Send to

Choose Destination
Ann Biomed Eng. 2015 May;43(5):1223-34. doi: 10.1007/s10439-014-1184-4. Epub 2014 Nov 15.

Three-Dimensional Blood Vessel Segmentation and Centerline Extraction based on Two-Dimensional Cross-Section Analysis.

Author information

The Intervention Centre, Oslo University Hospital, Sognsvannsveien 20, 0372, Oslo, Norway,


The segmentation of tubular tree structures like vessel systems in volumetric datasets is of vital interest for many medical applications. In this paper we present a novel, semi-automatic method for blood vessel segmentation and centerline extraction, by tracking the blood vessel tree from a user-initiated seed point to the ends of the blood vessel tree. The novelty of our method is in performing only two-dimensional cross-section analysis for segmentation of the connected blood vessels. The cross-section analysis is done by our novel single-scale or multi-scale circle enhancement filter, used at the blood vessel trunk or bifurcation, respectively. The method was validated for both synthetic and medical images. Our validation has shown that the cross-sectional centerline error for our method is below 0.8 pixels and the Dice coefficient for our segmentation is 80% ± 2.7%. On combining our method with an optional active contour post-processing, the Dice coefficient for the resulting segmentation is found to be 94% ± 2.4%. Furthermore, by restricting the image analysis to the regions of interest and converting most of the three-dimensional calculations to two-dimensional calculations, the processing was found to be more than 18 times faster than Frangi vesselness with thinning, 8 times faster than user-initiated active contour segmentation with thinning and 7 times faster than our previous method.

[Indexed for MEDLINE]

Supplemental Content

Full text links

Icon for Springer
Loading ...
Support Center