Name
Abstract | ||
|---|---|---|
In this paper, we present and study two local features for the tracking of vascular structures on 3D angiograms. The first one, Flux, measures the inward gradient flux through circular cross-sections. The second one, MFlux, introduces a non-linear penalization of asymmetric flux contributions to reduce false positive responses. Through a series of experiments on synthetic and real cardiac CT data, we discuss the properties of these features with respect to their parameters. We compare them to a selection of published vessel- dedicated features. We show that MFlux induces a particularly discriminative response landscape, which is a desirable property for tracking purposes on such large search spaces. A key characteristic of the proposed features is their simplicity of implementation and their high computational efficiency, enabling their practical use for advanced tracking strategies. |
Year | DOI | Venue |
|---|---|---|
2009 | 10.1109/ISBI.2009.5193040 | Boston, MA |
Keywords | Field | DocType |
angiocardiography,blood vessels,computerised tomography,feature extraction,medical image processing,3D angiograms,3D vascular tracking,asymmetric flux contributions,cardiac CT data,circular cross-sections,computational efficiency,flux-based features,inward gradient flux,nonlinear penalization,vascular structures,vessel tracking,Vascular features,gradient flux,vessel tracking | Computer vision,Pattern recognition,Computer science,Feature extraction,Robustness (computer science),Computed tomography,Artificial intelligence,Flux | Conference |
ISSN | ISBN | Citations |
1945-7928 E-ISBN : 978-1-4244-3932-4 | 978-1-4244-3932-4 | 12 |
PageRank | References | Authors |
0.76 | 13 | 4 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| David Lesage | 1 | 441 | 18.16 |
| Elsa D. Angelini | 2 | 740 | 60.44 |
| Isabelle Bloch | 3 | 2123 | 170.75 |
| Gareth Funka-Lea | 4 | 1383 | 63.84 |