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

Sounds like a database that I've been screaming about for years. But looking at it, I can see nothing that survivors can use:

SNIPR: Stroke Neuroimaging Phenotype Repository

The latest here:

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

Hossein Mohammadian Foroushani¹, Rajat Dhar², Yasheng Chen³, Jenny Gurney⁴, Ali Hamzehloo², Jin-Moo Lee³ and Daniel S. Marcus^4*

• ¹Department of Electrical and System Engineering, School of Engineering, Washington University in St. Louis, St. Louis, MO, United States
• ²Division of Neurocritical Care, Department of Neurology, Washington University School of Medicine, St. Louis, MO, United States
• ³Division of Cerebrovascular Disease, Department of Neurology, Washington University School of Medicine, St. Louis, MO, United States
• ⁴Department of Radiology, Washington University School of Medicine, St. Louis, MO, United States

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.

Introduction

Stroke is the second leading cause of death throughout the world, and the leading cause of long-term disability (George et al., 2017). The management of acute stroke is now a time-sensitive emergency that requires organized multidisciplinary care. The early hours after stroke onset frequently map the trajectory of subsequent neurologic disability, complications, and outcomes. Big data analyses can provide an opportunity to implement precision medicine approaches to stroke (Liebeskind, 2018). Pooling of multi-center data sets can advance our understanding of the clinical and biologic factors contributing to outcomes. This has led to a surge of interest and effort to collaborate on stroke research by combining clinical and genomic databases to better understand the biology of stroke and its complications. One of the largest such collaborations [the International Stroke Genetics Consortium (ISGC)] has integrated data on stroke incidence and recovery with genetic data on over 60,000 cases to provide further novel insights into stroke biology (Malik, 2018). There has been special interest in acute stroke phenotypes and outcomes, leading to collaborations within the ISGC and the formation of the Genetics of Neurological Instability after Ischemic Stroke (GENISIS) multi-center study (Heitsch et al., 2021). GENESIS has acquired extensive clinical and genomic data on over 6,000 acute stroke patients.

Brain imaging has a key role in providing further insights about complications after stroke. Indeed, most stroke patients have at least one brain imaging study performed during their acute hospitalization, primarily for diagnostic purposes on presentation. Follow-up scans are often obtained to evaluate the size of infarction and to exclude the development of hemorrhagic transformation. An endeavor is underway to describe the design and rationale for the genetic analysis of acute and chronic cerebrovascular neuroimaging phenotypes detected on clinical magnetic resonance imaging (MRI) in patients with acute ischemic stroke within the scope of the MRI-GENetics Interface Exploration (MRI-GENIE) study (Giese et al., 2017, 2020). Another similar effort with focus on MRI data is Enhancing Neuroimaging Genetics through Meta-Analysis (ENIGMA) Stroke Recovery repository which tries to understand brain and behavior relationships using well-powered meta- and mega-analytic approaches. ENIGMA Stroke Recovery has data from over 2,100 stroke patients collected across 39 research studies and 10 countries around the world (Liew et al., 2020). Although MRI can provide detailed anatomic information, it is challenging to obtain in the acute setting so there is not enough sample which makes knowledge discovery and practical applications limited. Computed tomography (CT) is the most frequently employed modality for acute stroke imaging due to its widespread availability, lower cost, and greater speed of scanning (especially important in acutely unstable patients where “time is brain”) (Tong et al., 2014). Thus, many millions of CT exams of stroke patients with information on stroke location, infarct size, development of edema, and hemorrhagic transformation are available globally. The evaluation of these parameters is not scalable by human raters when leveraging imaging data from thousands of patients. As a result, a big data approach is required to assess images at scale, including identifying quantitative image features and developing automated tools to extract them. This imaging analysis can then be coupled with analysis of clinical and genomics data from these subjects, facilitating large-scale genomic analysis of acute complications after stroke that are best represented by imaging features (Dhar et al., 2018).

Given the potential of imaging to advance our understanding of stroke and its complications, the GENISIS study endeavored to share all clinically performed brain imaging on enrolled subjects. The Stroke Neuroimaging Phenotype Repository (SNIPR) was created as a stroke-focused medical imaging repository that could serve as a platform for this and other stroke-related research. SNIPR is based on the open source XNAT imaging informatics platform, developed at Washington University in St. Louis (WUSTL) (Marcus, 2007). SNIPR provides an environment to securely host and share clinical data and imaging scans from large international stroke cohorts. It also allows the development and deployment of image processing pipelines to extract imaging biomarkers from these stroke scans. SNIPR is deployed on a high-performance computing system that enables these pipelines to be executed as containerized applications at massive scale. SNIPR enables coupling the imaging results with clinical data, with the overarching aim of enabling a broad understanding of stroke progression and outcomes.