On the Role of Patch Spaces in Patch-Based Label Fusion

Abstract

Multi-atlas segmentation has shown promising results in the segmentation of biomedical images. In the most common approach, registration is used to warp the atlases to the target space and then the warped atlas labelmaps are fused into a consensus segmentation. Label fusion in target space has shown to produce very accurate segmentations although at the expense of registering all atlases to each target image. Moreover, appearance and label information used by label fusion is extracted from the warped atlases, which are subject to interpolation errors. This work explores the role of extracting this information from the native spaces and adapt two label fusion approaches to this scheme. Results on the segmentation of subcortical brain structures indicate that using atlases in their native space yields superior performance than warping the atlases to the target. Moreover, using the native space lessens the computational requirements in terms of number of registrations and learning.