Hannink J, Duits R, Bekkers E (2014)
Publication Language: English
Publication Type: Book chapter / Article in edited volumes
Publication year: 2014
Edited Volumes: Lecture Notes in Computer Science
Series: Medical Image Computing and Computer-Assisted Intervention – MICCAI 2014
City/Town: Cambridge, MA
Pages Range: 603-610
The multi–scale Frangi vesselness filter is an established tool
in (retinal) vascular imaging. However, it cannot properly cope with
crossings or bifurcations since it only looks for elongated structures.
Therefore, we disentangle crossings/bifurcations via (multiple scale) in-
vertible orientation scores and apply vesselness filters in this domain.
This new method via scale–orientation scores performs considerably bet-
ter at enhancing vessels throughout crossings and bifurcations than the
Frangi version. Both methods are evaluated on a public dataset. Per-
formance is measured by comparing ground truth data to the segmenta-
tion results obtained by basic thresholding and morphological component
analysis of the filtered images.
APA:
Hannink, J., Duits, R., & Bekkers, E. (2014). Crossing-preserving multi-scale vesselness. In Lecture Notes in Computer Science. (pp. 603-610). Cambridge, MA.
MLA:
Hannink, Julius, Remco Duits, and Erik Bekkers. "Crossing-preserving multi-scale vesselness." Lecture Notes in Computer Science. Cambridge, MA, 2014. 603-610.
BibTeX: Download