Fig. 1. (29K, color, gif)
Liver model (6 landmarks, 15 livers) with standard deviation in mm from mean surface encoded
in surface color from blue at zero deviation to red at 13.3 mm.
Jennifer L. Boes, Charles R. Meyer [1], Terry E. Weymouth [2]
[1] The University of Michigan Medical Center, Department of Radiology
[2] Department of Electrical Engineering and Computer Science,The University of Michigan
Selected figures from the text...
Fig. 1. (29K, color, gif)
Liver model (6 landmarks, 15 livers) with standard deviation in mm from mean surface encoded
in surface color from blue at zero deviation to red at 13.3 mm.
Fig. 3. (54K, color, gif)
Three-dimensional view of liver model placed into patient data set after user
identification of six landmarks which are shown
as red spheres.
Fig. 4. (27K, color, gif)
Evidence applied to the liver boundary definition problem (cross-sectional views of 3D maps):
(a) likelihood ratio, TPF/FPF, (b) model surface location probability, P(s),
(c) liver surface probability given a detection event, P(s|e).
Fig. 5. (49K, color, gif)
Visualization of liver model (cross-sectional views of 3D surface) in several stages
in the organ definition process: (a) initial placement, (b) after two iterations,
(c) after final fitting step. Yellow points are used to update model fit.
Boes, J.L., C.R. Meyer, and T.E. Weymouth: Liver definition in CT using a population-based shape model. Proceedings of CVRMed'95, Nice, FR, in Lecture Notes in Computer Science (1995: Springer-Verlag, Berlin) 905:506-512.
This work supported in part by DHHS PHS grant NIH 1R01CA52709.
(See also abstract)