Method details

Download PDF file of article
Vessel Segmentation Using Implicit Model-Guided Level Sets



Abstract:
This paper proposes an automatic segmentation method of vasculature that combines level-sets with an implicit 3D model of the vessels. First, a 3D vessel model from a set of initial centerlines is generated. This model is incorporated in the level set propagation to regulate the growth of the vessel contour. After evolving the level set, new centerlines are extracted and the diameter of vessels is re-estimated in order to generate a new vessel model. The propagation and re-modeling steps are repeated until convergence. The organizers of the 3D Cardiovascular Imaging: a MICCAI segmentation challenge report the following results for the 24 testing datasets. The sensitivity and PPV are 0.26, 0.40 for QCA and 0.05 and 0.22 for CTA. As for quantitation, the absolute and RMS di erences for QCA are 29.7% and 34.1% and the weighted kappa for CTA are -0.37. As for lumen segmentation, the dice are 0.68 and 0.69 for healthy and diseased vessel segments respectively. Performance for QCA and lumen segmentation are close to the reported by the organizers for three human observers.

Detection confusion tables

Calc. cat.QCA (per segment)CTA (per lesion)
 TPFPFNTP+FPTP+FNTPFPFNTP+FPTP+FN
All  21  14  28  10  42  15  47 
The results of this method are based on the following centerlines: Rcadia team auto.

Detection (QCA per segment / CTA per lesion)

Calc. cat.QCA
Sens.
QCA
P.P.V.
CTA
Sens.
CTA
P.P.V.
Avg. rank
 %rank%rank%rank%rank 
0 (0 - 0.1)  0.0  15.0  0.0  15.0  0.0  18.0  0.0  18.0  16.5 
1 (0.1 - 10)  100.0  1.0  100.0  1.0  20.0  14.0  100.0  1.0  4.2 
2 (11 - 100)  14.3  17.0  20.0  10.0  0.0  19.0  0.0  19.0  16.2 
3 (101 - 400)  20.0  18.0  66.7  1.0  5.3  19.0  33.3  7.0  11.2 
4 (400+)  60.0  4.0  60.0  3.0  60.0  6.0  50.0  5.0  4.5 
All  25.0  16.0  50.0  3.0  10.6  19.0  33.3  5.0  10.8 
For ranking  25.0  16.0  50.0  3.0  10.6  19.0  33.3  5.0  10.8 
These results are based on 30 datasets and 19 submissions.


Quantification

Calc. cat.QCA
Avg. Abs. diff.
QCA
R.M.S. diff.
CTA
Weigthed Kappa
Avg. rank
 %rank%rankΚrank 
0 (0 - 0.1)  30.1  5.0  33.4  2.0  0.18  11.0  7.2 
1 (0.1 - 10)  19.0  2.0  21.3  1.0  0.22  10.0  5.8 
2 (11 - 100)  30.6  3.0  36.0  4.0  0.08  12.0  7.8 
3 (101 - 400)  29.3  2.0  34.9  2.0  0.17  12.0  7.0 
4 (400+)  32.4  6.0  37.9  5.0  0.32  8.0  6.8 
All  28.8  1.0  33.7  1.0  0.18  11.0  6.0 
For ranking  28.8  1.0  33.7  1.0  0.18  11.0  6.0