Skip to main content

Table 1 Segmentation Errors of Chan-Vese (CV) model, Region-Scalable Fitting Energy (RSFE) based method, Nonparametric Shape Prior Constrained Active Contour (NSPCAC) model, Original Hybrid Model and Localized Hybrid Model for different Gaussian noise variance levels applied on the test dataset

From: 3D vasculature segmentation using localized hybrid level-set method

Methods σ=0.001 σ=0.005 σ=0.01 σ=0.015
CV model 15.88 % 16.54 % 20.55 % 21.58 %
RSFE based method 12.26 % 15.20 % 17.33 % 19.58 %
NSPCAC model 9.80 % 12.19 % 14.15 % 16.66 %
Original Hybrid Model 8.70 % 9.03 % 9.78 % 10.65 %
Localized Hybrid Model 8.15 % 8.63 % 9.13 % 9.96 %