Learning accurate rigid registration for longitudinal brain MRI from synthetic data

TL;DR

This paper introduces a machine learning model specifically designed for accurate longitudinal brain MRI registration, trained on synthetic data to outperform previous methods in within-subject alignment tasks.

Contribution

It presents a novel model optimized for longitudinal rigid registration, trained with synthetic within-subject data, improving accuracy over prior cross-subject models.

Findings

Outperforms previous cross-subject networks in accuracy

Robustly aligns longitudinal MRI pairs across contrasts

Effective with synthetic training data

Abstract

Rigid registration aims to determine the translations and rotations necessary to align features in a pair of images. While recent machine learning methods have become state-of-the-art for linear and deformable registration across subjects, they have demonstrated limitations when applied to longitudinal (within-subject) registration, where achieving precise alignment is critical. Building on an existing framework for anatomy-aware, acquisition-agnostic affine registration, we propose a model optimized for longitudinal, rigid brain registration. By training the model with synthetic within-subject pairs augmented with rigid and subtle nonlinear transforms, the model estimates more accurate rigid transforms than previous cross-subject networks and performs robustly on longitudinal registration pairs within and across magnetic resonance imaging (MRI) contrasts.