Meeting Banner
Abstract #1966

Fully dimensional vessel segmentation in non-contrast-enhanced 3D PC-MRI image data.

Judith Zimmermann1,2, Lennart Tautz2, Christian Meierhofer3, Heiko Stern3, Bjoern Menze1, and Anja Hennemuth2

1Department of Computer Science, Technical University of Munich, Munich, Germany, 2Institute for Imaging Science and Computational Modeling in Cardiovascular Medicine, Charité Universitätsmedizin, Berlin, Germany, 3Department of Pediatric Cardiology, German Heart Center, Munich, Germany

Fully dimensional (spatial + temporal) segmentation of blood vessels is crucial to perform 3D PC-MRI based quantitative characterization of hemodynamics. However, most prior works neglect the temporal movement of vessels, making it a 3D-only segmentation problem. Therefore, the objective of this work was to show feasibility of a deformable-registration-based algorithm for 4D segmentation of the aorta. Performance of the proposed algorithm proved to be acceptable, with overall Dice index and Hausdorff distance of 0.86±0.04 and 3.63±0.75 mm, respectively.

This abstract and the presentation materials are available to members only; a login is required.

Join Here