POLAFFINI: Efficient feature-based polyaffine initialization for improved non-linear image registration

TL;DR

This paper introduces POLAFFINI, a fast, feature-based polyaffine initialization method that improves the accuracy and robustness of non-linear image registration, outperforming traditional affine methods and enhancing deep learning approaches.

Contribution

It presents a novel, efficient initialization technique using deep learning segmentations and polyaffine transformations for better non-linear image registration.

Findings

Significantly improved registration accuracy over affine methods.

Faster and more robust than existing affine initialization techniques.

Enhances both traditional and deep learning-based registration algorithms.

Abstract

This paper presents an efficient feature-based approach to initialize non-linear image registration. Today, nonlinear image registration is dominated by methods relying on intensity-based similarity measures. A good estimate of the initial transformation is essential, both for traditional iterative algorithms and for recent one-shot deep learning (DL)-based alternatives. The established approach to estimate this starting point is to perform affine registration, but this may be insufficient due to its parsimonious, global, and non-bending nature. We propose an improved initialization method that takes advantage of recent advances in DL-based segmentation techniques able to instantly estimate fine-grained regional delineations with state-of-the-art accuracies. Those segmentations are used to produce local, anatomically grounded, feature-based affine matchings using iteration-free closed-form expressions. Estimated local affine transformations are then fused, with the log-Euclidean polyaffine framework, into an overall dense diffeomorphic transformation. We show that, compared to its affine counterpart, the proposed initialization leads to significantly better alignment for both traditional and DL-based non-linear registration algorithms. The proposed approach is also more robust and significantly faster than commonly used affine registration algorithms such as FSL FLIRT.