Automated Assessment of Leptomeningeal Collaterals on CT Angiograms

点击翻译按钮获取中文摘要

 DESCRIPTION (provided by applicant): The primary goal of this study is to develop an automated scoring system of leptomeningeal collaterals based on CT angiography (CTA) as a quantitative assessment of acute stroke. Leptomeningeal collaterals provide an alternate path of blood flow in the setting of a proximal occlusion. The presence and effectiveness of leptomeningeal collaterals (i.e., "collateral status") will vary significantly from patient to patint. Collateral status has been shown to be correlated with both patient outcome and risk of hemorrhagic transformation, suggesting that rapid and accurate assessment of the collaterals would provide a powerful tool for treatment evaluation. The current gold standard for collateral scoring is performed by subjective analysis of retrograde filling in invasive digital subtraction angiograms (DSA). Though CTA is more limited than DSA in the direct evaluation of collaterals, the presence of collaterals may also be evaluated in CTA by the degree of vessel filling beyond the site of occlusion. Several manual assessment techniques based on CTA have been proposed in the literature, but all are subjective and require significant human intervention. Thus, we propose to develop an automated CTA-based collateral status assessment. The aims of our work are as follows: 1) adapt our vessel segmentation algorithms to collateral vessel assessment, 2) perform retrospective evaluation of the CTA derived collateral measurements against DSA in patients, and 3) conduct preliminary retrospective clinical evaluation of the CTA derived collateral measurements against patient outcome. This work brings together a strong yet diverse team, addresses a significant clinical problem with an innovative solution, and uses a two-pronged approach to commercialization involving protected IP and an open-source platform that promotes consulting revenue.