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

Abstract

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.

The original data collection was funded through an unrestricted educational grant from GlaxoSmithKline, United Kingdom (Grant 6GKC). Adrià Casamitjana received funding from Ministry of Universities and Recovery, Transformation and Resilience Plan, through UPC (Grant No 2021UPC-MS-67573). R.S has received financial support from the Generalitat de Catalunya, Spain (2021-SGR00523), the María de Maeztu Unit of Excellence (Institute of Neurosciences, University of Barcelona, CEX2021-001159-M), and the Spanish Ministry of Science and Innovation (PID2020-118386RA-I00/AEI/10.13039/501100011033). KL was supported by the European Union’s Horizon 2020 research and innovation programme, grant n°848158 (EarlyCause project). Juan Eugenio Iglesias received funding from NIH grants 1RF1MH123195, 1R01AG070988, 1R01EB031114, 1UM1MH130981, 1RF1AG080371, and a grant from the Jack Satter Foundation. This work is supported by ERC Starting Grant 677697.

Peer Reviewed

Postprint (published version)