Coronary lumen segmentation using graph cuts and robust kernel regression
2009-09-21
In Book
pp 528-539.
(Volume 5636)
| Related Files |
|---|
|
Redirect to publisher's version
(publisher's version.url.txt, 46 bytes) |
This paper presents a novel method for segmenting the coronary lumen in CTA data. The method is based on graph cuts, with edge-weights depending on the intensity of the centerline, and robust kernel regression. A quantitative evaluation in 28 coronary arteries from 12 patients is performed by comparing the semi-automatic segmentations to manual annotations. This evaluation showed that the method was able to segment the coronary arteries with high accuracy, compared to manually annotated segmentations, which is reflected in a Dice coefficient of 0.85 and average symmetric surface distance of 0.22 mm.
Keywords
- Medical imaging
- Coronary arteries
- Image segmentation
- Dice coefficient
- Centerlines
- Coronary lumen
- Edge weights
- Graph cut
- Data processing
- Manual annotation
- Kernel regression
- Novel methods
- Quantitative evaluation
- Semi-automatic segmentation
- Symmetric surfaces
