Label fusion is used in medical image segmentation to combine several different labels of the same entity into a single discrete\r\nlabel, potentially more accurate, with respect to the exact, sought segmentation, than the best input element. Using simulated data,\r\nwe compared three existing label fusion techniquesââ?¬â?STAPLE, Voting, and Shape-Based Averaging (SBA)ââ?¬â?and observed that\r\nnone could be considered superior depending on the dissimilarity between the input elements. We thus developed an empirical,\r\nhybrid technique called SVS, which selects the most appropriate technique to apply based on this dissimilarity. We evaluated the\r\nlabel fusion strategies on two- and three-dimensional simulated data and showed that SVS is superior to any of the three existing\r\nmethods examined. On real data, we used SVS to perform fusions of 10 segmentations of the hippocampus and amygdala in 78\r\nsubjects from the ICBM dataset. SVS selected SBA in almost all cases, which was the most appropriate method overall.
Loading....