PULPo: Probabilistic Unsupervised Laplacian Pyramid Registration

TL;DR

PULPo introduces a probabilistic deformable image registration method that models deformation fields hierarchically with Laplacian pyramids, enabling accurate registration and reliable uncertainty estimation in medical imaging.

Contribution

It is the first to combine hierarchical Laplacian pyramid modeling with probabilistic registration for uncertainty quantification.

Findings

Achieves high registration accuracy on neuroimaging datasets.

Provides better calibrated uncertainty estimates than existing methods.

Demonstrates effectiveness in modeling both global and local deformations.

Abstract

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.