USLR: An open-source tool for unbiased and smooth longitudinal registration of brain MRI

• Published in: Medical image analysis Vol. 105; p. 103662
• Main Authors: Casamitjana, Adrià, Sala-Llonch, Roser, Lekadir, Karim, Iglesias, Juan Eugenio
• Format: Journal Article
• Language: English
• Published: Netherlands Elsevier B.V 01.10.2025
• Subjects: Algorithms; Alzheimer Disease - diagnostic imaging; Bayes Theorem; Brain - diagnostic imaging; Humans; Image Interpretation, Computer-Assisted - methods; Image Processing, Computer-Assisted - methods; Longitudinal Studies; Magnetic Resonance Imaging - methods; MRI biomarkers; Smooth longitudinal registration; Subject-specific non-linear template; Tensor based morphometry; Unbiased longitudinal analysis; Tensor based morphometry; Unbiased longitudinal analysis; Smooth longitudinal registration; MRI biomarkers; Subject-specific non-linear template
• ISSN: 1361-8415; 1361-8423; 1361-8423
• DOI: 10.1016/j.media.2025.103662

We present the “Unbiased and Smooth Longitudinal Registration” (USLR) method, a computational framework for longitudinal registration of brain MRI scans to estimate non-linear image trajectories that are smooth across time, unbiased to any timepoint, and robust to imaging artefacts. It operates on the Lie algebra parameterisation of spatial transforms (which is compatible with rigid transforms and stationary velocity fields for non-linear deformation) and takes advantage of log-domain properties to solve the problem using Bayesian inference. USRL estimates spatial transformations that: (i) bring all timepoints to an unbiased subject-specific space; and (ii) compute a smooth trajectory across the imaging time-series. We capitalise on learning-based registration algorithms and closed-form expressions for fast inference. An Alzheimer’s disease study is used to showcase the benefits of the pipeline in multiple fronts, such as time-consistent image segmentation to reduce intra-subject variability, subject-specific prediction or population analysis using tensor-based morphometry. We demonstrate that such an approach improves upon cross-sectional methods in identifying group differences, which can be helpful in detecting more subtle atrophy levels or in reducing sample sizes in clinical trials. The code is publicly available in https://github.com/acasamitjana/uslr. •A theoretical framework for unbiased, smooth and non-linear registration of longitudinal MRI scans.•Based on the Lie algebra parameterisation of linear transforms and non-linear diffeomorphisms.•The output of the framework produces longitudinal trajectories at the voxel-level and a latent subject-specific template.•The framework is used for time-consistent segmentation of brain MRI.•Longitudinal processing outperforms cross-sectional processing of MRI scans in a case-control study.