Learning Accurate Rigid Registration for Longitudinal Brain MRI from Synthetic Data

• Published in: Proceedings (International Symposium on Biomedical Imaging) Vol. 2025; pp. 1 - 5
• Main Authors: Fu, Jingru, Dalca, Adrian V., Fischl, Bruce, Moreno, Rodrigo, Hoffmann, Malte
• Format: Conference Proceeding Journal Article
• Language: English
• Published: United States IEEE 01.04.2025
• Subjects: Accuracy; Brain modeling; Buildings; Deep learning; Image registration; longitudinal analysis; Magnetic resonance imaging; Neuroimaging; rigid image registration; Synthetic data; Training; Transforms; rigid image registration; longitudinal analysis; deep learning; neuroimaging
• ISSN: 1945-7928; 1945-8452
• DOI: 10.1109/ISBI60581.2025.10980859

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.