Exhaustive Graph Cut-based Vasculature Reconstruction

Unberath M, Achenbach S, Fahrig R, Maier A (2016)

Publication Type: Conference contribution

Publication year: 2016

Publisher: IEEE Computer Society

Edited Volumes: Proceedings - International Symposium on Biomedical Imaging

Book Volume: 2016-June

Pages Range: 1143-1146

Conference Proceedings Title: Proceedings of the ISBI

Event location: Prague, CZ

ISBN: 9781479923502

URI: https://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2016/Unberath16-EGC.pdf

DOI: 10.1109/ISBI.2016.7493468

Abstract

We propose an exhaustive extension to graph cut-based coronary artery reconstruction from multiple views of a rotational angiography sequence. The reconstruction is formulated as an energy minimization problem that is solved using the a-expansion algorithm. We enforce reprojection-based data consistency and completeness conditions on the reconstructed centerline. The proposed strategy omits the need for selection and manual refinement of a reference view. A phantom study is used to assess the performance in 2D and 3D. The average reprojection error decreased from 1.32 ± 0.99mm to 0.54 ± 0.02 mm. Moreover, an increase in Dice score from 0.50 ± 0.04 mm to 0.59 ± 0.00 mm was observed, indicating superior volumetric reconstruction quality. The results suggest that the proposed extension removes the susceptibility to reference frame selection and manual interaction, while increasing reconstruction quality.

Authors with CRIS profile

Mathias Unberath Lehrstuhl für Informatik 14 (Bild- und Sprachverarbeitung) (LME) Stephan Achenbach Lehrstuhl für Innere Medizin II Andreas Maier Lehrstuhl für Informatik 5 (Mustererkennung)

Involved external institutions

Siemens Healthineers DE Germany (DE)

How to cite

APA:

Unberath, M., Achenbach, S., Fahrig, R., & Maier, A. (2016). Exhaustive Graph Cut-based Vasculature Reconstruction. In Proceedings of the ISBI (pp. 1143-1146). Prague, CZ: IEEE Computer Society.

MLA:

Unberath, Mathias, et al. "Exhaustive Graph Cut-based Vasculature Reconstruction." Proceedings of the International Symposium on Biomedical Imaging, Prague, CZ IEEE Computer Society, 2016. 1143-1146.

BibTeX: Download