PULPo: Probabilistic Unsupervised Laplacian Pyramid Registration
This addresses the need for uncertainty estimation in medical image registration, which is crucial for clinical applications, though it is incremental as it builds on existing neural network-based techniques.
The authors tackled the problem of deformable image registration in medical imaging by introducing PULPo, a probabilistic method that models deformation fields using Laplacian pyramids, achieving high registration performance and better calibrated uncertainty quantification compared to state-of-the-art methods on two neuroimaging datasets.
Deformable image registration is fundamental to many medical imaging applications. Registration is an inherently ambiguous task often admitting many viable solutions. While neural network-based registration techniques enable fast and accurate registration, the majority of existing approaches are not able to estimate uncertainty. Here, we present PULPo, a method for probabilistic deformable registration capable of uncertainty quantification. PULPo probabilistically models the distribution of deformation fields on different hierarchical levels combining them using Laplacian pyramids. This allows our method to model global as well as local aspects of the deformation field. We evaluate our method on two widely used neuroimaging datasets and find that it achieves high registration performance as well as substantially better calibrated uncertainty quantification compared to the current state-of-the-art.