Uncertainty driven probabilistic voxel selection for image registration
This addresses the need for efficient image registration in time-sensitive medical contexts, though it is an incremental improvement over existing voxel selection methods.
The paper tackles the problem of aggressive voxel sampling for fast medical image registration by developing a Bayesian probabilistic voxel selection strategy, achieving registration accuracy with less than 1% of voxels while maintaining low failure rates.
This paper presents a novel probabilistic voxel selection strategy for medical image registration in time-sensitive contexts, where the goal is aggressive voxel sampling (e.g. using less than 1% of the total number) while maintaining registration accuracy and low failure rate. We develop a Bayesian framework whereby, first, a voxel sampling probability field (VSPF) is built based on the uncertainty on the transformation parameters. We then describe a practical, multi-scale registration algorithm, where, at each optimization iteration, different voxel subsets are sampled based on the VSPF. The approach maximizes accuracy without committing to a particular fixed subset of voxels. The probabilistic sampling scheme developed is shown to manage the tradeoff between the robustness of traditional random voxel selection (by permitting more exploration) and the accuracy of fixed voxel selection (by permitting a greater proportion of informative voxels).