Autobiography Of Editorial Board Members
Copyright ©2011 Baishideng Publishing Group Co.
World J Radiol. Oct 28, 2011; 3(10): 249-255
Published online Oct 28, 2011. doi: 10.4329/wjr.v3.i10.249
Figure 3
Figure 3 Example of a 3D automatic phantom image segmentation simulating liver vessel trees. The optimal algorithm configuration resulted in a vessel detection sensitivity of 100% for vessels of more than 1 mm in diameter, 50% in the range 0.5-1 mm and 14% in the 0.2-0.5 mm range. An average area overlap of 94.9% was obtained between automatically and manually segmented vessel sections, with an average difference of 0.06 mm2. The average values of corresponding false positive and false negative ratios were approximately 8% and 3%, respectively.