Are Registration Uncertainty and Error Monotonically Associated

TL;DR

This study investigates whether the uncertainty estimates from probabilistic image registration, specifically Gaussian process registration, correlate with actual registration errors in neurosurgical imaging, revealing a weak to moderate positive correlation.

Contribution

It is the first systematic analysis of the relationship between registration uncertainty and error in Gaussian process registration for clinical neurosurgery images.

Findings

Weak-to-moderate positive correlation found between uncertainty and error.

Uncertainty can serve as a partial indicator of registration accuracy.

Results suggest potential for uncertainty-guided decision making in clinical settings.

Abstract

In image-guided neurosurgery, current commercial systems usually provide only rigid registration, partly because it is harder to predict, validate and understand non-rigid registration error. For instance, when surgeons see a discrepancy in aligned image features, they may not be able to distinguish between registration error and actual tissue deformation caused by tumor resection. In this case, the spatial distribution of registration error could help them make more informed decisions, e.g., ignoring the registration where the estimated error is high. However, error estimates are difficult to acquire. Probabilistic image registration (PIR) methods provide measures of registration uncertainty, which could be a surrogate for assessing the registration error. It is intuitive and believed by many clinicians that high uncertainty indicates a large error. However, the monotonic association between uncertainty and error has not been examined in image registration literature. In this pilot study, we attempt to address this fundamental problem by looking at one PIR method, the Gaussian process (GP) registration. We systematically investigate the relation between GP uncertainty and error based on clinical data and show empirically that there is a weak-to-moderate positive monotonic correlation between point-wise GP registration uncertainty and non-rigid registration error.