Imaging in StrokeNet

Liebeskind, David S; Albers, Gregory W.; Crawford, Karen; Derdeyn, Colin P.; George, Mark S.; Palesch, Yuko Y.; Toga, Arthur W.; Warach, Steven; Zhao, Wenle; Brott, Thomas G.; Sacco, Ralph L.; Khatri, Pooja; Saver, Jeffrey L.; Cramer, Steven C.; Wolf, Steven L.; Broderick, Joseph P.; Wintermark, Max

doi:10.1161/strokeaha.115.009479

Cited by 26 publications

(18 citation statements)

References 30 publications

(27 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This study provides proof-of-principle that we can automate brain imaging data analysis and obtain meaningful volumetric data on large cohorts of stroke patients. Such an approach, leveraging routinely obtained clinical imaging data or imaging obtained in clinical trials to advance the science of stroke is the pathway to realizing the potential of big data in brain imaging ( 18 ). One notable challenge of sharing brain imaging data is ensuring anonymization.…”

Section: Discussionmentioning

confidence: 99%

Application of Machine Learning to Automated Analysis of Cerebral Edema in Large Cohorts of Ischemic Stroke Patients

Dhar

Chen

et al. 2018

Front. Neurol.

View full text Add to dashboard Cite

Cerebral edema contributes to neurological deterioration and death after hemispheric stroke but there remains no effective means of preventing or accurately predicting its occurrence. Big data approaches may provide insights into the biologic variability and genetic contributions to severity and time course of cerebral edema. These methods require quantitative analyses of edema severity across large cohorts of stroke patients. We have proposed that changes in cerebrospinal fluid (CSF) volume over time may represent a sensitive and dynamic marker of edema progression that can be measured from routinely available CT scans. To facilitate and scale up such approaches we have created a machine learning algorithm capable of segmenting and measuring CSF volume from serial CT scans of stroke patients. We now present results of our preliminary processing pipeline that was able to efficiently extract CSF volumetrics from an initial cohort of 155 subjects enrolled in a prospective longitudinal stroke study. We demonstrate a high degree of reproducibility in total cranial volume registration between scans (R = 0.982) as well as a strong correlation of baseline CSF volume and patient age (as a surrogate of brain atrophy, R = 0.725). Reduction in CSF volume from baseline to final CT was correlated with infarct volume (R = 0.715) and degree of midline shift (quadratic model, p < 2.2 × 10−16). We utilized generalized estimating equations (GEE) to model CSF volumes over time (using linear and quadratic terms), adjusting for age. This model demonstrated that CSF volume decreases over time (p < 2.2 × 10−13) and is lower in those with cerebral edema (p = 0.0004). We are now fully automating this pipeline to allow rapid analysis of even larger cohorts of stroke patients from multiple sites using an XNAT (eXtensible Neuroimaging Archive Toolkit) platform. Data on kinetics of edema across thousands of patients will facilitate precision approaches to prediction of malignant edema as well as modeling of variability and further understanding of genetic variants that influence edema severity.

show abstract

Section: Discussionmentioning

confidence: 99%

Application of Machine Learning to Automated Analysis of Cerebral Edema in Large Cohorts of Ischemic Stroke Patients

Dhar

Chen

et al. 2018

Front. Neurol.

View full text Add to dashboard Cite

show abstract

“…Several databases have been founded, including the StrokeNet, NIH Imaging Workgroup, and the Stroke Imaging Research/Virtual International Stroke Trials Archive Collaboration. However, problems such as data non-standardization have posed challenges in the creation of easily accessible data repositories [76]. As an example, the StrokeNet consists of 25 regional centers and nearly 200 individual hospitals working in concert to advance cerebrovascular research.…”

Section: Overview Of Strategies and Tools (Fig 3)mentioning

confidence: 99%

Mandatory Neuroendovascular Evolution: Meeting the New Demands

et al. 2018

View full text Add to dashboard Cite

Background: Traditionally, patients undergoing acute ischemic strokes were candidates for mechanical thrombectomy if they were within the 6-h window from onset of symptoms. This timeframe would exclude many patient populations, such as wake-up strokes. However, the most recent clinical trials, DAWN and DEFUSE3, have expanded the window of endovascular treatment for acute ischemic stroke patients to within 24 h from symptom onset. This expanded window increases the number of potential candidates for endovascular intervention for emergent large vessel occlusions and raises the question of how to efficiently screen and triage this increase of patients. Summary: Abbreviated pre-hospital stroke scales can be used to guide EMS personnel in quickly deciding if a patient is undergoing a stroke. Telestroke networks connect remote hospitals to stroke specialists to improve the transportation time of the patient to a comprehensive stroke center for the appropriate level of care. Mobile stroke units, mobile interventional units, and helistroke reverse the traditional hub-and-spoke model by bringing imaging, tPA, and expertise to the patient. Smartphone applications and social media aid in educating patients and the public regarding acute and long-term stroke care. Key Messages: The DAWN and DEFUSE3 trials have expanded the treatment window for certain acute ischemic stroke patients with mechanical thrombectomy and subsequently have increased the number of potential candidates for endovascular intervention. This expansion brings patient screening and triaging to greater importance, as reducing the time from symptom onset to decision-to-treat and groin puncture can better stroke patient outcomes. Several strategies have been employed to address this issue by reducing the time of symptom onset to decision-to-treat time.

show abstract

“…NIH StrokeNet has hundreds of potential research participation sites and so provides an unprecedented opportunity to perform trials with investigations that address issues related to patient subgroups. Furthermore, investigators within the NIH StrokeNet network possess expertise spanning many potentially relevant fields including genetics, proteomics, bioengineering, and biomechanics; for example, the Imaging Group can advise regarding many forms of neuroimaging 39 . Such expertise may be incorporated into scientific aims to develop and validate best methods for understanding and defining those patient subgroups that are most likely to respond to a putative restorative/rehabilitation therapy.…”

Section: Specific Issues For Moving Stroke Recovery and Rehabilitatiomentioning

confidence: 99%