Coronary lumen segmentation using graph cuts and robust kernel regression
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.
|Centerlines, Coronary arteries, Coronary lumen, Data processing, Dice coefficient, Edge weights, Graph cut, Image segmentation, Kernel regression, Manual annotation, Medical imaging, Novel methods, Quantitative evaluation, Semi-automatic segmentation, Symmetric surfaces|
|Organisation||Erasmus MC: University Medical Center Rotterdam|
Schaap, M.M, Neefjes, L.A.E, Metz, C.T, van der Giessen, A.G, Weustink, A.C, Mollet, N.R.A, … Niessen, W.J. (2009). Coronary lumen segmentation using graph cuts and robust kernel regression. Retrieved from http://hdl.handle.net/1765/17397