Skip to main content
. Author manuscript; available in PMC: 2012 Feb 8.
Published in final edited form as: IEEE Trans Med Imaging. 2011 Oct 14;31(2):512–522. doi: 10.1109/TMI.2011.2172215

Figure 4.

Figure 4

Simulations with boundary random raters. Axial sections of the three-dimensional volume show the manually drawn truth model (A) and sample labeling from a single simulated rater (B) alongside STAPLER fused results from 3, 36, and 72 raters producing a total of 3 complete labeled datasets without training data (E-G) and with training data (H-J). Note that boundary errors are generated in three-dimensions, so errors may appear distant from the boundaries in cross-sections. Boundary errors (e.g., arrow in F) increased with decreasing rater overlap. Label inversions (e.g., arrow in G) resulted in very high error with minimal overlap. As with the voxel-wise rater model (Figure 3), STAPLER fuses partial label sets, but performance degrades with decreasing overlap (C). With the addition of training data (D), STAPLER sustains performance even with each rater labeling only a small portion of the dataset.