Local MAP STAPLE in IEEE Transactions on Medical Imaging

Our joint article on local MAP STAPLE has been published in IEEE Transactions in Medical Imaging. The aim of this algorithm is to estimate from a set of multi-label segmentations both a reference standard segmentation and spatially varying performance parameters. It is based on a sliding window technique to estimate the segmentation and the segmentation performance parameters for each input segmentation. In order to allow for optimal fusion from the small amount of data in each local region, and to account for the possibility of labels not being observed in a local region of some (or all) input segmentations, we introduced prior probabilities for the local performance parameters through a new maximum a posteriori formulation of STAPLE. Further, we proposed an expression to compute confidence intervals in the estimated local performance parameters.

More information on this article (abstract, pdf, …) is available from this DOI link. It may also be seen on our publication page. C++ source code and example data will soon be made available.

Comments are closed.