Flexible Bayesian Modelling for Nonlinear Image Registration

TL;DR

This paper introduces a flexible, unsupervised Bayesian framework for nonlinear image registration that models variability in shape and appearance, achieving state-of-the-art accuracy in 3D brain scan alignment.

Contribution

The proposed diffeomorphic registration algorithm is general, modality-agnostic, and incorporates probabilistic modeling of anatomical variability, advancing nonlinear registration methods.

Findings

Achieved over 17% increase in overlap score on unprocessed datasets.

State-of-the-art registration accuracy with reasonable runtimes.

Validated on manually labelled 3D brain scans.

Abstract

We describe a diffeomorphic registration algorithm that allows groups of images to be accurately aligned to a common space, which we intend to incorporate into the SPM software. The idea is to perform inference in a probabilistic graphical model that accounts for variability in both shape and appearance. The resulting framework is general and entirely unsupervised. The model is evaluated at inter-subject registration of 3D human brain scans. Here, the main modeling assumption is that individual anatomies can be generated by deforming a latent 'average' brain. The method is agnostic to imaging modality and can be applied with no prior processing. We evaluate the algorithm using freely available, manually labelled datasets. In this validation we achieve state-of-the-art results, within reasonable runtimes, against previous state-of-the-art widely used, inter-subject registration algorithms. On the unprocessed dataset, the increase in overlap score is over 17%. These results demonstrate the benefits of using informative computational anatomy frameworks for nonlinear registration.