Abstract WP67: VESCA: Semi-Automated Segmentation of Cerebral Vasculature in Angiograms

Abstract

Background: Imaging the cerebrovasculature using digital subtraction angiography (DSA) is a critical step in the diagnosis and treatment of acute stroke. Interpretation and scoring of these DSA images is usually performed by visual review, introducing inter-reader variability that causes inconsistency in clinical trials. Recently, methods have been introduced to automatically quantify various metrics in DSA images, such as revascularization and blush score, and vessel extraction algorithms are often used as part of these methods. However, the results of those algorithms have not been thoroughly evaluated against manually determined groundtruth extraction results, due to a lack of tools for determining the ground truths. Methods: We present a dedicated software tool, VESCA (Vessel Segmentation for Cerebral Angiograms), for manually determining the groundtruths of DSA images to better evaluate vessel detection methods. VESCA interface allows the user to view and segment DSA images, producing a segmented, binary representation of the vasculature. The segmentation process is semi-automated thanks to the livewire segmentation technique, whereby user-selected points along vessel boundaries are automatically connected via the lowest cost path. Results: We have segmented angiograms from a database of 115 biplane DSA, resulting in a set of binary representations of the vessels. We are constructing a web-based system through which other researchers may access the database, and through which they may use the software to contribute segmented images. Conclusion: VESCA is simple to operate and requires minimal instruction. We anticipate that it will facilitate the development and improvement of automatic methods for quantitative DSA image analysis.