Stroke Localization and Association with Health Outcomes Using Clinical CT Images

• Activity Number: 170
• Type: Topic Contributed
• Date/Time: Monday, August 10, 2015 : 10:30 AM to 12:20 PM
• Sponsor: ENAR
• Author(s): Ciprian Crainiceanu*
• Companies: The Johns Hopkins University
• Keywords: brain ; stroke ; CT ; big data ; neuroimaging ; high dimensional

Abstract

Qualitative radiologic description of intracranial hemorrhage (ICH) location has not been a robust clinical marker of ICH severity. Using advanced registration for computed tomography (CT) brain scans, we quantify the ICH location and its association with stroke outcomes. We analyzed 111 scans from 111 patients enrolled in the MISTIE (Minimally Invasive Surgery plus recombinant-tissue plasminogen activator for Intracerebral Evacuation) trial. We registered CT scans to a CT template, estimated a 3-dimensional map of ICH engagement location, and derived regions predictive of 2 severity scores: the National Institutes of Health Stroke Scale (NIHSS) and Glasgow Coma Scale (GCS) scores. We compared the prediction performance of these regions to using location information determined by human readers. We conclude that quantitative measures of ICH location using advanced CT imaging processing provide finer and more predictive anatomic information than that provided by expert human readers. I will discuss methodological problems associated with this cross-sectional analysis and future plans for longitudinal analyses of the association between stroke location and disease severity.