Optimal Weights for Multi-atlas Label Fusion

Multi-atlas based segmentation has been applied widely in medical image analysis. For label fusion, previous studies show that image similarity-based local weighting techniques produce the most accurate results. However, these methods ignore the correlations between results produced by different atlases. Furthermore, they rely on preselected weighting models and ad hoc methods to choose model parameters. We propose a novel label fusion method to address these limitations. Our formulation directly aims at reducing the expectation of the combined error and can be efficiently solved in a closed form. In our hippocampus segmentation experiment, our method significantly outperforms similarity-based local weighting. Using 20 atlases, we produce results with 0.898 ± 0.019 Dice overlap to manual labelings for controls.

• Type: Journal
• Year: 2011
• Where: IPMI
• Authors: Hongzhi Wang, Jung Wook Suh, John Pluta, Murat Altinay, Paul A. Yushkevich
• Keywords: Fusion Method, Image Similarity, IPMI 2011, Medical Image Analysis, Medical Imaging