Presented at the IEEE International Symposium on Biomedical Imaging (ISBI) 2025.

Work by Jingru Fu, Adrian V. Dalca, Bruce Fischl, Rodrigo Moreno, and Malte Hoffmann.

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 optimised for longitudinal, rigid brain registration. By training the model with synthetic within-subject pairs augmented with rigid and subtle non-linear 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.