Quantitative Serial CT Imaging-Derived Features Improve Prediction of Malignant Cerebral Edema after Ischemic Stroke

Association of large core middle cerebral artery stroke and hemorrhagic transformation with hospitalization outcomes

Historically, investigators have not differentiated between patients with and without hemorrhagic transformation (HT) in large core ischemic stroke at risk for life-threatening mass effect (LTME) from cerebral edema. Our objective was to determine whether LTME occurs faster in those with HT compared to those without. We conducted a two-center retrospective study of patients with ≥ 1/2 MCA territory infarct between 2006 and 2021. We tested the association of time-to-LTME and HT subtype (parenchymal, petechial) using Cox regression, controlling for age, mean arterial pressure, glucose, tissue plasminogen activator, mechanical thrombectomy, National Institute of Health Stroke Scale, antiplatelets, anticoagulation, temperature, and stroke side. Secondary and exploratory outcomes included mass effect-related death, all-cause death, disposition, and decompressive hemicraniectomy. Of 840 patients, 358 (42.6%) had no HT, 403 (48.0%) patients had petechial HT, and 79 (9.4%) patients had parenchymal HT. LTME occurred in 317 (37.7%) and 100 (11.9%) had mass effect-related deaths. Parenchymal (HR 8.24, 95% CI 5.46-12.42, p < 0.01) and petechial HT (HR 2.47, 95% CI 1.92-3.17, p < 0.01) were significantly associated with time-to-LTME and mass effect-related death. Understanding different risk factors and sequelae of mass effect with and without HT is critical for informed clinical decisions.

Early automated cerebral edema assessment following endovascular therapy: impact on stroke outcome

BACKGROUND

Cerebral edema (CED) is associated with poorer outcome in patients with acute ischemic stroke (AIS). The aim of the study was to investigate the factors contributing to greater early CED formation in patients with AIS who underwent endovascular therapy (EVT) and its association with functional outcome.

METHODS

We conducted a multicenter cohort study of patients with an anterior circulation AIS undergoing EVT. The volume of cerebrospinal fluid (CSF) was extracted from baseline and 24-hour follow-up CT using an automated algorithm. The severity of CED was quantified by the percentage reduction in CSF volume between CT scans (∆CSF). The primary endpoint was a shift towards an unfavorable outcome, assessed by modified Rankin Scale (mRS) score at 3 months. Multivariable ordinal logistic regression analyses were performed. The ∆CSF threshold that predicted unfavorable outcome was selected using receiver operating characteristic curve analysis.

RESULTS

We analyzed 201 patients (mean age 72.7 years, 47.8% women) in whom CED was assessable for 85.6%. Higher systolic blood pressure during EVT and failure to achieve modified Thrombolysis In Cerebral Infarction (mTICI) 3 were found to be independent predictors of greater CED. ∆CSF was independently associated with the probability of a one-point worsening in the mRS score (common odds ratio (cOR) 1.05, 95% CI 1.03 to 1.08) after adjusting for age, baseline mRS, National Institutes of Health Stroke Scale (NIHSS), and number of passes. Displacement of more than 25% of CSF was associated with an unfavorable outcome (OR 6.09, 95% CI 3.01 to 12.33) and mortality (OR 6.72, 95% CI 2.94 to 15.32).

CONCLUSIONS

Early CED formation in patients undergoing EVT was affected by higher blood pressure and incomplete reperfusion. The extent of early CED, measured by automated ∆CSF, was associated with worse outcomes.

Artificial Intelligence and Machine Learning Applications in Critically Ill Brain Injured Patients

The utilization of Artificial Intelligence (AI) and Machine Learning (ML) is paving the way for significant strides in patient diagnosis, treatment, and prognostication in neurocritical care. These technologies offer the potential to unravel complex patterns within vast datasets ranging from vast clinical data and EEG (electroencephalogram) readings to advanced cerebral imaging facilitating a more nuanced understanding of patient conditions. Despite their promise, the implementation of AI and ML faces substantial hurdles. Historical biases within training data, the challenge of interpreting multifaceted data streams, and the "black box" nature of ML algorithms present barriers to widespread clinical adoption. Moreover, ethical considerations around data privacy and the need for transparent, explainable models remain paramount to ensure trust and efficacy in clinical decision-making.This article reflects on the emergence of AI and ML as integral tools in neurocritical care, discussing their roles from the perspective of both their scientific promise and the associated challenges. We underscore the importance of extensive validation in diverse clinical settings to ensure the generalizability of ML models, particularly considering their potential to inform critical medical decisions such as withdrawal of life-sustaining therapies. Advancement in computational capabilities is essential for implementing ML in clinical settings, allowing for real-time analysis and decision support at the point of care. As AI and ML are poised to become commonplace in clinical practice, it is incumbent upon health care professionals to understand and oversee these technologies, ensuring they adhere to the highest safety standards and contribute to the realization of personalized medicine. This engagement will be pivotal in integrating AI and ML into patient care, optimizing outcomes in neurocritical care through informed and data-driven decision-making.

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.

Analysis of brain edema in RHAPSODY

BACKGROUND

Cerebral edema is a secondary complication of acute ischemic stroke, but its time course and imaging markers are not fully understood. Recently, net water uptake (NWU) has been proposed as a novel marker of edema.

AIMS

Studying the RHAPSODY trial cohort, we sought to characterize the time course of edema and test the hypothesis that NWU provides distinct information when added to traditional markers of cerebral edema after stroke by examining its association with other markers.

METHODS

A total of 65 patients had measurable supratentorial ischemic lesions. Patients underwent head computed tomography (CT), brain magnetic resonance imaging (MRI) scans, or both at the baseline visit and after 2, 7, 30, and 90 days following enrollment. CT and MRI scans were used to measure four imaging markers of edema: midline shift (MLS), hemisphere volume ratio (HVR), cerebrospinal fluid (CSF) volume, and NWU using semi-quantitative threshold analysis. Trajectories of the markers were summarized, as available. Correlations of the markers of edema were computed and the markers compared by clinical outcome. Regression models were used to examine the effect of 3K3A-activated protein C (APC) treatment.

RESULTS

Two measures of mass effect, MLS and HVR, could be measured on all imaging modalities, and had values available across all time points. Accordingly, mass effect reached a maximum level by day 7, normalized by day 30, and then reversed by day 90 for both measures. In the first 2 days after stroke, the change in CSF volume was associated with MLS (ρ = -0.57, p = 0.0001) and HVR (ρ = -0.66, p < 0.0001). In contrast, the change in NWU was not associated with the other imaging markers (all p ⩾ 0.49). While being directionally consistent, we did not observe a difference in the edema markers by clinical outcome. In addition, baseline stroke volume was associated with all markers (MLS (p < 0.001), HVR (p < 0.001), change in CSF volume (p = 0.003)) with the exception of NWU (p = 0.5). Exploratory analysis did not reveal a difference in cerebral edema markers by treatment arm.

CONCLUSIONS

Existing cerebral edema imaging markers potentially describe two distinct processes, including lesional water concentration (i.e. NWU) and mass effect (MLS, HVR, and CSF volume). These two types of imaging markers may represent distinct aspects of cerebral edema, which could be useful for future trials targeting this process.

Role of artificial intelligence and machine learning in the diagnosis of cerebrovascular disease

Introduction

Cerebrovascular diseases are known to cause significant morbidity and mortality to the general population. In patients with cerebrovascular disease, prompt clinical evaluation and radiographic interpretation are both essential in optimizing clinical management and in triaging patients for critical and potentially life-saving neurosurgical interventions. With recent advancements in the domains of artificial intelligence (AI) and machine learning (ML), many AI and ML algorithms have been developed to further optimize the diagnosis and subsequent management of cerebrovascular disease. Despite such advances, further studies are needed to substantively evaluate both the diagnostic accuracy and feasibility of these techniques for their application in clinical practice. This review aims to analyze the current use of AI and MI algorithms in the diagnosis of, and clinical decision making for cerebrovascular disease, and to discuss both the feasibility and future applications of utilizing such algorithms.

Methods

We review the use of AI and ML algorithms to assist clinicians in the diagnosis and management of ischemic stroke, hemorrhagic stroke, intracranial aneurysms, and arteriovenous malformations (AVMs). After identifying the most widely used algorithms, we provide a detailed analysis of the accuracy and effectiveness of these algorithms in practice.

Results

The incorporation of AI and ML algorithms for cerebrovascular patients has demonstrated improvements in time to detection of intracranial pathologies such as intracerebral hemorrhage (ICH) and infarcts. For ischemic and hemorrhagic strokes, commercial AI software platforms such as RapidAI and Viz.AI have bene implemented into routine clinical practice at many stroke centers to expedite the detection of infarcts and ICH, respectively. Such algorithms and neural networks have also been analyzed for use in prognostication for such cerebrovascular pathologies. These include predicting outcomes for ischemic stroke patients, hematoma expansion, risk of aneurysm rupture, bleeding of AVMs, and in predicting outcomes following interventions such as risk of occlusion for various endovascular devices. Preliminary analyses have yielded promising sensitivities when AI and ML are used in concert with imaging modalities and a multidisciplinary team of health care providers.

Conclusion

The implementation of AI and ML algorithms to supplement clinical practice has conferred a high degree of accuracy, efficiency, and expedited detection in the clinical and radiographic evaluation and management of ischemic and hemorrhagic strokes, AVMs, and aneurysms. Such algorithms have been explored for further purposes of prognostication for these conditions, with promising preliminary results. Further studies should evaluate the longitudinal implementation of such techniques into hospital networks and residency programs to supplement clinical practice, and the extent to which these techniques improve patient care and clinical outcomes in the long-term.

Point-of-care testing for cerebral edema types based on symmetric cancellation near-field coupling phase shift and support vector machine

BACKGROUND

Cerebral edema is an extremely common secondary disease in post-stroke. Point-of-care testing for cerebral edema types has important clinical significance for the precise management to prevent poor prognosis. Nevertheless, there has not been a fully accepted bedside testing method for that.

METHODS

A symmetric cancellation near-field coupling phase shift (NFCPS) monitoring system is established based on the symmetry of the left and right hemispheres and the fact that unilateral lesions do not affect healthy hemispheres. For exploring the feasibility of this system to reflect the occurrence and development of cerebral edema, 13 rabbits divided into experimental group (n = 8) and control group (n = 5) were performed 24-h NFCPS continuous monitoring experiments. After time difference offset and feature band averaging processing, the changing trend of NFCPS at the stages dominated by cytotoxic edema (CE) and vasogenic edema (VE), respectively, was analyzed. Furthermore, the features under the different time windows were extracted. Then, a discriminative model of cerebral edema types based on support vector machines (SVM) was established and performance of multiple feature combinations was compared.

RESULTS

The NFCPS monitoring outcomes of experimental group endured focal ischemia modeling by thrombin injection show a trend of first decreasing and then increasing, reaching the lowest value of - 35.05° at the 6th hour. Those of control group do not display obvious upward or downward trend and only fluctuate around the initial value with an average change of - 0.12°. Furthermore, four features under the 1-h and 2-h time windows were extracted. Based on the discriminative model of cerebral edema types, the classification accuracy of 1-h window is higher than 90% and the specificity is close to 1, which is almost the same as the performance of the 2-h window.

CONCLUSION

This study proves the feasibility of NFCPS technology combined with SVM to distinguish cerebral edema types in a short time, which is promised to become a new solution for immediate and precise management of dehydration therapy after ischemic stroke.

Big Data in Stroke: How to Use Big Data to Make the Next Management Decision

The last decade has seen significant advances in the accumulation of medical data, the computational techniques to analyze that data, and corresponding improvements in management. Interventions such as thrombolytics and mechanical thrombectomy improve patient outcomes after stroke in selected patients; however, significant gaps remain in our ability to select patients, predict complications, and understand outcomes. Big data and the computational methods needed to analyze it can address these gaps. For example, automated analysis of neuroimaging to estimate the volume of brain tissue that is ischemic and salvageable can help triage patients for acute interventions. Data-intensive computational techniques can perform complex risk calculations that are too cumbersome to be completed by humans, resulting in more accurate and timely prediction of which patients require increased vigilance for adverse events such as treatment complications. To handle the accumulation of complex medical data, a variety of advanced computational techniques referred to as machine learning and artificial intelligence now routinely complement traditional statistical inference. In this narrative review, we explore data-intensive techniques in stroke research, how it has informed the management of stroke patients, and how current work could shape clinical practice in the future.

Machine learning prediction of malignant middle cerebral artery infarction after mechanical thrombectomy for anterior circulation large vessel occlusion

OBJECTIVE

Prediction of malignant middle cerebral artery infarction (MMI) could identify patients for early intervention. We trained and internally validated a ML model that predicts MMI following mechanical thrombectomy (MT) for ACLVO.

METHODS

All patients who underwent MT for ACLVO between 2015 - 2021 at a single institution were reviewed. Data was divided into 80% training and 20% test sets. 10 models were evaluated on the training set. The top 3 models underwent hyperparameter tuning using grid search with nested 5-fold CV to optimize the area under the receiver operating curve (AUROC). Tuned models were evaluated on the test set and compared to logistic regression.

RESULTS

A total of 381 patients met the inclusion criteria. There were 50 (13.1%) patients who developed MMI. Out of the 10 ML models screened on the training set, the top 3 performing were neural network (median AUROC 0.78, IQR 0.72 - 0.83), support vector machine ([SVM] median AUROC 0.77, IQR 0.72 - 0.83), and random forest (median AUROC 0.75, IQR 0.68 - 0.81). On the test set, random forest (median AUROC 0.78, IQR 0.73 - 0.83) and neural network (median AUROC 0.78, IQR 0.73 - 0.83) were the top performing models, followed by SVM (median AUROC 0.77, IQR 0.70 - 0.83). These scores were significantly better than those for logistic regression (AUROC 0.72, IQR 0.66 - 0.78), individual risk factors, and the Malignant Brain Edema score (p < 0.001 for all).

CONCLUSION

ML models predicted MMI with good discriminative ability. They outperformed standard statistical techniques and individual risk factors.

Medical management of cerebral edema in large hemispheric infarcts

Acute ischemic stroke confers a high burden of morbidity and mortality globally. Occlusion of large vessels of the anterior circulation, namely the intracranial carotid artery and middle cerebral artery, can result in large hemispheric stroke in ~8% of these patients. Edema from stroke can result in a cascade effect leading to local compression of capillary perfusion, increased stroke burden, elevated intracranial pressure, herniation and death. Mortality from large hemispheric stroke is generally high and surgical intervention may reduce mortality and improve good outcomes in select patients. For those patients who are not eligible candidates for surgical decompression either due timing, medical co-morbidities, or patient and family preferences, the mainstay of medical management for cerebral edema is hyperosmolar therapy. Other neuroprotectants for cerebral edema such as glibenclamide are under investigation. This review will discuss current guidelines and evidence for medical management of cerebral edema in large hemispheric stroke as well as discuss important neuromonitoring and critical care management targeted at reducing morbidity and mortality for these patients.

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.

Automated quantitative lesion water uptake in acute stroke is a predictor of malignant cerebral edema

OBJECTIVES

Net water uptake (NWU) has been shown to have a linear relationship with brain edema. Based on an automated-Alberta Stroke Program Early Computed Tomography Score (ASPECTS) technique, we automatically derived NWU from baseline multimodal computed tomography (CT), namely ASPECTS-NWU. We aimed to determine if ASPECTS-NWU can predict the development of malignant cerebral edema (MCE).

METHODS

One hundred and forty-six patients with large-vessel occlusion were retrospectively enrolled. Quantitative NWU based on automated-ASPECTS was measured both on nonenhanced CT (NECT) and CT angiography (CTA), namely NECT-ASPECT-NWU and CTA-ASPECTS-NWU. The correlation between ASPECTS-NWU and cerebral edema (CED) grades was calculated using Spearman rank correlation. Univariate logistic regression was used to assess the effect of radiological and clinical features on MCE, and a multivariable model with significant factors from the univariate regression analysis was built. Receiver operating characteristic (ROC) was obtained and area under curve (AUC) was compared.

RESULTS

CTA-ASPECTS-NWU had a moderate positive correlation with CED grades (r = 0.62; 95% confidence interval [CI], 0.51-0.71; p < 0.001). The CTA-ASPECTS-NWU performed better than the NECT-ASPECTS-NWU with AUC: 0.88 vs. 0.71 (p < 0.001). Multivariable logistic regression model integrating CTA-ASPECTS-NWU, collateral score, and age showed the CTA-ASPECTS-NWU was an independent predictor of MCE with an AUC of 0.94 (95% CI: 0.90-0.98; p < 0.001).

CONCLUSIONS

This study demonstrates that ASPECTS-NWU is a quantitative predictor of MCE after large-vessel occlusion of the middle cerebral artery territory. The multivariable logistic regression model may enhance the identification of patients with MCE needing anti-edematous treatment.

KEY POINTS

• The automated-ASPECTS technique can automatically detect the affected regions with early ischemic changes and NWU could be manually calculated. • The CTA-ASPECTS-NWU performs better than the NECT-ASPECTS-NWU on predicting the development of MCE. • The multivariable logistic regression model may enhance the identification of patients with MCE needing anti-edematous treatment.

Machine Learning in Action: Stroke Diagnosis and Outcome Prediction

The application of machine learning has rapidly evolved in medicine over the past decade. In stroke, commercially available machine learning algorithms have already been incorporated into clinical application for rapid diagnosis. The creation and advancement of deep learning techniques have greatly improved clinical utilization of machine learning tools and new algorithms continue to emerge with improved accuracy in stroke diagnosis and outcome prediction. Although imaging-based feature recognition and segmentation have significantly facilitated rapid stroke diagnosis and triaging, stroke prognostication is dependent on a multitude of patient specific as well as clinical factors and hence accurate outcome prediction remains challenging. Despite its vital role in stroke diagnosis and prognostication, it is important to recognize that machine learning output is only as good as the input data and the appropriateness of algorithm applied to any specific data set. Additionally, many studies on machine learning tend to be limited by small sample size and hence concerted efforts to collate data could improve evaluation of future machine learning tools in stroke. In the present state, machine learning technology serves as a helpful and efficient tool for rapid clinical decision making while oversight from clinical experts is still required to address specific aspects not accounted for in an automated algorithm. This article provides an overview of machine learning technology and a tabulated review of pertinent machine learning studies related to stroke diagnosis and outcome prediction.

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.

The Stroke Neuro-Imaging Phenotype Repository: An Open Data Science Platform for Stroke Research

Stroke is one of the leading causes of death and disability worldwide. Reducing this disease burden through drug discovery and evaluation of stroke patient outcomes requires broader characterization of stroke pathophysiology, yet the underlying biologic and genetic factors contributing to outcomes are largely unknown. Remedying this critical knowledge gap requires deeper phenotyping, including large-scale integration of demographic, clinical, genomic, and imaging features. Such big data approaches will be facilitated by developing and running processing pipelines to extract stroke-related phenotypes at large scale. Millions of stroke patients undergo routine brain imaging each year, capturing a rich set of data on stroke-related injury and outcomes. The Stroke Neuroimaging Phenotype Repository (SNIPR) was developed as a multi-center centralized imaging repository of clinical computed tomography (CT) and magnetic resonance imaging (MRI) scans from stroke patients worldwide, based on the open source XNAT imaging informatics platform. The aims of this repository are to: (i) store, manage, process, and facilitate sharing of high-value stroke imaging data sets, (ii) implement containerized automated computational methods to extract image characteristics and disease-specific features from contributed images, (iii) facilitate integration of imaging, genomic, and clinical data to perform large-scale analysis of complications after stroke; and (iv) develop SNIPR as a collaborative platform aimed at both data scientists and clinical investigators. Currently, SNIPR hosts research projects encompassing ischemic and hemorrhagic stroke, with data from 2,246 subjects, and 6,149 imaging sessions from Washington University's clinical image archive as well as contributions from collaborators in different countries, including Finland, Poland, and Spain. Moreover, we have extended the XNAT data model to include relevant clinical features, including subject demographics, stroke severity (NIH Stroke Scale), stroke subtype (using TOAST classification), and outcome [modified Rankin Scale (mRS)]. Image processing pipelines are deployed on SNIPR using containerized modules, which facilitate replicability at a large scale. The first such pipeline identifies axial brain CT scans from DICOM header data and image data using a meta deep learning scan classifier, registers serial scans to an atlas, segments tissue compartments, and calculates CSF volume. The resulting volume can be used to quantify the progression of cerebral edema after ischemic stroke. SNIPR thus enables the development and validation of pipelines to automatically extract imaging phenotypes and couple them with clinical data with the overarching aim of enabling a broad understanding of stroke progression and outcomes.