diagnosis, and timely interventions such as rapid reperfusion are in urgent implementation to control ischemic stroke. Otherwise, the stroke burden will probably continue to grow across the world as a result of population aging and an ongoing high prevalence of risk factors. To help with the diagnosis and management of ischemic stroke, newer techniques such as artificial intelligence (AI) are highly anticipated and may bring a new revolution. AI is a recent fast-growing research area which aims to mimic cognitive processes through a number of techniques such as machine learning (ML) methods of random forest learning (RFL) and convolutional neural networks (CNNs). With the help of AI, several momentous milestones have already been attained across diverse dimensions of ischemic stroke. In the context of predictive, preventive, and personalized medicine (PPPM/3PM), we aim to transform stroke care from a reactive to a proactive and individualized paradigm. In this way, AI demonstrates strong clinical utility across all three levels of prevention in ischemic stroke. In this paper, we synoptically illustrated the history and current situation of AI and ML. Then, we summarized their clinical applications and efficacy in the management of stroke. We finally provided an outlook on how AI approaches might contribute to enhancing favorable outcomes after stroke and proposed our suggestions on developing AI-based PPPM strategies.

Supplementary Information

The online version contains supplementary material available at 10.1007/s13167-023-00343-3.

Correspondence between development of cytotoxic edema and cerebrospinal fluid volume and flow in the third ventricle after ischemic stroke

OBJECTIVES

The importance of monitoring cerebrospinal fluid for the development of edema in ischemic stroke has been emphasized; however, studies on the relationship between intraventricular cerebrospinal fluid behavior and edema through longitudinal observations and analysis are rare. This study aimed to investigate the correlation between the development of cytotoxic edema and cerebrospinal fluid volume and flow in the third ventricle after ischemic stroke.

MATERIALS AND METHODS

The ventricle and edema regions were obtained using apparent diffusion coefficients and T2 and subdivided into lateral/ventral 3rd ventricles and cytotoxic/vasogenic (or cyst) edema, respectively. In rat models of ischemic stroke, the volume and flow (via the pseudo-diffusion coefficient [D*]) of the ventricles and edema volumes were longitudinally monitored for up to 45 days after surgery.

RESULTS

The volume of cytotoxic edema increased in the hyperacute and acute phases, whereas the volume (r = -0.49) and median D* values (r = -0.48 in the anterior-posterior direction) of the ventral 3rd ventricle both decreased, showing negative correlations with the volume of cytotoxic edema. In contrast, the volume of vasogenic edema/cyst was positively correlated with the volume (r = 0.73) and median D* values (r = 0.78 in the anterior-posterior direction) of the lateral ventricle in the subacute and chronic phases.

CONCLUSIONS

This study showed that the evolution of cerebrospinal fluid volume and flow in the ventricles was associated with edema progression at different time points in the ischemic stroke brain. This provides an efficient framework for monitoring and quantifying the interplay between cerebrospinal fluid and edema.

Ischemic brain edema: Emerging cellular mechanisms and therapeutic approaches

Brain edema is one of the most devastating consequences of ischemic stroke. Malignant cerebral edema is the main reason accounting for the high mortality rate of large hemispheric strokes. Despite decades of tremendous efforts to elucidate mechanisms underlying the formation of ischemic brain edema and search for therapeutic targets, current treatments for ischemic brain edema remain largely symptom-relieving rather than aiming to stop the formation and progression of edema. Recent preclinical research reveals novel cellular mechanisms underlying edema formation after brain ischemia and reperfusion. Advancement in neuroimaging techniques also offers opportunities for early diagnosis and prediction of malignant brain edema in stroke patients to rapidly adopt life-saving surgical interventions. As reperfusion therapies become increasingly used in clinical practice, understanding how therapeutic reperfusion influences the formation of cerebral edema after ischemic stroke is critical for decision-making and post-reperfusion management. In this review, we summarize these research advances in the past decade on the cellular mechanisms, and evaluation, prediction, and intervention of ischemic brain edema in clinical settings, aiming to provide insight into future preclinical and clinical research on the diagnosis and treatment of brain edema after stroke.

Association Between Post-procedure Cerebral Blood Flow Velocity and Severity of Brain Edema in Acute Ischemic Stroke With Early Endovascular Therapy

Objectives

We aimed to investigate the association between post-procedure cerebral blood flow velocity (CBFV) and severity of brain edema in patients with acute ischemic stroke (AIS) who received early endovascular therapy (EVT).

Methods

We retrospectively included patients with AIS who received EVT within 24 h of onset between February 2016 and November 2021. Post-procedure CBFV of the middle cerebral artery was measured in the affected and the contralateral hemispheres using transcranial Doppler ultrasound. The severity of brain edema was measured using the three-level cerebral edema grading from the Safe Implementation of Thrombolysis in Stroke-Monitoring Study, with grades 2–3 indicating severe brain edema. The Association between CBFV parameters and severity of brain edema was analyzed.

Results

A total of 101 patients (mean age 64.2 years, 65.3% male) were included, of whom 56.3% (57/101) suffered brain edema [grade 1, 23 (22.8%); grade 2, 10 (9.9%); and grade 3, 24 (23.8%)]. Compared to patients with non-severe brain edema, patients with severe brain edema had lower affected/contralateral ratios of systolic CBFV (median 1 vs. 1.2, P = 0.020) and mean CBFV (median 0.9 vs. 1.3, P = 0.029). Multivariate logistic regression showed that severe brain edema was independently associated with affected/contralateral ratios of systolic CBFV [odds ratio (OR) = 0.289, 95% confidence interval (CI): 0.069–0.861, P = 0.028] and mean CBFV (OR = 0.278, 95% CI: 0.084–0.914, P = 0.035) after adjusting for potential confounders.

Conclusion

Post-procedure affected/contralateral ratio of CBFV may be a promising predictor of brain edema severity in patients with AIS who received early EVT.

Automated Measurement of Net Water Uptake From Baseline and Follow-Up CTs in Patients With Large Vessel Occlusion Stroke

Quantifying the extent and evolution of cerebral edema developing after stroke is an important but challenging goal. Lesional net water uptake (NWU) is a promising CT-based biomarker of edema, but its measurement requires manually delineating infarcted tissue and mirrored regions in the contralateral hemisphere. We implement an imaging pipeline capable of automatically segmenting the infarct region and calculating NWU from both baseline and follow-up CTs of large-vessel occlusion (LVO) patients. Infarct core is extracted from CT perfusion images using a deconvolution algorithm while infarcts on follow-up CTs were segmented from non-contrast CT (NCCT) using a deep-learning algorithm. These infarct masks were flipped along the brain midline to generate mirrored regions in the contralateral hemisphere of NCCT; NWU was calculated as one minus the ratio of densities between regions, removing voxels segmented as CSF and with HU outside thresholds of 20-80 (normal hemisphere and baseline CT) and 0-40 (infarct region on follow-up). Automated results were compared with those obtained using manually-drawn infarcts and an ASPECTS region-of-interest based method that samples densities within the infarct and normal hemisphere, using intraclass correlation coefficient (ρ). This was tested on serial CTs from 55 patients with anterior circulation LVO (including 66 follow-up CTs). Baseline NWU using automated core was 4.3% (IQR 2.6-7.3) and correlated with manual measurement (ρ = 0.80, p < 0.0001) and ASPECTS (r = -0.60, p = 0.0001). Automatically segmented infarct volumes (median 110-ml) correlated to manually-drawn volumes (ρ = 0.96, p < 0.0001) with median Dice similarity coefficient of 0.83 (IQR 0.72-0.90). Automated NWU was 24.6% (IQR 20-27) and highly correlated to NWU from manually-drawn infarcts (ρ = 0.98) and the sampling-based method (ρ = 0.68, both p < 0.0001). We conclude that this automated imaging pipeline is able to accurately quantify region of infarction and NWU from serial CTs and could be leveraged to study the evolution and impact of edema in large cohorts of stroke patients.

Severe cerebral edema in substance-related cardiac arrest patients

BACKGROUND

Studies of neurologic outcomes have found conflicting results regarding differences between patients with substance-related cardiac arrests (SRCA) and non-SRCA. We investigate the effects of SRCA on severe cerebral edema development, a neuroimaging intermediate endpoint for neurologic injury.

METHODS

327 out-of-hospital comatose cardiac arrest patients were retrospectively analyzed. Demographics and baseline clinical characteristics were examined. SRCA categorization was based on admission toxicology screens. Severe cerebral edema classification was based on radiology reports. Poor clinical outcomes were defined as discharge Cerebral Performance Category scores > 3.

RESULTS

SRCA patients (N = 86) were younger (P < 0.001), and more likely to have non-shockable rhythms (P < 0.001), be unwitnessed (P < 0.001), lower Glasgow Coma Scale scores (P < 0.001), absent brainstem reflexes (P < 0.05) and develop severe cerebral edema (P < 0.001) than non-SRCA patients (N = 241). Multivariable analyses found younger age (P < 0.001), female sex (P = 0.008), non-shockable rhythm (P = 0.01) and SRCA (P = 0.05) to be predictors of severe cerebral edema development. Older age (P < 0.001), non-shockable rhythm (P = 0.02), severe cerebral edema (P < 0.001), and absent pupillary light reflexes (P = 0.004) were predictors of poor outcomes. SRCA patients had higher proportion of brain deaths (P < 0.001) compared to non-SRCA patients.

CONCLUSIONS

SRCA results in higher rates of severe cerebral edema development and brain death. The absence of statistically significant differences in discharge outcomes or survival between SRCA and non-SRCA patients may be related to the higher rate of withdrawal of life-sustaining treatment (WLST) in the non-SRCA group. Future neuroprognostic studies may opt to include neuroimaging markers as intermediate measures of neurologic injury which are not influenced by WLST decisions.

MRI Radiomics Features From Infarction and Cerebrospinal Fluid for Prediction of Cerebral Edema After Acute Ischemic Stroke

Neuroimaging biomarkers that predict the edema after acute stroke may help clinicians provide targeted therapies and minimize the risk of secondary injury. In this study, we applied pretherapy MRI radiomics features from infarction and cerebrospinal fluid (CSF) to predict edema after acute ischemic stroke. MRI data were obtained from a prospective, endovascular thrombectomy (EVT) cohort that included 389 patients with acute stroke from two centers (dataset 1, n = 292; dataset 2, n = 97), respectively. Patients were divided into edema group (brain swelling and midline shift) and non-edema group according to CT within 36 h after therapy. We extracted the imaging features of infarct area on diffusion weighted imaging (DWI) (abbreviated as DWI), CSF on fluid-attenuated inversion recovery (FLAIR) (CSF_FLAIR) and CSF on DWI (CSF_DWI), and selected the optimum features associated with edema for developing models in two forms of feature sets (DWI + CSF_FLAIR and DWI + CSF_DWI) respectively. We developed seven ML models based on dataset 1 and identified the most stable model. External validations (dataset 2) of the developed stable model were performed. Prediction model performance was assessed using the area under the receiver operating characteristic curve (AUC). The Bayes model based on DWI + CSF_FLAIR and the RF model based on DWI + CSF_DWI had the best performances (DWI + CSF_FLAIR: AUC, 0.86; accuracy, 0.85; recall, 0.88; DWI + CSF_DWI: AUC, 0.86; accuracy, 0.84; recall, 0.84) and the most stability (RSD% in DWI + CSF_FLAIR AUC: 0.07, RSD% in DWI + CSF_DWI AUC: 0.09), respectively. External validation showed that the AUC of the Bayes model based on DWI + CSF_FLAIR was 0.84 with accuracy of 0.77 and area under precision-recall curve (auPRC) of 0.75, and the AUC of the RF model based on DWI + CSF_DWI was 0.83 with accuracy of 0.81 and the auPRC of 0.76. The MRI radiomics features from infarction and CSF may offer an effective imaging biomarker for predicting edema.

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.

Role of the noninvasive imaging techniques in monitoring and understanding the evolution of brain edema

Human brain injury elicits accumulation of water within the brain due to a variety of pathophysiological processes. As our understanding of edema emerged two temporally (and cellular) distinct processes were identified, cytotoxic and vasogenic edema. The emergence of both types of edema is reflected by the temporal evolution and is influenced by the underlying pathology (type and extent). However, this two-edema compartment model does not adequately describe the transition between cytotoxic and vasogenic edema. Hence, a third category has been proposed, termed ionic edema, that is observed in the transition between cytotoxic and vasogenic edema. Magnetic resonance neuroimaging of edema today primarily utilizes T2-weighted (T2WI) and diffusion-weighted imaging (DWI). Clinical diagnostics and translational science studies have clearly demonstrated the temporal ability of both T2WI and DWI to monitor edema content and evolution. DWI measures water mobility within the brain reflecting cytotoxic edema. T2WI at later time points when vasogenic edema develops visualizes increased water content in the brain. Clinically relevant imaging modalities, including ultrasound and positron emission tomography, are not typically used to assess edema. In sum, edema imaging is an important cornerstone of clinical diagnostics and translational studies and can guide effective therapeutics manage edema and improve patient outcomes.